From ff30d4c02a85bb9f7b3d038b777001bf707cfcb9 Mon Sep 17 00:00:00 2001
From: "lea.douchet_ird.fr" <ldouchet@hotmail.fr>
Date: Fri, 25 Nov 2022 17:16:40 +0700
Subject: [PATCH] kulldorf scan statistics
---
07-basic_statistics.qmd | 214 +++++++++++---
public/.07-basic_statistics.html.swp | Bin 20480 -> 0 bytes
public/01-introduction.html | 2 +-
public/07-basic_statistics.html | 262 +++++++++++++----
.../figure-html/MoransI-1.png | Bin 0 -> 17107 bytes
.../figure-html/distribution-1.png | Bin 0 -> 20163 bytes
.../figure-html/inc_visualization-1.png | Bin 53636 -> 53661 bytes
.../figure-html/incidence_visualization-1.png | Bin 0 -> 53684 bytes
.../figure-html/kd_test-1.png | Bin 0 -> 15737 bytes
.../figure-html/plt_clusters-1.png | Bin 0 -> 44495 bytes
public/search.json | 250 ++---------------
public/search.json.orig | 263 ------------------
12 files changed, 410 insertions(+), 581 deletions(-)
delete mode 100644 public/.07-basic_statistics.html.swp
create mode 100644 public/07-basic_statistics_files/figure-html/MoransI-1.png
create mode 100644 public/07-basic_statistics_files/figure-html/distribution-1.png
create mode 100644 public/07-basic_statistics_files/figure-html/incidence_visualization-1.png
create mode 100644 public/07-basic_statistics_files/figure-html/kd_test-1.png
create mode 100644 public/07-basic_statistics_files/figure-html/plt_clusters-1.png
delete mode 100644 public/search.json.orig
diff --git a/07-basic_statistics.qmd b/07-basic_statistics.qmd
index a685dda..c93cb0f 100644
--- a/07-basic_statistics.qmd
+++ b/07-basic_statistics.qmd
@@ -11,18 +11,19 @@ This section aims at providing some basic statistical tools to study the spatial
In this section, we load data that reference the cases of an imaginary disease throughout Cambodia. Each point correspond to the geolocalisation of a case.
```{r load_cases, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, class.output="code-out", warning=FALSE, message=FALSE}
+library(dplyr)
library(sf)
#Import Cambodia country border
-country = st_read("data_cambodia/cambodia.gpkg", layer = "country", quiet = TRUE)
+country <- st_read("data_cambodia/cambodia.gpkg", layer = "country", quiet = TRUE)
#Import provincial administrative border of Cambodia
-education = st_read("data_cambodia/cambodia.gpkg", layer = "education", quiet = TRUE)
+education <- st_read("data_cambodia/cambodia.gpkg", layer = "education", quiet = TRUE)
#Import district administrative border of Cambodia
-district = st_read("data_cambodia/cambodia.gpkg", layer = "district", quiet = TRUE)
+district <- st_read("data_cambodia/cambodia.gpkg", layer = "district", quiet = TRUE)
# Import locations of cases from an imaginary disease
-cases = st_read("data_cambodia/cambodia.gpkg", layer = "cases", quiet = TRUE)
-cases = subset(cases, Disease == "W fever")
+cases <- st_read("data_cambodia/cambodia.gpkg", layer = "cases", quiet = TRUE)
+cases <- subset(cases, Disease == "W fever")
```
@@ -42,7 +43,7 @@ mf_map(x = cases, lwd = .5, col = "#990000", pch = 20, add = TRUE)
```
-In epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, ...) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use district as the areal unit of the study.
+In epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, ...) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use the district as the areal unit of the study.
```{r district_aggregate, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, class.output="code-out", warning=FALSE, message=FALSE}
# Aggregate cases over districts
@@ -50,21 +51,21 @@ district$cases <- lengths(st_intersects(district, cases))
```
-The incidence ($\frac{cases}{population}$) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as $SIR = \frac{Y_i}{E_i}$ with $Y_i$, the observed number of cases and $E_i$, the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district.
+The incidence ($\frac{cases}{population}$) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as $SIR = \frac{Y_i}{E_i}$ with $Y_i$, the observed number of cases and $E_i$, the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district. The SIR therefore represents the deviation of incidence compared to the averaged average incidence across Cambodia.
```{r indicators, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, fig.height=4, class.output="code-out", warning=FALSE, message=FALSE}
# Compute incidence in each district (per 100 000 population)
-district$incidence = district$cases/district$T_POP * 100000
+district$incidence <- district$cases/district$T_POP * 100000
# Compute the global risk
-rate = sum(district$cases)/sum(district$T_POP)
+rate <- sum(district$cases)/sum(district$T_POP)
# Compute expected number of cases
-district$expected = district$T_POP * rate
+district$expected <- district$T_POP * rate
# Compute SIR
-district$SIR = district$cases / district$expected
+district$SIR <- district$cases / district$expected
```
```{r inc_visualization, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, fig.height=4, class.output="code-out", warning=FALSE, message=FALSE}
@@ -90,8 +91,8 @@ mf_layout(title = "Incidence of W Fever")
# Plot SIRs
# create breaks and associated color palette
-break_SIR = c(0, exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = "pretty")))
-col_pal = c("#273871", "#3267AD", "#6496C8", "#9BBFDD", "#CDE3F0", "#FFCEBC", "#FF967E", "#F64D41", "#B90E36")
+break_SIR <- c(0, exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = "pretty")))
+col_pal <- c("#273871", "#3267AD", "#6496C8", "#9BBFDD", "#CDE3F0", "#FFCEBC", "#FF967E", "#F64D41", "#B90E36")
mf_map(x = district,
var = "SIR",
@@ -115,54 +116,201 @@ In this example, we standardized the cases distribution for population count. Th
## Cluster analysis
-Since this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.
+Since this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The definition of clusters emcompass many XXXXXXX
-In statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.
+The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.
-### Spatial autocorrelation (Moran's I test)
+### Test for spatial autocorrelation (Moran's I test)
A popular test for spatial autocorrelation is the Moran's test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran's I value of +1 indicates a concentration of spatial units exhibiting similar rates.
-Here the statistics hypothesis are :
+::: callout-note
+## Statistical test
-- H0 : the distribution of cases is spatially independant, i.e. Moran's I value is 0.
+In statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an *a priori* hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.
-- H1: the distribution of cases is spatially autocorrelated, i.e. Moran's I value is different than 0.
+The Moran's statistics is :
-We will compute the Moran's statistics using `spdep` and `Dcluster` packages. `spdep` package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. `Dcluster` package provides a set of functions for the detection of spatial clusters of disease using count data.
+$$I = \frac{N}{\sum_{i=1}^N\sum_{j=1}^Nw_{ij}}\frac{\sum_{i=1}^N\sum_{j=1}^Nw_{ij}(Y_i-\bar{Y})(Y_j - \bar{Y})}{\sum_{i=1}^N(Y_i-\bar{Y})^2}$$ with :
+
+- $N$: the number of polygons,
+
+- $w_{ij}$: is a matrix of spatial weight with zeroes on the diagonal (i.e., $w_{ii}=0$). For example, if polygons are neighbors, the weight takes the value $1$ otherwise it take the value $0$.
+
+- $Y_i$: the variable of interest,
+
+- $\bar{Y}$: the mean value of $Y$.
+
+Under the Moran's test, the statistics hypothesis are :
+
+- **H0** : the distribution of cases is spatially independent, i.e. $I=0$.
+
+- **H1**: the distribution of cases is spatially autocorrelated, i.e. $I\ne0$.
+:::
+
+We will compute the Moran's statistics using `spdep` and `Dcluster` packages. `spdep` package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. In this example, we use `poly2nb()` and `nb2listw()`. These function respectively detect the neighboring polygons and assign weight corresponding to $1/\#\ of\ neighbors$. `Dcluster` package provides a set of functions for the detection of spatial clusters of disease using count data.
```{r MoransI, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, class.output="code-out", warning=FALSE, message=FALSE}
library(spdep) # Functions for creating spatial weight, spatial analysis
-library(DCluster) # Package with functions for spatial cluster analysis)
+library(DCluster) # Package with functions for spatial cluster analysis
-qnb <- poly2nb(district)
-q_listw <- nb2listw(qnb, style = 'W') # row-standardized weights
+queen_nb <- poly2nb(district) # Neighbors according to queen case
+q_listw <- nb2listw(queen_nb, style = 'W') # row-standardized weights
# Moran's I test
-moranI.test(cases ~ offset(log(expected)),
+m_test <- moranI.test(cases ~ offset(log(expected)),
data = district,
model = 'poisson',
R = 499,
listw = q_listw,
- n = 159,
- S0 = Szero(q_listw))
+ n = length(district$cases), # number of regions
+ S0 = Szero(q_listw)) # Global sum of weights
+print(m_test)
+plot(m_test)
```
+The Moran's statistics is here $I =$ `r signif(m_test$t0, 2)`. When comparing its value to the H0 distribution (built under `r m_test$R` simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is $p_{value} =$ `r signif(( 1+ (sum((-abs(as.numeric(m_test$t0-mean(m_test$t))))>as.numeric(m_test$t-mean(m_test$t)))) + (sum(abs(as.numeric(m_test$t0-mean(m_test$t)))<as.numeric(m_test$t-mean(m_test$t)))) )/(m_test$R+1), 2)`. We therefore reject H0 with error risk of $\alpha = 5\%$. The distribution of cases is therefore autocorrelated across districts in Cambodia.
+
+::: callout-note
+## Statistic distributions
+
+In mathematics, a probability distribution is a mathematical expression that represents what we would expect due to random chance. The choice of the probability distribution relies on the type of data you use (continuous, count, binary). In general, three distribution a used while studying disease rates, the binomial, the poisson and the Poisson-gamma mixture (a.k.a negative binomial) distributions.
+
+The default Global Moran's I test assume data are normally distributed. It implies that the mean However, in epidemiology, rates and count values are usually not normally distributed and their variance is not homogeneous across the districts since the size of population at risk differs. to be the same since more variability occurs when we study smaller populations.
+
+While many measures may be appropriately assessed under the normality assumptions of the previous Global Moran's I, in general disease rates are not best assessed this way. This is because the rates themselves may not be normally distributed, but also because the variance of each rate likely differs because of different size population at risk. For example the previous test assumed that we had the same level of certainty about the rate in each county, when in fact some counties have very sparse data (with high variance) and others have adequate data (with relatively lower variance).
+
+```{r distribution, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
+
+# dataset statistics
+m_cases <- mean(district$cases)
+sd_cases <- sd(district$cases)
+
+curve(dnorm(x, m_cases, sd_cases), from = -5, to = 16, ylim = c(0, 0.4), col = "blue", lwd = 1,
+ xlab = "Number of cases", ylab = "Probability", main = "Histogram of observed data compared\nto Normal and Poisson distributions")
+points(0:max(district$cases), dpois(0:max(district$cases), m_cases),type = 'b ', pch = 20, col = "red", ylim = c(0, 0.6), lty = 2)
+hist(district$cases, add = TRUE, probability = TRUE)
+
+legend("topright", legend = c("Normal distribution", "Poisson distribution", "Observed distribution"), col = c("blue", "red", "black"),pch = c(NA, 20, NA), lty = c(1, 2, 1))
+```
+:::
+
### Spatial scan statistics
-While Moran's indice focuses on finding correlation between neighboring polygons, the spatial scan statistic compare the incidence level of a given windows of observation with the incidence level outside of this windows.
+While Moran's indice focuses on testing for autocorrelation between neighboring polygons (under the null assumption of spatial independance), the spatial scan statistic aims at identifying an abnormal higher risk in a given region compared to the risk outside of this region (under the null assumption of homogeneous distribution). The conception of a cluster is therefore different between the two methods.
+
+The function `kulldorf` from the package `SpatialEpi`is a simple tool to implement spatial-only scan statistics. Briefly, the kulldorf scan statistics scan the area for clusters using several steps:
+
+1. It create a circular window of observation by defining a single location and an associated radius of the windows varying from 0 to a large number that depends on population distribution (largest radius could includes 50% of the population).
+
+2. It aggregates the count of events and the population at risk (or an expected count of events) inside and outside the window of observation.
+
+3. Finally, it computes the likelihood ratio to test whether the risk is equal inside versus outside the windows (H0) or greater inside the observed window
+
+4. These 3 steps are repeted for each location and each possible windows-radii.
+
+```{r spatialEpi, eval = TRUE, echo = TRUE, nm = TRUE, class.output="code-out", warning=FALSE, message=FALSE}
+
+library("SpatialEpi")
-The package `SpatialEpi`
+```
+
+The use of R spatial object is not implementes in `kulldorf()` function. It uses instead matrix of xy coordinates that represents the centroids of the districts. A given district is included into the observed circular window if its centroids falls into the circle.
+
+```{r kd_centroids, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
+
+district_xy <- st_centroid(district) %>%
+ st_coordinates()
+head(district_xy)
-### Population-based clusters (kulldorf statistic)
+```
+
+We can then call kulldorff function (you are strongly encourage to call `?kulldorf` to properly call the function). The `alpha.level` threshold filter for the secondary clusters that will be retained. The most-likely cluster will be saved whatever its significance.
-Kulldorff 's spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.
+```{r kd_test, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
-### Expectation-based cluster
+kd_Wfever <- kulldorff(district_xy,
+ cases = district$cases,
+ population = district$T_POP,
+ expected.cases = district$expected,
+ pop.upper.bound = 0.5, # include maximum 50% of the population in a windows
+ n.simulations = 499,
+ alpha.level = 0.2)
+
+```
+
+All outputs are saved into the R object `kd_Wfever`. Unfortunately the package did not developed any summary and visualization of the results but we can explore the output object.
+
+```{r kd_outputs, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
+names(kd_Wfever)
+
+```
+
+First, we can focus on the most likely cluster and explore its characteristics.
+
+```{r kd_mlc, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
+
+# We can see which districts (r number) belong to this cluster
+kd_Wfever$most.likely.cluster$location.IDs.included
+
+# standardized incidence ratio
+kd_Wfever$most.likely.cluster$SMR
+
+# number of observed and expected cases in this cluster
+kd_Wfever$most.likely.cluster$number.of.cases
+kd_Wfever$most.likely.cluster$expected.cases
+
+```
+`r length(kd_Wfever$most.likely.cluster$location.IDs.included)` districts belong to the cluster and its number of cases is `r signif(kd_Wfever$most.likely.cluster$SMR, 2)` times higher than the expected number of case.
+
+Similarly, we could study the secondary clusters. Results are saved in a list.
+
+```{r kd_sc, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=6, class.output="code-out", warning=FALSE, message=FALSE}
+
+# We can see which districts (r number) belong to this cluster
+length(kd_Wfever$secondary.clusters)
+
+# retrieve data for all secondary clusters into a table
+df_secondary_clusters <- data.frame(SMR = sapply(kd_Wfever$secondary.clusters, '[[', 5),
+ number.of.cases = sapply(kd_Wfever$secondary.clusters, '[[', 3),
+ expected.cases = sapply(kd_Wfever$secondary.clusters, '[[', 4),
+ p.value = sapply(kd_Wfever$secondary.clusters, '[[', 8))
+
+print(df_secondary_clusters)
+
+
+```
+
+We only have one secondary cluster composed of one district.
+
+
+```{r plt_clusters, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, class.output="code-out", warning=FALSE, message=FALSE}
+
+# create empty column to store cluster informations
+district$k_cluster <- NA
+
+# save cluster informations from kulldorff outputs
+district$k_cluster[kd_Wfever$most.likely.cluster$location.IDs.included] <- 'Most likely cluster'
+
+for(i in 1:length(kd_Wfever$secondary.clusters)){
+district$k_cluster[kd_Wfever$secondary.clusters[[i]]$location.IDs.included] <- paste(
+ 'Secondary cluster ', i, sep = '')
+}
+
+# create map
+mf_map(x = district,
+ var = "k_cluster",
+ type = "typo",
+ cex = 2,
+ leg_title = "Clusters")
+mf_layout(title = "Cluster using kulldorf scan statistic")
+
+
+
+```
+This cluster analysis was performed solely using the spatial
-In many case, population is not specific enough to
-### To go further ...
diff --git a/public/.07-basic_statistics.html.swp b/public/.07-basic_statistics.html.swp
deleted file mode 100644
index fd7d5cafee353be3dacb5819006d3bf0b628ff15..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001
literal 20480
zcmeHNON<;x8SXeh0*QG92^4{#(k9qzyXUdH-pB0BDE8V88!NW)8%S`fyK8ou?HAoO
zJG(3n7UF;qK_Lfj2@eSl+(6<GP9Q-zAdnD3LP7`$Avhpj7XritzN)UC?Vg_5ovgzl
zqDT66cIvPC>#wi=`s-=duB<#t7AkcOpSNn-=YRgB^~2ge?be-|cKNJxMkMd{xqNoz
zjB&1Z<;?Vznc0QqvDu##3acjrtLHJF$JGnh`$4o8S642atX_yi${p%fBlVBb2_hr#
zS(j0lcdKE~bRDZ&n>S1vJJ$7>BYVspE3S08=Z>wj6qF2<41j?i?-&dFFV9TZYl4ph
z`UB+c_gyZjDH$jkC>bajC>bajC>bajC>baj_&;KRhxclqLVNeAHeXWTcMN_1M|~bq
z>FLfP&G)jBKcwVe9xDHDC7)91zZsI>Qu6nz^t+YfRR2p#{x&5)I3$0aO21!yFAT~5
zsmiDF4-U!yq2%vS<v%tge^JR#EBVbK`QMe?R`M5y<Ty@|AC;^fR)nX&mAL#W87LVj
z87LVj87LVj87LVj87LVj87LVj8Tg+tK(S$c5SqUzHln!yPxt?SeT$}j1Nb`d1>kYu
zF<>8X2cQ9;eY2+B1T0_?xC{98eogxda1*!+JPaHJ_5=3-KfV_-;1S>;@Y{Pd?R&u2
zfM<XJ@PLm32JrhgY1;3Ap90?mo&p{Q?gRevMooJT=mCqsoxm^d*0k>cUj?28P5?8&
z5#U|G3wLSS4}i}AM}U95LDPN$JO^9@jsmw{uW8Q%PXO-({(!@U=YdV&8gK-72^;$F
z0#5+%0sf5r{P%&UfDZ!?0xyEo9|3~frv<;0e5}A`1aBbx%6d$;h!wa&)F20DYx6Z)
zTOv0|^)R`@A`{Oayo)??{8e(es%1*iOsV=}eSY3bOVP-orpxmAW1h*Mt7Vk-IBSz>
z&dn_>DD4+RX5szD$U@fGDw0CWT^i-B3d2kh)0(HXwC(337Dj=^;y4&86J%Rb17Fi=
znRC3$hBId?n3EsXkaHo6C?8h7*3TG}D(?h7H~P$3?eYdO1J_n6&ah3qY_aoAa{P>j
zIdrB8^G0ZpNipAaS%Wy7;?;}Ny5i$WjE8;?{2|R=MsuyUP!nX0&@6pt#S4Ro=M{8%
zSp{>`3-e6XdAjFY#R@xaCjTs&GM_Si+70NCa<+lYvg%VCocVFVe00sWpLaU2eh2eU
zMbU8A*z1|{IcrWb>k4)AZMCyrvIrj;c-BeE>7~tZXnfc~M!QL;>(g~b?x;RWA2*HY
zB`a&@UiyDI@Wi{RE5l>O%37FHJjz0)B~OZ#_00w0Kxv0A2R@!!`9pnbbu*;of<|#D
zTb)ea-9`?o<5A$kjrw^D&76xWAD3QrqUX4LWoSs4*#_l&;slM^*}QIe?6w2W+i;3S
z<^IPxBCOftLq0*X+H;KOgTdILeBAc~@qlf3B*R&^E!k}-9CukVkZ)*V#7G-+h0Q8)
z(2Fd#EM}3moJa6Q8yzQ#xnXr3*KRaShCsql6K5OTu$dJg;K7y#>G?K`T*nu~Uwg=7
zwnIs5MU0`r8bJwyblX|a)FSGx_&v{L(M4G`a(Ogbb$r8R9mK^M<}D#OM$oKM>fr{7
z1J|+10V+RBgoM<#F_)<vv*CuYK-7jR2a}-6Ez?wi2B{I5yYJY%+aR;3P09@~HhMAY
zjG4<U*x}<b;Swn(CArtcE5cC)3@`Y^i1egXpP6e8H+ayqx`stvH|Py&!o(njV`@wo
zNzJmIICSYIBEB!^H%vFM){=&VLF^>G6EPS4w2oFJ%o=q;t?Wch6RYUINK8dbWF3y-
zz#Ky*<H;nGy$Y*^fBA^Ru+s{9_%Aw?xQrokOf41rQ?4y`_9dxz2SY`#q}3UY504U&
ztN||&&MIpb{atXSOx4PCX|WNpnB|KT5wJ!p&~_OgY8*K5ePNSvOc<N@N0~HE%@*l*
z9nK6a+APf3XoS&^XqXv7A(m-~F)$=QcF-9C`l^Fy*C4dVgG`yhuoI+Y26Z~R;P@hU
zL18lX8U((P<QNkb264vmu{d(zHHBy}klfJn7Hk{6?!*q3l#2VYF{r`3kZ+>7UA0)M
zSEdEa<0w_$wnavd3nIrzM%S_Ns*1gX&K)tNZlHHaVdQv@ZKHXRq`cNht+F7v6)hk}
zy)uV}K(6AC6fS8!x58<>2G7R&+I29j!yf+#$LgY`TU}<YnZbtsI9wu|aZBVj)TAxL
zRnos*>LZ-4V&Di5-O5GRdPVxC?7M*nCy7a6Y#@4`ztwTsM(Sf}_ZewQHfOvw;9Qhh
zBC9lP5YO=s&93*45~+G>>4qk^D6xl_XVEa;l2hHf*kQ<VEz%JX!x%Y*18$8TA~&?A
zY;Id?a)-OD{U{AXv8AEDEhaDVA{_rycQa-&NF*1qu8qh!pOFv9ci|-FJ==lIAoK6{
z%^0H&6TD*~9fjrla9JX+%ZZ!Sq(1D(njYhn_|!w!tUIhPmdAP;BwM=d*OtxJ9Rw=*
z<0uS4L`Hax5o1}aUa1{b^9p{89ad|T#d<rhdX@Rfz9OUh<2@Sj06v7_aIB6Ji7ghk
zLx^uJUB20sip1<hHayplTY8uCuu-k{`~6CPrV>P})%xP%Vs%60(TNLZY3a<@MfS$v
zSG$Ra^fqdE;N-dGOCLIaiiqrOP3-@FhQ0jX#GW4e|8$!wev31J@>4QUGEg#5GEg#5
zGEg#5GEg#5GEg#5GEg#5GVmH?pjkBod$ZlFZtwqpiDq0A8-MKo)A#Yu;x7M700$1^
z-u@Zf)xV7U_@{yUfzRRo{TA-qJ>XZkS3e1SQr)S43wP-620o3u^FQLQ{1U)%NB(Wx
ziBsTDs7us$H9c&24br%q$xU%SMjRW*edfF|J*~H!lyoE3Y3T=43K6GeMi(cH%x~#D
z>M@;gYKl|5jh1fUJg8Zv?L?8~(ilfSR-m^J5FDRVTuGVuT8rgT8H53D-#N2!aD@j0
zIKFln=d4*3W<Zbp!eLv^C{aV+sJgyqqt3gyf4{hL0Y_^))mbalS(~)Zk&UP?4l6{;
z9vac<>20rb9d|Ie!ck2)l;fUqy)6$7NlVE|P98(9ulSaO?z9*QI^-%j&2YT0tL#(i
zd#D@g3xyUeOxOaFd~#+8GhMcN{S}z1?8>Q$ExrAiKT?7U4&jXisn>88UaL***1q{d
z`{r-6eemv`I^hDdV=|MPb#x5va|N^JZqqDryuXuORyT-(-OM^xFzeWDnuSyOovgxj
zT;j63SvFg+Y<5D+a-O9|nny#`F~woFv28CdBX9+8@o~L4Q!r{~FGeMSRmQLZA0+ku
z(SfHB((BWc);wBaAspBD6pmk|NOo3U>5DLC;r2Lw1@Wv9;_H)!c#@B(6Nj>8VPWdN
zW5R4<o|tr+7-1CV*liEZIk%hy4lFK;7c{9sM^i@{3jBq*KY7^C)hQ>YT|y6@%!LDc
zMhC<~n4UaJ7tC3w?sbo5hH);3y{@;9)sz)u26iDjPad3ebqR8I34qeScOj<`l_w9%
z1#>dA45Hf@7b%3?S1aO<j6j80x~EXOxA;CahJiwqojAzKwQg?REW>;9RB1b|^<r_~
zEXD`!eenniON)5Z!(-0WpuuRtQwyT>W!__0Ox$$iid#=t`<RjNW@ALw2#a%DTq1Kk
z77D^mWE2Ubazd0_s~6{nN#~j@4Wes88mSf)=UuN8;oaTn<*g`djVvjKb3Gl+`3NpV
zGfFhI9hfsr3i@<n<LRa0dukViTk0yZ;48zyoPp^uw_lMdlP&erah4m4Vu|}cWgIpx
zdCLRDjR6t67Eh+gg7&J?E}pT-RZJmAT0h&sOK5E0RDotyI7YjPr-vMG1m#-3r7y#0
s2oK1z>x5=NBO6Z%(tRQPO1PAflmJmqDl;AYsyaX-!#{9O{FM~{7k&RGS^xk5
diff --git a/public/01-introduction.html b/public/01-introduction.html
index e455ef1..203c6aa 100644
--- a/public/01-introduction.html
+++ b/public/01-introduction.html
@@ -2,7 +2,7 @@
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
-<meta name="generator" content="quarto-1.1.251">
+<meta name="generator" content="quarto-1.1.189">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
diff --git a/public/07-basic_statistics.html b/public/07-basic_statistics.html
index 4123e0b..9887eb5 100644
--- a/public/07-basic_statistics.html
+++ b/public/07-basic_statistics.html
@@ -218,11 +218,8 @@ code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warni
<li><a href="#import-and-visualize-epidemiological-data" id="toc-import-and-visualize-epidemiological-data" class="nav-link active" data-scroll-target="#import-and-visualize-epidemiological-data"><span class="toc-section-number">7.1</span> Import and visualize epidemiological data</a></li>
<li><a href="#cluster-analysis" id="toc-cluster-analysis" class="nav-link" data-scroll-target="#cluster-analysis"><span class="toc-section-number">7.2</span> Cluster analysis</a>
<ul class="collapse">
- <li><a href="#spatial-autocorrelation-morans-i-test" id="toc-spatial-autocorrelation-morans-i-test" class="nav-link" data-scroll-target="#spatial-autocorrelation-morans-i-test"><span class="toc-section-number">7.2.1</span> Spatial autocorrelation (Moran’s I test)</a></li>
+ <li><a href="#test-for-spatial-autocorrelation-morans-i-test" id="toc-test-for-spatial-autocorrelation-morans-i-test" class="nav-link" data-scroll-target="#test-for-spatial-autocorrelation-morans-i-test"><span class="toc-section-number">7.2.1</span> Test for spatial autocorrelation (Moran’s I test)</a></li>
<li><a href="#spatial-scan-statistics" id="toc-spatial-scan-statistics" class="nav-link" data-scroll-target="#spatial-scan-statistics"><span class="toc-section-number">7.2.2</span> Spatial scan statistics</a></li>
- <li><a href="#population-based-clusters-kulldorf-statistic" id="toc-population-based-clusters-kulldorf-statistic" class="nav-link" data-scroll-target="#population-based-clusters-kulldorf-statistic"><span class="toc-section-number">7.2.3</span> Population-based clusters (kulldorf statistic)</a></li>
- <li><a href="#expectation-based-cluster" id="toc-expectation-based-cluster" class="nav-link" data-scroll-target="#expectation-based-cluster"><span class="toc-section-number">7.2.4</span> Expectation-based cluster</a></li>
- <li><a href="#to-go-further" id="toc-to-go-further" class="nav-link" data-scroll-target="#to-go-further"><span class="toc-section-number">7.2.5</span> To go further …</a></li>
</ul></li>
</ul>
</nav>
@@ -251,18 +248,19 @@ code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warni
<h2 data-number="7.1" class="anchored" data-anchor-id="import-and-visualize-epidemiological-data"><span class="header-section-number">7.1</span> Import and visualize epidemiological data</h2>
<p>In this section, we load data that reference the cases of an imaginary disease throughout Cambodia. Each point correspond to the geolocalisation of a case.</p>
<div class="cell" data-nm="true">
-<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(sf)</span>
-<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="co">#Import Cambodia country border</span></span>
-<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a>country <span class="ot">=</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"country"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
-<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="co">#Import provincial administrative border of Cambodia</span></span>
-<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>education <span class="ot">=</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"education"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
-<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="co">#Import district administrative border of Cambodia</span></span>
-<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a>district <span class="ot">=</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"district"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
-<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a><span class="co"># Import locations of cases from an imaginary disease</span></span>
-<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>cases <span class="ot">=</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"cases"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
-<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a>cases <span class="ot">=</span> <span class="fu">subset</span>(cases, Disease <span class="sc">==</span> <span class="st">"W fever"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(dplyr)</span>
+<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(sf)</span>
+<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="co">#Import Cambodia country border</span></span>
+<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a>country <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"country"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
+<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="co">#Import provincial administrative border of Cambodia</span></span>
+<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a>education <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"education"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
+<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="co">#Import district administrative border of Cambodia</span></span>
+<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a>district <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"district"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
+<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a><span class="co"># Import locations of cases from an imaginary disease</span></span>
+<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a>cases <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"cases"</span>, <span class="at">quiet =</span> <span class="cn">TRUE</span>)</span>
+<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a>cases <span class="ot"><-</span> <span class="fu">subset</span>(cases, Disease <span class="sc">==</span> <span class="st">"W fever"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>The first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.</p>
<div class="cell" data-nm="true">
@@ -292,24 +290,24 @@ Projected CRS: WGS 84 / UTM zone 48N
<p><img src="07-basic_statistics_files/figure-html/cases_visualization-1.png" class="img-fluid" width="768"></p>
</div>
</div>
-<p>In epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, …) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use district as the areal unit of the study.</p>
+<p>In epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, …) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use the district as the areal unit of the study.</p>
<div class="cell" data-nm="true">
<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Aggregate cases over districts</span></span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>cases <span class="ot"><-</span> <span class="fu">lengths</span>(<span class="fu">st_intersects</span>(district, cases))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
-<p>The incidence (<span class="math inline">\(\frac{cases}{population}\)</span>) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as <span class="math inline">\(SIR = \frac{Y_i}{E_i}\)</span> with <span class="math inline">\(Y_i\)</span>, the observed number of cases and <span class="math inline">\(E_i\)</span>, the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district.</p>
+<p>The incidence (<span class="math inline">\(\frac{cases}{population}\)</span>) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as <span class="math inline">\(SIR = \frac{Y_i}{E_i}\)</span> with <span class="math inline">\(Y_i\)</span>, the observed number of cases and <span class="math inline">\(E_i\)</span>, the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district. The SIR therefore represents the deviation of incidence compared to the averaged average incidence across Cambodia.</p>
<div class="cell" data-nm="true">
<div class="sourceCode cell-code" id="cb6"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Compute incidence in each district (per 100 000 population)</span></span>
-<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>incidence <span class="ot">=</span> district<span class="sc">$</span>cases<span class="sc">/</span>district<span class="sc">$</span>T_POP <span class="sc">*</span> <span class="dv">100000</span></span>
+<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>incidence <span class="ot"><-</span> district<span class="sc">$</span>cases<span class="sc">/</span>district<span class="sc">$</span>T_POP <span class="sc">*</span> <span class="dv">100000</span></span>
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a><span class="co"># Compute the global risk</span></span>
-<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a>rate <span class="ot">=</span> <span class="fu">sum</span>(district<span class="sc">$</span>cases)<span class="sc">/</span><span class="fu">sum</span>(district<span class="sc">$</span>T_POP)</span>
+<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a>rate <span class="ot"><-</span> <span class="fu">sum</span>(district<span class="sc">$</span>cases)<span class="sc">/</span><span class="fu">sum</span>(district<span class="sc">$</span>T_POP)</span>
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Compute expected number of cases </span></span>
-<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>expected <span class="ot">=</span> district<span class="sc">$</span>T_POP <span class="sc">*</span> rate</span>
+<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>expected <span class="ot"><-</span> district<span class="sc">$</span>T_POP <span class="sc">*</span> rate</span>
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a><span class="co"># Compute SIR</span></span>
-<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>SIR <span class="ot">=</span> district<span class="sc">$</span>cases <span class="sc">/</span> district<span class="sc">$</span>expected</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>SIR <span class="ot"><-</span> district<span class="sc">$</span>cases <span class="sc">/</span> district<span class="sc">$</span>expected</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div class="cell" data-nm="true">
<div class="sourceCode cell-code" id="cb7"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="fu">par</span>(<span class="at">mfrow =</span> <span class="fu">c</span>(<span class="dv">1</span>, <span class="dv">3</span>))</span>
@@ -334,8 +332,8 @@ Projected CRS: WGS 84 / UTM zone 48N
<span id="cb7-20"><a href="#cb7-20" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb7-21"><a href="#cb7-21" aria-hidden="true" tabindex="-1"></a><span class="co"># Plot SIRs</span></span>
<span id="cb7-22"><a href="#cb7-22" aria-hidden="true" tabindex="-1"></a><span class="co"># create breaks and associated color palette</span></span>
-<span id="cb7-23"><a href="#cb7-23" aria-hidden="true" tabindex="-1"></a>break_SIR <span class="ot">=</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fu">exp</span>(<span class="fu">mf_get_breaks</span>(<span class="fu">log</span>(district<span class="sc">$</span>SIR), <span class="at">nbreaks =</span> <span class="dv">8</span>, <span class="at">breaks =</span> <span class="st">"pretty"</span>)))</span>
-<span id="cb7-24"><a href="#cb7-24" aria-hidden="true" tabindex="-1"></a>col_pal <span class="ot">=</span> <span class="fu">c</span>(<span class="st">"#273871"</span>, <span class="st">"#3267AD"</span>, <span class="st">"#6496C8"</span>, <span class="st">"#9BBFDD"</span>, <span class="st">"#CDE3F0"</span>, <span class="st">"#FFCEBC"</span>, <span class="st">"#FF967E"</span>, <span class="st">"#F64D41"</span>, <span class="st">"#B90E36"</span>)</span>
+<span id="cb7-23"><a href="#cb7-23" aria-hidden="true" tabindex="-1"></a>break_SIR <span class="ot"><-</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fu">exp</span>(<span class="fu">mf_get_breaks</span>(<span class="fu">log</span>(district<span class="sc">$</span>SIR), <span class="at">nbreaks =</span> <span class="dv">8</span>, <span class="at">breaks =</span> <span class="st">"pretty"</span>)))</span>
+<span id="cb7-24"><a href="#cb7-24" aria-hidden="true" tabindex="-1"></a>col_pal <span class="ot"><-</span> <span class="fu">c</span>(<span class="st">"#273871"</span>, <span class="st">"#3267AD"</span>, <span class="st">"#6496C8"</span>, <span class="st">"#9BBFDD"</span>, <span class="st">"#CDE3F0"</span>, <span class="st">"#FFCEBC"</span>, <span class="st">"#FF967E"</span>, <span class="st">"#F64D41"</span>, <span class="st">"#B90E36"</span>)</span>
<span id="cb7-25"><a href="#cb7-25" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb7-26"><a href="#cb7-26" aria-hidden="true" tabindex="-1"></a><span class="fu">mf_map</span>(<span class="at">x =</span> district,</span>
<span id="cb7-27"><a href="#cb7-27" aria-hidden="true" tabindex="-1"></a> <span class="at">var =</span> <span class="st">"SIR"</span>,</span>
@@ -359,58 +357,216 @@ Projected CRS: WGS 84 / UTM zone 48N
</section>
<section id="cluster-analysis" class="level2" data-number="7.2">
<h2 data-number="7.2" class="anchored" data-anchor-id="cluster-analysis"><span class="header-section-number">7.2</span> Cluster analysis</h2>
-<p>Since this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.</p>
-<p>In statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.</p>
-<section id="spatial-autocorrelation-morans-i-test" class="level3" data-number="7.2.1">
-<h3 data-number="7.2.1" class="anchored" data-anchor-id="spatial-autocorrelation-morans-i-test"><span class="header-section-number">7.2.1</span> Spatial autocorrelation (Moran’s I test)</h3>
+<p>Since this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The definition of clusters emcompass many XXXXXXX</p>
+<p>The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.</p>
+<section id="test-for-spatial-autocorrelation-morans-i-test" class="level3" data-number="7.2.1">
+<h3 data-number="7.2.1" class="anchored" data-anchor-id="test-for-spatial-autocorrelation-morans-i-test"><span class="header-section-number">7.2.1</span> Test for spatial autocorrelation (Moran’s I test)</h3>
<p>A popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.</p>
-<p>Here the statistics hypothesis are :</p>
+<div class="callout-note callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class="callout-icon"></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Statistical test
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>In statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an <em>a priori</em> hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.</p>
+<p>The Moran’s statistics is :</p>
+<p><span class="math display">\[I = \frac{N}{\sum_{i=1}^N\sum_{j=1}^Nw_{ij}}\frac{\sum_{i=1}^N\sum_{j=1}^Nw_{ij}(Y_i-\bar{Y})(Y_j - \bar{Y})}{\sum_{i=1}^N(Y_i-\bar{Y})^2}\]</span> with :</p>
<ul>
-<li><p>H0 : the distribution of cases is spatially independant, i.e. Moran’s I value is 0.</p></li>
-<li><p>H1: the distribution of cases is spatially autocorrelated, i.e. Moran’s I value is different than 0.</p></li>
+<li><p><span class="math inline">\(N\)</span>: the number of polygons,</p></li>
+<li><p><span class="math inline">\(w_{ij}\)</span>: is a matrix of spatial weight with zeroes on the diagonal (i.e., <span class="math inline">\(w_{ii}=0\)</span>). For example, if polygons are neighbors, the weight takes the value <span class="math inline">\(1\)</span> otherwise it take the value <span class="math inline">\(0\)</span>.</p></li>
+<li><p><span class="math inline">\(Y_i\)</span>: the variable of interest,</p></li>
+<li><p><span class="math inline">\(\bar{Y}\)</span>: the mean value of <span class="math inline">\(Y\)</span>.</p></li>
</ul>
-<p>We will compute the Moran’s statistics using <code>spdep</code> and <code>Dcluster</code> packages. <code>spdep</code> package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. <code>Dcluster</code> package provides a set of functions for the detection of spatial clusters of disease using count data.</p>
+<p>Under the Moran’s test, the statistics hypothesis are :</p>
+<ul>
+<li><p><strong>H0</strong> : the distribution of cases is spatially independent, i.e. <span class="math inline">\(I=0\)</span>.</p></li>
+<li><p><strong>H1</strong>: the distribution of cases is spatially autocorrelated, i.e. <span class="math inline">\(I\ne0\)</span>.</p></li>
+</ul>
+</div>
+</div>
+<p>We will compute the Moran’s statistics using <code>spdep</code> and <code>Dcluster</code> packages. <code>spdep</code> package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. In this example, we use <code>poly2nb()</code> and <code>nb2listw()</code>. These function respectively detect the neighboring polygons and assign weight corresponding to <span class="math inline">\(1/\#\ of\ neighbors\)</span>. <code>Dcluster</code> package provides a set of functions for the detection of spatial clusters of disease using count data.</p>
<div class="cell" data-nm="true">
<div class="sourceCode cell-code" id="cb8"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(spdep) <span class="co"># Functions for creating spatial weight, spatial analysis</span></span>
-<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(DCluster) <span class="co"># Package with functions for spatial cluster analysis)</span></span>
+<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(DCluster) <span class="co"># Package with functions for spatial cluster analysis</span></span>
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a>qnb <span class="ot"><-</span> <span class="fu">poly2nb</span>(district)</span>
-<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a>q_listw <span class="ot"><-</span> <span class="fu">nb2listw</span>(qnb, <span class="at">style =</span> <span class="st">'W'</span>) <span class="co"># row-standardized weights</span></span>
+<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a>queen_nb <span class="ot"><-</span> <span class="fu">poly2nb</span>(district) <span class="co"># Neighbors according to queen case</span></span>
+<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a>q_listw <span class="ot"><-</span> <span class="fu">nb2listw</span>(queen_nb, <span class="at">style =</span> <span class="st">'W'</span>) <span class="co"># row-standardized weights</span></span>
<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Moran's I test</span></span>
-<span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a><span class="fu">moranI.test</span>(cases <span class="sc">~</span> <span class="fu">offset</span>(<span class="fu">log</span>(expected)), </span>
+<span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a>m_test <span class="ot"><-</span> <span class="fu">moranI.test</span>(cases <span class="sc">~</span> <span class="fu">offset</span>(<span class="fu">log</span>(expected)), </span>
<span id="cb8-9"><a href="#cb8-9" aria-hidden="true" tabindex="-1"></a> <span class="at">data =</span> district,</span>
<span id="cb8-10"><a href="#cb8-10" aria-hidden="true" tabindex="-1"></a> <span class="at">model =</span> <span class="st">'poisson'</span>,</span>
<span id="cb8-11"><a href="#cb8-11" aria-hidden="true" tabindex="-1"></a> <span class="at">R =</span> <span class="dv">499</span>,</span>
<span id="cb8-12"><a href="#cb8-12" aria-hidden="true" tabindex="-1"></a> <span class="at">listw =</span> q_listw,</span>
-<span id="cb8-13"><a href="#cb8-13" aria-hidden="true" tabindex="-1"></a> <span class="at">n =</span> <span class="dv">159</span>,</span>
-<span id="cb8-14"><a href="#cb8-14" aria-hidden="true" tabindex="-1"></a> <span class="at">S0 =</span> <span class="fu">Szero</span>(q_listw))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb8-13"><a href="#cb8-13" aria-hidden="true" tabindex="-1"></a> <span class="at">n =</span> <span class="fu">length</span>(district<span class="sc">$</span>cases), <span class="co"># number of regions</span></span>
+<span id="cb8-14"><a href="#cb8-14" aria-hidden="true" tabindex="-1"></a> <span class="at">S0 =</span> <span class="fu">Szero</span>(q_listw)) <span class="co"># Global sum of weights</span></span>
+<span id="cb8-15"><a href="#cb8-15" aria-hidden="true" tabindex="-1"></a><span class="fu">print</span>(m_test)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output cell-output-stdout">
<pre class="code-out"><code>Moran's I test of spatial autocorrelation
Type of boots.: parametric
Model used when sampling: Poisson
Number of simulations: 499
- Statistic: 0.1264291
- p-value : 0.006 </code></pre>
+ Statistic: 0.1566449
+ p-value : 0.014 </code></pre>
+</div>
+<div class="sourceCode cell-code" id="cb10"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plot</span>(m_test)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output-display">
+<p><img src="07-basic_statistics_files/figure-html/MoransI-1.png" class="img-fluid" width="768"></p>
+</div>
+</div>
+<p>The Moran’s statistics is here <span class="math inline">\(I =\)</span> 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is <span class="math inline">\(p_{value} =\)</span> 0.014. We therefore reject H0 with error risk of <span class="math inline">\(\alpha = 5\%\)</span>. The distribution of cases is therefore autocorrelated across districts in Cambodia.</p>
+<div class="callout-note callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class="callout-icon"></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Statistic distributions
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>In mathematics, a probability distribution is a mathematical expression that represents what we would expect due to random chance. The choice of the probability distribution relies on the type of data you use (continuous, count, binary). In general, three distribution a used while studying disease rates, the binomial, the poisson and the Poisson-gamma mixture (a.k.a negative binomial) distributions.</p>
+<p>The default Global Moran’s I test assume data are normally distributed. It implies that the mean However, in epidemiology, rates and count values are usually not normally distributed and their variance is not homogeneous across the districts since the size of population at risk differs. to be the same since more variability occurs when we study smaller populations.</p>
+<p>While many measures may be appropriately assessed under the normality assumptions of the previous Global Moran’s I, in general disease rates are not best assessed this way. This is because the rates themselves may not be normally distributed, but also because the variance of each rate likely differs because of different size population at risk. For example the previous test assumed that we had the same level of certainty about the rate in each county, when in fact some counties have very sparse data (with high variance) and others have adequate data (with relatively lower variance).</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb11"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="co"># dataset statistics</span></span>
+<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a>m_cases <span class="ot"><-</span> <span class="fu">mean</span>(district<span class="sc">$</span>cases)</span>
+<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a>sd_cases <span class="ot"><-</span> <span class="fu">sd</span>(district<span class="sc">$</span>cases)</span>
+<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a><span class="fu">curve</span>(<span class="fu">dnorm</span>(x, m_cases, sd_cases), <span class="at">from =</span> <span class="sc">-</span><span class="dv">5</span>, <span class="at">to =</span> <span class="dv">16</span>, <span class="at">ylim =</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fl">0.4</span>), <span class="at">col =</span> <span class="st">"blue"</span>, <span class="at">lwd =</span> <span class="dv">1</span>, </span>
+<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a> <span class="at">xlab =</span> <span class="st">"Number of cases"</span>, <span class="at">ylab =</span> <span class="st">"Probability"</span>, <span class="at">main =</span> <span class="st">"Histogram of observed data compared</span><span class="sc">\n</span><span class="st">to Normal and Poisson distributions"</span>)</span>
+<span id="cb11-7"><a href="#cb11-7" aria-hidden="true" tabindex="-1"></a><span class="fu">points</span>(<span class="dv">0</span><span class="sc">:</span><span class="fu">max</span>(district<span class="sc">$</span>cases), <span class="fu">dpois</span>(<span class="dv">0</span><span class="sc">:</span><span class="fu">max</span>(district<span class="sc">$</span>cases), m_cases),<span class="at">type =</span> <span class="st">'b '</span>, <span class="at">pch =</span> <span class="dv">20</span>, <span class="at">col =</span> <span class="st">"red"</span>, <span class="at">ylim =</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fl">0.6</span>), <span class="at">lty =</span> <span class="dv">2</span>)</span>
+<span id="cb11-8"><a href="#cb11-8" aria-hidden="true" tabindex="-1"></a><span class="fu">hist</span>(district<span class="sc">$</span>cases, <span class="at">add =</span> <span class="cn">TRUE</span>, <span class="at">probability =</span> <span class="cn">TRUE</span>)</span>
+<span id="cb11-9"><a href="#cb11-9" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb11-10"><a href="#cb11-10" aria-hidden="true" tabindex="-1"></a><span class="fu">legend</span>(<span class="st">"topright"</span>, <span class="at">legend =</span> <span class="fu">c</span>(<span class="st">"Normal distribution"</span>, <span class="st">"Poisson distribution"</span>, <span class="st">"Observed distribution"</span>), <span class="at">col =</span> <span class="fu">c</span>(<span class="st">"blue"</span>, <span class="st">"red"</span>, <span class="st">"black"</span>),<span class="at">pch =</span> <span class="fu">c</span>(<span class="cn">NA</span>, <span class="dv">20</span>, <span class="cn">NA</span>), <span class="at">lty =</span> <span class="fu">c</span>(<span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">1</span>))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output-display">
+<p><img src="07-basic_statistics_files/figure-html/distribution-1.png" class="img-fluid" width="576"></p>
+</div>
+</div>
</div>
</div>
</section>
<section id="spatial-scan-statistics" class="level3" data-number="7.2.2">
<h3 data-number="7.2.2" class="anchored" data-anchor-id="spatial-scan-statistics"><span class="header-section-number">7.2.2</span> Spatial scan statistics</h3>
-<p>While Moran’s indice focuses on finding correlation between neighboring polygons, the spatial scan statistic compare the incidence level of a given windows of observation with the incidence level outside of this windows.</p>
-<p>The package <code>SpatialEpi</code></p>
-</section>
-<section id="population-based-clusters-kulldorf-statistic" class="level3" data-number="7.2.3">
-<h3 data-number="7.2.3" class="anchored" data-anchor-id="population-based-clusters-kulldorf-statistic"><span class="header-section-number">7.2.3</span> Population-based clusters (kulldorf statistic)</h3>
-<p>Kulldorff ’s spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.</p>
-</section>
-<section id="expectation-based-cluster" class="level3" data-number="7.2.4">
-<h3 data-number="7.2.4" class="anchored" data-anchor-id="expectation-based-cluster"><span class="header-section-number">7.2.4</span> Expectation-based cluster</h3>
-<p>In many case, population is not specific enough to</p>
-</section>
-<section id="to-go-further" class="level3" data-number="7.2.5">
-<h3 data-number="7.2.5" class="anchored" data-anchor-id="to-go-further"><span class="header-section-number">7.2.5</span> To go further …</h3>
+<p>While Moran’s indice focuses on testing for autocorrelation between neighboring polygons (under the null assumption of spatial independance), the spatial scan statistic aims at identifying an abnormal higher risk in a given region compared to the risk outside of this region (under the null assumption of homogeneous distribution). The conception of a cluster is therefore different between the two methods.</p>
+<p>The function <code>kulldorf</code> from the package <code>SpatialEpi</code>is a simple tool to implement spatial-only scan statistics. Briefly, the kulldorf scan statistics scan the area for clusters using several steps:</p>
+<ol type="1">
+<li><p>It create a circular window of observation by defining a single location and an associated radius of the windows varying from 0 to a large number that depends on population distribution (largest radius could includes 50% of the population).</p></li>
+<li><p>It aggregates the count of events and the population at risk (or an expected count of events) inside and outside the window of observation.</p></li>
+<li><p>Finally, it computes the likelihood ratio to test whether the risk is equal inside versus outside the windows (H0) or greater inside the observed window</p></li>
+<li><p>These 3 steps are repeted for each location and each possible windows-radii.</p></li>
+</ol>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb12"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(<span class="st">"SpatialEpi"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</div>
+<p>The use of R spatial object is not implementes in <code>kulldorf()</code> function. It uses instead matrix of xy coordinates that represents the centroids of the districts. A given district is included into the observed circular window if its centroids falls into the circle.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb13"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a>district_xy <span class="ot"><-</span> <span class="fu">st_centroid</span>(district) <span class="sc">%>%</span> </span>
+<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">st_coordinates</span>()</span>
+<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a><span class="fu">head</span>(district_xy)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code> X Y
+1 330823.3 1464560
+2 749758.3 1541787
+3 468384.0 1277007
+4 494548.2 1215261
+5 459644.2 1194615
+6 360528.3 1516339</code></pre>
+</div>
+</div>
+<p>We can then call kulldorff function (you are strongly encourage to call <code>?kulldorf</code> to properly call the function). The <code>alpha.level</code> threshold filter for the secondary clusters that will be retained. The most-likely cluster will be saved whatever its significance.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb15"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>kd_Wfever <span class="ot"><-</span> <span class="fu">kulldorff</span>(district_xy, </span>
+<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a> <span class="at">cases =</span> district<span class="sc">$</span>cases,</span>
+<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a> <span class="at">population =</span> district<span class="sc">$</span>T_POP,</span>
+<span id="cb15-4"><a href="#cb15-4" aria-hidden="true" tabindex="-1"></a> <span class="at">expected.cases =</span> district<span class="sc">$</span>expected,</span>
+<span id="cb15-5"><a href="#cb15-5" aria-hidden="true" tabindex="-1"></a> <span class="at">pop.upper.bound =</span> <span class="fl">0.5</span>, <span class="co"># include maximum 50% of the population in a windows</span></span>
+<span id="cb15-6"><a href="#cb15-6" aria-hidden="true" tabindex="-1"></a> <span class="at">n.simulations =</span> <span class="dv">499</span>,</span>
+<span id="cb15-7"><a href="#cb15-7" aria-hidden="true" tabindex="-1"></a> <span class="at">alpha.level =</span> <span class="fl">0.2</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output-display">
+<p><img src="07-basic_statistics_files/figure-html/kd_test-1.png" class="img-fluid" width="576"></p>
+</div>
+</div>
+<p>All outputs are saved into the R object <code>kd_Wfever</code>. Unfortunately the package did not developed any summary and visualization of the results but we can explore the output object.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb16"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="fu">names</span>(kd_Wfever)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>[1] "most.likely.cluster" "secondary.clusters" "type"
+[4] "log.lkhd" "simulated.log.lkhd" </code></pre>
+</div>
+</div>
+<p>First, we can focus on the most likely cluster and explore its characteristics.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb18"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb18-1"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a><span class="co"># We can see which districts (r number) belong to this cluster</span></span>
+<span id="cb18-2"><a href="#cb18-2" aria-hidden="true" tabindex="-1"></a>kd_Wfever<span class="sc">$</span>most.likely.cluster<span class="sc">$</span>location.IDs.included</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code> [1] 48 93 66 180 133 29 194 118 50 144 31 141 3 117 22 43 142</code></pre>
+</div>
+<div class="sourceCode cell-code" id="cb20"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="co"># standardized incidence ratio</span></span>
+<span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a>kd_Wfever<span class="sc">$</span>most.likely.cluster<span class="sc">$</span>SMR</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>[1] 2.303106</code></pre>
+</div>
+<div class="sourceCode cell-code" id="cb22"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a><span class="co"># number of observed and expected cases in this cluster</span></span>
+<span id="cb22-2"><a href="#cb22-2" aria-hidden="true" tabindex="-1"></a>kd_Wfever<span class="sc">$</span>most.likely.cluster<span class="sc">$</span>number.of.cases</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>[1] 122</code></pre>
+</div>
+<div class="sourceCode cell-code" id="cb24"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a>kd_Wfever<span class="sc">$</span>most.likely.cluster<span class="sc">$</span>expected.cases</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>[1] 52.97195</code></pre>
+</div>
+</div>
+<p>17 districts belong to the cluster and its number of cases is 2.3 times higher than the expected number of case.</p>
+<p>Similarly, we could study the secondary clusters. Results are saved in a list.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb26"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb26-1"><a href="#cb26-1" aria-hidden="true" tabindex="-1"></a><span class="co"># We can see which districts (r number) belong to this cluster</span></span>
+<span id="cb26-2"><a href="#cb26-2" aria-hidden="true" tabindex="-1"></a><span class="fu">length</span>(kd_Wfever<span class="sc">$</span>secondary.clusters)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>[1] 1</code></pre>
+</div>
+<div class="sourceCode cell-code" id="cb28"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb28-1"><a href="#cb28-1" aria-hidden="true" tabindex="-1"></a><span class="co"># retrieve data for all secondary clusters into a table</span></span>
+<span id="cb28-2"><a href="#cb28-2" aria-hidden="true" tabindex="-1"></a>df_secondary_clusters <span class="ot"><-</span> <span class="fu">data.frame</span>(<span class="at">SMR =</span> <span class="fu">sapply</span>(kd_Wfever<span class="sc">$</span>secondary.clusters, <span class="st">'[['</span>, <span class="dv">5</span>), </span>
+<span id="cb28-3"><a href="#cb28-3" aria-hidden="true" tabindex="-1"></a> <span class="at">number.of.cases =</span> <span class="fu">sapply</span>(kd_Wfever<span class="sc">$</span>secondary.clusters, <span class="st">'[['</span>, <span class="dv">3</span>),</span>
+<span id="cb28-4"><a href="#cb28-4" aria-hidden="true" tabindex="-1"></a> <span class="at">expected.cases =</span> <span class="fu">sapply</span>(kd_Wfever<span class="sc">$</span>secondary.clusters, <span class="st">'[['</span>, <span class="dv">4</span>),</span>
+<span id="cb28-5"><a href="#cb28-5" aria-hidden="true" tabindex="-1"></a> <span class="at">p.value =</span> <span class="fu">sapply</span>(kd_Wfever<span class="sc">$</span>secondary.clusters, <span class="st">'[['</span>, <span class="dv">8</span>))</span>
+<span id="cb28-6"><a href="#cb28-6" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb28-7"><a href="#cb28-7" aria-hidden="true" tabindex="-1"></a><span class="fu">print</span>(df_secondary_clusters)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code> SMR number.of.cases expected.cases p.value
+1 3.767698 16 4.246625 0.012</code></pre>
+</div>
+</div>
+<p>We only have one secondary cluster composed of one district.</p>
+<div class="cell" data-nm="true">
+<div class="sourceCode cell-code" id="cb30"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb30-1"><a href="#cb30-1" aria-hidden="true" tabindex="-1"></a><span class="co"># create empty column to store cluster informations</span></span>
+<span id="cb30-2"><a href="#cb30-2" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>k_cluster <span class="ot"><-</span> <span class="cn">NA</span></span>
+<span id="cb30-3"><a href="#cb30-3" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb30-4"><a href="#cb30-4" aria-hidden="true" tabindex="-1"></a><span class="co"># save cluster informations from kulldorff outputs</span></span>
+<span id="cb30-5"><a href="#cb30-5" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>k_cluster[kd_Wfever<span class="sc">$</span>most.likely.cluster<span class="sc">$</span>location.IDs.included] <span class="ot"><-</span> <span class="st">'Most likely cluster'</span></span>
+<span id="cb30-6"><a href="#cb30-6" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb30-7"><a href="#cb30-7" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span>(i <span class="cf">in</span> <span class="dv">1</span><span class="sc">:</span><span class="fu">length</span>(kd_Wfever<span class="sc">$</span>secondary.clusters)){</span>
+<span id="cb30-8"><a href="#cb30-8" aria-hidden="true" tabindex="-1"></a>district<span class="sc">$</span>k_cluster[kd_Wfever<span class="sc">$</span>secondary.clusters[[i]]<span class="sc">$</span>location.IDs.included] <span class="ot"><-</span> <span class="fu">paste</span>(</span>
+<span id="cb30-9"><a href="#cb30-9" aria-hidden="true" tabindex="-1"></a> <span class="st">'Secondary cluster '</span>, i, <span class="at">sep =</span> <span class="st">''</span>)</span>
+<span id="cb30-10"><a href="#cb30-10" aria-hidden="true" tabindex="-1"></a>}</span>
+<span id="cb30-11"><a href="#cb30-11" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb30-12"><a href="#cb30-12" aria-hidden="true" tabindex="-1"></a><span class="co"># create map</span></span>
+<span id="cb30-13"><a href="#cb30-13" aria-hidden="true" tabindex="-1"></a><span class="fu">mf_map</span>(<span class="at">x =</span> district,</span>
+<span id="cb30-14"><a href="#cb30-14" aria-hidden="true" tabindex="-1"></a> <span class="at">var =</span> <span class="st">"k_cluster"</span>,</span>
+<span id="cb30-15"><a href="#cb30-15" aria-hidden="true" tabindex="-1"></a> <span class="at">type =</span> <span class="st">"typo"</span>,</span>
+<span id="cb30-16"><a href="#cb30-16" aria-hidden="true" tabindex="-1"></a> <span class="at">cex =</span> <span class="dv">2</span>,</span>
+<span id="cb30-17"><a href="#cb30-17" aria-hidden="true" tabindex="-1"></a> <span class="at">leg_title =</span> <span class="st">"Clusters"</span>)</span>
+<span id="cb30-18"><a href="#cb30-18" aria-hidden="true" tabindex="-1"></a><span class="fu">mf_layout</span>(<span class="at">title =</span> <span class="st">"Cluster using kulldorf scan statistic"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="cell-output-display">
+<p><img src="07-basic_statistics_files/figure-html/plt_clusters-1.png" class="img-fluid" width="768"></p>
+</div>
+</div>
</section>
diff --git a/public/07-basic_statistics_files/figure-html/MoransI-1.png b/public/07-basic_statistics_files/figure-html/MoransI-1.png
new file mode 100644
index 0000000000000000000000000000000000000000..6e841a94cb233b4ffd4a279d30121824c07592d9
GIT binary patch
literal 17107
zcmeHv2V7HWy8ag;0Tsm#2!f8Qh=pRI2?WPc9F-;tA|(+8EL7<wMV%1^1x7?vlwcV^
zse<$p6cFh+5ULOaL+GJH5|Z2#YNC7huDf%8yZ`^){0@Y3zWP4z^Oo<N^Kr{SPiNVZ
z^-BN%%YHuc(+L0&(4X*pVL0?v*!JU5=<AEY@so$3ZvfN*umS4oKppxW3~bV%bLfP7
zf%~yhw}Fmeb?AC<vkg>L9Xh73+5m0|_Y-Ur3>|4UP=z$;-~_9KU>oRA4~ELPh0rH0
zIJlYnD=jTJ4f=x<+}s@8%t^BWX*TL<!O&sDErg1vf6~&L)0&}!lg8oH)YLQwt2YPR
zG^asFaPv$V)S6ob`f#9H(643=2kMT~9L#A>n?8e@a<46BZ*7F6T<mnj)CGVIe%v2e
z5M{_3fQ{hipAMY#eB9sSb8dD0{U~R(6&jm1ncD=`Nd4%N<+Ih*Z*PtB#(wz2tD|U<
zb|#MSTb$XhmzSEYPjzEr>qeNeZ<XuHS}!MB_nvs<3j;6q8VUh$K@sX$4g&lyMF8Mm
zhyxJ32EzTW6#&{NL;yJA4+G$5rT<h?0(a@28V`>LViTAnRG}fG)Yhrgde03H@}_Lq
zw8?QCwt-!~ok{N-2}$(O!fdWT^F}YPWXyzJG)4A^Chrv<K-1F2kpb%1-z!&qyr8
z8Cdv{&ón{}Qz+4Qz@gWA0UzE})_COS0hATXu4mVB_bp&tBybvHE02W-X1#e4!
z4Hb@@;*gh|snE)SRXb25K!!Zj^RF<c-#3ZiQ%Z)(d+x~4E(6zVFt8FTkV9zey4V8O
zFhs{&aO4IoA2g^edw(73E>#BZ$qb{X$jN%pG*MGtE>y<(;f~?Ut(xJuig;339J}**
z<3!HbWI?+RO8HsJAvlw%5};r1>+Ll$T=~dRCUN~xKvBHD0&=K-gp&S9$MaKdY`P=y
z(d#CVo}9>)#jBde5g`vv4zG)qiDlQMt=qD*X&)O#8rqA=vMkLQZa!v|GMuWU;MiLi
zBI*X;h>h{~$(A&v+Z}9;63#AzyNKY=C#Zos{iw&882Zx|<<X(foyU}Au^(mSi8bS3
z(t0GFlSgOklu^?a7*z6(s`ebu47PD9=iZZM$9;fJRxpF*`DS`%v6E?+Z&VIEs};ew
zBiq#BXxoeK#(Bz}j5G&gf&>WrNMx|e^lm@8lTis`0u0hM6pO);PH%Wy&XxONGR+qc
z+L9DZ$;j7U>pQ=6;fi2R9z&nKBwsPJ!&oB&ozGDmvhGc{-d8bn>3Bpw(t+h;B@~+(
z5MyKLE~HJDak>LbVpcU-(wiQHib`WrSTu4^YbdhTzHlEx+v1ld%2hQ;RrTvZsC=GQ
zd$WC)2DT*G>o~yyld&5pqr@4-ulDCPu*0*-xvvJsn?>;bIC3S?o2fUNb*NDSm`uSF
zq`|&pDWQ4FHU(LZCmp>;dbRrxn`?reA8Hju%OUbMst+%1h6qIQ9dk_KFh|Q?(R^=-
z9+IzQew+&IP$>?ly}n?a&arn1D;x(8a4i&-ESC4!p{F=3hZ@#RR3MIz$C5nA7iE{F
z<5)sh#mE@h{Es1`s3;O{^bG4+-*WsP$hIDsLH6EF82j=ffhyW!vlg|KeZU=Cl2PM%
z*+dkdCA@4O+>xu&eW3CctFulNxl5+2+5TW?_5pcj;j^E2VuQ`u24^;avg`m4Y+H+K
zXlcuVrxyo437y0-?GgFy0m`r*voD9C;ilDC3Ns+?C5@&k#rEdq^!KCC%H;OpfTii~
z6cBT#+F;M%dq{^2c-sZ)OQ~l23z*_^dQbSt@Va5qP*~DHSq+lyKA}fp+99;Z@`foB
zYKf9ySvuJU?95|6i;t%vvyABDX6dHHZO!n=DbWmu3cl(0mr;p#8s7}84X5T=VzDcq
zjn^eefz*}jFCkjRL5cZg5SQ0gCrUhJ*6l8N#^ZyV*fJSQ-#5F#rGYgK(xA-7i1m^<
z9=Ze?#|rEuc625h6Rk!L4iA(T9cq*Y6kL941R^VYFUc-dDZDP%%Eg65AoV)*L!wGP
zeQMKohikafixRY6c)HTYdM@t}!o^l4M0koLbG+2s83N1Rj<z5%DGx<RvI@qMXZpc~
z4Awe0nj~*RXuycOT}G1>O2@%A4m?2<wEtm8#-*%Ix!B@yzprw5e<9hSJ>Fs;=-Irt
zRwM`FOlE71HWC>pO=~Xe$k7DKnl@v_4L6lhZ+wvKqB5Ou@}V9f?J>0-sc`hfxZ~i_
zws)X`A(!cHcoe!I;}j1|%HB(XIT5{DVvVa<YC(jS+*C;sJX3epvgto2b(i&69Llab
zlvx5|-cVGA0%OjK;F}J0`-0kCy0UQekS^Ao745azK^62|o`INirJ7)gP0^|da7d<F
zXooAH@(>dPqC{4G-8leRpQQ(kB#MtsNKZ-GrXmBzCbH_~D=I-lphTiWt<$c^q9Ary
zdMe|OCbP@ppf~5&(583^&vW1}H3KZr%Ax6m`DG5Di0>4-ipyy~(B^jijD|4N7Za``
z4v~Xc3^Le)_3xg!YJi@wsO|%83`z`ch3D8WPf$VW>#V4C3G0DL+{w7<9$j*Uu99<o
zN6FY$`n6aB;*9;7{rd1b$fw3ceI_i4Q={#H(5@kyzeL@0hetNW?9e~l;v2&FU2bY%
z%$j;x5@G@))?-JkDef}q*tOcu_<2%84(y}Iz{xx`RR#Y@%*vj)@gntCbnJb@+@(*4
zr>c$Nk)OvWBtSr3=9D0{E4w(cUFG8Gdl2?TNRLd7*A(TQy89qAjdBZ0Bg<!gu1gcj
z*K5rZ)}6J_G0FU4x4046D>;~qZgGYCGMEYKtHo>N1&17{CssHEDNR$<-nOmWQOe-x
zhq+j=lS3loCU>)ZS}3wTV!yY5(^1$w(}*lsQp&VLpkyJ*S&MX9euyJptcmZ>(ejja
zwD{%5qpK>A<5S5J|CD?#F0spn$nYE7@_WGBBHNcI?HROGA?<>GmF4(L<2PVQto51k
z_3<QyquCIzG|b2^uor)1G(9k}6mbZ-#7wT<pKgq?xPpPim~%4|8wcwa6H)Z0F+yUF
z)TjyPT+2->vxIT~?A~LC)1|n^z8Ab|ltkp$3EuILro>rr_26w?^_&>je4f?SvQyU_
za@i!?&$x7Yz{lZiawB7;F8&lj#DI{l{3E6!UlNMim$jC5wVP7DAWbntJ-be>+wjGn
zvdmPOoHTyt=d`9_M!b1ogk3^bjXS6%V>=FJhW6>g(IL5vpw<|(d-vh!kwRuOk`OO>
z$!)Z5S4CZE{rkrW1udM0y};e_Hw&N3pBvGsUcH-Z>qX+YHaT9St-$Uc&ee6mFmwLU
z6{D$7w)EUZiQ&w0wsgcgtqw!&#T_f`w595k%ZYSK_QChjXVWA=YC3t!JVJN;JuJyP
zq~!TvP(o{4<+C>%07{EBTrrHeB&6N{hi@Y{MA77lUxo;%M?%^Zbtlw%$6a*?ETDLt
zx({wE0!BNVs^Ww;z6IKTQTnuqsW({mU*G`pwAz06^>@Z;XcEHUusm_l^~Z4hVrmrv
zrQz~;?n))I!bx;RTL28NXP=vPGwiy+d#Ivu#=EJBQCz+_99Z};!^&*0%V3z3`fh8$
zmj5K6e@_msieH@jenq%I8xRM94Qqf<K5#0G0;&Lk->fW{4^sqEujRmUJgn`eF3bst
z03Ev}csLrUS{VT;XrZ+-T;RV+@hi4k)|SC;FY{ZXTg$@wc^|;P{%r8H<oqx}PaG7y
zXRBEmRsRCRFMo}L#@%}sL>}xTKtt+6T3x}U-qby?8UfS`zpom&Ed>oH4)Q-Z$3UI`
zeW%|sT+D>-!#qyM=;&zrgbX8Zlk1%s0T?a!JgT-zPFRk4n{};+gAG<3sj*BsF;Ur%
z{RE$!eRK7^KiwPY@TwvDBo9_hiRvK7JzVCir^^v!%Ga|;N`+c05${Zh6Yf6TGVx6I
za#EvSHX-O2W^Rjg)_VXBC!`<Thf#lMNB-=h_0YE><tpMjB&)fj-=*;mb|p*GP3HP8
z1W>#p0w7$$=6Wd7=`>d{zQ{)&m_8>z^?qH`PZeGIsk?u?dLOqcYs0Ic;*`aMS;JQY
zOgUuw?|^HEkRoD=b=9(cyX#Bzqg{ydmW$t~Xba7%jq&N8O0ikkHC69FI^v&R76Gm|
zSuVA`QO8lnI{6>ZNdxIMGb-%yF^Zz;p&}kX*3iNnnvhxl-)i=GfnDinPz{-_@nP4~
z{j)uiqkO%Im*|dSjv_9jnxb%#C9??Qc13n8gi~QdSjB_yxVUg&gI29{;(j%+y)v-l
zc-XYGOrT0gWfftNBgYOnDOJy1^n9HOK22FUnJ=|c<uYbW6TFkW?yS}|gV6*KrooJ`
z2OpFq<h}c>&aL4k3IcOhaa97>KqPsI;)9C&r3E`b98&_-o5rgQ6XEDqdesimsWglT
z{_by9)0BR$C6r$tkMkT0>P5jiWiE~F+<5e`{|s%srNPp$3FdJQ_S3i<xOW>`Jx?<y
zL$1a{L1u#^BH#CiH@?Tv^9>ldgAW?loL+`+PE4F)ER0cLUpk6BlZHEb`1VZCaVo#g
zO<;4c?$h(o;+(6@58g)GB%l?$;*~l-|IG@}vi)!+!@&8=?_BXrWwr<AKvNJ`>pfWX
zTNt#8-|P{5?7;D~geA`XPEuZ5cqv7Gn&tTch%3)3c*M%dhbW}6Wpfea%Nvk77>A>t
z2PeZL=LU|c*Oem*4U(ou=UR1-hf(E3_UfB+vwV(Kv1Yg?qF@U(yo|IW9#8dFaFn-f
zwpIb<F%!1v(~3HE;XjrfQ39p4%sq-bAIwPChrp{J&~{EMyr!1iy5{KN(u9szs~4@2
zJ)EEAuXgT)`v#LI8zWVf1nN$eON1o%X7ntA72R5ylwei);GRYCDOurddbjazYhB*I
z=u=PN_GGmvF80Bmt=9F<q{RaMt2d)9iXJP;We3LUtuS~j4(r|CdHd%^H*>dZ_;$Nn
zf-dKC<?h{{?Wywq+$8^X75;H)3WZObDA^wWdjM=)wX}1FP_ww~dW{a8Cf+Q<|B4Fy
zy7>-izJm@aTh^8THWp>DdyZIUR&S+D9hX2fo#D&BqQd_Ux%mOKJvMJ}GiLI&!Tl>L
ze21y>OY<Gx;orfgznQ~7EY0_Lhkpl~{(27IVXA-AbN@{M{~c`l>pA@6(tL+^;M#N#
z21?jCs+yXtewLr)l*N2R<r+8?swpigCGT@h>^bUuKF^R4er3pMRSP?_MFk4|v$1r#
zLuaGPAgV5BpyZv(2vUmG(6gW4eU5#d{-)E{@rP8Fed%l(Y@a8{KdfW;?uB%?rL$3+
zzh$m{X<sqx3Dc)X%NWWXc*1fa&|W<k)URsM1k{_bb+R6?W&U$Xfi~{clvQ+dmCU+~
znoct(p8UW)){|kTLZ){N*$Lz%__kTqaXhec+uG;zf<oaw;~}b0h@%<m&C|+8$}yrI
zR{aUnZRlu{ag~5IxG+19LgCuwcu9*4+xqa1_+tm8G%rd7?uj}-mw6Z%6*-E94XR~L
zcu%<W&!pBJX(o#(JOkAl4~<e(%I>qMd1M@8V3bl)QqoalqLLxKcRrL)Yc5LHv;uDy
zkF%q#;79PRk=8C+ekRL&9~?@+c;b0!c=BUdKP{Ksw&5+JY$mOm?y5a1$Ab9OB%4Z0
z9127qv{{IJh9glqm^V4_uH*pnd4a(|bOCQ+LDWv%II4A`hOvHmn5RzC)s&fZjGHXP
zI2ajwe6q6?9vsS`_;_JHZ+Ls7if7Cy69Ih(WRT2dO#rog%G(kP?2!Go<FAeDo!Rg9
zU%P{!*I)~X$wU+~>&O`_$#=&uy~#6mEuK#gyEeQP2R8FbpQn!E-q&;K;f0v?Zq7rM
zo+=It<-lHrZe3~DHDB{m>}31L_Jl`OqFZ%vx!oR}&{Qkux{XZmuQJhZAo?D@kgYQG
ziVNLBS(HB&nI(h4dC@AOQ4YQmkqSAR8>)Foc``-rb0t$uB~!R?2~Ak}!ff`+bq4(o
zM|~NUef3w<6kq}5J06Q9ck<}!5^AxzS29~yUf`nypT%xQfJY4r+3HCjF$2mETK1@H
zk{n;X=Z|#NVl_r=*|#Glk)p1S{ARQ-{0hB~<5NW@;yA@qcVMnWV6giP&+JI{rNx6^
zDkO;_XdHjjv9N0mIblrAmMYG@+YjbdQ&ZH&o@|E5Dq7{($_{hfnHEnn@>k_a*fDuB
z0FG{$hn*4I9^fZ}KRc`XTPwR>`%@LRHPGZ<@Z{%L8Qb%G7ojPB;aV#UCh`X3c?~zg
zcm0JjANy;V#LaJc76TVNk$4A0{?w1Fn4cCG&KFG6l6_)Dh$GIMI8Ln~GDo{Di30r2
zi-Zyx=%m3?C><pw#MUWCBfiX#WV!r|7u|0=Kh&|UqT2p<f8$A&W5(q-B0!!ZDBU(4
z>&HX|Xk&e>fv?6Q%HT^9p~WKaa$}joqW#`e>^4JpL;j()gg-SdeLMcsyw@ufRs_|B
z^F*})8d;K<GVq~f?$URxn6!=7;?$uKQ4rQGZ6eSQ=6#Lq;mACHvTus#cokJB9VMe`
zuy(#|+IckT(yhlv^@l<a$nklb9%XBGpkg|Q?x_qqY0C!3bjhnczv9v|$HnyX;{}{4
zL9`Dsk!i{AuP!N5iYWW9?SeFEf!XillT`OrIaw5qC33ESa_olc7NG@TxXZZO$v|`&
zY-6tSUOw-*5)O2EVp+TV#yKZ3!;S-O%wCw&`|J4^7hL+uA^Pw>^axCmiHksZYp+)5
z*(%vkWGJ>YDgDv*2;>B(i|z}Kb1?6gzFmH#h2{|xZig1rv5?Pi?Rlk|BP$NwRgubG
z7p=DfY7_=FYT6#bS)No_)VBOXLeb0Bi`<=SDFS`*PyH1lDiVdfU1_AVHFhQL@B7X?
zRzEP?Q(UZSvqZ{e=blAZEu`EsfzKVqi1@j80a6m$?QF~E``SITmM$^g?Y>Lz$;PCB
z=kj4!&%Tu+<*b@?l>I0QeQ7WB4KKK+_9}OsL18L>c@cjf2>i<Vd6(rUp#vd})G$L)
z1l_=h9L~t#%lpZpw=DvUWQF_MW6G?#D|!>V(&CPikb*@oL*mc#50Z7ssPbO@wGUrU
z%OX`S1qI8H8hzT3s_J$vUp_F)9C1U?#g!BV1stLC_3gEb1+rCpuE56K?~tK;n|@Zj
zm&VS4oGoA8F0{qxu7%<`79yVp!fD$)1Y&4M6XJ^7wy+HgQx<G!4u!YftcOYQUNfrz
zo~|Ap&Ba;uusxvgrqSJaRi&eKrylp;ZseOGbgQ88=zD(5dUe0S-PG}D+TGXlx)TwB
zq9YVz*sAd(;cXQ3*IhinoU`fnfc@ETuoVHD=cSoZXsh7pu;*_2Ky*zF?h$K3+JjfP
zX??hbU%_h7v5f;&TSI7~k7U0=pJaE`Q}lsYNJ)^;?bX&hB<2-9&2Fq=F1y)oy^~tk
z!36<;Pb_9d#xP!iChV>~KO+cV-U&jd`>F)I&*V099(yd>&u0LSwrj;|baUF@p1;D0
zy!tBni4yOq3|kn)uPTlsqw_R<DS&GSsBUTWU;X?fQypJ)8Ap@1giSHp9@g<Tn_;I4
zrGJRAWCdy|6PNWh;Af3m+16TchZdtWj_;Op^9+&@pS}Tbo=5WO&f-+In3XJ$ic84a
zH*y5|M2;G3B=T$;FI3YFdQ>PCDgho~a;i;PR6r(>-!4+ahs%0)p|y}Pmf{0#->4Q+
zlX5S6)>(%A+V(42h<}QP1v{=1%CVCKl;{tZ;$79eJqR|K^)q4R<P|nbpfhnvUJ7%I
z&|O}x;&Vxs%Uq{j<=_oPK8vcG#DX$dJ`*MtJU?N<21$7SP2N)vm;|5taVsX--r(`j
z#=*}E5J98NdrI780J+Kq<C~$YUFlRNN2iJkM>A-vEqTc^Q*K`h<=D&Q1)WvrSv6DO
zP&(y--y)CjSfJZ<!9Kgvq7?d=cF;hsy4|B)Ut1D%L-8A9B-xcJq!VPcbmHy4Vu4}D
z(zjCI@L;`y;OC8BGvOpt65?gSyyZjQJIeoe6Pz$FCm{pM+KzS6$Yj+puj@31ex;F5
zf}`mn#N)5{9UlaumaxWIaD)$65xkDab4Ljv#OwKNEQ%T{AMmIt+-<Gx{&W1${T1H>
z-RI+F&$OE$=_+Lj7ykH-n>q`8y*bf;(YyDxGk+xmwi1_qgO)fr%<uHAfcOG)xSsDO
z3|%;n+jOMjjWSD<RQ|lv^mv%lXifL0#Nt>^IKBV+PV?kFHuHuL8&88?aTvTG%o9$y
z&R``k_h-R*$aX&Cm;FtA{44bOJMpdyzxy?!$*uRkW+ZfD@*9M|@=N$!QxoSjKC%8M
zUO=Att626AbTVyzf0D2^wIrXloL?ly^5kkJMpPb6^|N$aO?EFBorK$%WfAi1VU|N_
zwr!|D?!>EpRMl)6u~F|9$8<>l!OZ=NUfX-k$aE%x>j|P`Rxc`)8$#}2FW%Gh?L7-F
zvJubpR;-9F<it(Nmd6lv=~L*sL4t|apu6&lJVtIsIyYKs9(uBIqu$SHDc2lEO_Xi-
z_hYqI4M2A^8vUDQhbVD3uD;V+YQu2d-I!NE_1#U+f}Z0guT8bkH<T5I(ue-INXgvL
ziuoHCcjIIFz5StQ6OZrO*$TFxAsgwHgPvnJA5DI;*7bQ+Ha;+oFjiurZT;2g3hr5~
zsk2x2+vgohdzQxAhL{Y!l^6~ZcgSQs7~?!aE%9F%za3{hwc4h(BkHk5-e~Wa=$cHF
zSmL6~V>_!|As1)_WmoO@CJECT$dq#oOotrs=!+JW1>t8APK0jFm~MdS1T|Z(+zV-E
zYz_3xM0E?>ma7|#W9ev1cUeeCNO5$cgOg?#m(09<OW2pLNOW%9#RvL_3r6B#R>+xA
zKAu&!W)ycj;?g*mztN(jkyb7$bt*kT<%Sv~Lg;E)-wceaI4SJ}#pmoq!M!Z&5sgT9
znovl>`Pss0jJt3k=Ya>Crl%)ep#x~b##XbFJHLNN*I^pG&9`n`Y=Tv;AozCwwa_`y
z8Y`D%ePn{U$BQ|ePhaKLDMl1O_#SP(Jgc0S33)==o}%KdE24O>F5|kj8M^(Y+4O+Q
z@<H+ZPEDXCy$2lS7s65~KWBtsB0Wh_!tdq-E2avj=+Y}=$?9O3;OTyz>kQ^*Gpped
za5^K0Y|EH9XDMW0!-xJD-*ZTxV{PB4o^wMnMJ{PQNJpXQV+Wu}FiWqgDu3L&+so7C
zYB(1f*&|TGKf~&oF=ta?UR#@WWW2hcaTGj!Ey%K4;ODe`)LDn{TSbz5xZNRp9xdH)
zYdpW>5-*5xWn0Y*n`ddr)zw)GWqz|<)|*^nT+2tWS*OZt`m+)7pOk9`s2TsvXBsok
zo|mb!iOGy>nc+R(w5BQYozhKvsMBG({Ep#!fu8XLeERwm<(l!de-7MSSNXltagF^y
zH2RxH@*f&;qxJuz-l!CI)TaGV%V8*>HxzZV;`&OU$XplxhfhfileOGUa`8<gE3s&5
zO0o)+Zkalk!Vq}ICq$v#CcRrYpE3OhkP}h_FZe4hfouD#ZgF?^*4iPyr8gN`nyid2
zl-H}W6?}f)LRkdJO^-#7L*I)ly8+vH=<%v-RZYU$+jrd>7y7zpm@F@ez^`#W+Sfkn
zYpi&*&bj~u|Dbov;&DXPlEWogcH-bfq1@|$ni12+a46nD?;gze6`D(zEr*=OpIYTy
z=U}vi3OZMARstoL$(q}eNv&(9XL-};9S|4p)t#317u7AU%&SSQvb;qYD=rXFkqG{u
zFX{z|ceC<s(pwBiZ=4gq{hs3gZcz(%W8B28X{cw%B22?PJB@#`Xi%LC&R>Ug8n?fr
zX!q+HmmLz@d)?-A(c?~xr5f)(S=alHOQFTiM=!M>S-l&qKb^RAnyZC!XMxBsV_DPm
z`|<Ir6jc%Y)`i;T?TX;hLS3bR0&u}9SALoY&|+Zca(Lvef3Wc{^)TLn5&7B+<M7Yv
z&nfze*1H?SDems>cBCOcwb7*8?zI21FB7_9#<l5{@W=zi-r)h$-|Jg_NaKlnxTZaa
z2PUDcs36|Khe>rOM^5~(dxuf`y%i9j4~gIrnh9m}p`32Ars<>&+wZxI8AfQ9`c~`w
zVAU^(Zr`kw(6iQH<IElb6I*2t7h7Z%!<^D;2B@1qW5XTa&Z>$F{(2v~da@JriWu*5
zX_j@jOr_E_RDx=(gYx=bTi^;p8-tkpCnjn!ajOJ@LA4tJ+RT@)?b;H}%vsuXfoV#x
zrwIrsuG3gqY={dVo_oC8+z(TH51eYDw+%HSbn*3}qUPlcPNjk%I03!x%3Tb0dYEo_
zGUcj1(c2!1j*k#rg5C?gG&}Paq$pZSvwNrxh@XS%x*0_&#BOfuQW6DlQzalZmJ7Ym
z7p<TVEhGqe&zSIA&^73-+W%>{oD;}d&V9l5JKoLp4_%DciU~@St1G(6xDB5FuJtME
zwAkj87Z=AGz3W-?T4UM&?X!R7o<w|8QA$V2m#)^{8~QlxAc-ba(eW%v-ejjK;-s$O
z$nbGg>yzVK(@%)$uZ3&(Rm7d32C~mEySr<Cu6%BOI&8=No$yytF<xHAgonrTOcsq4
zfNFI@9P9K*cXz;7Rkjlze){;!9w=NgrqH`HHJSFKEd@=R_cMQ%ry9z~m90H?A9l*9
zHb*0j;5BAF^zu335IqiZeU)275|QN`TkHjzBW}E(LW`9Mx^mW{^w@oY>FU&80+UK;
zH^D22fOu1h1nhFUXHHyGYCxmDT!@e89%;(EtTkafg`jyRX(%X9EVkYiVJ`xHZ%lj<
zyFKn+{~vuq51-4b$yDx$JLX(+CGwJgg2|@P#G`j$k*=0>&C#Oq&BnGmWZV&kZ{S={
zUEXWofzxQP?TN|2bB*Q%lKu#z-0R-b-V^4@QZbL7^`82m76dc50^3gYj^vDQs(7rE
z38AXc*k!oyQ2ndmMg<^8)B5xl7_@JzKL_p^Kv!P|(|2r{6hsHYA`1-@iov$0&`b<B
zHKOE9`0AaJ9sp;ofK<~I>1M#v(5Z4mhy0n!<`GLR5jk&x>YE;r!C1UhEogU@z;<po
zXCmlhZ4S{EPwYkT2b-ZCJsQ?(RKrd;u;rxg$F*fH%EVRM62a-SV4DT&S<z#ihb97H
z(3~g~y7k==Y{6Ctu2==TkdbXJyCPRXKxSyzeqzZefformZ>;}#UQW_J21)&H__6+0
z)Q~0mln8i95-gQea3G9s6RV??ZjnSz)5McSTaLijRfdb%lP=Uj3=(TydHa>zW%G!X
zpVy|eL1AxzX6A@0HMHCoS2iBK>e(g#_4ld6@qdT|7+kx*y)o`g&_Mja!!O$u*4A0~
z8c9HKj+Lcg5z27%9oYZfjlCPgyPI{2LrT8Xi6*MZWP7%bk^-uZ6ZG;JtiuGM+e#p~
zJltynHR-J;5JfybP>&nx*`vFR{i+IHCk{SPd{4Z#Yf1^)CxR#0K3YF@iXa5-%n9Z`
z#3<>f%Ghuw*pxn#tBF*O#~oPpmzh>aD0ZY#Tdm5i`9UL`v(tO7Pk1S*F}zrQje9fp
za1`L&Js819#R2qCbiht}ZN`*!TTNMZ3P+PMKAfo;UKK~{Amly7vFkdJl3GaSHAfp9
zr?t0V5+TAJym26?j|2r?uN&2VSqP3ZYt1tz>XJ}?v0s4b29{?RPNG^G4qle;pPazm
z5Iu#+kK&-*C!ZjYIAO13`fv*@iGHnAVLg5a0$j=L8`2@OPHqs0^%<u2Gq0%U_+<FT
zdG=n6NFn+%Nqs?L`n^aFrKryb`4GeYJp55GAKK+m5{D8V?;j!6Ts5|z@@+}8C2liU
z9*swEtmsGHW_@<VV3iN7L(&sDLQc?bA?2EMQ4^0E4a?j37V2>MdQXe%$mSgH$zzk@
zWmS$_KQvxC3839UAG%t~bb9@~JrMcP&~{CYmm2^zfEmQL9*aF#fsgDzrw!HVX>UC5
zQeSli>{M8jo_GAG3d~d)dBeJ(O?{sZ6>dO^uR?&~ro3q4@Xo3mFhz_+gitBSPl8Y@
z3GkGu7!D#qPae0X=dnIVb6(*@&;$J`lScsp+<-PJ9j|P!*;CaH9w5tHhQu8UuIC>k
zU@>W4FU5mk=nQD=^KQ{q@8axH?7}>|j##9;)`>k}`#H4Qru78DHyNdipdFj|<2HA^
z#}2Z?%48a1?Xi1+ymT!RF=)lQ;LHLKQdtxa&(|a6C-Oxh{g`W&`_M>!q%xSXD8*7s
zX0*skeW!G{1<S#S{;;%0yIx@}^qh}Q+Hp0Sc--%dZYlsU4EO&6ydqu%QCxCXytw47
zQqf+5M85Y}nk@xltL%`=T*r1k?XNPCUstFA28)6A?$}<pN}nl|n9L)xl568@oGG$`
z)7}306UnwtACAdlWT)fUCr0RHvEU;|X^jYYF*4BD{)iJUHmXOh>Y-!Dk&aY_6?xF+
zaK`6P6kBCcPM(jud2V2JB~<}>J!5zmO$fgU{r~?z5#Y#ds<@U}Sbg&|fIdGT()%gl
INA$J-0v^7IivR!s
literal 0
HcmV?d00001
diff --git a/public/07-basic_statistics_files/figure-html/distribution-1.png b/public/07-basic_statistics_files/figure-html/distribution-1.png
new file mode 100644
index 0000000000000000000000000000000000000000..036188ef50e949526f41eb9d6831f975e06bd90c
GIT binary patch
literal 20163
zcmeFZcT`kOw>L;P4Kzubj3CgGMFGhf4oa3NNwP?4a!^!|(4vBX1j!OxkQ^mS7LlB@
zfPj)DBRRvI7T@RI_q*Skxij;}th?5*u&q9)cGb@NS9R(Tq@|%mN<>eDgM&k=qAY(G
z2M316!NL6u#|5u=1#Jc6;6R{SYPt&GR~#G(92^@QoO2ur2^<L<9Ek`V8yg&(3h*lU
z9eWM?V<RCEAz@=9VFP|vNJK<PM1Y?YAeoH>_zT_viNH_rC&DHI{H?G7?^aaURDhr7
z5fV5NAiWJvgbn!l=YB**M8pL4qoN|B0&JW|OjJZnOhinaSJ>cG*ho}FfWJ1_`(O`n
zm_PqjR7_y|PJsV|jq{50iHh^{!NI|a2#JXZn~4hW7aRt>362DQf<NbAFYsgH{QMl0
zu)^kiA_7Z<y#SJ8FL#G8Pk=fgbX7Kdh=aozi2Vl%pWn2`!9n7v$jj+IO<GGP^&1jP
z!I%nJv{BG}BmF7i(}i$eTAEmJh9_3B*AYw@B=5j%uCnR+oEN$KR$6ts=<(k1Tk`a6
zc*hZT<4)|(*I27-Mz}clSW1#{aNx8s7|sX);M^zuAJ?EZ-%sZ<s^vdDS<5-Q&Pwa|
z-ENEHzQ-Q2y|wB5uu67S;L_#EX`ciyu{Cu?KRBU+V9M3Q$ILL@kI87>@U$jIPFLdr
z687)JcK~Rx4K5<W#gP@0XyAs^>fo6WghG|?DgqS2Hk21P%0$G>I*W+UNmR2%p^;ib
ziD<NU`fZ?2IeR|mZsbWmeqe=p1GyFhyiL>}(HF6v%3XGP6p9`PfcocX`uA(2F0dhd
z=vHW>4-hxanLgIvI6FGltM^NlDtXSL(2U(;oklKLFtyoj%I8cxM6y7-GvDWA4|%N6
zwKgVqRI>Bi^J>W8>T=!=Et&Z*ZFZHXQwvc?yTd~C_D+ITuh0W4Qo5zuy}sm4z6lsj
zBbY+VnL<tBV@U?i*s7Z2nTO8=1p~9EYi#<3Hk?COc}FRSYUOZ=tlyc6B%Wd>n{2of
zcJB{LvJ$~``L%%g`;WWKys`~D8<_Oua=j|O-Z2~3<`6GBdF;99orHKFsp^mV=_vNQ
zgmq-UF|;#j&;c^%Y@pmlr3NNh?@nJP#?3c!rpCa7-<<Bx<x4i?y4m(V2%sF*Ti=r@
z6Do~GggzVPqHmfUzL%^A$%Vah?nB>dhdt7UjU8)!wN+L~XL5XM`|>%OJAiP}$PRt@
zQIW?ySFWS=+@4O#=p>I9^J3L?;FkKYOpjBHgx7|P9!rOQ!Ts0icYv0;OoIJrHe1n_
zh|_ZCj2Rxy&ToG8H(WHX&O}vE4!;N?$b?nCLfL#U6IzJOxmTy_=cnmmcbX4*6`Atn
zd#!2a!Se3?CP`LOP!GyLutG<!cG3K(S43^Vl1ELx^c`u8{zh<uw~=h=<(lB7BSxqI
z=MzK81or0W)0X~B(o5x+vWw<tBR0RrGGz2od~w~dSFo(D;Vzf-`R4WlpDOr}DM3d&
zkAPw7vKtZ;Y*g2lP0UsB=E)hw`HILhlb*BOJn3Y^NkcZit+B!VTb|kz$9HzGn9^!d
z@P=}E>i0sevlcu~+p~6;r?-lqZG?PdnC##gby<1oOqh~&U8Q4KyZ?q!NouCc=FGNN
z#+4z#%=)kTrxT2v97Ph%#;*_G7Lb2=x>1(KADG?Nv1oSXhd>>5Fgt@N3V2Vo|J%cG
zA+R9l=J1QnCyH0#*$*PnvGyMI$4$MS1QzMBzdR)KYE?YC&b+Ms*0vg~a?x9(-Wka@
z?K$+H_5uxZeuT=-F051%WwRgLt<s2jY`NF%-Y=N>{k>4dvRjF7npgVP_mKp{JMir~
zosdj+`86{u&mQQNifIhw)r0!L1>Lfd7yM5YnZSuZp=pX%evLSI9zJ+vDxWrduu71T
z9BX#(^lY}#hdo6Vuy44<)LZUe`(ggb32IMVpRb{NiJ{c5K<JfFwUA2r8`C)1jCY#n
z)>0qW6!pqp-JFtKb9o{D(w8q-DwXNv_jYR-gAhh*sHuaYj-UEyZTxpn8!kkTghGpa
zah<FoTiq~czM8tE!6>l2X-r!I*p+Qw$wUv;Pf9V(s%6BkR1#+Me4?pV3*kRDqU2+C
zvA>+>m6DgmH5=q4n#<naf^dQg1fr^FrLl^=kw`d9Ie^f5iy_^3BZbgv#%Q3*nO!$O
zT`|z(Rx3!RP0u*`X-}f}Y=Fzq^z=|pk9C;bpqz#tZ^->r1X7MS%E1yF+8TXoGm4tO
z%<iV}((bnq?gHh6v#xO@!_}Q<wiH@C^6lj`ZoQ=RT3i7yxe5Dq-cJ^)UrbhPap0n4
zU(S{JcnD8d@6C)--QG~OYFR_IsBLeqEq^I`=qFn`I$?B!D&p!V-`cL!tH%K&cV%u}
zyL`Q+KDUy18!J+*)x*~db$OM~ZoiIw{R|te{NJ07opNqU@q{)AZUF!_E+<Q_&am2T
zo<z8E&JOKS2*v>_VAXI3Sf1A?JxPikOE3X4pJfrZ(WSA^q%f4dLaXKU6^5d3Ssl1v
zsk9~Q2!5;goX5N|_s5~`w-?O5htCSgP|;`(FT6np`Tk&sF;Nfac-}baqYssL8R>FU
zvl|HBnF)>GqT5L3Kt8<SN(&-v-uNbG@zZqEh3ubp(K2VdhDM>$IsR+OeVo$CeMk4S
zMLKjhUNUiGVpqbKUh>ws2G4f$8VesUI8U|Am-Ht+Io7*B8^rMBR^o<fIx6967r8kf
z)9KFH!(&o<Zj2&lnK<?2sRHg_?P@IMmD-;F&Lqe9(V69K?pi$6X`avpbS^cC21JC8
zG4G)Cu83<zI$|AhH{j;9<gV)-_`|QwTn4{xp5Q=)*WZg%2khs80f+Vb*XR-nS98L?
zr%(Ykle}IQ2Q_&iX|L<$PomLAg|ZJ=(gdUdb(b-^m9e6Q)r?-!-s#G&XO8(QPJjG7
z{&v~-nj;eB+pov#v}F1CHRbacOv%XmlF7!U9aUcW)`-;pvDJ$d^p<#$N^-SS?sAu%
z@6NK0wx@(l^Cx@n;P=F+&9svN3ra}2NrO7T(^y)eeg5Wi(&_4A)F-!7eV^C&KbdSE
z4h8vQ9?y83ehIa)A?bJDh)%O3?tgu7>UCPVd_5?ZLFgW^M4k8STO^T=!Qg=;>m{(}
z_P1txGMdrIGUdvm<f>&9hneg2atWWk`0M5{mk(^xgGr}HR6P~EStoft_Ks6eXEK@7
z6E>2Kgm|t}y#bppeXbBaF6OGCqPsPwe{-lsa$k9ZTlUN0>pJPN*F*Pv{H{BMn{5u^
z`)cuy@!ti&^hg;Y{?tp$Q1w=_%_uydZ@}UTsjhog8U0|;xJkOw@!R+BF5iy-JB=c5
zE5AJOOwTB$V@O%y^s&=Z+YewN!VmM$n5d-^UREF%^GoP)_?l6I)}wy!CY*C*Uhl4*
zM>}k*XNhN3@0*8y(>T}{&|KCv)*x<wMab0IP`GK2(vmcKRP4mw*`@{2@+^y5{SI9C
z!K}YkCWFvZy0eDhGMfFq_}~_7B7$QR5mP|J;lpazp~=9an4?IZn8WM?jqQb2N5bCy
zarTZ~^$FWw`Mi;BgL>kf>x2DJ0kZ~EAoIsN^bWO>WJzj~VRiPU1YQH5z;U++UN`F!
zdu0oZ6W?8XxinQ!o@Ph*{()I!x#tVTF5Fx`2M5(xKe1BEKS!_j=^r<8R!5UvgQIx$
z`N+cje5b|xNu+QgyZ-0}7G@v4%&7S3<j>3qEj~C(Bvwz!N`$<vEJ^AB23^L3bSqlc
z2~K_XCiv4mT?7&uyd(|JriBTyjtkt>%#NFSf%cLEO5G2AKC*6Poqa|!!iI>UP#gy&
z5~mpdzumw<OitWT${w;+FUM$@5)W>*__XfwcwXAc2!4{9$*;S_9Q`^Ls^4Rp;M`WM
zZ0KD`3>)g4@Bbb1tUi|kQdmc$^}%`Mrcy%7O;w-(uQn8&t4yv%3(pRGM4Rvyn(MSZ
zUw}@K3|SXYx1_s@34>0V0QMi?+2ANmpN3~c^vFU2mTJ%vMO?Q5M!ec8^w3}OZkX<k
z{nb?TmV<ZK{>H;c=G>M?lKy)%ziFWUya+9_L_*YFgYQG)?6%x=;uTipH6(^fgsSiR
z#6}k%=7!o6z6fDN1QkMyb~NB@#IfOfO}KfYM)u?SHg1PW;_j$8L%q{AxeC1vI~ubI
zg!tsQ{U22Vi$2fv^H;|wCMHR|l10Pv4BQ^jhRbq2FO_~{?#;x8aWDnC^Ot_|HE8-W
zGonO$p7v20D5cd5PA9)Mf{YS1^%3Y!SQ(l=6rMO(`#^5z$B61R={((p!-f=e0Q2w;
z+-Cu*?;Y!+0*dO&=`?zlPbOxP)PM%+{;wX#nPNG)O$~YmhC6B^{IKraXP2FJ1FNOV
z_AScLYKA&ZdCw@;mR#J*Uo3nwqAa+t=J$l<4V0TW{VHae$R&D!fgQvD&Y?=y>^Zs`
z1y`On%o-z#=8oD6L&fwyb@%#>kz%LrlcQdqnzrY!_&Ugf)aet_3Ex`@94_M<XsBU@
zS#>2)oEc3}@`N`%EoLvQkWbvGi#%JGkB8|}E1Ck&G<Qoy5q<Gp<=>eb0Kjwz@57m+
zBc2`Wr|pe-zTpmA8P6PM@lXk|{6g)wcI`KimVI6lTTO<?+Ls3i%1~0ux`YK^MhSio
zayUqRqcOOXMr|}OoeYmc=dO(44b`6AgM_wYbwvUjx^1bbRHp2u!)vdT@=ySBYFkBG
zd-u>tL*M?fJCe39N^@nnVLotwiq_Uj?<Q&F>hC1!((4~ZBP~f14EE>nez-TF*ynrt
zH~SN7uRS4Nte(=PH_ZEzWwCL>em1%`u@&6%!pW_i&FDS*sdP{u@h5#cbqM>uz=VOM
zWHT31r(h``ccH8N!>AzWW%hb^&lY}p<eV8?qwFghi)!^L*eXv-8eM&m_+>EH{nvR9
z@5dqIXEd6RFW<J+2@_u|r*PV(j}cBishTOX|GcoM&pf?uaLuXRh}t)2>T8Yc$%)<M
z<6<7(hiTN~1JhCPbae0+6r8K3-aY3nls={^cE<}Jx-6HYY8Z3PtfnxgLpPF`tEh-G
zloq|vZr{zz8z-7>ZAcp;8#q=oup!IDW$6gQW&*tlml*D5t!6S@n_Jh(KrbC0KT8|2
za{+Z7C*Hp+>7wkX$)W}o@KG++y;Gy_^#V_b_aV>HE~xGocVnms^Fxko?C}-$txv*_
zh=FaZVS(oPE&4iL4HZ@qnV*jc+vs$KZDTI+_>BGZg<Nw%1mx@4aUZ3vpZ&hG+lIQB
zg~(}XL*=CkU~Msk_ej%6AUEYMJ~7H<!DwLRGCZ3ggL_zHT$ogk7TR&1%{X#)Mz1k)
zR<`^$cenf+W_UQ2S$8c%2k_Do9#4Sp5_~j+toba~^64cEU7B%E3E8}FY_cGKy)2`F
zlN=v%c~qc}gC$|Zr~%z#UC3US@*M4zO`L5XliB_;14PoN=LH5bP3_B;J>y7BZT&K|
zTKw6F_)q2cmvxUNO>8t>uCxR-B%s$p^xAmk(~0()kMvy)p0Cytf7FE)<c_=!pl4C$
z`^LW30T)k5>fyp4!&vA*tjYTP=s1wumU@Y3-kru>UdTKD-2O1y2sw9LSeaRJ&NVyP
zZ)1uKL4}-Y#=wHS5Ewu$`5=Dli8t#70BOeqqRdN6dky}f6k0Oc`#%EB&!$ERtVrw&
z*T?(iQXfR`H27zHPm$(wX+N!ak?eBK6l#CR&xJ)1o_!E{NUgSHGciZql_Wl^zD)=Q
zizeqIr<?c4wRXP@j6)1JT1?2uwMHxttE=T}&|PwpFd+;jsDq09%U}FXR!WtLO=Z8)
zjNXKJJib-Q_TVMDOhKPMW0Vg=Drj44SC2+}eRHI%C(*)Rz7oL9ic$0*$FsTwa%R81
zL?0ju&-SD9_3+qRWuD@4<5UVIkW|X8fepo;rO3abh@kPgeQo*v5q{I}(0_%`BqjNZ
zlP<N^p`pSATiMRsN9f%^bhN%j<n23svCD;ObDgc`0Yuq64%ScC%$5YH?Fo!$m#MXk
zk7_7CGI1h>y{w6T2D$gYr6iva9F6^>J}b(HGWkU^F?V|QeS<giwr*d}ouBK5Mc*Ls
zGxja7Tc^-sMcpy(8NYjU?Y7L3z&(Hm4E|patE1eKI@4#iu(7`j&Ug{}nt=UIplXkK
z95X5#+QI77rNkWnHw53W-jUJudp$Isi8;^cc=5|=#CvPepx8_3Frq-^(gKFZ$#bVQ
zn~_!`=aowrQo>FW%xVp2MZY&j4O2gHAbQ#6){m5Orz*g#tWsnP7N;Er{avD=5;pm3
zm|7xgr;(>yC`iuk)_qy~4F@OU@sZeJJI?TqzTL$xM)H<?;j^7lC>`13f_wefFtI!P
z?6<D}V1h6jaMD`md$-je$Q+(WDSjAtVu-4WJ)Q;YZTQI=yGvMHhu2*vKGxwHFMa7w
z5eEs+lbhaEABJZXj4Bg}$@JR!@tmAG^9-y_&n4~xE%`Y=T{=FM#(miXs|r56E$M7Z
zJ{#{lD<;a_NKg2BvBVAs@!)IS1}95_QFp&uC}cOXU>ihF+`mEeq|m*eS-jhGt9-QI
zdkdeE+<>+{!LU8yefh85%qwbglH*%?3B$iqN7C`EIue-97J8Rd&7YK$>V*=hyOEMd
z@SoyRXj8kUqIWXf1)Zl`>`d9nbD?)x3Z}6ttCD4Uj>h>+4~OIA{|{>XtU$BixV~OW
zJecFxc)eCbiX#zKxtYW2Xt8^I$d}rhQil7}pM=Yc^X+wvi)OlHLzr}s5#0@{x+o+P
zjvG9s!bZ5bm)@aw1GB&BCmR~%e{mB|p>@(``C!NrQGW9tNG%5-@Ie|lMc>f_*<hMh
zyy*?45T#8&KRQ7wMII8GKLeqBwgrOsWaec12uUq5i^=lQ=#iD_nbs6pn{#>KCO+8d
zB_Yb^A(g`ZKp+wZ`_m@@J(A}alGYp|4E1-@+R<Rq09JNK53Vk5+QMMz*ikTGkIK#4
zeGY#q($FQ4L#1OlJm7Y}WRMyp19yw{7cx_e_{FQVClv3YsswZ72$Dds{Sj(3eIn*e
z@rdX`3Qz~37#e(Hg$*`1{0kcF0fSip;2^FL4^8|8OF~Bk^gr$u;SIg~s}0(|qgdhh
z76?!U%CvpT*{>RJ^-B^${cnQ&!60&USiZG@yzqw9)YS7Wx1A?+4)zwGSL+w!jz)t<
zwI7LDtmefz&GJmADDKNV!TaRt6t=SB`>5gk%h=f3N0&e$h-uy3fFb4v=4TR6qF6)N
z2N9G3tjuddxfKqfwq?b<v{FEY)``xt06?QaI65tAOUVFc^{>0}E2ke`lYx7aOl-0@
zG>$ZNu)RQ_qc2g39!F`m(m~dURG_LAil*5`rE%$_uv-`RIYQ9^NEM(nz?p(Qv|1X@
zb<c*pFa30xodiNE7lEFkc)iSLvbnZYy-$kJD(+&z+@24&8h&ID*E^$>9$2)U;6*<=
z)=9AWoGeE|pLVlhKa%r!*l@L|hA;TQx%X0}MnK@$?FKnOv}nd$_RwSl*T|IZ*QC$c
zHBE)+eRaK2y<@a<3cH0Y?dZL^y4=l;8Rfjvyv~&>mGGjT859VF^IKV!fy|Bi0~!*1
zQ0&Nt$U_~4YZ&)MwrPDSnns0jze5h~R=>I~U(b61HRg(OQD>n}L|kO98ynT=`gPi0
zjD;)Ej-os`7g@5W?Q67sl}gxotFOn~kD&Lz@PtK+oaZyrKvj<j-Ak&y=qD$8<)h$>
z=3CP|XIlbyC*0;!Z=?jEJ8=B^U>{6)gOn+?+$L24KdxI@GnbJVFK2!0+&iJ6w<6Hd
zH9B9e(~-zuJK7M*+$PFF=caVr0<zqi-k7@$?B^XHKDU3id7v`mb8>I9>}lqwuG{Pl
zUXiu(ri=<L+Iwt(`>hg%82bC~n&X|XL{)@tspMBXvtzi!jvZd06PkYSe*XY9sy#?r
zAE}gk@)ikU_beJy^!&ky4?0WkqUe4v0>bVg;1uXN7;5Z3l^x=zw=4Emd9Qax`Osi1
ze5J(3uUq7E9x=)=DFP)=-e<Q7(@(+>El%0)8Z^JN9yr1qYEzG#lrrsn8_KT`i5@u4
zc>IVxl6ik95bbZBX;7RSx}a`g7n?Qqc5qAODtVvEW>GDNs2BAXt}x_U;k}VmbeUor
z;bO6rVWrAhjW0ylUFWDm!kQ`)7G1Z?8|EjY`82Lu{>pwIc03UX^{r359y&YS3r$nQ
zZ&gJy{n)>somt9^6>uQg?@j&Q#<8pHp6S=jAku}*j~2jm=~$orSf<rt6%Ei)ys8R}
z9T#@YD4eTsgAThusdc91YU-EGWwdDL`9TNB>$Fwy5GBq=t(99G45m3*&Hm0s2d{|8
zHlxaecriB4UnsOj_Vt#29ez7u!Q6kR2^{9BU&9PAR9ypitMl#-l0xqqJyQo%8MKen
zyzs0lRBi+1-(eh>_~GHhvCYlR?d^Sr{MP57Ac_!cK8p!yh;`HC6Xvtu+tZ;wz?vq&
zA6G<$y9t{^VA-S6I-(d^#qCh4z$Zi*_81F2xmCFbng3q@jM~me+Xmv)PcY=w!G%D)
zY)pcxntwU_E<-fJhs-cFXE1M!CW|W5zR7-%$u<ieTwHZeW97EPZN)}JpDQ*TxiQ`e
z?h{fNeyHjK*W(^sZVpPlUaml+)nsUghdX18PV{=50iy&N970L}!RxGrc2v943%(!3
zmsq4;6?%r(=@q>lJC#IuDw8N-${fI#rNt?7t%2qy5trAA%DWHAPq$T)M%=wTJS*%t
z9{K9Qgs#A-Zfp~AC58>|@qEL9m?{x*K=iJjwM&thoA5DcNb(bBpU~V0sZm`?-O^Z}
zSq*df7ppfgL%2@nO=On?{EXXvd5%mBp3uvrQX8Dp*B?neDmwToeJ9wB>IU;#Z&WOw
z1U&(t;#hF0WPN}V&?E<@s!DWp^HwnRqpfL@q}TB&(fLC<mqdqQW%ZurE=FW1pIv*|
zyCcj-?6Ve{;{iV@-+wRQ7@Dk~)QmE^wEfFgbQG66{nnq6{!7;OM<cPt@o#ziTM|KI
zK>ni)T$G4^Pxk*kvYVa$R`c|^1cwzLNJ&<L)s-Fw7SoFsIS?dBzVwJlmUg;?HG4i(
z^~#QtB{C6eRHql`s2e3H4>XU#QN&mq^I+@=WJwdD)nOInT23!gf&j1(m%_7MHL8oc
z*X0KTO3X_MU!dJv;3%Vu!8$5R`DLJM6tFTy;0MR;;IlhlS`7MNx=sQTtZ-B)`m;Jd
z)oEN3X%U7v`@2Hjw-ye;+hZ?Es>PHmC$A}XF3TqN7$-}=PHUbe3%xU48?45#gK{%7
zFxAO&EAAA_4P-7O^-9rW*b#a>k<;Vs+$YHP$_cACW2n9JT-K^Vg3D#p!PuiIztuPz
zl!^HJdWH8)S-hB#M<3SJABKEU_?T!>gl_pzObzO_&wR(c-q9A*a{b=GDyi{h&U3v>
zS)9XuBFP5YpWauywlE7phG&Lgk3@x=eFizY?dEV{LL9Hwu=8asuB03e+%i6(d6V3i
z)xOY?I+|B{x*EjgQt$SyZhtde)GbdvN&9^4k(u{g^Diq2jRHXqez`3~r1Nk-Je%Bh
zEF{X2!AH{vc_-C3SZu3vSX8QjtSMaiXYqq~@T^3!KdE)a-)>uTc3;{+3%0{Q_Cw6B
z!fmCS!TqeL_ArIU!q`_NIj-SQx9-lcM`_`&qT>YgvYS1$dcW#%6?fQ)yEK$O>dPM^
z-zd7zZMUtP@L*3vUpo2wF(%dcyvogNQ&)T9g{fO}$r<cJbI#uc>QTi6301bB1tH4)
zSdB$RzBapE-DpyeU)`c>cMYYEa!{GOsp`LmLn9~~o>S{EZBLh(+@{oGdd7}n=~&60
zcNhMLTpu#o-I^Jr_^whlgMfWoS7yEN+)=8?6le|yv*VF46@=PN_-|(9zqSemp-h)F
zIlscGGk582H@3B!?zV*Tz0%Fv*oA_Vdz4zI^tZuHQj^=j3!QIxApD6x)Oqt}j}sH$
zX^_iUmYU@W%{70)iCjTq?tf%KmS=rfHPM#2Tj#US9UR?abml1G;>fHuOP>rKPb16b
zdu56>q$Je-GM*0A+oSZeKNBUtkx7m=$b${NE;R-ez70M&yX%B<YU84VF5^P*LKq<)
zUAP_QwF2Tppr4G6)OLCT?Qi6Lm?CIwE79)BCckE%%vY9)YIgri`Og_4cH6HUZqI2(
ze$2^BFUuIcARK(xw=ufXIj**-m^At-=M6NN$uBokIP12Tri?8yLkv{)+#!K*^1_18
z*&*fL#QK-s(zdS1GW0k&O*KC;>X&^N_%lSTq*q<D3(DPq*E!XkyK;VQV~)3H9fT~9
zU9d_tN215;1BzrOzh9S;J@Hjc`qx>2QD2dy(WzR#lAn7=qrVp%u2j77pEqyXn2*XT
z+P-?y^dP!GtY+5XDQt)UN<?D}<u>SU_v5Y!C^B198n&0{PG$JzA+(WrVAA9T?1~w*
zKm8U}VR0bO)$9fESGMmvZq9dFoSm#LcmcQXe#8Gatoq+eUm!3hgl@&5>>X`U*I#l@
z8z3Tz)C!q@?rS{V^1*`~s#2Xc*pd5g{Jn)lGX8Aer-sd4hbt>x^dN!`kf(T?%K`QN
z=tuu_ORkFaJ6x8dQh37Lz#Go>Y-*Ll`We%<%TBj|uCv+bC7~xPOGwEY={*f_LL@TT
zGty7n8IO*~Y_8RWwr|<#<5M3G)F*UsDS02_rDz&I*hM^&SyVCRJ3%3s({7}Ln+*1e
z)^9)-K?dHj9=3D;4&h{;^_xtIsZkMQ#fXqVJ1(<gNH6%ZQTDBmQCB<?iWX6a4MCt=
z)UXew$8(&=L)lJl?>06A(GuVp08jv%G3wh6zuIL)RF1nVlAdNdi+=>OW<W=ZpOFJW
z$J%v`*?3;&uLNd#l1@~{>O=k<#t-B>V(GY#Tsq9?*Or?zA8>Z)$)XaixvsgadTS?7
zf~-o-_Y~!oij9NWwmUHZ?TrUnT9rENU|JI&)gF7ZtzMbi{pR6TVBi)|f88M8KSb!H
zLBAJySSY)TSqd@Nbt1~tI#z!VKV7aym*mykIn!2fJ*HWqj<8@YJO5V1dl&bQ4#qsU
zW@!u=@PkvOA{TO<B@;x<tu_1eRrFQc(#1m8GXvMJ_fmIoblCS<Z_Y9=LvznL!rwpk
zPzMh6)EP1}uQ4N$O#wO7&F$3iHqZ;gB2Q43)x55Z!>PcQZQ9V~_Sw%0^_xcm6P-Tb
z5>S$T^84wo#Kdc9pC2j#gX<Y&h<WEgLq9cElov95qS(6jDA9y`H_xC>Y*<fkBIlZ@
zqs%?#0E5amy_zZu@;>@r^Txr}EJ=l#Ul{u75D^+NC*7xmoEWe0HM{YdNE?$&ZJcZS
zWf7`VsOui{y=p42kJ!=%XFL_is&!|;t=$84-}0kjVaVih{#owZEnmnyq+BQM<f`*n
z?QM9QF(RU;C&~q7mVpk|Ph`ADLq>01yfw_`(vvk`dh5II;A5s^j?zFTUH)4IWVMHh
z%Y@1`)f|}R+-mi$>0M&wD&qNTs+tCtLYMxf+L{z}@Z-2wDv}yB;l3SYxlIO#xV?76
z<~3aj-XlE>au50DW%Iggz@a?v)K&9hPI6<=JJI{Zi@FRIf~jf#f2`hh72~xn!E=Nr
z64dimG5o;#)4s@c$~0YS@oSb<uYCJkMXhFKFlR5gM4QpiFDIab^Zr6wBs;(ah2+3p
z<ShX}LSLyd+9oOYhZ-ZH0e%JO=u?gEfkOV=PM{16E<}(e17==isX9HB+vV0{aGl9g
zOCAb=EPYERh-S_?^E}Lbgnn<zjV0T%nSxihQ%3lDq@Wk%pR&^9LI*xdP#SHhv{(7;
z=ROV1^;0S&;*vT2Al3)3mSfghTbBNl*LSHdl7MZBOXH9;YTmdw?PuyTGmlj)N=CvC
z8tmuO@HEK|rguq5snNc{u9j^+Y?&$|)?K(wK!B)Ch$sN9dJ)!)dFD;OLboKi7a;Sv
zgYTd-+v~d1db*}P)@4u5>LOHFQ8~%-ehZ#JvrDcm)!OnTbU-I1DT(our#(%C9TNh|
zO+NLy1&w~RpzK@C)b|ifl-fH7I>O>&m*IYqZvb%d)x5J{Rrvd8&uOfO8j|trmnKUn
zX36{4{>pBKCr8;4gEgI5otLn;Ey&;2mydb&Gahb#(Xj4c&2>edR8W(5^5q6=)~N<p
zwXp{p;wS)1tt8FQ)LBuUKT?;c{fGT@Kzv=8LRyd<kEeUbQ<&_B=HWaR;o{u}*e|@i
zN2<L+iaT+7M!{F@FjMN>zwQWl$mftaTHZS=49N&*wC>fEMtvkH|LJfr?$Tj#Fg{$G
zN@lFsxDy>0C#zeNu_ZqCE<M4#i4{ZfGZaMvSGFyjGk^D_SvkSFoJs2nw_V$CnoORc
z({rRLa72=B)MquEdOEU;-cw(J3>Vd_wlt-bkv5Iq^*w$pD_%~&(A(==NT93u>K|+T
z_p<wcvk3e@>ZVYLF6{9;9AeH@1j-SRCAemN(QC@SR!7oEM~C#fQJ+Q!m@YASMA+}S
z<KP>R$=Z%Mx9bKm-U7V-X#1-d#fY38<L%MboM=@(5!l*#JX{@(OPEc=a#6g%O_I18
znWqR@Tt@3Wsls4&7(OL<Is=gS618z1T+D6+MavLaJ3Qhfeh}^jBl?F<4$58WrCWin
z4NK@Wc|!gVi9bx&`EhdLu(_m2#6KLo<-!~=W1p*jV3j(oXSo9yhHo$XT{*Elo66XT
zAJY6sG;kA6;4o`ywl;q+pHcpw%gPje9+rKl3)j-`gUCA>{@rTJKSkn8<RjW;zkK|<
zfen5|Qva*q{#qEnr<^9EMRR33*WGIG$e^Ivg{v$WS3H;oiz?7A7|x5SBb#LbvG7$S
z0(}Frlz-N%e2N4Kov#`K3<xdOTL2OVThHMz@UR>n<T=itf{Z|e+hu;lBCYwjwsQaU
z_)(5d05KZ^0S7*zM=F_>*19P#Mp%N<s{o<!f5>sLB^CxnaAAg9r+a&Q{SL+K8N-s$
z^yE+|M47U0_`0?7>E`jrEP{*SV$sfF_N88XEj$D-(FlatD=vs>ma!o76<aA~-+M`K
zg0Er}U!nmV&_0Fe10!+QD(29{z}J7evO#zlst;Szb_$T7j7Ug~vEcP$;fGj}kbifU
z^0CbPsqg@fKa8ruUs&YlPwGEc5o{PMhlK>ENaw2+HX<+n%&{Xp2G^Sm`n53sEtwG4
zULHG=3eYa*?U*#1+DkcQEl92u`h^wLq6WBCu@Z7Ro<$cz`=8Xz{!B3M$Wvx7<lsVL
zIHgwC^76^*!NI}d;W6pR>|cXOL7Wu+H){LKDYg(J;5gVC1ce}xAjbONn(D8v|Idje
z5q-21p3n`jR|zr1M^5f0&p*R=IKy5(zkm0_@c(7B#h3X1X>v7r81~yw9TLQU>G}Vj
z*|E3idv9?wVUWX)!W8sPgc|(9kFZ>q${<N#gU>IVbOF(~9G6q{ksl8F+#Rs6g8SZq
z8(H;THb~4G9w?234TV;hCG8cgH+}kg13b{F6!aXs;MFmAym3J^L|7;BEJA$oFe|4>
zln5pSJ`v!stk*97BKIWKFXbq*iSSR<e9mwBU1@uq^J33z!d>gaS_>%z(UK^OC4R08
zw-h8^+|r9KeJZ&7D)1tv(BgQH4sZBDYP_sF0f;aQ=zsAb)+*IJTQB#ztgxR|zl8(+
z<5@Su(S=*0MfNOxqo<2KMLOoysc8Cs4ZN?q$oPOmn_I0#W=H(6GM&fASSwL1P-yvl
zyDsy%_X|J=y#@TB*oL?LCT(fWDUyW4gx+G623@&unXVG1zKvfETt&tWsbj}<xR9$z
z*PwSt=;%wfcP4u;!%^H23uHX>BKnIhA*YY8Y@hm;J$+>2N_7<@4gg3rBk|&juhr+4
zD~lvBp?9Ey?vEDT&%!@nHGGD13xLCu9*jbbl2cO~Ld+X|W%xb{;&Oq{_g<m_ob4yK
zjM*=mGz*Y1wu@%h%f0^;iZ#?)BgavEt=f%Jn9K2UfEu2^6A0J^S}76u{ybwJ(J72l
zC&Gt*$$@axJ{a6MKH$we%;3$n|JB<&q?&%y!7Cp8O25xRhnEQXk9e144iIg;c|vlN
zk{$*yV^<shThB#@Yl91(f2BVh^QPktN9Y4?gySXbq|;cALjNo#030xIY*ul<0L9m~
z2~i#%zP@L^%Xy)&KkBW5J@SkWM@ygF+{J4}|8YJkaMR~5{!g;3`WZN)j~8o2ods}%
zb~U*<J+<fjsLmP}o5^|kL(qkmD<=;t#J887^3z0h%pcyo@KhGe0c5fMFtADvkR(TZ
z4*28m!+|M9$NhD^I_8hK{yLZn&@pO$q$zljl+ohg(*^N&Xnot>OH8M_(m-hFjSDM0
z+=V1Z%bK|K6YNa*N<=g~HRFOq%KbsBmBN*WU!I8xg;|ToWiKk+0<bytv(z@2p3~|^
z=Nm+Jdq)orZ8vsX!(F1zZQdd=`e4-G&vf!+VhiWl^ou(GKKV!*W4$>?X?#Nz0kyZb
zf$&qqMdbQgUT$_8_s2w^2zro%m)AMLXl4NOb9u^#vg-^Nv-^+W4p>EHuOT2FH=kk6
zys1pBHNaZ;^aXkxoBZUUcaP8%g|h}#WbkaP9~HA;!V`UnD~7Uew#ZH$Ho&t(4+DSl
zBi`6>KnkW9X|G6qd&KcTfNXIyYx&pUru6uQK3Op<rz#>GCL=vQA%8|j8^U(<_BD5&
z4$h15?s-gqm1V`y#1oQ2;}wARsLt6Zn(57{Jz;4mw*eCV=;3*?gj#)<ee#IQ*s!(}
z53}mg*i%0dDEY*685@&Sf`zX?sR`>csHMKUC;(lbSRT|P`b1VBPU;sa#D+?%p6<~J
zrNgaW95B6iePVNPPEi?sxgOTFb9GhM;4#ymu~kMskY#Tnpb1!yj(4DwS=wt4Xe`XS
zf<J3q{73hN!tW`U*iysm&nE^|B;UKp`Yw~{lK&~o=yx*B%A7YiS$`8cc1sa}W$fl)
zYj&KH-F~n3aw@Hkxx3h3&+!xw>ztkal|J>3gX6+S{At*(-}5;+Jvljv3#FkZx<C+r
z9%41*`pNF?{1uE7Gpu*=U0|F}LR6{TQ2H6`aVc0aV_`e&7NefHF7bDOxK|QPzTc#l
z9ZgGLc-u8UDs6h}@C=CoQ_G#6o>Br|Fahc>hYbGA<mVg=qA7~Ojk6qOz5OS-FhSV!
zM8Tt-kIqInD*5|L-Y0rLDJBoP4M<Y=#qrU>TW<c184*;uSIwrp{GjSB%Z3#IBsO`F
z8Lk~u#HS&8O4YP8NjvTT$H76%#7FTF3o*fjh_D)UlM|TLWPNSkNYCd|>tBA0QwV;)
z1+U#*#GGug%p&oFF>2`e%AY(728~`_Yhn>$vLoMP&1A(#+wP9xBGB=V==j(0^mqqp
z%+`A)zbo{u0?A%aPqsb3)Hrg?eB$?kl{r8lZ!A(g0a2y?sg*7BM7}mJ?TH5-I|ED?
z+W%I7u9uc<Q)bqmIp;X9diLAZ60e{~7mp_;oKb`Lq6mfI?F^Oio-AzKC(O&+E}aF9
z^=m_vu8Zu#E+CMI`{a6ou8hf0cP>iHzahHM-q31wj*XKC4;7Atu@ccdBwU<n3=n*h
z`8Q7s5-t`9;O|+LguZM2n?k_HXWq9zKK1rJTh|i^cm0z5t`$5A0b)ilVxqkjj;vOw
z$+M7uJw{(X$^Wlclri;DU1!md147$M(D$Nn1CS_%uh#(JAt4;M5%Cvk6y2|XU<}Z~
z@d3^<Y+C;8$UsR$iQ!9I*z@0h{wH^O8w+lno@~yxK2cJWPa<4_egXP=rNGCWz1KdD
z;{GY_&1%#B1s&myG$OL#N()<(>gUCL&o@D=6=<GW|6L5x_XY}Ge1+Hk2i}5DKPS9(
zZXRFY*!yQeul4`d`IFQK_x_~`X~<Q~7?^U<hDYdFeNN`wzui-`i$hMWSayaC#?ff{
zx5Ur~9EhEpo!7sGw@#M|Z-4)U1k;*y*AQX%)bCO(m@I`ajy><W4J&(=ga8wob3EbN
zzhmuBS3!#8RWm@e-8mZs9tlSh3>UH&;_33j$_{3SXvbl&m*~&zk9jbI_P<YEm#;hF
zKog7s9Mjc%KzrfuXGOBUwNfS3?B0Jd_~RRx!3TtkRsw0b;eWvg=wp%1i`&vqzaJol
zFYE<Y-;?h;wNDKv5#@i&vm~w7=42d0UL@WhSpFZ-(@hcRg84rN4JXD5@(b?H{|k+-
z!{NAc*DtW-{rzpUuZ*T=rTN+R39SRAKLP=T#(k?os}*zXkchE?l;COxONnOmBi=i%
zA~b8X!2yfzy~tq$6AA=C{0}DmzlOZ6Fc2Z#1o2=qKg8ls<3E+}e_-QG0*Hv{{#Uf{
zcXT%m07o5^X%zsb?Y{LO4?sv8lS~XJY}^Cc9NWE4N8wKh(h4XsBPjfNu+YSSQ)t7o
z7!Txg;R@bux#Fu>Fu)wZj6r5X<w!v&1%jR3>u}uXmp~S-Q<5K3fnbOLau}TPu5Xg)
z7JzvHG7K&kO#juMsl3m4`vDzX2;}45DP6gq9Q;rF+Zp{-J_rlw!3i9RxpcHn>7Y>T
z1bcW^`Uo@>9G(`05*PyTk_H@(CnpMT)2#P)lLrH;8UW0;ni(PQk&8GG&mbLa)DS_p
z-tsvUf*rxvpOlg)BkZvp<3YE`_hBEnK^ubmz~r=ex|iV)Y?A_PUIVX!d!-bjc)E1p
zRj^4ZiWkidHbF9Kuqh3*K(>KenaM`q1u@K@W-gin?{BjZ9ZyTj4)TA626TNa&g3QL
zVkX4}H9AuPn&ks{)TA=&Z4h{1Mdb?AT^^_nki*I~iUsgI;KC}A6?`E13-7A~T^mK8
z*RDYDrOIFkqzdatX|QPeMXN+OA_6O2BkLVNMYb>7pilzd#sldmr;_*rK02IQ2TwVO
zb0A5m#0J1s-%F=$_)D}2C8Ef}f>j+@DQay!ci1i^k9Y<Sag|jAn0SshA=fH#^w?CF
z!Y85y8FmJXl*S$<J`oLUj&s_FQw5;ox`&8}^ZxY-UGLopM1U!l&90{e_SMxJgG7?4
zOqAS&SYU3F^J3QD^=G;m*s3M*l*Hap2W7(p)f!gID9MBI;w+1Ghr_|cCu}$n>VkV1
z^i8d&aPR=i-fR|s<0-AySimGr-#8{!7@vp?Tv`Y1LvxLaXQ9jLvM|sJL>Z^+0H8A%
zg$oCl?v(Z`)ZCzmG*G;<ql4qa!$Ur1Sr^yBY3RWC`X!i<hc~V}Bn6b$peVWl6Fwa-
zJ?Q{h;xWhvCsl5v(6TgtgFSTe+Yl&!eBA()4=GQ$=q3BMr_rtD#av+XC*fsj8m+ov
zBG8CL1mNz;V-AyA{Yxh6;ooVxEFr?<`BtFB_aoRa*0)82A{7g?H}cRV=I+7R{&;dw
z0Vkrzj0*cLZvs5Ik%Mt_C7^Yo;K>uUX`fA=d;T9k644?$AHIY@Bg3mQRB1sXs2nud
zypd*C`-xejk-7dHxWLi2x9$1N3Ik6TjTfsA@I3NUqhcb;E{N$M2m8~hK#!`K85Uo-
z|KQluoPD27c@7&ISM&iB?iLfsaLZ52*(>MXDZhCWgT$P(o^HT~rf%VZmFQIn7o>o1
z&mr}}4YM~PpG6@aWty^JP)RApg6EM0_2fc+SvI`hR|8B7bRt1@75|rY{O>zJveO_f
zn1G7ja$*X8s{)feI?-U)Y$WpIPT3tl>}dE9m5d_24vN0Vo_OG)l=nLoDyiW0T0BVm
zhXw^Nb|eY*c?uiuc)B_0h$;SPHh~YqUZC5~al)06FUHecphm1nW;tMsZtupAWc1C5
za3s==#G4kJvZo4Y61)@%00VU6B=ew5cyK61%MZoH_h2_aB+`(?#UBc4{0lBb<w2Lk
zni&xs_YfaS@ip6r<%9}U5DAPe(9KCR4dmGsiR6Fd=vhzn`t%EUEKkM4v2<G>pljnq
zL?9GJCEh~Ehr4kM<NyJ>={axEx?A`#Hh)t3q*0J-@Q^24vC6}3u%5SpZ)4(!*gK{W
zgHu7E?y21g2^(M+Gc-EMwkd!^A9xWkQ~8Pi2L-&%L&VAE0m$AhC`7!cCG-XksL4Yl
zvU038sGS-#EgUu{WGqyS1l9H71^S9jUU&+O81><~R>XZoM2+KU1r&6ENK&YKEDuAh
z6(m#ujO|D{ps>WLlt>AnQ@#mr)2?vVO~VtSFl+kikN$3TOhXNtG6D?ZD7C&6e+rP`
zt{lKCpx{8H1`=?<+vGUx?z{&z83cn=wF>cE69ah)LLz^~XEVM6S1oJ^*c`o1Im;%L
zUX+##4>t%GBHm)<#3c`Qa|2nAFT@L??Nhvuv_K-`;@xFT<3ZWK0Kg^wCGRN!@9PJY
zArko{zGD6*7`1FfusIUS%EbF%l8a|UM6jxzJ(0W*jwFsmipHPSUA2O2(sSU$=3tU2
zJ~>dKDq#Nm%xiS#8+1lk4GwREJRZ=$1qKZT1X|J)HbvtPwj*(%CEbNy*S*R6;$C(;
zLm1`OU!ZT4mWs>-q3h=yACcXR*hV62RtsMtF))%jF?btC%?a^Z;Gc|U26inO6otW}
zpFdB+hZtJ6GE%|00>hATazMp5j~W2LqieH3L@+*{<~l+2RV4Ra=4vxUL{QtH$l=Nm
z+$thyN#m97MoNg2Ah|XkUKJrUA=Pu-pAVWqL^8()M?JQ&CxmBTB63H-ghU^fLt#TW
zxK#wugt)_T9H;>Lxd|?$yW@@D3-Sm;CjTqom$v+JX2|76!1+0P!E&lP9BuR&;04<c
z)@AG9*`#16D5U%AYWb8g#7UNi9JdM=nt(^FH)RQa<)_E1f<hB;8FnX)L9M0&KuxQL
z^}YcRMF+>Lf<VW`W9_S3p$R<zSDOeN)p{>)UWOP&kGqMO!-1nJzva!E5u^Oy7gJGL
zF~G|1IF7hLpb1HvPY7`h@gZxMYLZFdC_1h-ZaB)|+xjdO5@R<zv6I~MSnd@mbew#|
zK^RI;LR3Nk9Vfgrgn|h{2|BK8A^I-4&hT+V>0c2m(6GQ!?n!-QQ2G$oW*T}p>OoRY
zD;#yBhssnLiBWOOzQl^z6w~#7k4AHR%{dA|i!|o2kU(HUm&1llVP%)YsM9x)m>}1}
zDHe>nTOpSZK1ALBg$E79DeOh_(seirnv`DzM=>PbxC`bF<5`p`sWvc}-~aX}>f;eU
zbUbV$sUS;^2$g2-FYukmI2-^bez;RB02ABEop`GRaMZ)^g-OqeP)4{vF{UrjB3}=^
zg3y^zf;Gf*sL|imVR)*j*pq=A7H0z$n9x;dhcVXx?9r~O;qz_m2CrtM>E&{Ah<eDI
zyR?Dee*KkU8pzZ$L0*3qnfO?3a$M@ZOB>noX>l*X9p4Sk0dcXOrx7Q`Vwb6#M8-}v
zB78>RC{E>E909PtxM*7b#8#e`Th-eu@mv+gBKLHMiSGh}-woWT8=cq)QDc4TX&;*S
zwH-^{{EH=M)6h26<y&X;RUt@7ftjNA>8llq;PueUq!W)eB%a6c$V0j-`{VORH-C0L
zA?PI5NO_gRdgC?o6Z#F~OiR-@U4?V@0qDn*-fW|n1RqW}3PbIc?xj9_fxr{;d|CIz
z(2J-4qbmU(A(t<n@sQHwlO3Xk+Xe3RK9Z@Q-zTe{DZ?TC6<~$OA=SkGT>uaFe@d6-
zS!U>+q=#bD^~st)vdx_Ma!H}fb1S}%7_yG%iQi;H1Jg7Dh)|9LSH2$Zt$9P0$nt{X
z5YT0tcRThx|D3cFCX$_<`aR<IXTs2yU4@45s~9HUJqMpv>}E7*N?nf1*{GZOHZ^y5
z(CDLk$vH$uQq0E+wcC34C6ZjGdpHpgbytF8K5<Wu%&_8?f7_vUttV0o++LeFgsmf6
z!x|E=V(nj%qvqWD%lD=B&b(wyY~-<ktKQqCCc^_MG7#aS7sQ;r*OkOhuTRdYCH{mE
zQ-L6wyzfd@XzwZ9X~G(3(1s2&EO)`yL)k9~%5VEeoF>5JwEsIQS<9JKf$dZc97=e0
z%bTFm&Ms=w&+>gxdx{A3eaZSc5|R;GSJbC=)<;s$zu=YCpB~t$xx!$#FN=9e7mr=K
zB<lInnNzD8t>}-w|KPjxAK4&|&7V0l8h_r<kS~h>uzx!N!G)x)u)#-Pi{Q9u1VykT
zSBwR5KS#f&h?p#R2f1(0M%cD6(uGru3pS>(4N4ec+X%LC9c+BTHgpgOoO`z;&^F%_
zF5}pMSjJ`?+qfNxUKsn^_?B?_v!FcTYjDVuTd`>D*X!WH=x&gl>8d7R%-^kgj&qax
z&pGZSiV0B$oJSlkvpPy*d{ea_Jfq0{+-KAklX`-hR2cj_D<4x$S$$1SdKyKZ^>D^@
zAmGPV0plyt%bT2>;Ps^>v81xApS&HEeyS^;v<Hb^c9Y<|#OVa*ogUW)N&f$#{#{o>
zIKLVHKlwu%Kf#UQH>w(roHmxu-~pfhnN5O;rEfH{s<RV=k`4N@D!dHBoQ1KWt`MJR
z%L`77&CR~C&zqT@vaIgZa)o}%;D$z;h!|;@@G$%Y4-0;;EwKC)oBHYsv#O;B{k3j=
z_p!2tuQ~bPI%1%pri!pVHM8!3@O)XhfRAMpBQziyQ$oiU7n(w8+o|{ot<gLjg74P-
zX<z(M>8|A^r!1T6b8#)!M=g2_w_L}D+-Dre+Gw;)_)3Ua;>3tUM8{+s);oJb4+cI3
zF+WOcRkGHJF&5cP`eZCpf=4CGGF_P*z!OxeHAIq8A0qE<_mxa4gjRL5;Co5VudkCO
zZ+S2)2hDp6hBuA_i<~&Eb!Kiv3(pSq@9#W+%@;a9({Agrs_Z;A^l-)*oVHKE$UAj^
zRrc`~q%_qb<6+})*cWWS3AW*C^vhUvY0mZ7P)A5Iw`GWP{mfpP{;GqWbg~2!c>K(v
z;!CF@bwsH(s}a!t?d#0pFRN;Mwjy6Ec+nh@Omxe*4y4LhBn@w8&2CKaQ?#fy>+PrP
z2EX46jieB@O_q@JAYaLE`cL&=e`(+@_~4G^S`K<Aoi`>_3=%V4Hl(N!x5cd-{9AR(
ze`w&|F(0zEqlE!Nn2)^Xu4GglVMOnssn~ee2sWobhD3I@B|8kf0{e~Pu~j)D`jX%$
z#4#*SDx7HV-mx^@sE#oaSu47KDJB#JzWP?GD%x;k&euh^H4r2qC}NKbol2ZXjlBkK
zaD7WMDc@&ip^~=_el}y&8ZwaG%N%PWqN?$ohoK*;nq^RTkW?@_6FJfvQ7FD`wvZr5
zZx$WEiyX7oNqxO&g&l-tkHXClL&R28o%K_}Zc&;uty8f(2vn0XxC~Zmj*tH={EXO_
zvUa^VfHvd(lSx%x2A&I7EHH>`r^f|1rb?0{oFZzs{R7A{v>7BROhmjiuJAA{fv*HN
zBL8o_8~i`NGtnDss>#FhqfLq6ORb8V9<tT4>JRj7$<k1pRtaqY3!Llb14zzMF*jzo
zlWQOf_x*D;l$BiT(cLqY9x$5Y*TRW&0)gNua$}a+yK>PpW#5mbRMe2vFe<t`rv<GQ
zXpN)W&wG)W&#xIy(@%4MvLcI#phRyz^)qv`T2!I+`O=#cSC#YQ=IRzF1`lNOLI||W
z_9X~iX^dCaLs-6^?sk_R{Q5OdJhVK6^ey%}kdSqyPxZc>di?u^*V^!WDYuq4M2A+(
ztG#)4t9GK4ZKk<tbo|x2%=wV}ybX@)Wsr{`bYy?l$>mHP;C#14>ua~RZe2AyH26FY
zlN9|i?j0*l->akJXqLzu5r%;I_RWwefhuuB7j4h?Gi66H43N)u2(9~UP*r2QkuQ>X
zJA9rxW+(I3{kfVY2tTgXx5;|tM<@NuLe(|q%ocp1QFsDG*+fwaCWoBFSzq5;V|?co
zaa<WdHo%uGmR_4egHySuT6=jkLw<#Ho_2BBrE6X?nIniSZVwsH6+;kn`C1)f%*ACY
zUQdq=#8n+D7-=L}m|69zDty(9d;*>aT_s1o%di8_t#Rw*m{u|2TmcWuD{^4w*l+l3
zEmCQX_!qIxo43nSKw|jh+wDfJEyH_NXT_aF&ZY8?iUQEVgCTw<alKlb;z9hHA%Zh7
zPFc}H6Ed8z7oc4!wXQwafLN<nmEGDZ`k-yVtulUWv2|{3uE{iQS4wPSSQkOv-~`X6
z&^R?X%!n%|$ZLsNfqZrY6?7x7CG~0M9pI2se%9Rc^~)i;CG=Rel%#f>T`7U0xbB--
zQP_|Guix=;__6lpSIUMD(nr@COtw49aehdEPDTWo=d)lS%6=NFa-Q?}WTD6*>*yfP
z_tn6C(rG%48gKnaf>}XgJV)7s7LR9RhW~@;?gTOTVu&?ct`1<Gs<!!KfDb9Wyt7kA
zTyuq5(8Q1orx27Zol0wuLZq28VoO#3W<RCY-phykKgndz>(ss;ZRuU3Yl_*u7?B&2
z!Dm6a3mGOzN`T%yMhDj~OvzxZ#T&F5TGna|mT<#=c6g!JpF#HIfaltTTt0-y56>*E
z-&hL)fI_KeL1cVBe`?lMj9dEsrSzDz=9L|4HP7%ng9D%3r9b!8Kq~;?`Fl85s%;W6
zm&=i;W+3>gk9TtSJ&jCZ-@Y_aII2ww!>zWQtqQ2*Zg~Qp%cW&P|1!^Q@DX$KU8y(n
z;CWxcV35-5Bqw1o>1*jz^3+GiBHSD-BCrqLFMG_wjBIZeO~ux$m^GG!&3oHC5EeeF
z|JebGC<ba;7h+v%Gr*h&S(BA!L}Ip#i??2cMUFF=Dy$h7m#YA(@l8gx^HdHz6iqQJ
z1`u$q{QNy3ms8<b_~_x{?$64rQ11GG-kR5)r6J$cpt(Mz4I({~H=3+AYkB6jr8d?K
zV^W*f>-f#8$Z^0$H(mfQW-f^Jd~<Kjw<N#ED;|AUCwm2wY?t?&4o|m`;KPRu{!MXH
zvTP$IE@{>(jWJp5>k$JZ=i+$<=Q?CKyf6L-zUBDeej)Rm8L1P)b0h8K|5z3S5O})!
KxvX<aXaWFF<vkMs
literal 0
HcmV?d00001
diff --git a/public/07-basic_statistics_files/figure-html/inc_visualization-1.png b/public/07-basic_statistics_files/figure-html/inc_visualization-1.png
index 1a2440ffe6b9c03562d1a847f0bd173ed1be0dcd..f51d9d8ad227415eba0b327eb30d51e5bbb0ca9c 100644
GIT binary patch
delta 17162
zcmb8Wc|27A`!{}_nK8ybcG+fZQ7WWD#Z1zkr6Sr;DpH{$vYjKcRH9V0F=-PmDx%0t
zD{o2)5!oe?ExTFHeY|^rmhb($@5k?P&tK<p&h@%p+w*!}%j-2UH^|p+kaJVcpc;Q2
zy18%mg0Wvt?(5t)EpHs$8MUJ_{<n63CC_4AFJ#=>@Y;Be--0?$(wvV@<2e2{D00=_
zm60y4F5W?Jr4sA!JrKQb=kMOVd*wz0^q0EllwNuFO2qrJ%H=ImzzdyFEJK1nj@&V1
z7aE79Apx_%2}0)n7~Hm8+?ncN&qwVbpx|Chj_O;A<=6msF-eWuzBJ7Bf(l?mQ_+vg
zk>Fq-6;e#m<G2}+N&+!V4l_bjL(iA0+sIPC*;@=4hJSJy;otj0##Efy-JNHzDPpFS
z!L<?83NCzCoeycZ52}2!h2+FtJzb|s><{U@%Mg#yNAVrNq26{!bLhNISfA7ku-=~e
ztW9-q)NmNSVkQ;SY)s|8wZfw7N`HJU%68wc17#+E)qI#ChF!LfT8I>@b9PHkM5l{x
zAOYQZS2VHyPxx+t+cT@8$gPifFGwL(TZUS2TcBNgQCVy38vX3kWZ+#!SPBW|_3VwC
z{b_b?vP|1Ll;*U)deJE#cQRP?-1v;dJaMIh<EP(^F~SP5l7vqTagflJKil2n9?C}=
zX*^xA1J13n(eXbnj$BfL!yA+Gj#x>p7LcZ52g7@oMz~(s>xasK)7MSh;TBsMotVu}
zC0qTM8c|cDT>VN=ndNzdWT9zy6V-?*+1l5F$3WT4s4Fz6<nN~?593BJw^5;7MYT>X
z>xRE$VNnI`gD*sjVM80r8`pi2+iMUYgS?kC*(S6)iL7sMwJsRJll*pK-{ZMm6;u-A
zg&MQr@Vy1Y+_g5483Z3iSGI@`?&4IM2fOU+8nXaX8+9_r4r(3iP)8>O%rE-KqM2&!
zI}r<0Z{p}r6{_2riTx!9n1i=e$#&b$+}$dl5*}RPGY|6ak;@vMKX?)A>D2!A6Yw-_
zLmOk4nZ7lY05?Z9%ZG?`gKs`+IH#m)G`K{152b!_hVO3b?z4_OO+e+b9m*<8W$gBs
z=mOhxM9%M9LL=(2X50NS|5u`Qlq&M7%Gmw7u;khg!(q8YY!c64=CADB)_u&a!^#L8
zzmD?Ww%?u<?RAxd)g!<1zpoTOMOn>9Erl#9Faa8DnP<)8)7@=tUnH(+@ILzC8~OYe
zC?mHTM8vfitg;^RC53w%+jO79*EY{LJu8My+|p&DOWy)J0b|@)%>E{_{cO>)TpI>{
ze&s}_YL33ikr-6G+_-OMNVWqj(s;u_MyQt6jSFeYF+lHEHT_G~vgkRmccsA8nZwe_
zLpTO@l-Bi(6=ZlB{nKN|&Z<$mXTLVHXTA4cVaoF5??N(kjVl#fi;73GxN?^nE;lh#
zHd_4HX)b)R#hx`Xf^Me(CmKxOg~@L@ln!qSS!c=Yi48knIoeR;T~)Hhcw1?v8u0sV
zYi6bO&XK>KU-wUmVlN_}w%;~d^VdF3!??X>oAovoX!d<lu>UX0`-6bVEHMAPoC0^X
zZ9Xj<@6SO%TWljeH+b9jvwK*ZfcXVwtRI%Cy!W+{q2Z$d6lCL$i2Tg764xeIGAxz6
z$@Cm}TButQc^l~d%G_6D8A_0FxavVlzc~5qjntFx<Y`zaq;0FQHO+e_H4$Y?g$+BM
zsF;$&&D+8ZHR{^2ks#K!TyGx|wnOsv9zlz9_@=Mof=qe95GRFcA@qMpLA~qd`6B<>
zC3k<3BR|oA2W3VndMg%PnlCsRIMB#EXBrlC0X#!-(M@!?%=Kwx%z9eu)qtg4%U`ou
zO_UGj+^$6!a`jl3gp(>Ti-Jvag=lBz0~SN`*!?|*S=n#*QNd^GPQt7OE=)<J_$R&;
zrPxXS@A5{<(vNT{iX~rlCx*af(Y{@h_R8_L;6KHZLr!GQY`-Dm3ayu6x^Q~DH{<AS
zr%HT-uj`%g7bPWoVuB`?!p28Y#lsW+0muhGh`#%5`)o0F1r81K%zam>bn;hoG$sxj
z;uHwj#5O}A^DgIif}%VWa8<g^E{0R+ivJSTr3!}Va#SplOoGB$95wjl>@@i%f##Xm
z$1(%z;Y|~rBCeiF{PoMWi|A$IU_^nDE4?D|64~VbA05wc)JWM6%2Yl)0m+wpj!+;y
zAoGh9C4MNqP6yaW{-SDzNUy$x79HC~26?ibdDH^PQV&dth(6-01GI-9_^3HtU9yB`
zM=|ZNX4nGOrJyc;*o$5M?SrBQlr5J3w3NB}Gz`&`={v`Cls3kC<lCmTt`dXu`TT2P
z?MmygH#?|HrLp4KbyKliR{+P_Ax|t8TaPkG&?@52p=tr#LP>L6n6nim*MMfNK(6ll
zM!#`xvRKAA$2H=s206m5C8T)tsH9t_P^!{#3f&=e<oLClF-)~0i=~-8IK!_YbD3YJ
zoO{G=ZP^WHomP`Pzp(JQ-q%tUudvVo+T8|wEO#%J=lT50GPwvU)GrT$suUY35kC87
zOe)vuR5a>=2$%L|Q43-aXZcn)2#LEZ&tOQj#_4<ZSb8R{qR=|XLHMd|>Y-bKGSj}N
ztw9~T$M^JK{Wh*ohB5C{9<Bg`vYYg5Y!rBMYj~SSmuV-_=<mdPL?#FKb?-rPQ{7G0
zMsi;0#qQXHxH%pnd(vHWz)2YA3+E-E#tQ8`H}`W>$~!H=+RCxOF!i)s-b0G^W6G6T
zV$z;j4I%>)`w}Eut+MY8*1-yF>*ok1f#V-}n#MVCn8N7$0w=*)xo4=4YvMmu<Z8`!
zk$9zY!rY*>{dKoUD{^c_10Eqp(w*+>(h>H6K#IN+T93v^PwSW=&zAa*(n|8Sk&Q@n
zNHde*EIRRYdmU7<8u9?BUgzy0>pnk)$(Di4XICU3Ch1cKl`h$xx|NKm{6wgJ+sIh<
zbC!Xn8>w~K_0+MZ`V4Jw54{%7Kad?mr$QyU>dL1i!K+S@hg=<g`2LO1C#3^TtZzNO
ztjx|k-!#}4L`zXYOS5UPc-$x9@1Kbm_v4GexmGyq<x2&Sle}y2u4iH38m1f!yl^Oq
zSma_$Bf}3QUXvHT4318T5b*8om=A*?HeU;pu13y+i5#(C-7H&@aO0+k6GwcHl5_h!
zNYJ13V`{9dqvB5YJXX0>boDygO^<Jk&bo(tND{$lT&hG`74E_kwoMJ*nJd%SKNR*O
z@wYF;=i;6}$6||3Y)%hwm#=)Zou3L&FU%2ebyu32FMFMEU6Qnu-)qq>_q(@lepF1+
z>k7)8Zag|$e81mTSh{_j2BzyW*IGg6kNh!o0hA3J0rQE4e*<IPF3{JH*xZyglYL8w
zavzW}lL`5QqIeJ0EC4z32^e&^{29NnEN4g%T~TBmIZzxCX#iuKaN&s;Is>QVI{3jp
z4>7R@{DmLxOLA_&;}*ljZ%N8e*J@V$zcg&E!Ch=U7Va9i0#}tdX(a0e1dU~UV=}K$
z;=k;7L3oLRE5SQ9sG{c)=FPp0Y1@vG-0+8wP%C|NDr7}^w|`$wNz-923|r8HSA!Z0
zvP9`F560-yh0_DlZVrK8XE(iX7JY8`a6fw)XE8r@`Ft<Hb|GlhU&oE?uo<L{PgdO!
zv1G7k;+UL#<~mXi?2W-q$XJ0kY?ONWZS4bfd^~v>3Y=ZX9i`y?XHO}ty?SsCbJoH#
zKYthCJm#D9O{l?}E#68|lx4jAOHyey*L3u5OM`RCW-|DF)8<lOr3}(0(~$~1{!DN_
zir>;=kTJ{NU%So*yr>iZr^Q7XIIrz5=ZYl~;xKnUMTv~f5!?Bz*ssN802N<@Er#TE
zA?v<qe`I_Qf?0P*H~-$O1wCWJP-`m8Pq;#blD<a%esO4;%upp<JkyTEUh@2(tx!z_
zjyweMBO}zvaOsUb8Mw+V%`8iZe;~Yzcy2vrQV?gpoIReJe+71aki~SUutoa8o;ni?
zxATQd_LQSFI=h^V@<+xm$WSsDR!U>%vk}j|T{V1E55QlPE&;kE=)u<wC#_1jtx4MG
zCCq-}cLds#t^qG?ALmpT#QH+oC96?U3k?<;W@!=wgc@A+i)fFU?wqBR-PEb0mZa`Q
z;;n$q4w=m`5O94FHD`qRWLEJ&_op@J&qTB-#A)cRtC>U~;c*{-XC81#m&6%j;AH$X
zTi~IZa0)o9V%o)Crp$~Qox}XfEwT+0D1h1{`hl-o*hVDmfECSL*MkK$!~j%j|1|O3
zJF!aYc&a@qXAApx``}*WSPG?Q!4e2iv9u_<v%9DB?%gAOZV`9URPBc&qk^UThUMYa
zP2N@kdY#65ihjb40V`j!0GRb9b?2iN<sfBq_r1~tYcZc59p)3+)>G@Q)tQG0HiFMQ
zG5I-S>0Dt;;~dk@r!kLawNi0^gl($6`>5t77JjYaL31q9FLwV~Dq@PxqRlAPf!43r
zYqwJ2>7vL6^l^&u@m1G+CE$UA*iZanRliBUck-|SU4hJ$)>nhI^Q4yU?mC_+eIOsN
zTTea_gG+ra#snx87zgb)q^hJV!fR1$U-RMnYw~}s^-LAho_}Q7C(SBf{NW|4qy#Qr
z75uXhYkttIK_)F|<nE>UWSa!I&jrX^vUxs*U5ZwOi8f#DaT#2Hh5O`i-}t+69Z4D6
zYB`njI^9Ohd%Ia_V$!@b$lVo)7;ZuW$G>KgpmuOb$hxd)_rly-xH1kRw|Z`d_^s?G
zh-ceYwx9IsxspZ`s62$Mb&!XwSjRM(iCOxj(FY^!<gNC<zAhniHXD&vCn49bvJpTp
zS??AMCvV#H;@GRdK5bzyota2}p)Vt*;6DRa{w;Q?Ep0yGy#Ja-=Fyon$ozUe)6P!t
z;M;pgf0?v$@_QQW{CouQ{OQa2KZ)Dos-^M4-}gqAXSkm%$fF-fMDbw~%->%yh!0cB
z4xl=U=Uz2DA2*kQ@hj<FDdL#LC6^b<i87;W?o5$>)E)+KxfVBqey_bOc5FG?M1h4h
z9pktL!hC@Tsgc6p)4^^J%?~w@0;k$zt8rKN9p*Ahljsgg>qp@X1bzw`ujs8g(nzP<
zC-p|u0qSLKTzJ*J{2vldgj<`5+P(b@CSFbe>F;~|?Y$P%23y{^NP_yz#m+bb;jppI
z&|NttFOP-aG9}SgML`j(fOU=tCH_l5ZHbK}FfwUOO)=6hQO-g9D*!p0BHzee5k1-d
zIlaHhb*ni&sa;9+cvSFKKNa~9|1bTrUa}7iXs8<n9t#r<6koHbGF^=oLEUCB`!Vm!
zbtzz`@Cf>IH`Rf`E2(Xj&Mj@HxBgpLUFNCfwg=0T5T~<ZPfNA~T%x>#_?{P&+sKv!
z76T)L{@DWoD?i9#%dB>W_Rn<JV1Hd2<fjFh<ww3>;I$?x?`e<oaUuJl$G0psg_~>=
z^wqCEgSYO`s;2SAJQm6*Z3#RAbZGT5DsW&T^ZZbqWMD5@bgqM?s#?EvQ{|aHuCKb$
z@7^vV^<pnAAGn?HxpnIf{znpMN!|L<?=;Unea?9+<39ZDF1D|-n*ki?X^7&nyn<AD
zSNjGIm?7|Sv0|h)!T+6jvr0*TJ`hx*?(vvw4!W1df}f@V=6y|qB?nHwaVZo3FnuVq
z_Fy|GObZwtYeXpX(z}1%fq;9sV!jsX<4o09`8&st^~wUp?>1lI$7g{xyGc~`Heo1Z
zE#yscS%(azpxC<jtQ?kQcU66S*;k-~0S`ghbdvsJ{;dBg1GFbR&L+g~Y66m+tkHZd
zXGx_BRUc7sX>PsWd$jJJnh_c9lahxcGr!`^CrKaizHQ0_GtFxAaHc0hR&(a-ZKDQA
zc$|a00t+f!_i9wbsMw|0%i1K}>Jsc6q65$Ug$9j`uk%s0B5O?p33gbR7tj|!O+<Vk
zP3ZY~Ia}n+7#?0n1hfbHSPW=4fXdQM4jF@}7w@|?yXg$KKWz~nc)In2pynd3QuTmG
zA%}9Q7tJ68E|UJb9=Ujq&wH@j(#RwYUX1?hr|m3AyRLm&Dd0(@%}mIplIGNlt}pS9
zokD-+a?Hr|JqM#{yepcsQ^RfnWb+5a5WjEYTBn+a@><%Zw@N~^tIUGlVSn>k;LmvX
z`DE0|WBBbl|BMvCwlS%GU51N0iy~u^{^FMI%TGq6Ev1sjC-0Oiu`e?u@L+)IAL1}P
zd}AgwtH4`z&vbnXuf-hP5Jcqwim%P!X01nVPM#e^#lbWp5=>d#8VawG#Bn3PPl<tv
z*<?(a-g+L&-jCfI3~cT9ss#dbYwVUe8=Xcr=*_>rJno4w;VVufdCIhy@RKuqB_lj2
zh7|VRr`|n<s-(_R?A)40GNf;xXiHQS1KuO*<)IEf-jZP5*@T8AUl!!Nd5*s=cwBj<
znH^ckJ@4{LmX$p_`WhWBeNDgH;Z93tkk`&UDE9?zdnGqGHa3c2UWvJ{8F8dewJJeh
zhH{DN7<-4B6p5+J_A5c#16uEGA!7DcHP~sFoHgU@Q^9BF>S}kA!CY^UM-C4Q_k)w0
znaU(LKR|$zA}`lJTpMHA;g8_*{-gnKYP_S_etx4mFKl#^^VC;s{${0f^|c4+k9YG|
zsWh#{E}Aj3ZJ#_15RjU8NAg7e2p|r!1ur~a7#iBVO~6H?Cl29XH4d2<n>t9qt1f%-
zC1)vTt}QH0R)8!d!{?z%`R`4ac22EsF@EJh1N2o_&|Z$87JJ^QWQ6VcIsFNlJ`0$Y
z!?Rg2feAJ(;eFg_lgOQk9;+!7IqtC===qG+7+@Z7_onuIK{_APW)NvnA{nk*igAKZ
zjO$7aOxixT%NRJ1;)P?3Lp!gkz@hb=A2NnZtphjnDoVE^AbNNV^wEcF7MR1$cvSv(
zH|B@m%n|ou`|9Iru=K={C5kY(`~>$7U^MK9wLQMaS2)=3j__(iB8y+l82i|ApA62Q
z7wqqCQ%hF=izxo6wvBNmU}Bx5;Ky*}p$AD_(~UMusp8FVRo|Thngkn`rC<0}tGHvo
z(DE_Q>C4qkVI?(|Q#mv}R2ox1q1S0f@7(fiE&ZV$DJyVZP`?_4kEqPj*TpoUY|qPs
zeR6xQKT(F50b}dt<KJ`zxBX7>Ry4A5yVYpF?`=1Tmy<`F7pE=`mWGmlHQPRyDNt8L
zlVnumi%etr>z?IbMR$%+fa7RPW`@q@xy;xVR~jsT3uVq0Frsc!K}(TCM0^qIHXREk
zFfz$@I4(q)cb3Qn)*>)s^m)SyowZjCi-bWjN)V{YIjX1_cB0AS)kFU}F+%5S?{Fr<
z{QNv>a(S_2>uT6NhZTs21P$k*c-zs7kG}POm0Iq@@K7@(+^6V<!#W4jS`zOB>3LTk
zY72WRlkMA{k~q7ve;V@`4=k?9!e48KFMUU5LAdJaUi6MU_)bMy1Cz>LN*XaMLpX`A
z+-ELY=(7(ugWO}*O6}u|C`y)Lhd+n!J;s&<mRQFWYaa!>T;d@&UFuB&v5)Z<lGPQo
zu4{4)B=DaJhjxyTVMIBRh(FxCQ|ZaKuVjmz|EsMM!3si=Vd<9cp&lv}3O4~w$UtDw
zd=@k7>k<XA8^8%hOsiLz>kzr<%<9Hkk7^ox+i~4vlu=kWx$dq8w2nC<%n_6VypK0A
z$O!+PZ~%8at{r9oBlBSIb05E&Ql!;d23vE7ln<@4{y4gPyIK>GG;P22`T4RI;eByv
zi5k6D|5Ho1{TV)y8lvO&u5&*Ou8lLCdh%iLt@d?yXf0s%;WNOE6#rwg65-h_5Q8AO
zWH1#y)JsqzL`^rf9}neEJ-NWWeH2=iFinyI+7o=up8SEt^G6$SbI7I8KMto56?1(<
zw3i5wiBjhT_l*8V;2FPUih;TGg10Rw8NQv+i9>BrRd=;JWVZ8H#b5;U1WN3gjF|3x
zV~Ft*`ec|E?I`yCX4fAw8`7*~&BLE`1kHz-TRQ2-#~u#hb(jRFGdAXUs<}-cEB`kt
z30XK}k0LgPUa{po`Fx>|MMB~Ee#7Tsp*r>2q1$LGz?>s<NInlu#8Fre1{V4;z_CTV
zJ~uy^-Dn8d6ux26%Z$kc^wGjI@#C!8=}}glctoZfla5PyEdwQAE566+M%(w|@Zg<S
zhJjVR|5^EqVF7n0#?S7LN)p42HDrXh$QRAAvZ3YZh{MxuX#5@ovjvaP3By27{je(I
zA%daH@f!<lLlx-Cq;6H`hg%O2RRPVr292x$K^5agN}tNEEfCJ>dA<d(ILuKn7A%iV
zB$grMwXkYm%t*jL%|Zn&Xa(JAjTDJ<o;>gB!!Z6+^`s>i-HQ0-x1)tRj16UpBl}I!
zIX=Lyox|}oxtjP#(BmY~pv?4jM$%pJkxx0%TAgQgf$lAT7^)1uR~-h*l{bbmHsi<s
zOFF(ZynO>3KWusO!({ubd=>(SR$4>g8ml}_csX-u%{FdXEg4g9PiQu;(p!0ZiI!Ou
z3Dal0J=d9sD(>EzadhwolAIXiaF6h(>g_rW+}-#-9G5-jSJE6fIJ<sNlM=_s<*GZC
z=>;yEj)z1>WDQzhvxY1k?Mz{X5I>LOF-tAt$qOXD4TnBds6-xrOj(1(yk4H29%HW^
z#~7KQw@L&3IZFaQns2Izs1_x?iW$sxm&8g>prqBibA+vgPh~Tr5cZbCQzLggO<I4`
zs)Fqbh>73<l5i;qb_RIrN?fxEFv`9!{RjcO+p7`Y@cMGRT93_|lq0MFRh$L8zaTL$
zqZ0H3r+C+W9+%U-r;}GZ?^|`TMCDhWNyYMoWqb+6kIfm|4DO|W+ik1{Gf;5qOX@f1
z<0g~KhG&+Ebw{rO{dLQ#Dn7K{nlV^Vol@cjyMdk0dY+nx+sg8+FH0iFw_}Tb>chEP
z%<k`d2b-lQ8h@@K3ZhPNB_vp`0*f;)OTk(QQ63u+KH)himXmd@_R;JucY(Bs?j#1W
zb71#sCv8$W9eZwqx{G1W<`P&|nr7OS!_V(FuZ%@ZCzi97LG3Xl>nuA)Gg=OkD~D#o
zNcx&;xsz|A?yAgP8$0`e57iVN$2z>|_%*q83tn);<kQQ%h*G-IeVKL6lA|-{T)MDN
z8jI0O>B~T{eRv1bYNARbLGgDY(ykYMFWSrv7x(}ZMI%Tfw-?DlrnFO=pdP<)MjRqd
z4$ZO*H<W<``0pK!uUoY#s#tT)W+Yh(QAb)I^GZofRZ3yelXc{7t(V0HQlSb)BNlQ#
z%gALXAQ4Q9!uEJ0-zA8CuH2I}I|%_f*oQ`{3@n49F<zMK<QU5pI&HC)0O2MVuAyS*
z4M74MUq*pFQ0T(zIv8z5)&!oTJ!8`Pfjk^mru1-$V!(MvYjrqri1}No<+oPcM#Ti)
z_t`Z8Rc}1{<+ql@ZvGOSB@1o+XKo<$n@Hf)7kOTVLD7TAVp+B0d)8CoBJ}LI)W#9G
z2AzTAz5xMl32L~bB1Zv*W$NrZ{#r=!_W28YydqCE;5kf+(?GejxYp#32TG9DsGZnd
zm2{n;?P4lKwe*sW@GELvj<wRi=X!XD>KqGYQ?c}!$LIM#*4E{n??$|Qz>*)VQEWj5
zlOg+?h%MBYl(^Em2YN_@Hrd;bNJr8*<0fSV_%jl?>_=(8SZ(oTm-g{hDQXg6y=v8c
z(Qk*h(QMJ~%tCx%rRYUc&lk;T2B}*pbw<GV(1SNi%9RK1FqD+|2gYz$e=kxRhnZH&
z=nU<sF?kw3B>nK}P{p|VRV^E}rv7a0DqAYEk+lb31BJ;t-|>8iKRdh|0e8)03Z_vR
z#Y06m3KBn)#%>?;TK-7;y%mWa`RlyU5NWlIJ&)HB5hWIBepJuYVu!gHSX?DX30L`R
zH0|@hY_UkwL(b;}IPEdb`gHX)-eGnl22TaLiCESC(&8z(`ceC&^zivXa`m6WzfIkm
zU7ZG6`(}`x`ZBst--)v`f(em_1XehLW<3r!-y`lq+o<unB0(Sl-7;1_<E|NFUi#A5
z=hUD`!ag4!Snw3@Os0uJ3vP_iW8vNJAPTfIh<r_AEy5<;p{S=iQdxrB+U<WN0@Sug
zSR7vC+Ah-=2kJKJV!(~D^UJ$!^u&Kd&BUc!<YkgO+Xu$f=GKq{N1M>@6VL97Z+X4)
z3Az%PzfsnzQ>9Vt8FLU&G^ziXa-cK~d}vt$mun25y0#?F8NGA>ZH!*^kF@pgXbU3m
zwJZ*l#-!MPHQVx6i3Vb^nG^Hsq~S2dNQ+e1U)X!p0^s0`y^H}diXJUlboh|zOBmb(
z>@%Qji^7oGf=PUW#*-HEQzkNgo%-qEPJ_w9?02VVo-JK@P+u{AY>(fm`JCtKKKCzD
z!HVQeL*96O>cl(rz<gw2fQIh$SYLqBU=3D2=174GGAQGz7SX+4W*{BP79Z`DmpW&S
zRfX@=gjZYatit9^q7THrza8#z(J?@CSAcZGhesbSp3>{C&2v0VU+v|2lBgtHU!{Zf
z)ZZ;oMVNJc!!3o!KGQ%s>EJ1_yFMP>&kED?E4TK@aQQ{Kk-wY2PHx4bZS&4>T&vy7
zmN65fX6eGg$>zPL{nun}3-zF;08KVM3Tf@94j{a1MQU$83{JU8g6Ct{i%PF#d>~<0
zFDv@#rv&fUfZ`PenF2pWm~E5YZM)muGa4X8%rqi2B9Az;doL<kBx$JtCym-Bq+e|~
zy6t%E!58m05wUv;nJrk+*vLH=eUy^(`Ej2=cs6qXtA*z(EZ_&D&8TSZvgQ1aHJLur
zKKtMox|b+(9y2etxk$oFNCyx!*sYXYqvu0@2dkBRY0w&{^=bK5Fm-;)N!{ZK-D3sS
z15G>YdL5QZ2adPwjf#LO3e%O;*d<r${k|!tG}_fMkOB=7K*a08K4D3(4?YsBDe*N{
zyS1m$gUtLUFm4e&=leh5*?<oz**L1N4jtbE(9s`LYAn)3uo<+ffT*RSwvSZk*&7lu
zM-I$nv>D^KKesMf`#|)?@)(r_Wusa$@5mgY{GPB%8pL5|*2Ki7OyP$nN5_|Qsu;Zp
z%nNnWKh(i;AIBx+nV}}#k3NV@en^YmV1K92pB=8G{3^h($Qmb-0<%Is8nUfGIqge3
z&|^;~d2}{<OwLOen~Jao-U_*s`oBHD3At>_>O9;MPdySlGebN^bx!r;hmVRLTS0_*
zp^XX|3;huqrxG6Thlg`*nyHwLmc9D#ndi=kvk&%OUtGK4?ela2`e`G4?#sw-XtB-&
z2$fzP+{ION)ILG!tU|d4Y~Qtu^Cq}QB1{Wjz9{(YwGCSP1oMu7>x(Wp-{_H-k4nIZ
zT5|vUiao9yR<mV=+erG2+_$*+b|&ez1G$de+BQD$UM$l;wyyLQU_Q#u?Y%~_eWks5
z-NS?RTs@u})KDRM$4pNWL*S4kP%*51Om%7!jrCXI9Vi{6Vk5n8(wr1vSFVwT+Na-Z
z?&JGOg%(7u;b_Q@@yH{vR<D6If?HBJ2vfM&Z030irgr^uws2aE({!pgW9Cq2Eff|#
zvZh1~@3z7gDc>1aG<*}+d>fn;tu?>n(aoRhyPm&5uBX#-vyePvDmb4(qR>?aF#jhS
zAN!6$-68iXk2QwxqE%6_BIA*=W~AzY8aP=|DI%>4P<B)Aa$`&73}p+1oA1RvKYhGY
zF|S+Z`BwxUGdzMXt#eqPPS;+ql02BR`eQpDJ!45=!Dx=bkEPdER%oyrQ&-!;LLES2
z-l#d9*G<a~IzCo9aBGl9q&P|_mL?O5PZpIno{7V5HZ)|!gRd?2hC?@_D&3;(^+g5l
zXCk_$G}(Ew%wiiAarSev^gDyTL_MTcjxVkQE|R-8;&L{c^Tc25fxMNU%^>?779YY<
zBBdSKD^Vrzxf$R`hCpwJH^>sqd&oB9T&O>hWxIH>?Up)8BJWYF;XLlR-<gQVdm+nm
zs7C7LNYNc`tDxblIxZ*2C$mMr&CX}u&&O{FTHXiOnxO9$?eDz}!{$=iQ|MxutBs7<
z>>foDZ~ew=KfFGYup70<_==(o2l9`xxS^b>Dk!W<asDw`Z%AS<s~}^Q{5QhE?H5ER
zmmJT$?%xs%sOj+X)FB-C(A=~LP99?gW-jXD33b8p7Bc8e!5l~*iQ^1WBbB|5zu!w%
zz#?Ir)IoIxbn6eU2X-I#7|^rTKks{{x83Bxm(%hRQ6~h9i26h_XDfRWRRW4p76~?x
zeU3t5QvM-umNLSVNEnE@0Mi#f$ig`KNDW>FC-=k}CK2a*p-5UPxhj~hoZ$P5YgnDW
z@s1hx{GlSzNDuSbNbkm%5h+w2E2f(5y_U4VhYVQ<&~m(k#=NXVnL?9Em;~a~uS({O
zb4M?bncCESeLX)agN;%989%Gq588ZD$Xty{6yY!S9U~`ugeS(`eTE7SicIE{JQbdY
z@(d0iD_A@+t0sJ3Yv?uN;7}F6o-J$?dhDj~^aDq+b)CQcf(BP)O@8Jn`t|`$@%jw>
zpoaQq#dyKXjKWiLPqXu^tQeH5{^O`+0#XyI_7h(L0^0Su9Oai;x>sjU4%*e;_M1Ct
z8ds?W<)y|BHw9c8iVf(Dgy!o`y!syH@|SpoA%Zna1ndQ$^nnyITo|&y+O;RHnr6A5
zKcE5+^igw&JUuna=|aBFW5vWWgq2`v2HV$&_Ch#gw0GGD^5Y$mG#S>^iviYTJ{eTR
zK+En;b+p|A`X#jbX1+@gg$iPFPhOknDW0J~;dT_ryq`*a9)M}3>-=J6P%07FJ`Y1$
z1Bp8ii>-PJuHq?v8CoP?F^s#_P2gM1J@lb`ZGJIgMAGMOUodC67<}+ztAmloFB8eV
zFsDVtsA)cv5cbJQMgn_k#w5=EWX4p*%)tSH*VrK!#^E)s<#S(W^>rOAXYViZM>%@e
zs1S?Pyhvwk+UvHSyb1>IkXH=b-0-jxH#G-oa#ol%>o(o#zrQTO8$Ff))nbizC=?%m
zzD49W*dmT0)tduJWYZgbB6nB;zK7*VY}28P%hd8GSeHLO8&2!O!e`<LGi}1rp4=xG
zKu3YT5p`H11%s8tD}XX&>!07Sw{Dg+d-VyZ(Yn5D6V*+fBAM};47EQ>EiHri8P*Wv
zOk+36tB=GlV2@~OLzWHe-OIa;+$?hhBlUGcRYL1$CG<QID;`rCJbK|u)lXm_&13hy
z>F*gX)+S?2NuCwfc^Q^RR~O(bA=wwj<;rfp_4oSCi&Sd8u*>1Tgy{my2)=3%p}PXH
z_&|Q8oO+??hg+MRp#C@89PMuooKNO(_oXnX)+#Bcy!lXuFb})rjzy58FR_A8G=OJ?
zu-T)$d?2Zy%1P#V(OBK&&MGgn&ZQi6NG7v8vpxIxR4SopRt-_^+JI{2rMC1aFV+pR
zg)D{v?$5*)8?k=mY=l<jQ&07l<@kv91uZ6Xl1d^En!h=uY<a}T7nWKFJ)*ef$UtyI
zKjVRatniM1Y>{d^*LU=bh+$JNeQ3K_rRHUVCscdgNcU=U4Q`eg<#k@X-h4JiHTsGg
z5GC?NsNXf<(d~><+2s>quf{r)+x9=!_PGcPq5I~zNeu-Pehj4Kq9TU_a(atsgJTl&
zvYw2&iqgBsE5`1e<JoPtG^3oS@V18Hwxdv`dO~D>nH$`h2U+DvU1~JoS(<hJz*8y0
zU$2p23SJ#dWqrqfA5S2`!d-MSycf+2B0A!;P|ow0`@SAw;Dg?sV{zO;<%1Gy^6)rK
z&_|e(P-CI+kF49eanz@XeZJ4QPqu4-VKoan`I=H#*2XNgv8dM7PaC{7iRdgLtmY?i
zFXnJ9u_s|zs)-jRUhinpDh9CMEB2M)!lu`&pA|eWdetO+?J*Hbq}3=Y2D$}t%i}Cp
zVwS%z>_h(+-I0RJ-5n5**wlT%i~pd*KS}zI7_V_Q>81m1ZMcHBtzVsqiA3=ZoOKH+
zJjU*dUCCB}sjIn9@Qp@`Pp%WiQ5&A%1uz{J(1`=AhsGqHc((8fRQ-s#7O}8LURzi`
zyFni-Cy!T)&=m_2-a$C<K*_(NTaoP9Ifvt#`D@s?`dJ<8^$?@1pRXYXPtazYpsnym
zyq5GRP}Y<4j=x8muFX%I31Zk+mVdrF1O!J@1;M%n1@rz$?Iudt@uh#nX4`}0w2GfK
zB<$L{iGKH(Rk0~@$gOwYCm{swef+}Cg7Hdk1>Cz!HofcM18ttSY%UXr?(^QgwpIc5
z1Re!M`LISb3L%9TTdtq{<x=Wry{6TfPZX#dS?c|d0AAs86eEOlXUrrUfx?1^M`K$i
zQ(_!xSeqKKiDI5m@+_|SQGw(sN@~30;0@$`u>6%s7@)Hf#b!cr-m%<8@E$*uQ%gsr
z=jC$o^+CTj&zA`-%R_JD{*EViK@hFEam=606EK1o*OGbLm278=VM(<6O0Zn8n&xLP
zuoo}wsRZhd*=N>6h}^r$=2VmXVXm`8RNYrPbDpXNe&>E24Kx=A2QOB$v=iI!Mq6~V
z5hw3JMLMCTmE$Go!)qRn(Sl?dr2X)rVYETQMGlT^h_B?Tt1Vb{+Cc)#PT)x3j922Z
zq6~46gBjPVKp`heV8&cx9<MgX(i9@kn@c#CdT5$M2ywA1K%3bh#>tr;^VyzU;fufJ
z4&VcAVYQ+Gd%gyQ6Vd$#v6JXgq&r)9%J+)c`MRG-Rf*2~wr;w$>?;j>aBF`(c2`yg
zex1y%o2Pfx&9bK}DNSzy9GK}QVr7djs1w(`MVtf>pXKK1ZEq4ye^IOHH{CA_l{DD+
z0hkr57a)M~@vVjn!FF%9xFiB)63Y`x*WsxZZ+DR_M;mdpMFD7+##ZS7SnV_#3i*j2
ze&)6w?kJDrA7$bGl~;0X>s$nmS|@xu%*bbr?uG224GNq`i3ccy>aP}H!COoFxci9A
zWR?4udeKbM1ngAjExF$@X43Nwl4ruR<5Fd%wPeqrKI@$4=Gd}>;{Ep+3L4@!wf%s8
z3+Y0`Dyn@Op{j4-f4mN>km?mca`qUV!3aO2D9bnttUC2$tcQdS&i>n5ss=+A>Z~Tc
zVc?hg<~rUxNM`!sGnZ?O#4si3sKEPaL2+KCECfn3i%8MIF<FcYRLr8sOGVaX>h2d#
zzqDrnDwwL<4A@mvRY4lL-~AD7g!o3TGGq&*bvVlT=mu{Z=+aETa-y4O4;bob2TvrB
z=$Z4rJ<jl6*z*x$UrG&MMquVC9%NNXHgM&MWRfP0Nsf{*QyRODt+R=IG|;ervSaQm
zl}UQ<rc`R{-GvgKjPEDF*cYW@cfROj5$9D&_s}fisl|?9bOXKRI%ylQYV2%iV5uzW
zdOG(cvvMB<>>Bll?_-WOz9%HGD1`1C&d=~7d0K9R)n^lTe2v^7?HL@)%IV73Y;1}(
zj3qf(P~5ig&4HBYk9OckigT)eUPahBN1ystjWX7QDPLpz!!Mpt+vorBT~hQy862gV
zfvr}Z$a|qcFV7xo(tUsv$+*my)2Q~9_WVYUQ+|p{LBGktJr7^oKdMf#JbpBMHgRn^
z!k2{Iml1_X1t{-e^a92*VH(#?mR4JTd>}Neoh{9|E=-7fa9^ka%!0|y8sST~d;B$*
zH71kK5%<FvW{ZJb-R(ucnugKfOqIZZh<jpSzqm*xV}r37HuHWl(JYrW@_l6U!@b6)
z`F*SM3x#!eF3Rj|mC{1e4z?ff?U;k`vg@qWdF8cfWcmi4Co(t@Bs`jI`%Toli42js
zVJmwx+D2bOePKO3S3G~hvE{D(j+aqd-<Arx7;V*5Y5@PCqrGZ8itt2}7Kgc<)+tXo
zu>Alu&1xRCQKDi^9it+J$cQk#*kg>yqFC#wEndn80@lQnV0%K~hL8wTSTt`D)=xM}
zt^UfNhuqD-ZPW9^NB3#M_UAMYhBTIVN`|u}A3T5b;W>Ey4ES+>1JGGB;GPrF$z23=
zId$jEF$Z^PK3Tq>#d;D1a~y8~^ER$I@66!821CdN&+iD<`!Uv6OUlsVJ(*I10$j3I
z77j(kpYXK!^sgyy+NLnE`Vc?mz)S0t4=-1xB)?Qc@2J2xk8*`1+oXcb_Z{wE#P7GL
zr4w7H?kc-=2cs)ap6uDNi`?xX19S~!U^Lw`*yIgr%a0AMnqEaI(0=gYE$5+J@TJve
z|4bGz&kR;=qoQ+`N&!AqLj<ki*YzMGqOig)0m(h|2njSalFE1>bQiefyg)@qKlWNs
zI>tP%tItbjG`G#wk*kX<T7O;*G*mU%!N<9&od}!%LRj%de%UQzhYcr6ZoWz9NyBEN
z>6N9zlexvhig!rl7GgY#WNhIjVlOu-!qLTIzaTek8EfubV#N~>-sSbvODYCSmb8`b
z9q;e?fysUo?MG{jAV48)MFO!83yB-I=5?vn!~BMg@J(b)d>UNfq+&4L4`55IzIUt~
zn_@ipF3HeragCpbw>Xs8JUFJKR`GZ9O44G7=|xcl$z6Y7LUdbx@}I8%&(A0{{cj)I
zIjJ1ttgU|f?Ee3!@&Bjo|C9V(8OSO`i;9n-v&y44pPHTz@H+0_7al8=IGjWCudt-@
z-o2$(UAqi}0evU=&02mZ=eCb$d~uEG8uQ3d2P_+Ju|^FGl6bDtWY6Jgl-Msh{!;ZR
zs{sGn)+L%Ox^2C4+9*STBjmofk)Jp@Lk+I{y{(UbJ!2I=L4;@rLv-LMUbGjkKIt)`
z=aF-tIaDd@z4^x`!{;QtM}9qc|Dj1oGE13&6UF0#9eCmbjcb~_AonV<*VUG=RL~sQ
zcQoX5f&L%kYF%p>rv|-MuSa#x@9(ZiR3w0;E{+vxL>#G0CJ}?bv2rEMw0Z+>C(xt2
zD!+6bto9hD5x~5&0g{`<<U1@z@n^!iEMnaHxf3tJEvet+`_-nn-b-FUfMLOWagJa4
zrAV1}Vi|gnR(tXb^|8lCc;FV@pML4)i-{F-)IK@Z_aUvU6<T9FpJ~PNQ24|+yg!iX
zWK4{au-G`>;H459!jw!MNDo)If5aVRTV4=BhecdQoW~o}hcx+LQA5*9dJrr({vj+P
z#2L98*Q+}AH20WQf!D(&eBTh7mZdF$>pvI@5WNC5=ZUdjjr?`WuYZ2so@&v>lb=>X
zn9F8qY&g{-_lV&)kN5p_O}e7>$YHJqdZcxF;)YZ(Hm35ZyU+2K6n>4?9+KxW=HTy)
z#|&gOhZg_4gIwh2K8~(JawHzIUy=APkWDmlL08R~Sd%y4x#um^AOB{X%db#vuk&tM
zTcK)>^~>UR7kS!hCjSwMc~hyKtrU~ihYKExXP~Ol_~-t&iK<gS4(&hjm7rlVc0u_c
zGyZ>lo~9%JgJx{AeQcG)jX@;iw|!ijg#bGkVOAcyO;VGeOU3+QAcFNchq+;+!)X6x
z(ZzGqTvnZRxT-y~D*ttWgxNp9Cm_B^P-Sp^RODDYz1J%b(!3&-gWgq@Z}^YIQ$d(u
zD$(k*?lkslE+*S9d3MhyuD8_u4;@nWT-x-BG4a}8wBgK<4SxIXQYHaoXEZ7Vh+8!K
z(Ur9&$t(YH1TQzOQGz#W1F!wL$`{DvGN)b>C^VdSe3Q6OD~=1*&i*s_L&PnpZ{I2s
z*u@5&R{Iw~=Z9+r)wF*Tb$m*Ay9JeZEJquh6(%aL=)eDCO@z;@TELQTZXpsjK}5kX
zrSd*5YEw(b3T=)zBV^Cz=OUs!uhR)*@kMyA^S5{Fg$6B2wphVGtT1t}7O;saT9<@5
zJiQUO|Jd9KsT0#gD+Oo%Vfjoo*zfXoyD3`UDqAwR$#&zvQNzm~N5kd{1|6i46Mwh*
zv#*|wy6<104zC2SPy7eMxjQ84(C;-=L<0LW6vE0M6Kv{SGO0&%wsBtpqV=Z#0n^RZ
z;}+6cq0|(zCj`#@2gDa1;l7kIN<gktJi+Q_;I_pKp57@IuA`jKcr%aEp&#(^AFcK$
z(0;Vq(uw&WjcG(tYd$Uh4Z(YAaPOWPG;X|)C+PyQD*rTEJ1X+f#r{HCcb)zB6mt#o
zC(v|wu6A`U-FTWaw*nUMz@Lhl{2c}XJXa?u<d>ZAbv#n_tU<t91+LPvb>v+rVVoUf
zWK#<=FZB(9*2D(6*0!mY=ZXIp{5oO=Q=9#U>biFY6zUpHb6A01TFDGj$=@_rbH?*I
zh5b|k$Q+BaA`cJR0wc9jg3;6)l>8+h`o;EbQ}_e4m@tw@3x}~$8hfBjhQZ6gQK8)w
zk5Ypix`2zGBN$mFeB(wE6fGZb5hfEHbFZpd;`JTbTj^(zT*>L>OBCZde2)(PYYQfg
zl_*WJ7BcNL9pqcnQ+WI7gt^wPhF{M8!Q-<^7OR0)Metalb^KtuCWNT_jQau@MimfD
z+L{y9L)_{J-Q0@L;v4p_r?cH9<?4!2`aS=JfZd7m+b{}j*VjUC|0+3SDx3SeKvX`7
zhM=$4ZXh<Nh6IVjMaE&~5WeOQ8Gai*Waus4)Xf-srUp&r!+5c9)t%GZB`f<{qPIdo
z-n8GLg3?>)-kfYYu1+$A&2#?XV<zQhew{pq<nAKohE8LH^96WI4rY~*ro+I$`Nvbr
zR~FXlU`FKli{Seof>fcz+^<u_3Q1#~o$UXB=J-r;EN!;hbTIb^Zi_gXc)@0Jgy8Z$
zIo`jaq(R>;<TePkKs$0cX>i|r!kM7|VovNFB;W3DVv0v)u4CUr(20Y2E6@LzJ|%dS
z&8h{uZn@p#|L`>>uSF3-?19Sjefx)jvDHwu#O@2?iT`SB6CH6Euj2l}u?8K%oL4vv
zge)f2BQ7(~5xVoC6&?DrD7z%#OwHf%3}C?vyRRX|eY$FJO|rc?B6PW0duoHtH2T|x
z(@1ELW1o-RJg2Z@u8u254K9i89NJg=7MotU0ouEA-_A3hgC~mf@foYY*olHQXuTw8
z!ByBG+pHLplFelg)(*a2l5o6~CAfs-lFR^IWIVw#AVSBvg+>YAl-%Evii|6fd$z3_
zVf)sVwW_2>yFZ*B{~3aj23pKuvkn8^o(y<-Ng5j^BCGNqHTc#vIENF|O$2MPrpCmd
z9xNq_R}kqxSN+ZRLvuG#if4u61cA87K<hrvHfL)P<V4jW_tpkbAjGj1Rn8HEIPGg`
zwR6Wpt1L#7wjLs4ei>lbiIY9|OcT#su-y7@{~Kt$l<NG*Sk2~1B!wUs;zGsW<f0R@
zPz4f*l2`P97(phH%GL$beD>1+z-MJAjSZZjb*r~Yy_pV!b^-b~yV?Ck=QIe+ATp$M
zIXh?Crj*H^#w2x^^!h1nO7>L#hk91BPb1HS9)k|1{ds{M=EQ3Jf%M+p;!)j?Ic*=-
zQ{CeKF<JuGdhw84umAq)g>57vI63hT4mPgFJZ<O;CRk)otzGCJdR>DMcWRv{|9<u7
z%~~fpELMTOl9&(?G$$229l7!!n6QV4++)Nf3H0F|pQXV@+YeXWyZ7!w^zDaoRGwsv
z1RH6k;ojtK$6_66<D3l|uk;@fAJp|#Mtb()#9>7Q`Lz0sy#)86#RmF>z&6{N(*lcc
z9>?OLzcs5LC#>eWdU=>BJk6RSymr8%!^<%4RPWzka{Y*Pw=#pu)tor2cq2V~?6nWy
zo9tFV%<!rjcpJ<R%W`5*az&$Q``Qk`eig&0EmnsVCcfSL)qHwbt5-zU;FZ6vW^b_?
zLKjq-E1i|rBmxwd-nOmtdY=_N{)2*y{FBodAd;W@r-j0Txqo~7+=GYs{@aL1>T}0j
zp7Okjp^&hY2+-hdA!xpF@dM!u$f;`@4j#{VvFwueBFz5ZulJ{>x1H(=eS{n!_^a{D
z*}jk9Ruq_X1Fh9=C)K~M?dW59ygJ2y&25!G06z$VKiFF~<_-6D@PD+xH;O7xRBaK*
z_}F5-J!hgyQG;jox8}#fYN$W;{&;PRh)?9UNAo9N5427$iQo^R?j%8V(YK%X67(B>
zRy8+^4Svl0uwoTYFzoD2<TkzZ0{m&vZoVOk42JMM0=ff&7cLbnDyr}7?-^=&Z}22c
zl-lNBAahD_%Z+@N;Hy?ceG#Oi!|iV5)-jI+Vm<EbHL@fy;S(0xPoJ0GDH_)NEN9~9
zv8Ksqmg6h+xkC#XB>^l6{m3Pi#2rOfA~>3!kR#GMG`3a&#cc(Oo9z9^@IlmYVzTWR
zP8rMzj*CV^$NJj3KDMNZ3#NL}`AI6)SlbY*>Dlju&gG&|i40Ni;KYYp((<1ab656M
zSv9iwi_)k^yHz#!5L3#LpPtfoqTm=1vUZZ!bU|QP|Cm3L)ZW!J%w4MOzHj{Jm7VzT
z>kUt)T3f2p+OD^uliW9GSoM!=LwPyk3UNii^p)V!z6;}&duPv~*9u$Xd`DGR%^-4V
zU&1vXBnluB5dY=u_n3aaPS(qSW5a7>XNZ>&7izeI8<9MrH~xFc)df>r^m(|bGCe2V
z?zEnJOV*Q?G8-h6^krAJDfr>$M6mSKg^XRBvvkt-wzAzAidP+NFKx>xv(i)_MRQJ9
zp@RM&Cl|NtPL6z#-9e7qUv`zy6mvfGyzj#dZEIw|nTr}RpczEE)|d?#Y4p0#uKma0
z$4*T4pwSd5Q!ik`{^`IqyXTUsZJREf*gX8U|3THWIJ94<=M2I^_FG+$!5Z<aL|}Z-
z1w0MC(UFr~k)nQo?j|kdlTYRhxlfHAtOz}{NKn`2Kl`?#*eq>)_e@etf@YNmE6l6X
z#Zg!L_uv(lEE+L(zp#T9IXO3ywE4;GMJHz#D4S>yLsOq#EBntPeHdBY6xEqjFqq>n
z+tzYla^MY@>;CE^uIn!|`-aKrga;Bint^)Ya-$U)^N`3%)guog6(*BkEX^F?Ir4m6
zi2L2f93Nt5_fLa$p*=qZJn!4;HD;_suKta{H4Pa^t~Fs&+X$0V`M;SeQDX6IY#(cR
z`gcWv_jG#de@YbxiA6*k363W!I*rpCbAbw{-tKzz^v0=8TttO<ytY#HP9%8_@whl~
zo`aC;Mmz?o@3=Z8lS@4IE_iM^s^R&_ZO)f{frol5c)K3C-K*|yukptSEpB%{y}jG=
jw?c>iyF!EiP2&`<^S0~0bkHRR5Wh7m9PA$0dLI8@xbkts
delta 17134
zcmch;c{o(>|3CgbGh-}S#uBoQvb6{yyBSN-Vkx9WXcvmgmgF2#XrnBNWYQ)rq=cfG
zqK!x)BH1EaNZDuR{Ek<z@B97vey{6yUBByh{jQ(Cj&q*(^S<xr{&?Q^WL+o6UMCkM
zpGOzHJ9MRgN6^i2@dF7@PMH_7P9VoZO)pBAD0OU049A?l7ph6W)|phep1HV2d<4hO
z406xEKg-Q~kXJi!TF%ocWbSX@`0Vc8-vy0&5|zp8QM(0g+8yg%Z4CSo*erokzjO>=
z=KrAxdF+uefaL-p0)cx}qx}1@ThXp)o0TMdO&dQpek&c`@cDNaVLRyOA33}4M?gNG
zA%8a@DD2r@HD<|@W9dlHVsL?QlAUl#-F=JCqlff5R&Hl!k2-p67<sf+0=Bv!*OKi+
zo!}*nlR01@&lk{UCm|feJ&)pLN!T(OgTPvCXt*bQPZ*Pj4ZL;%$lHMq+!sOCi*p+K
z#DMc&SY3|$a#>K+2>V?nBpsL?+i-<!5`H}L%JIB`a)Jl<;`=hw>)`T8vp^Fw7Sz5>
ziu%-s8iIIgXfnCZXeL{9j!AF_gf9yk0hQoQ+*xlSxb~>2G@{2>ugNU?>cE?W8-bJj
z^vkWah9b*$+oDslB$@h@nuQrnz$u!^4TjF4RD^THkh^jRei#eP8GnN?V;t<%XFmD|
zTKXs=n{Qy}L_Cks4jo*Ry#}G1k2{!OD#t3xb&4;4-|7D2>Yh=`H3H@yXI>RL4`~>@
zJLJ9cyZTmC3Do25>~d6j&x%zF&cU*coYevkOyf}pW1-{aE$w(Lyw!}(6oT4Wf1#w`
zxb}-}RH%}bdn2D)KH^;Rv|6af4^9YRzcy60uKO&pS3O7!c`u}EK6^xloc=i9toRS^
ze9#B$iD&dyQ%Tun^7O5T?=}2pueE}lL!isgTp&2=$2xC7D7JUZ81$?Z$SgZ>cSf7E
zask_4ZCu0HAj+zLp0Vx|&OS^gFSF<Bd#|KTRh>a{G~P6LN+w5!Rr@Z7$7jiJTb^D$
zCia3=dFDET$;JLj6Fb2=<17UQSM`Ft$nuXH{cxwvk=F)BA{SH%75t9OOIwhX97*bh
zsS_}iThL)hJ2!nAz`CAM5~_tRM>P%<wXlU}btRd`N~Ver5+ES#YW90ZB_a%$(hIJ?
zjHzcD_AVs>#SzD}&Sdt^W^T6x`i4hMX^KCWNzs4eJ0@{?zyN%OqwQ+xX63Q5PtUHY
z+80{mNlw`UZ^<1-yjX7yd!t`|q{w~yBI{iFOOIA?>|~*<_%w=*Dv?2h6m_;2=^B%}
z_<UM&45l0=spEIQ=W2R6V%aY3PW3Nb-DiH?v@1dfj_*#~l;c4oF-yES>fRkg10+aT
zMe5V4(r3QL$t0R2W^i0a3@Ey{RG%hTH`!vP{#fpctp0K5m0}CJkDtG1;*5=qeY(%L
z@{Mx4KzfP7uUeZT*gOyEU5>h4b|PWoB#!*Zs@<=Sl4w8qcH+=!e^Qt+El>ZpC07>w
z)i?q0)|o2jJ}i9QxmIz;YJt#h15Wc}cgL(DYTohoO380u3So40X1Vt|O`n5g2w+`K
zQ&|WOjiU)7PbWRaAZTe)40gPw>-3cg0|7vHa$gv>cf8Li=RS<qM3^+Xd!xsq)BXDz
zj~D^xK2wA=vH#4{!z~|VpzCIr$7X&qiLS5w`0kC_7tHT{H`jCvQJ9wSUe<^vsxwTA
zVkIF=Lw#*BQ$%ZHJ>S`otl>ZN^r};{fg!>X7pPys58NB+`bCg?OA;`|Mat<0dW)Cs
zOI`c<Pl#n!!9HISG>2{a->H%|Xxg6+Sg~hne*d>gYxNzU2bLh520qUT?@bLH;!3Vi
z!;ZW>lqn%bKK@kr^uDN?13)(U{a%{29GIaaK0br^+jrZKTQ&dQR2}N#exhC!Tqd2R
zU48SIGNkY}6fYHym-#>GH!P9giOUHEP3XP^GBoh&D`hg4&`yHaBzlk}vMQv~ejJ@O
zvBnm{*~vlnliMz}_y#|Z+mYo@pYMqcnX-V552GW;rUHYInuBoS@{v-*`MwSWb<Asp
zR#)x9V-h442vDK{Cj>=aLHyI0Drv2SupHH?JFsk8h_1<$1nXVrelE5%oa)w85d}p-
z3IuIu>O;;0)>vhNkk7duhCWaaZ<zW%!(K#<zh-(efSx1)E<(_E;VxhBxp>lpAKgdo
z?-*xvC|>cNhtL}ve+Yp^x7~d?A=*#NKwH3iFN&E2DWXX$!j9}DgCyC`GTIPwP5U%w
zsXrQQfaaAsiSGrIuuxjOkWb68t2V?CDL=u(2bfh~YZAoZyM^Qi2HoK?9Fk6=?U+!L
z*?7v^$R@qRUI0>xW>b%K(bi#=u2c(AtZd1fnNx{N0edzOuE%s_-g+*9KoHN{iK+}J
z+$1e?r)Q|kTm+N6Db)wnuBC1G{VStKB_bLwwaNFjMRfoAylt^h!kDfJqaP3XjgpEI
zS|d4bQ@`}ETt3?TIGI{{-YWdh<p@)|<X9Uic*N(bK9C4prbTV=w|8h<PKq@$0IF+|
zxL=<EaE9~9*zlh%qqwn}Mj7`cs-VQB_Wi!MYh{UsDC;!5A#qwAi>9U=fT4~UB$6k>
z?Jzwnmk(&6tF7}qjB{g+rRO$s(r>F~u{+_#ZKIuq4%4~_1R6JXbuU7=NtB^`R&To{
zk(X0UOFT78Az}**-E2Cum{HdvS@Ga7X|wYYvJdT%4X~zF^AHzJ6kOgU**<Xyb5;l&
zO&a>y|JhK__CuGn<HY>hTmey^+^u{K67w=7nXV2Q3{%65ZJI@SBET|ctfJJ}n8rAV
z?uS+2Cp++~hpnqS^UTADX(Sz+B~!Z|ksDe4VPy1+++sX&zEC{4Xu|IENcos9Qy#&#
zNv;6w8+XY<6qBuzjNEgH>O!G|-YzMoj>v)12M7y)OcVg3ueCG5#eBp$28<wn=Ab6f
zp07p~nA)s%KQYSY8&vs{17eWZ%Uk^7g%lWzlt1y<g-1a6PxrB(Um9d=<iSLOsk@pn
zHZOS)we-Y)7o8udQDBFmNAB*Mm2{1&DnihPhU_@JRqS_gfug0ZbKqmo>0*TC_bppW
zX&Dl9JxO8by>GV8!rzgO>mKil_qn<X?SKvoxIj+V72-IxGk~dc+>;6iKWGh3T&UM2
z0@`Ej0MFimSYcj%kQ3p4Pq^!VGyco7P336hG;Mp2{m~sk5n|DQGH1_mXUfs_^v<iJ
zD-h`!cHV7<r)pHor-Glv61|q@Q!$}giL`^p-;ew{$mJ@pINejlrVs|?-Gk59kLedy
z2o-gw2~~T0$G5-DZ?C3E4GZf^7qD;%Kda4;_9LS~ZHs^-ny{n?lCqmx@Q*-Gybjp=
zZ=R3a(<;HiVdh>-t|rR7$z$IqW4cq4I{f%{xm*Ba@<|vK&-jF=THl@Eo~V9i6g5&7
z5~TqXtVmvJThfPD&wl+jf4qr9>cKZ$LXD6mKk+-_@Vrbo=FhW!h8<v;(KZk+s55{s
zxt1^Ta8?P+l#LTba-$(+BHNQr&!oh^_IF1(McmB0=!0~*6oh^wqBZ@#1#%B>YGwyq
zTtEgxbYIs`TS~enz44e~9$pXf?T{PwVTs2vA?nvT`G^Htz{K0ddv($MKlk3vlgzE<
z?@4|y53J3cz~Dl<h@?*j<~H&%m+wsW8K!pF#`az0EWs9Z;?>YmE{HWS^^7mxeT}1*
zyJ?Wy*HKRb1H)z#D_mh%K>en|m!F#iV98zl)A>Y%c_n1EqyvpoR&+dpX}Ms<&MIK`
z_!~jT>-)dffsdOs%}Xyz7$O5m%su1YEx+_3{!#66S>ZRwEWbRrV_g+p@Gt;af5MNI
zkOL@sd5G@?O_n@-ccZ<o9sG>)#`sB;Tr!x(7VrLf2;ZP0m~>GgP@{MNT#ARATJ<4m
z%~wMheG)hls0_h9s2319o+b=G`$BE4<VIe9&{aT~i(ue0FG7I~mn$8~;C(u9#9172
z{7^qg-}tS%r*pk@9dFOih0M*5$UgB1(}~(tIB>~-*;<P%bj2P&xsTc@3Ny2>sicqc
z`>4#dji6_FWPryea-<ykfdY~UG~zd>-`uxzU5VUz66L<7*c5*4(gM9(ihVhz*fj;X
zwa=*>HzqO1g_j8ar9WAO&OaqI<IU>bdfHcv^#)0BeCoYN8b1+XzJSAZd%tx3E8G
zAM4Lc_5;h@@B#N=(sn}<HWW+?-E>t1R}}!4MNjg$-p*2T2(wt|6*)%Bku>PVEQ|^}
z`FTnM^mfvl3(GMV3Vi9OuRjxcob0j)+`Q?zW2ogCPYTpmFcfHI0aBaCNf(Xdn&!P7
zRCl@k1;HM1O21iZxN1o_D*Lyh1M7<Zgx|>j@ncP9BG5DiK6l~sRuN8nhVPAlVYw|C
zVtS6%7}o7Igi>|KbTaE1IJQxCzeXaD-uWG|_nfx~)VNwxY@>hZ;)yHgiI!^Y2oNcG
zfo}uaW9sGkZyMUs+i7=;cVNeC{fGC!d&d0Ov)wcZ8maTsA%i(;9Mw{oyeP(A*-sb_
zYKnZq+gXj?U)$+F*3s3eOnC=ANb!^nfBQ#Z)q-X}JinhRB8<xw9z~{cQLy@Ax@!B@
za3>I*JyCqDqDZr`a8dO3ztqQ>cX{kvirVU2RVL$RHz}etB413%B@oZhWZikrIa&lz
zH?a8~N`s%e`P17D<r<&Z*TT(8^=BJDm)PJ-%ZSoriCWtuJ2VDgEc1aUVh&;=+Eb_`
zl&o`-1YdF0cKmv+bwg_Zu(26sw4U^c#C$Jcs0gxG=e;dL?pPxNxGo98-Yq6UO{er;
za+F8{b9?GRp^euQERXGj29Z_JzmlGUN^1lC(W$ej(qX^6mCh!nW+L%THx9AlZd_w_
zS&}(I|B%%yxl*BHx#=E|Cs7b)gSp#!NlEY2!Rh{Ui0e^o0YYCNu^g6JDr%pGPY0N{
zOm7iDZ2RFV(4z>EusZyeRac(p2j}Ugb-&W6G53E>GIW7%5IPTMpw8HPsTFFA@7+I!
z)<aNYuyM8pl-1rF*l4)2K`U!u-W88(1R91cZs1GvKQDW$IMb>Lxwll<{B|Me=LJ^K
zI$TcyeebD`F^@t3BXfy<yy~w1)98hG{u$stXDkAGIlfpFd0tCnKAC_2A@>IbyWim|
z9Uc*aTOfHT!hA2hLEn&5EiVI@`J<V2_41D6%C)&S0YWz_=kXK4h0a_G!Fzb|Ld@r`
z@<{A`Cf1f+t-6K`LpRLac&Z4CiERRTb1M;W-aw%}At9l7V;UYnRJb)1$yWBN6VqLv
zt`1vzC>YR+yJQ4oqQf>nkdq9T^Y@6;N6nk0D9cE&h5!0uLa*ux>hGUDOa92i{4G9%
zbpk~2@ezfcI_Wf+>e^Fc&=_WNT^7NXp}XGM{Z3qcBI}Bd$F(<*`<ArLdpTh1NxQ)A
zclq=>vdM_CN5quz9DT1Khjm4-ElfI5j1_Rz?1?yhe1D|p0;i*R{+_Nl)Ypyd8?(hi
z4{k6?aKG8%3EttZTrb3#@NN{7*%EvNXwc!RZR|uxmM=%ul7P8%<;9;2Ik{#F*V^+x
z*?EfEV}rdw2j<tRk*5itI<{_~{y+ldc{gW=U6y+dFH12c($lMVSc7)KT4-)4B1fZ@
z0|znF>h>=?NpKYn(d1eH^BrEU5!vYgL@;T5zFXA*7G53;dy)>=zARw|QP+;)^K=7`
zsl!_%Z)T`eVd4TvDeD1}oU_}6E0}!76H1jyA2bC|Nyf#L1`7hoxc+#;k^OuH)^hZF
zm))$h25jZEkCY?}fS1a*w}MQ=Rag8bt-k;j1q}{?dPwR^W*5Wb8Fu?2t$9#pQFcKB
zgdTBNuE>L|1SBcR|J%|0rM0qDbwuh>*^6TyKOZd6ccFrU0DYEcSB{rU3S7lo*Uk4x
z?(=IwX$2S}n#aAMLoSKcT>~wxie#+r;Q>)5nG<a5XpCIg@6CLN(V*=T|03Fx7_i`M
zo65vR3ah+aAB2=!UxOjMkI?Jaq_giPPS4I)M+%;dWlO*>8vN*9eA{`7t>1B&$~ySU
zyVyAsHCsIz5#?8nO8C0_#31GE<Z5}$8P-Mbc4a8b8t#Rhdk1Jpc*Tp|Vb^3}y{p7(
zkrFRPwiIk8BeKizIyB3`kr%wVE**(4d}2-M2oX=MDBlR+&YO&Zrr{G4t2``z7Mq+%
zBXK%vs2Stalb2<%V)0%3E19d<sOw<y4|V9E#zzlMCxlKvQ0?3`HgagI&Tb&rlD;43
zm#z><>a~A~D+8xt8sTtxH-xcE0?dch^yFBW@~6U5l+KCi@$UaEm%11;WJvKx0B+Sv
zK<|i0283?`8Gp=ljS!Y^0GkoSNf=un_~ZKfTR_;`8ar#Z4<gQSHj1>yh0<oh&8^ve
zyhJ*D9_8&<9oz1BZ6vdU=&AgfSpRd<28&d5S+V~Za30NLl!fL1VKPk1s7M@NiatD5
z_KbSx9eeG)SvGG|?eAN1NvgxTJ<E2)G29JKWYOUAx2tz}UP4KM<h7ayBtD~^FC|7l
zPmCkju5$%1RpUsz73;V?+4G<4PcYl$=aJ|OnGe|L&ajSqTZp2)Lmqb6C8ZlIJTQIp
z!L8fn0&BO{!a~ybnb{^_>Fr!LhNAwRQ(|1hhm56?U1!-8u2z{)S@r_D)vJ3wfj{8e
zUG~mf*==V6U)f1L%Mh?hTZX^Q*(O}~iE39<cTY!&9o=+UwSY)=Of0$L$z+|m>9563
z+}S4M*F3qA%Dv&cu1G;_O{PfbLSZFy|MO}Z;38)AajSPq&+Qczf37~aM`MXC#?}nJ
zXSSJOp0a9W0^(Ti6QpkhrqYiZF71=XOyuuWT>LqAn?KiPAw7I*+?;niGDez&6&%f4
zkgF(|RK0LF(9#XXA+}2f^P2zdjC$GclfemA?Tb-7e3;So+C&Gs(wUQrPT>)K_prFc
zA`)=pj)J;slX?ca05;mqJNnr668fp}#7cVOMN|~7Ry@xVhN){Wy<LGx;qb2B!dDbU
zO$FtHPj7fsS^0tqUB*2!xP3D8AKams<oAw21-Z^KHZjIlg!}ub#FfG8QO@<~<;IuE
z=t!61t~C%#p=0#KwVwwP@`|FAO<%ZtzT)ctyuk#W$rM^7iYc7b`L0j<zM=Fo{o87a
zOTXtpvp!6H7u)Dy2d0oz5z|_wT4iIu6olG6BFY3x?WP>tq@vHHp*|n~9d>mgDK~g|
z$dEil_WV1nq!b%Hww`Ob@+*D#wLD=|pAPfSeUt{w>Ygap=Z5Xu6R(V_FjlP>*wBd!
zsT)CGIw&L1S1~FXxCWGHv<yb&bvRGK!dwW%x9!6D44ItA;f340?Hv&28^q5@|KX-)
zo(6XybUVO|USy@TFkJX7_FlDX1K5-3yQZ(rzPX-xo5zc*-tzkJ$i6_)YsVvZU7>;7
zY@*q+FT&cwAcu<dnckjH(mrx3K%{s+%-`<V4*a0<{$Owj&G;ZH;ed2JV{OOH&w)$Z
z<RAk2&?U=qwiX8+nF+Ipxz_8Z6A`Rt@EVO>tjXehNzUpus332Isl~oc_!^=doa99S
zQxq!^&^B4*rM+HaQF<}Mmx!=eq4L~E38+Io45{FgwcUo9anNr$YrS}wIFvP!)AvoS
zPV_JaPER(8*@p`O_TdJ`iWqT_IZML41USKRHL(O3%~&7kfjTaNps<rF1F9t+)9dai
zLdTdhLjQvjP;K8vCicN<c6}PY&-z@s6hzF2`t62I1Klusfy%kDJ$fskL2;LGwS#95
z0;c$2<Nh|*F#j7F8{y2X8TunGd8i%b(p7}g^rsb|>|<vFKfoaJp?$6#O!YX=qEtwO
zE{k?kXufm{SXU7#c#VgsUm$^s@ZMV`tmWS5ld+}-akxTCa%6Vhj%wOsT(=CkW4Cz>
zGOU9`SF@D}xJv)B#e1AY`X7U-iy?h4YjG4#H0z8{1@NbP;znPaC_~O=%R}=)h|2Wo
zn^L#Cza60m4B8LIe(CA5?AAQ|#uefGIh5X+shppT(61<TnQG$-I65yK);?IH9d6!T
z&%cw36Am?w6R7?%-YP@NN_~JX!zH24-F!n^J^95%T`RKyptFG{XFc6Cg-iR8v`aPB
zC@^0{K6#=xFCZHr54Zn9VgJyI^7&!1@By0Fj*_A7+(R;L5h+G-mo>=r9-d&!7ssYc
zfQ4eB<+{R$?F$!O8GfPM#jrmwU?mF&TYUR;l?$#QcIQ=RuA^ZE+ijN30~ylPry9mJ
z@}e(U-((mYfW>93U39}7*`S6+*^WPWH5N$bT-aL3CBKp2eKc=gu9haikv7WD6o7D{
zsrS0591?GDCob<oG9iX#p2(#!+1DbPx=~!mk*T30gl!Zr2`YQ=v-L~(*XNbZZN@8=
zhm5D=6TYGjY-&Xe72L*2BA;J=(T26A9WQ^~6v6-#HQ@5opIWPyn>VjkA<F1OvTA~0
zc~eP29P>$@y7A(Nl{2Iq=A7(aCkY7r%J^U*(kB>K-h4%Ox#zSr(Ciz?Oy|XMr^xhX
zb*ue@a-|XA;%M>Fh}^bwcV4|DQFuF$Vo_J)%6iJ>Pq&r1zOZ{&mh_-Hurk8q$8^7-
zEjZiuYG!tzS-9L#;e&ZDDNCFr$VvKGhHH!o`<wgJ)mjyBla|=P@0mfXaMb3iVkMG6
z87}+wEcQ4ybacgHB1AjXXzfUT(<x|aMKK{m?65P5^ZR{6Q2S&2x}MtC`*A3#BlH?b
zefbhK`rHp#i5y@pGd(_aq(C;PRG`m1rzIOOwz&ZI-UQP#(Yp}qq-rA5SS$Jv0lQlc
z2<P|uD!g8Y$(YuyML6tu8CcN`FFQDPQf9|HTnxXwr|lCa(w&|C%{Qm^aN8y6RIG^i
zc2-#WgH^Vo#yzKlh3I@yOcZj*>_1$b@P3PYKPvs5^ru!GF1lLRRn&A8?H?^}OMbo!
zb^|k&5s~&7w-M)*XNVv%p4iI%|Bzk(hb(F*utbgvz^P>rY-J<|DKM&euYcA)`ln`!
zpj}}-Z6K%;<hhzG5fCNL1(H}_DJiHLjC)#$z;**+%y)&UUS{F5J6@|#A$n7e%=sW+
z2uW(zrNY{_AhP<GHU!t)=od_`jJ~Y1b^U_8f@=#n@K(Vr<kgq%qC$S)Ht(FQ{j=xQ
zToe@3(ib-j7VKVqOCO}puTLXF#Vu~4Aja^d3&H3`vM~6}Uh=rF5;=qJ2D+*h`Dtzq
z8B3?;21O3xYu^wpgmo74m7*?E;R$-QG1Rz3?u7vBOv@5Dtj1gfp0ZP$;d=~B28a4W
z`NDML-PU2Gll&P(#}`UzEJ@fKk{_VUvOpZbC)r(XwIm#rDJTu70~)1Zmqgj!s!Mn&
zi7rPnBtZvy?9RWWk)jJho6I>!T6syVS11U8VRZcaWXWoHyMdO=kCFiwt8rhDX^DPo
z8(AHuv^GSYbm^{3jkPpdYVW(4oYXVI#Z4gguK9T?Gl^Q)zs(+WFAe3*{4((oI;Fn=
zHj{GiuBfq|&L2=h=+*7h_#x2aXQP@-4Tv$soZ8Ju;ibFt8sAu)uEGcD6c>*@87Izj
zmwSkS+kwQb!F^42FzV$+)F&h3;wiYJ;qTkMqGLMV`y$kihBK+yRkN7ozTo@h)Z26Y
z1ZmL3h-`Qu6;!%19mugz5OO?lA&WpOoY~xi@AaqDFfTUUoBu-u1;cH&KDe;GUG4f-
zHl5=DeO6|Ee=db-AEb<#OTQXNo5n_tyBYV&b7{<c@1XA^=sBQyq-2(5M{UsivhNYj
zKB_9sp$J$r`1B^l+ffgD&KQ&(daavpWMUSn-!klH#X2d<Ohc>q$q=MwTZQ{0v_(I@
zkf6+jE(}fR6>>Ds{?fTmq|kcLW|u1xy@Yfaq5qRwlIeYRyU_cPru7KN=m*mW|G4M6
z*3Vm|1)WpV*d`$`5~DU|B>zIc?oAoRrJ(B?L=2@H<K)oeuGh7kZ(T)NGZNRa4XX_`
znf6;>gWI&$lJ0&@NfCICdyr82)d;sO&-)8c>=oKLucG=qR~Y&POnoOkvL{^CMX^tp
zLZZN>CqKaO3BEg7NC4XLr3md5ydDdoK$j{B^Alc+FfTEF@(1dpl!eJ1eSt@ggZx+S
z!S6{ADg|0EfuEHE(UlcR@bq`wu(vHIchtaEFh=HOW&2P4t+`aRuQ%+vVDBxj-C~O4
z`~?X17UwDH926w&DWJgmG9QL>q0%lAOOrL`K`i7SzHZs?#)^%?8)o-WU?JY5!w9$b
z5ydLDy@3))8PZ8XzvB;tePc!r*8qJR_DK!9d;XbU7?Gte?wA<&V(P^}zpk91v?zE}
zVK+L@MU6tsUzLR?Cc^r9c6$Q;<@x0Y-%mnP{@o>I@i4LCwgAV=>qqJr*?Mf?3)8>I
z5Z=nNY=r1uXUuR_RV4iuimsZPH@o*K*OrLrZfWR3*sKD+V`%Auuc~JdpE@zKT+PJI
zN%xT0-g(_Xn^;)&<;Xkyh=z9HRbw<zWO1|($*1n%`2$ZZOk-3WXO}5P8&Yq@!%Nu+
z8B*@)tfyr{Q0kYBcJ|(oge6|BvPgWwH;JcsS5|Y1|MTa$n}t{VzZ<)xaysBIgJWv{
zGI-o`?97XjrHbpP?IBker|%d7y;pKyNSJw;L43_9f3pbqpoMTtZ1qSD(f7-cUap=T
z=C254_S-f@6$`_BRd+YF6@dlTfW0H7o0Wgt1{~OX+*?sVNf=h86db2^YCl_MT~X-O
z+hDC&_Z?_#-)FqRFyB=LOLVsJiQvVZ2lAYIBmUR1MF>0*5c1$lo-eGHGE89%tDkPc
z(x@Dizi%ZeDYKLJPzL@e`)G}ZJqxj5mdC6lRN7!Ch5)x<QN)^gaH>k`PobzNZ0A3j
zEpPql*OqW8`T@UnS%Cy(z;_3qZQLERXOCu#hL842D<fDaiMge(PkHON?gE`Oti?k|
z;QHf$X@7`4gZ5N=d*BCTn+3rU4y&UDyqV{O9KL3ahQG>Q1bSpd;b796cA{O+JaB6A
z%^1+yI(|jvFBOZ*`93gmE_ojvFwgdnJ{FM2Yaa}+gdm`uIz7qIs%p33ah3j%cn?*e
zBS&zRR1?439nY3Ta{R6H4@{t6_G$YHEQw3{SZV*!PJY;@xVJqBU5qM(sRj<Fk?OZ9
z!AqB4{4<f$OWR+SGuioqP||08!EX5MU0g0662?@2;DsORzVonAY|qvS%TSM%f-K_`
zv%B;mcWKko#~s^)r+*BN|5^cmI&<rjnl1!efZsZa8dv3-%}vR;uGxGnc=ku$SXjO`
zU<b*cQm02M-(62av4ELkibKenI9WXGfy7?LuSKa|tt1HS3A;=#888xLedXueCyr29
ztyu6LFY#xmZAgXv?NanDd>uZcLwKRjfMJj&s6@@a_)3p3C}YS{!R|Us%G>_oeum2J
zRjP5Vd}ZV{iM0~shx8EXsg9+VW81E{RVy$<rdw~@qIjY$D8Q$D=>s-vApUiZ=PtWy
zts;KDaL4k!8)0a)YJ}GdDXUY^KKzgnlgyk6$#Eor%SRg{_vvkT6NPzKt|?pd(3l^5
zZEIGD`DU?2oaOjxm{*DXdN8>d8tf$Or*YOL!zZN&^R08WNXz`-=V=5|4=_6z8-y`*
zy;;t+(Kzc5f;*~IXHk8MFNxDOKVr`a_<9g^NdTFIC#;3tpCoH~0%y;jcH~?N9lEq}
z9v0`nMWEa|QyJ*9zd}+=zgK=oI%~gEr1;A|J(|LOTEyF)L>2GOzFqHol<Yezl_12@
zBoJtlFZuLFifgKq3x8^>h%V70MAsql-&m7u?r3-`agge^ZCYBA=_r)sE3>c#%aM7p
zz9%uir`e$C$J{jz!b?ox(|jMj<@=2ZSlB+K8Ve0>wB#9dv~x7LZX1>9udYmH<%z||
z3$9heO!uZiP2y^iH!FeZ(QBtvKn|Cb__O%V<X9r&(nz(dB;TZ=93=zi>0=&8hTdf$
ztgcE|2}-?(Gx}os;Ugoy>hOdj#_imty=t33Za>ZLAIWRyr%OBDd*zSmP?<BRnb?(W
zs;4p<wJ2Es4YLn#t_pzt-QQzcTt*hP_P#{-hXGr1hfUbVtRK6wg+M?@0?bCFn<|bx
z`r~0Cxn5z0e;gHpdPeX9T-9Zy?EsmTK4~lHw@du1E(vp0fDfynPknSfaooc`0FP7H
zD|<QkA~3m$1Z|*TP9)-J#EqXR2-os7v(mI){(8Chz5E5*=C}CAxHc2W6G*}B5hfP1
z1ZYQ~MjR#|t`x`o5aQ4bXe^=ztW;t?BBPw+%c#sz<r{gO?|2%3sX%WJ{E@CaYiBgk
zp1j}rPQ5&{tw}fqe<R6kSS<7hrwf2#5hJ#Zxo<7W(3cFk%ZS>$TZld&LzzL7NSH9<
zGAu`CO}5WeAvEI?k2j4UdGqW7d#^%&UDpAt&r&%KnDAY^eE(5$l6T~}IP}hQ?g75;
z3X+f1)2A;q4j(l(n=);P+}{zAWeVTra5s1U&;R4|!nx1FMWGOzP<Ix8VkFitZWq<<
z?D<O2{O)5@6IIHUz;V<h0cnVk@5fgGSLj;PUC9@|t4)l0Dh!N_Lk3eMj`V#+SdnF2
z%qkQ=15+wC`5ud6bUjrzJ5IB*)uGNDsTGA9-toi0TJb!gqHHKg0oiu|ZzFLW-?fWk
zs@EedbEB9~swA#;+7rE4Eh?6Ik-Y%g?Z+crcvwKHs!c_r$|Nt@+Z=p0K%KSSS4#&w
z@`Y*RkgeNpI{ARhs9vjutvS)~MX_oDJ-FhufiD2fy$fFQf3N9KB49sB9-Op@lT0mp
z%c^Nc|HKzf)+U&`e)5%VH}Bl8O`Gz1#F&!w>7Jau3zmQ{5zm16#RqlKBl}E`p&R|p
zHLtF6G*X9_7R(S_RyM23yay8j5GB8^nMqnl@>srLwT^M1D|IXS`#4#--w^afSy#uo
z=_@LBDwvS4c4h5>$px0*l{oMJ*B2Y6zL*li84;HmpFOJ*%5Nq1Mr~TNF9OP<pL+2h
z{Aw4(korx*B(mQ9Spqq%g1jRVBxc>O>;Y<3Io7L-FM+cQp|MmDq4!NWhme1AC)p8z
z3N5~!MS$3zY2tQB__gBFmc31jMVSsKp+WkZwJUYAA4TLtCxYeu-lcTqDffd4*es#2
zt_q1o*eTG>;shbDHt|r<z?km9dSEflO(A$;Ny97EJqRa6MWD>HM>E(AlIH8UEPeQF
z`slawM5|k%Ly38KJ$CIye>J)YP={1pdd2=<zUx(*6G>%v(p`6vM8%xE`Kz)7Vc;;w
zk;pe^tE<|M+#6Ml8v4UDK!?8tuOPG7`;%3vZL-OFoE7kvN<ZvYFmarG;xZ%bWDEG*
zo-Jpm7_b@NY$^ik+EUrI5+@FxQJX~?0SkbI_5%Lx#(L?~N1U%w0qx7|VwH0@<=3g)
zktQ*Di>FaC(%>|0+MYrrp+etQsmG_gvNzo}fQXUS;+3{aA4vN`9mTL8KbD^Y|01Nr
zsg+kTUQ>W`+kz(7ay{;UtHS%=?Tzo=(((Sm9VF<`!}DsKtzzqJ1~P5dEnhJ3({y@w
zkTe-M8ws4W?H&)EmsJH03sC3gs{tz_*VPJUXfVaV><(|95#oazC?iAOQMBrccmYyb
zNX)!}d)!pE)&Q@Ndq-XG!h9z~L<1>EYhk-s!XL+Ls%w5vPF#@%chioUembXpY3sNm
z6ucV1gEo?d*g@NRoK0C}J92<oBwq>e==nNjFhlR~C49eiJRW+O$i^2Po~_W0T(!<d
zss~RYW9ndsU^A<C0=A|7ra1T$qz8=S3y<Gyd%@*dY6)OvwGSbFugLrwE85Vz+KC1B
z@CfZv2{9wb=Xr)e{8yEZ@j-cHXX5tZkAgts*_jjV=5f7^!yCgqN}i%qCy5#Zb({78
z`r%_HZt=S)@s{41W0M55XM8l8#*=2E>WojGU-@KY2|x5h&{inRU&tK5d`>%eIlR3;
z)1whxJc!>mgeHl%0lpM<gq0|~bT<EFPI-70UdKE(fy;sgcY;j9HV=lZg7BOw#ymK_
ze)AUs_jZ2Ezn`;;lxq=$GJ3q-q~R-x)9dsr?W~nPtezl6EV^|(YS)s<nZRZ~`AZ0T
z9egG}wBB}_hlSr(pr_R$qHf37XOWl3vp-Q-pf~&D{w6XEA9Oi^JAI${Ebx~~6e=YT
z{U!6hEzCp+7Uo%7q2P#cd)wWh4?$y^EVtS9#DVI__9vHedu>Z@3t>j?pxG!aMi02x
zaE$1bHNGk-eM15voIztzu&Y&U6_98eGk3dCp4WU|OZdtXTn2)s?Q1M$fjNaog9iL@
z<F7ITXqsrO8Z~Dpj|wAt#P!1Xr&G`3Xw!^CX*BqaezhVrB=10$mzo%fL+9y}43Una
zniEBc4?l6+{Zm3dLD4*(T;9&&iw9Y@x3~u5=rI==a_;ugk7=kP^x`G;cZe)?i?(qw
zQK|dh1o<uxn}XEH44&#;bF%y&w?n&0oMZa6lh32>XW>O_h01D9!LQ&$ztNV6bHKTF
zIPCU`Xj`{}Q_()QPq}DzU%zUOTzBNio5Yss5aYME1B7VKa>n@WESGW6Gd`Kiy?e^~
z(VM;$$Q=;M7{%2hcl6;$A&8vxkr0%=!rMS{q2-DA*D+*rhy9miraSkQ6&Wi=0Dd4j
z?(lR8z7mw~h*!7!&(Xad!&RPp^xz*;*a*iJARpCrc`U;8AdFy}F00H*0-F%nA$}~b
zFNAi`5b;TnXuWM_2nCB?etUX0XlF<6AY<o59TZ&lnZ|vsSfy4S+6R=u$3E7w^lVVb
zbp6~Hm%A1BOu=LkI2e(!E30#a0X*?0vpWcF#db^Lf*dncer=i83|ncrtTg8i+CGD)
z0rPDNLj-}h;<gD*>+nkzuXd75?w9b<Q1IO@69oe&#h{>j&DpfsT;3gHvdhgg7vbEV
z-HWhd+AXB4!fZM2NG34wSmEn2V@Zy5?0y(2IA6`qJwj#@;6!LS-P=O~YfPQIH&6@I
zBBhc?Q4Y(Lk|IhGW(rD8AGvtD@d?7JZr{RCmlby?{|fZA<o99k<_&ToDdVTwH^!8b
zmXg&%#HvZ*C?o%=0mkyXwWV$}qEXF(R2hh0{&`XB^Am)22~EBx_S80s65q}@Xw}fY
z|A-9A<hOa8j-P71iEGIm|8aeCoE*>1-zAKySE9;}Y8C-BiDwg|$(qmO7K>pe+-(S}
zis4Jzx?x%_gg91@fn+hWzVfjssjfpOv(v%m{k-C#A6w4N7+^a_UzY79fZ;+tSn@b#
zERX`}%SdFFO*zm-Np+SkZyT@!Z3+JT@PvX@R+TdiH<55ZM^dxLQ8mu#s%)g=j*+mB
zch5-_mM+0_YNes7uf1=>bDG74<2MhsJv_(E?af~pf5Z>2Z00F4OS#GUTX&Frd>~eV
z=-Q-%e61{O+`Ypi&0B`toZ9&zZ|ZiVh$!m`_j-jGvS|}v6k~Q*w@=|p9wBB~2H@K`
z@mVa7e?l1cvN_{^VpNyy{0U#K*=AStcOs2UZ#dM0ZmMC}v{INqqp2|PtIiW`PT#Z(
zy1h*96>zsf5W0WggjvAp)T@;$kGovgc=88brD5o6M`AH}eB?b8hbbPZaAPX^we9y%
z6}s{MOHioF4)1TNVk2<)a$phXO~rVs=h&`xJ-I)e9`@=Y=;&;DFLn%_96OOd&#Z*;
znS^O(ZBO`+n<~#t-sHs>gJ#u%!x48p9?7I{ow&YrZpP{uz0sTJ;r)t3FL;O2z^8Fg
zNzA9m?>!Q)?Nb2Z-0i%>Nj7tYWQZ#8Up>g~<h_9Al4f`+opMs5{f_MR7tzXJEx0oy
z9lxp6py_;PN7OhT;qZHm50|q#_&yNe831jIy~eF%sMz-IalTYk$gxEkM^*WU#QaH*
zUN70)aginfB~tx4qyLNgjxd;eX4U^JyH#4enwY%a1WJM>pEKk^QBIK==7(@<x8WXm
z^8)yBpQyZv1HXGN#3XkRSjcL+h+1M^VzXq)Vf5(UZrFTvHNp(WO}{GrXXV6RhIhXn
zSv~Qy^)6y%j>(NLhUNJDJZ0$O)5tFl=FFZz3JyI)f^R=jAHC2u=AE4ZE;O=F_fB%3
zlPGN3BnqE*|KC5O|4)eizoXHC5_XEKg^1<1)B9B>4@cFZGbcMsxlOkZ)mz`4t>EhK
z{Hp>&Iy==m%DtqAhEu1UecSa^4KLv{4I~109x>>ft!UHSD2kmsBgQf}0{Z43&W#h4
z`FXE;*j7g1Bj`OK#B5g`Ub*34X2Ml3<NVojY`>z<?ZbO`F+QIBrEV2sV-<pB>ge}Q
zeo%3O)V~57ZMtXyzU*RlfU>09>1y<N%*eX6_k`br&&fF%9ss@Sm#y9_#Yd~>BrOm3
z-c?fTvNE8cezA`r*0yx!@#7M1lNJ^HSIntI7KQ@iR5RP2-5nvD5%#v>I&jwb$ZD*_
zh8qBz)%D!YaGD(PUxyIiT!?RN%q=N|wf>{?ONokG2GNqVMUg>~-fGM7@jJ>e#V_fN
z_F1MiH@<mZpUI)=WRz_w+J4b>9e@OT?oL2*0oxnBy%JdO+Io6<H`7%f|KmDjPzn6`
zH9O8RY2B*ub+7ed<?=Zu6hffJr6X-ST$f3*@v^AZzH<{H;5&goyQKPkOmgb{4hZm?
zv)BEr^rk+2{xQKY4;c22^4%(ZiV#npAZ*2}?@33Gq(>tKM~OXaX;-VDvlW7hbqqc~
zaql?WpUN@4%coi|h0Iw>o4(DzdV6vE;#(!oa8<yt_y*?vIiXEGRVTshrS`t>G&0sR
zC)d|VM`!UZzv7AmWg3SFZ|w%~Ff*-$&2cIZB(8bdZa;X1kQU)^U)%a>w%dxNSEJ_?
z79i;;!NF&KOM=z5#9~KwujHKSt^@t<yoIj=^Y9~t9>#&W#^+ZYQlQf2U1jx5qRHS5
z5S!e;Tby~I>S~nOoOTD0ju3LW!bIU=4s1R#?3I3_Je;L?Vj_-x7#D9~i9g%*cy4wf
z`1(cCD$I<QJAckZ0kic%r)=6)chcpxqMH`x_o7;vBVNimF_{(Z737cam)cOC?JAqo
zvLc+9`8y;>9*z%m&ZM@<uGF0k9SYgwZ6t9`**>1IZ++OjMIUOt<>7=#yI15f^v+I`
zw#>n?*Fz>Y#EKITPSt57h(D$fIvhKD=9_X1Ip;bWr!pM2D^y91P;n*r?0E&v*m|jO
zLE~d}I#yl3UW^5ny?b7He$ltM|4guw-X`W|NBT6P8hC)zvD$K<9&00I*DFE^gpuEq
zhiyrULZRsNT8qeE_a8@oB=-%EI`0-9I{)iGp#^hvxHoj|Rt&A2hkEm;JAUW<@@^?_
z4!?=37;j4d&qSM(6aHU36Y1jDXD6z*nb_Mk*BdONQ|A<<0N8M1`H*hmC0mC!v6p`%
zz3V*UP(7G^Y<zOKCoXOAwYlK3q2BsTrp*WCQ@3fm{u5t(Ur1PLJodux%=t%suE37>
zw)!9B6-=xC<ulhXM-$n{_DwvFCoEl|Nc~2gllan>>$2e?xmr;rnZSg8b1zcJhHT
zUH1MAm83bBU|XXW@YTCY|GM9HhecG*>p3ZQl&XtB&bi4>RrY)X!C^&e9ASpeqwZ@G
zgqSP&v-%7F4M5#M4{rWieV$pS{@v8y5We@;ZrdOGZ-l2p<r=GB@kr1&!tYWk&wrZ<
z8~p3Y01Y+Hv6Dn2jULsG>MT8Zm|#B+^x;HSC<mI8c5kQ4YtQ-ARu~P^5uAzN+9v+}
zmbSMODZ5AkXzi-jj2%=?=${~+5doA%`<u8v{*^LOef!+c>zmgbw&3fFOHpebPXAYf
z<NUypld4wnnyjFIM(u=x!ks7tY>O>zT9b~Nxct|KpDgX13B1xmrz12`ng5#2xhi9n
z5?$4FSBNtr{Q5rzmnqZFKZUsO(=!Dsv*{nU5a6<4Hh(p?9t6oJ2?vrUW2y7WKF6wB
z*>=on_0TzoJ0?rKM2WZlOWg3xmT1ykNFwf8EhY5ewu`t@&Q$-eQ>6LvP#NUEoLuuJ
zaea!<|4N*g&Yf4dJq;svJ7<5g>n|-YPnc+!vj#tar;5Y6dqyO9Z{m@<(iSc|>z@Gf
zH3IfZqd)IR5{_-?XNkoPD(VYh{9PYjLEpCf{A@K2!qa8g9s5E=j*|H={_HKFx^4K!
z0EvHO;LBx@hw?jZcrqot<he*1Idx7@Vg_Yht2!HdE%kfCoaX8qo|x1F;mG4B_zwE;
zbQ2Zs*IR2{i6++h0$-Yd6rlTG?9<SQ`eWWmDX`T+M6s(zCvgM#tVsys?n7w46FDj#
zCglUc_fqg}fr0xeQis}?d+DV8tJZTAj#E!mSa$cb6G+`dsbmJ3#{#%O;Wz4#S*Q_U
z$((I&mN44JY{VCU<(bjYmm`ZQHzG)fr0WzK0ESWO(^ZXRXcL?CF0)06=)pU!ckJn_
z+X`UUnDkegom<8Kls+rWoN=Cu{kN%5GTZI6QlY(%G2tnS9h^TM@wA3vWoVU^%aeAu
zol8|D?E2pX&(fwci$%6u8f((c(oEV_!s*RR{*7|6k*>NAgf<a(Uv&Pf<rtFvhZZ!r
z(&e~d!GDZFma--+Uk%7U<^P(NwJ3J~^gqG0K)|}Hm9R$Goc}lWDY`tvkG*l%`X81;
z&LDmkC4>AY02d%g|KK=<buij|XS_B_xX-_Anat7%G7`Uy=%t*8&-A~RNOhwy2P2@O
zdjx+=q?UhYq3!0eqfF(AGGhJ@*rfI^X$nz@Qn0OJobqKBofUx$J=k=OXe@kdDP@dn
zwzw|(o3FpMu~7V~m>!t9i$EuOgV9;PhRBLRx~!1+CbG{SBR@;fH+sDDg|e=2DT%lR
zw{;Q6;`GyKD^Ee`X#Y7M@sd27+W2<<i;i`rJ(B`EAb1Ijo8<);GYn(iAoo1Pjw*Xe
zho2#W+i2V92|tqfObjvEd;#oxjGicVM2eezQ64g7JyYzKi{ztGxV1Np%FK@;YMLX+
zec~ix)225-ADZ_P`rP&5)1sGM#I6VD6TaF=-1(d(ctyBVu%{Yojk3Bzk9PjY#<<U{
zzpCu`hZj-Ixr;%^LDrn@ai2vKt6JN!?br@SAM`{M#p~f#2+IAK;MEr95sJFvcm5`0
z2u2BkX;L|>8~=CvF(bja4l@9Fe-mhd*fjAY2<A%YI0Scz@?$QpD2@?gnh&aJLh#;`
ze)Yd$Vo{6|wA?=N`AGEC{|IB+!kFLhH!u}_`vmG0_ixseTnI*OwqGffekv>a2rQNS
z%i4fMf`b#z781GUOSVsmV(tV8A<}rkf(>e5YVP7loHK6zmqqJ^MNrPfiZ_g+RF2ud
zcAi8B=1yUUBMzZL@<gTcudS^)1$!Wcn~k6a;(yDAl^WT^W!gM$w#?sv-hDr7#xXF*
z(&*p7UPho4-aJ1<?<M{PW~7}3YpVRd2G{)|VAJMkJ>vev*-3OI#;=_BvY=3*h`zpy
z06q7tq3{Dk9q3nMkkv(^kLGMg>SAhRu7;ZQq#)Tx`Qiks8V8ynzlEpT3}$W>e^f*<
zojg8u2V6Nv{MyA@lob!x@8V=d&eK=m(^E+_D}*VzpH&9&(}MQRjQ_q~dZ({;WTv}F
z=qyc<lksYe&nBlU6f5IBEhpY2i1{>j9c10RQli+mz;DHGxt-+AMJf+^3a&m|`V75;
zH=M4<@43(Ik3eCZCq(2p@VDkYaHbk<-3eDNsRSYqMq^bIi;cg?6(CnqOSr}Ny9s1o
z5Ybl74Z>fUr}Xb2H>dpPb!flJ^W1!bSz0B*OnD1|v5VGSGE?}eb`Z1lwEV`e*C>0+
z;Lh`UK}Ca{y2jd{oL@$$tfdH@7UMVuk%t&)*wpW_ii)Ds5|$5<E6H=57gaOFu=2Od
zHuHMe5{c~U^DEIQu`({JSQY=F!C^$cRj$o&$hjik^Ro?b^(s#{%6o=$2$ew4;)kXK
zx7nwmQjl1T3&e?sc~n#|_6lZx-EPT8@0RWf)x{0DJx_K7E%bjp5trR|?QFSXM~`v-
zc_RWorV=@<)vS=449)DRZe8V<uhtBsmu+V{Ykr#FIhWSIX7hE8=e-qj!&=dm*Skfr
zYE<LzhKPorN?^YFugUyM#>d7#dvRkF%T}$O6~x$hQ1f)0T)WCjl#kYyb$GC61%LZ(
zAj_-Z^~y_~)xF1ltefI`pL!Fxd{2D56G!2WZBGE+)yh(AzUCE_GKYW&^xXRS5OL#?
z)0r}M^4Zd9=Yl<x)9i$rXP3|ji?aIR-(eN}A93Y-|GZ%5tgNtofp?(^{`GJ2lH)H8
zd2#ob5LW`iyC$m4QN;ho_k3yRscUO_jT`2qr7$P0H>oHIa)Q4H+k_d9W&4zTExWkm
zb+oSEgKOU0%%~SUIh?C_#c+m=mPAg!P`T^0uthRIu;Js#?kvc{iqe-5a=_2dSyChT
zXlY%I)TkF(IE!kV|N1fN{9Q@><P6(=bsr<@_YriJ@}cBN{=vB6=nBi-=iRj=)ovcV
z*)mvvUAjQl^(3*^?1yvO7XfV-)hcK8C~<tfc%RFuoaOW-q&WM+$Px8V?j=Imcb7dL
z&<zbcdESzHM0bO;=oIB%kK0N@e@A35;ZNKVENkfF($lj&acu5tcZ%J$gq;?4fheDg
zW<>^1>sENXt=H1L5zal)FBGYDn2GYcvP?H+*_D0oY{FM^r(YF!CE!!9iV3cJ-IvKY
zE??w2$J=PmHZpE-*Fay|Q}R32z|Il2X)Id2q)Zy;M+!6W<gW^DtGx$)u}NGW${$8^
z1<?}9)T`|G4`<ZJG>(<pGtg*fj-R{#bgMbb7d-j?G-9<zj?>BDbKhoBb@pwNiS(R4
zl2aH&^|q7T{DcsO&Oe26!GXCC|3E~a);W{=zw_U@MosIS6bNiXG<crqEXNNl6$9Bb
ruXY}=N9Arm|K~Al_5Z(5xay0cpPQ~oG_o~-_*=8e$?k!TPt5-X7_?0$
diff --git a/public/07-basic_statistics_files/figure-html/incidence_visualization-1.png b/public/07-basic_statistics_files/figure-html/incidence_visualization-1.png
new file mode 100644
index 0000000000000000000000000000000000000000..573c23b0e3e6d18f1b59f99d3f20f6d3aeab929c
GIT binary patch
literal 53684
zcmeFZc|29o*FV0_b<Oh>ks%Qw6d{F6DH)<NM5a<HG9;1=_h=$2Dnn(uWQtHIvwKTQ
zROZZ)$eek0@A+MQKF{=hp5OC&J+IgAkKgz8dX96CyZ2h_eb!!kpS|~4d+mGI{ODm$
zHW4-e;5=e@@HhYy{VM~oFwp<CvDnc7knQFs76!7Kmv_75s%{)Ms;U91Ha4m@^lO4@
z0R1edXVKF(ssS6>HuP)4#w8%YCV>8>+$Mp3cAkx`y$Boue}w~7>9h^*0Got>jiWpu
zAt4}ve(ek>FApfEUzeT&Jmr#zC-)}Us3!bHObAd-_$xqXO-QiWkVq(}|0R^uubm0y
zO9`DzrCjRe0jlKzHsuNQlMY5dmNtl;o#mZN<x5LnwkUu3^5yHV>COb3&V+!@a{8Ij
zS^k&aNk5k8T%Aix3;T^1P4yNR7njNdmdX>BI_YQm5}mw(LBB3xUe~bLVC-oUR`m}1
zR)PKK$1v=arHmTgaI9X2Hdg?|LN`80<j~AH07*D<P|xC8!bBx|r1W9$VH=fiobTQp
z324mfEX=GCUzEIhA|UgWqQ~uvuD<M?<<BzPZ}j$my>Qah%9)JCm4r{nm6liTf4^<F
zLa)1~eau7gB;M0DSaSTz_#dK4yt;c=(bma7%|a^lFBe;socW<8!!%w!%M|_+N$SX7
z%FQl3g-*}lbp0PQ#3GP!<mwKI#Pe~%6y~mUiOIrO#``XIt*9eT#l}?or2kv<KSF;^
z^%U_9ZMLS`uX!|?y7-Cgx<+xN{rUMb)NzkvW@VQUw{FP+N9|>|HK{HBt2;X+h%L0u
zajWI~zc%O62D<wSb@UzYHjuFpg*K-aKkGA3Ptbm^g@#ICGs-;?*h_84mH1axIfkrx
z10(s4>q^x6KC7wRrEL3g+v(-}odKJ3{AdePYGN@%{y~9?AYS!Q`Q0q*AgftqYN+e0
zwqRQ2+U)v3H#2e4aV6lXRO-pHHdRC=$ZzMJr1psES7e6A@yR<tJloCNR|LF1w#Sy=
zBhOpX^j>%iLC?Y>6Ggd->g-(GXzN~*rYuey?Uv{XSso#G)Fl0_w`KoXVn}TnIIaG%
zRn*RFAQP8~$yJa{4V@ASoks`<1P>FbH?o5khx_7I&*jZU=kIh^77t$U&K#c0BnOy_
zw}``fMENugR7&5rdA&)ha-=RxB#PpaPltz{nV%DQ$qyM*dDYFo!ikH@v5p>_pq?7^
znA`>^f7RQxAR1M|{`{XEEGvf;OPPT<{>@&Z&3ZiFcty5|+MT)lOQOG!?7zBXT`#--
zDYG4$P#S3nUYefHce9$Tk-*yfw3q7x3mh>&>|=!Drqu~$y8bidJTh(8Gbw!edTg`q
z>bh0-?tO}u;}vW8kv`3-Dnky13SI?ngPs>X?sj8Svueg>AA`!1s~XKbXw{CxRo>jA
zaYSsMaarR}zKpiY>b)=b>DB5sI(mMxN=V1@2JO)6<R%Ryh9y$Bvb=SL(Wrtng{SRK
zoLMj~9!}e5Ure@klng$iJpX24EZ(Ee@k$mof=C;m7(3^G$nUYZ1Uu?kb@Eq)2w?7|
zb7X36fVo-ntH6@+wQ2uq;z`e6FHVyBpY04d>F5&qRl?8akoDOY!v>0p)_1ug+R8i|
zX8Uz9+CCO*vuoQd#lxtAtLtOx9*zf_pU)6OKJTctb}Tvcb9OfQJDD&~8Bz7RJ6b;e
zX8xKk7Hqnk<U+My)Cga{SH;@t_&Q*Hq!$OZmdo`%b?wR-C~avWJ~U610fIJk_x-E;
z!5=RVTPuH7trDGIz6P3&7I1Q8emv8ahNG>&$jfZkrR@n^Y^xsY*Ih4v<GCKc$9Tay
zs~~gtv`e3|<xk3JO|=B=%u05yW0uU&a=mAAIK3qgQIy-u4_XdXd%saamd<DokIDrr
zEY_AhNb;%7+xklDcIEwUp@%*>Kb5^M|M85=ydAhuv-;ImM3_vgn&0PlNPbt4U*#Q(
zp@?%Fjk;7v@+@EB{wwnv#Uitoe25@vjRf$u7?tLDrCg~BHjq`R@@QqfM^1}d=?Z?R
z>$dLoC?zLuaI^is;6NP2hTQ>*Mt{vU|2~(L@2TPe<mJUsMW*l%wo`)kmAVfis=Oeq
zi7T5=VpEQ<(3D+4LgeG?Pc^0&w2tP_i28{#gc+8#O$&`Yv(r6WwR*;#a}_2-*F&0I
z`uSS?+TA*n+leQ;9}t(><z@%IJ#T7Qjz^6vrXL1f*MR<r(0+%h?6UBi<lxcr`38)u
zcQ#@RbjHo^cI;N3b-6Eb^qg`+!Ijy2`C_^{2)Ko?!GrPo+%i{tf%#j7JZF|+$HLKD
z><;y*ISrnJg}T%wY-mbCzjiL4xFj2u8vCZs=VYFGph1EJ`Lhz^Cuf@>HyN75Z*?Xf
zx^cI%imoRWU#w#1ZZ2kxdYq+N@K<5;j$|D@h{Wj=>B^48N5yzWN|48qe%qlAOMgMx
zK<aw>`s$kQEu~bSUe<r=svlHs8O>nytBw7ys$Q(Xt~;iK_L(P7pIN!(C2AIW0rp!~
zgVSgc3vZ{3NA$QvFoR9Z=qtP2fZ^NRuYw8N3cNkf#^kTtNw5UaP0DgM(wxS=&NXmq
zB;=vXpxO1+Kdzjvr%v5H8aUl2$3$4)epUtt&E+YXtr|v;>Ggb~D){HR@;Yx|uK?&D
z|2?0-lNEZHr^)N`<=2lTwY>Sotb{nR3I)3}P)^*PczbFanosY+h_pE}_Lv7-A0@6#
zadYbutj=jET9>yjej<*GH@lFjR4f5U=KEAKD<ePK>g?eRyhn<=TJZ<C?_InRV;VbJ
zo})IH%+Z#@ElIuK%nM5I4#L*B`}S{CaTl=FnoF(LN^+F;%AGjP5jSHToV)woj;rjt
zUQ+QvsDHd76c>HjIbIG(I^Z+9tRAfcgL#=<&5C5t_5g)XrNQD2!~EXU1D`N~)edZ#
zJj5+fx;=kAM*@rVq!x!%-A4{e_qwhKg#}v5o^Cpj+K|<w8RQppCplkYz2tgr@rkCs
z3$v=LbW5G#-#x_;=JrL>`gIT-4x&my@XXG!Z@%r7x!nDv{GFU=L-oX)h42}A{Z*uM
zOMY{As9bdEYk}pN{GV}TUoP5=XZu4-U4i1Q4{)nPp1nND<f{>Gir?&2uaK`EU_2AE
z{K{_9`!UA1FM-Aw$@sY<B;Rl6<^lcRf4imJSo-i{o#HaajK$Q73;QtzH`AXC*X0$R
z_3GsP+Mi{)g9?`iu{BG2$3#u2Vzs&3aqD2;<Eb;v>C4~K^oIkf18Ca9^@4GSsW-j?
zjmI2Mi9r21#kmyPyx&lp@kW!=*4Yg8LR&?BjXwxuJI}Y%_=bxc-TQg7R{CFDTh57M
zT-z$K6rQaZT3yhVH?@4m3}5Xzc+>mX(DIf)|IpEDL&rA4r3vZTd+SHc`s{O3h6USk
zY`^Bo_1K}u8{K`}bfj)Fb5z+rA|-F&H?n1MAp*QM?+EPu<FMclnSt(`A#l@ooUQD=
zjqas1NE{`9^i^x0qBpdB6A8-hg$apXvHUB(*iUP7+Cs|S3!ToVWXE%d;`+qt!$0k-
zNW5aY1Z_q+T)wdS%$r@sak4S;p8a*lyy|{@Os6TC75e0~IZDpPB!`!N*)!i)x6!$W
z%W4PtrPJ#?*<tLC1GXYUeNH|$F+6Wdk$L~iY-$rw#6LJ@s8$7E+&(>Q9QOD{!}a`C
zll~J`Z#f`I1S2L}F&J3q*I#+Ux<#U|hnwQ@cUGfBMY)TNb-P?n$6akMnsdkf|0{nd
z1Eso%_nshX?ATFs;?gSdQhlHfqLO5a2zO^-pWd>f@7&oa9qLrwx2C}1aRNTR9mQU|
z<D9(WaVl?3u}F7*xY;d$zILaJ#)EKA2HbOR!JNDClzw$ar%UlPiS7vi)Yz`S$oZ=x
zv|t(+{}1vrP$475E<155RARu!jh-Sf$L{s`ydXM?br;cZm&*xrqFz_NOK*s~(8c2g
z=`v7!@euNaMn1N24-sSo<h=U^h}#Cp=D#4%&-2qkPQBRx5!?WA{w}uxa()AZ^Dl_&
z_6-o54UlJlLC)oFfSmfP32bOmc%FAdlfNKh8z3jX|1HS54G_k^AZ|<>Ag4D#)WIp3
z!Q*omqthxDyJ1jOAkAazxSmI&8@Tlwxb6sLovA0vorjJqT0mFMl$kJztuU5sJ+UE{
zv0=;>L}fC=)Dt;cer^MHJ1`aR0O#&`tb_gnQu5!|&sRLEOJj1_PhF<w2hU8V=UwU2
z`?o@TWkVZ+_mM&4-`Vdapvu36`nP}mYaZ8)l5K|RHoDrWHXACbZ>Xe->o3ICKCjSi
za`WE|ONZ+VX4sHs`VZ1of?luL6R+O;ck&GVKbe=4>70vS<muH=ywMcm#Xy%PNTJ^;
z;pxVmwr||2kj}Y8e&&dFs}_O@)|a-?(m3JT^7&xIqhVshkP-i=AeG6hU!|bMqy7J@
z*7`p(^#ANZ_+MyxegFHO;eQSCzXtj5$BzGPA^$hG5EiEOQzwAw6@7&JI)<^L-D*G+
zRblL3{5zVg5pn(MoPRRm-lb_xs&2u%UOc6dKDg0m8u#ea3TM$Cv%e%n<u9prF%4S^
z<nv;q<aR%%=^n)*-ON^rF7p_k@^$n6PCTXL?J^PPWOr&^7g2e&bBw5af>7O+N{duw
zRC`HJYMdba>SBY_0v!Tq_gg{w_)|?!7GkpCL4n9s#;9)W1bBR7!|EroQ7pdjJ?6ck
zVHpSES>fp%DYuy%gd%{t6^PRsY}Z|ZJ_MP5uf}X5964b-<b95&*<KNR!DW6OGQjTf
z4(glV^2fzU^Yqcn@!zNDv=F8CT;FADRp#|A96qHUxz*%nG$I#MnO*VspN?O3&|xRi
zgO1njm#6fPFdV0YMTBUb`Q-4)c^bP1N%#Meu>YHgG?@HxjFE{lEBFMi>1=uva9B_n
za_A*Wy8lnghSi79L`k8OeW)b%5T~^P7^)WzSC_F}s>UX}s6;WQ9k`C4Sos&lT{U=$
zuQ0e)dgc!$73^gjT;+r}KZ@ID4Lj$t1<`*H9?%IRn>(~<vh_bM<=zI=r%nLPdF8uq
z7F*eA%Z|Wk^eFZp)2!&Y3ZaWLzL`*8d<T!(wbKRunURCVGtehN|3d$pWJQf_er}R$
zSrV0399Oa2!`Q#uYK5HA_RZqt_tV*~tJr@?;`;TiKKQ3!)gU6m3&~J&T!Gq`)^#>0
zZPg6yUc}HmkGmJ>9H%DlgvExtRUTI!2hYVVR&ZKw&BXYj{enlcC#^ZDI7NPNo?h7^
zUrkrPI(E&eTii~d>FUDEM9KW5m(_K`)^3;Em_hQf#+?A617WOa&fAi)n@hS6OFcK*
z-<5)YOXWg;TQ>ExM>L%NDz0<om&+WRBg4EP@7S@b!`6!6RlO5^b)Gx9bf(b%D{a_~
zSNZHJCbjAN#7|X?VD<b?EO6(*Z97pQHDWScngb_#$Z>1ItYwb3kad}lmBIciLd6UY
zldE`mZ_iK>xH8MbZ6AX9_bR`KcUX#VLp`}fY}(a&662Q8>B;`j1SZso7Ql=Ihv1i}
zvy;D!16ePDm((}QpKbOm+c+F&6!_t!Wgjb<fv~iiO!FUK#}+5MBUbwGAUj|u=+Jvx
zWx!??t9H%7;*xvEiL1kp=det(WToFken<$rVtLJ1=zW+K<|qQbb7XCnsCu0vLuJ49
z`AnmB1VrxvbSpX>mvFFId9VxLe@?~h#_w+`HJImVDznv!BdgbDtQ(>5P?n@>k4RJX
z^S)vdH~jhL7ctqBScoOf8fW(ry9z4!=}H!Fz9ZzQafEUs&=xy&2AZDcoZJ-t^wCV6
zUuMpcZ1=}Ac$J?YhNU5R<$c`kJ*x-ju<T{eho#oTYeZ#euG4#ex1kY}U>l#nEN67L
zUdjKqggHQ3%*|W;$@~y&wKo&ngd^Bu9WKjZQmJ2(I(aTM5p6$l?s?)dY>Nj6Tso$l
z%URTqMM~(-(ufKjr8LjRzYP18F(MdYx<#v4Z@FIurptOY4-=hF{(kuY=Om511!B*a
zlCbfpM&^%tJaellm${po*D|b@cJ)D6`(|>6DFVJWy&k`{@J^;w{@G+b!XozRP2;CX
z1>^!|ygIejtM+TnxCza(iD>khbI*QN>{FVV`*w_cioG(Rm=9efr(xo_&>p*rZ-dw-
zYG!ngc{LN3%mHEAG!lc8Y46}RM=G~d=!rveB`%)4-3R`(EVY%Ny3j^+m5zMD)Lm(3
z4&IpRfW$t0Qg}rs6{7`3(|Yy`eE(i)fF-kudnf<Ej6c$NZ5NV7K09ase7cg%i*;;$
zm9=k@n7KUVI%j_J)Y2v@QT|$O&~;3C^V+_DLf_$}=?a0vn_p73k7&yHl2A=;`2lS?
zvKohYW29BnM3b~(*ql(aG&b1frGcPBM=FA;*H^GJyAdlk&2*yNI!2><Cp2O_oXhw~
zJxl?77Ra7)#h-Oc)q70A$)8V`I^Qyj)ttq>6!0>_%$NJ#tguqKn^3c9;dwHSV2!O^
z^^aeF>{hMq2_>1Yzs&{R9yI!n?O`g3>`cr`=aqOA-1R25q?t=&BLD4A{W{SwYhLow
z>cw_>_&N2{*JC?WEDcu?C4z}l_ZTUMA5XWe_SIt!E8RX44E?Vc$#m&8EVIW1SUMA<
zNAKPbiiJ%-GZ)BlSmkW-s16gwev(Kn8poq86PD}t=lg^K4+oD(TRdtvEBqcS)Gf24
z$a1BLGwo7F<W>%NW#97|$McLDLnB)~B8bD$$v*3=JWwWm`>nh#6JehGPbS87a#m0}
zrn}>aBsZOj8%KysYqT2r1YxwLUAGW;8?jFea?}M&6UUz5;E>Fzz9xgm6GV6N@Ynl9
z9|onKyGII#MG%X!J{}xT8Br0|@4fC_swkb2KzI(VAL!8hU3v&&{%G8SidqRg=sI6o
z()RRNKMc2cF&^~?{;|ApYtyBai9G^ZIFe~VN=g6G-uGf)J{XncECDgg7g-T?gk*pj
z<9z6Y&PTYI>^DI2Ng8ebwnzrJ5Ao2Lipd~a2C&Z=Eo#_z*<7o^=i)FTNngfrCksQ*
zqvx-cakC0<$Fsbr%Iq|Lbj>lKa<mMd{!6g@=a=}>4+dC$m&5d*^AwoTIGIB|d#KzG
z^&^b3jYi9*98&Va#=_U|A!QE5z0cBxI_P&|MWrxnUgWIz)X~Xb*dG{aWA#eH1Xsx6
zERv4{{9Gk4KW0MyQM3iXng!NVE}vuc`Mi*ls6qa!eh1oR;QAW&L<hA3C#*eGy>Fch
zE^#9Ct}9>x+wvdt*ddjsJn(}ZE<DMSimq|F!(r+BS?m#E?IS{8I<TN>a4~3$fah!M
zZkE%p-l--m9?)#;<7v`ihJOA<U0%UU6>Hk7#BDI0`XReK8?*WTJbJ}jYqNzX56;Fx
ze``EHh?%x+OtYBK4Eo?!%z<ipB{CCE$a=}lU4D5s+l;?%m4O=l)90(Hk-RQg=E=y&
za=ThOw5U+dA-{V!lO99Vx})mpHHHyx$gLZn#WJb?XJ*c3CJ`p$?(A{|ZhdKQbECUl
zx%nj{G_>~P4e|_jcxrY9HifcN#;{^7dXaRQ!SgxxBFky*zz8So!I#Km#AbvvhV6xA
z0jik+W4DC9CuD7<yfMK?JbgCAoIKief?%HE|LRNM75*>FUkfy$bu`^L6gXf|KG)v*
zFgtumv{u4FHy?o!fpBdGt^Ids5S3FQg#`#!vcM%{5X6JrBFD(I@G1i#kM2t41~^+P
ze6fb83R(UiEG8)tvNxqF)SEW#+M^wM)%lwRI90s5$tZc`1qa-uc`^_RX^#y@X0~WC
z5Ll7CPne#;(io-=YU8?hZ;3ags6sT4(_?Infg~JR$N)<w8n|%fT0hN&H03jy&*~!2
zC@{PQ%6g)<6%-t-s}e^Gj}xSkvi;$?9340`XGZr?Q;;^eq@#v7AAf;Un_n?P_d4+)
z{#D(vldC6is0kX7C#uH?j|mqU2yv`GPt6gwz^$<fp+Fz@=>ZtgLmg;S>}X=Vp4PrD
zOo*Aljhmk(I>JN`M{_4DP>hLe(5QZ^lLZdRb_37i)(%YNt#G6aO<-<MA~W2DP1L?J
zVLJ)j{3)R_A&|z|MPje-{iz3cdyYJAWHpz)mmT;J^;L`q26qHl^*avDd9&O0crrt!
zkjXaqZkrw8Mzy*$$>ekZ<>IZk1d0G$!cz{9+(yTKJfo61A&`ag{9T}_H3BE#6)&7N
zenMr*`jgv<bps_7_KSRJ_fdiDL%KqEC*-igyc4yL4UQAy5%c0~D$_hCceyH*^k<9)
z_`ig+UG)u2>Z6zy_>3`2US+=`)zgnvfs_8r@XED+i3LE%XNegp<v27KMq0TE6Ptb?
zEP00oA(UINZ=DFh@^C0!C>wX-qfp^9IUH!~gnj><ag30XH1Q1#gnxh9`dvA2_mwAF
zT<-RpnAr&_Df<9k34*;8`UqaE^bTNEcu9mXA-SXT9ZgxyhZ)em#bXE|j)f#ma1AbA
zCMzR`z_ZWL=&B-&#PnSQf}m8%0S^TMcVRj01EdswLX*q9U4*Zk_&u|V02YEonG_<o
zr*(=IcEk7MqZ%idZuKSM#-3xIS1{+Vd)COxkoD^#rV^jX2D%@0-0@$)X=hCEO<%L+
z$sHt}RcyzS?sq%7FAj%lB`tCncBTMnPCIR$Dd)#+>tNMoX}^hsD%T&p3KEX0D#P6p
zGp+wsuiBm*FdRbqP<eaUX|d@cj$)YaOyGiAjw3|r_Xhhye%)rqgmzvo#P%_eu5Y^}
zaelGsHO=K#kqOhg&>qZibsMiz7wZ<~{mbMFcjKvjo1sng^qNXx<O4=X#{>{_o!i%x
zS>me%4(@k!!&;Khnx9Et&iCyg?rJ@pN@Q9o{nF-jIL}#FQlU~1<}2atBI46Z3<Z6^
z>Z6sLuqA0o!FYmggM6|uf0>>8LfZZt7HOCm*O3;B>l!j_Q>Zz_NvjC?rcpN9Mv%#Q
zMq4Sb3R^dMOLy5$4%OR-!Yi%o4zgZmU}1{crukw^3~<bPzqc68#dp5qXnzu9J)^xb
z9H&h&Lu%f&L4Sn628J+Quh%ZJ<6exS(v2OmtV)(f0rIDK2n+;GZ!w$`6XjSn0r|1C
z4K=Os#rzmhuR*PK&%e2G=M2kvDcgUPVdV%xb2b6c=C#?5El2j=9^$*S3srd`&!Nkw
zBQDgQ9FZ$!mpLi9J+19X91yg{=T$(_b5a_X+3vk}pT=fZiM^2Z>83any3n#XR@Eok
zoYl7Kyw?HC$HB*R-2=bRQuT!5&YA}|Sbs~hoMbf-m=QdAZVmN-3}&><V$Kp@&Ic#Y
zp!cEUFvRs0kCT-u6X(e~Yz@K?E9|rl7I`T{OOvbl#-6g&{K)q)2*GYyHkT`8XhIka
zWmorpGOAgiNK{qO>@Eq$w3EcY1?aqVD8ob63NYjPsY;-EQLqp*UG3w9p`RvLel_+o
z+v6D<{jo{DicpT^JfV6vV;&&K?XpUo1j2ar>6I}~G^(Ogi{`LmzKWlGt@ge4d1gnE
z<Tzg`7vdBxbQpM?Q3mKAelW?3JR2(WlYq#i_4|S6-^VN`yIF4gS?tG9#2_i{d6kD`
zlNYdrOpko-t999KhrnP=pKGTU9?~q-JMS!(O;1lgJowT?)K7r@neq(`H@~2pQ+^VA
zCyu)Wglm5L5cQ&VK}^Fc<Nm&I#;-z`ld!$VYDy&nSY9FUP;(d|2sj2v^D4A_6sx)M
zJEEW3#}7_8Nc!PR+yZa;o$BwdS9@9$XYgN+r5>j2R$5U(c+`Z(vBwsPfKK8&cAq~y
zOLR7vWxdeIy+@}1J#Bc8;OPGgmDG!gAuvmeJeKz8-cH@?k+?d6g3^WDpzTDyxgJrS
zzN@9JEH*7MDvsy_THHawH<-jWgo}|9FhzeAQrmI0)!`e)X?gMnV^;7khtD(rV40Gl
zv!ISQ&s5W*OvA<A#LW>82*x@g*^c+D-!GFzA#Im-e%(XrwdizTaZtWJ+jO4kQbMtT
z&QffHx<E}>Kl83VLCETgqm`uqC`$R_fRFho!1MB*lf(nZ?y<aGPG48fk!OQV548}u
z%ODGAQ*Z1dIYsUe{?z(zU~#|B2-nK5u|oE1Hp4CM2PlhQcozl(aFXQ7aU8n60PVse
zx8g}cw^|ap-OTcNA(y42;=1T0c885484b4=0=0*Xtu!+GR;ZLr_)ITqk(ATin0pZ>
zDz6fVlV9usSfLmhio88{TbvLx<V2D+e{=TC7nyOh)5*q>+}~s~Cp$L(=7Vcel(FQj
z<7!|Pv+Z`}mT`vHPQU5nqdQB->&N?susbbnW0zlx?W?xKff@cJmESU)iIVNDpQBqB
zNFuCjqahVhoA47IpA%<^)uXNpB^?hEPd@+x-&G~Zy7N-<h#NhK#!<j>+9;WYH<)+)
z$Jq~so(Ote{l4e>@wD$X7A|6vP*!Diz$*JPX_uDDh;AM7E+Bu!gH0t)jm?87N*v_^
zqkvODiZ+Pnr6fT=4>n$A%VqQ8W5~x53JL2ZM{&&>N%SNI|10DDI<mJ<0C?d+<>pho
z`Hqu@HPM3CSt>ueW9ovHvcK+piDnzDqh?%gVy8Ybt056DN?oZJB9&vCFYjbz|E`T=
zp%(K%R92jp^1Mhtt^%8UWFO%<iNzMiloblC`#OYRoMmj|;>a!9DHgPwcJ2b{h8(lL
z`_<2RHN}g>`c9+XPIj7B_j(^I7zPVNRAnI{!Gei>VK-^O{7Hr#w*k-GO5U}1Toh)B
zI`^}!?5@}1l!FjNPP(?Wz#)m}DE3_A9$dq!VgooKYmiBBd#kz&bN@~5A@$ux_NG%F
z^fg?-g!s<7+9;c`WMWOChrpZ)0avsque{xT6?B%(J+?h>ZJYnIIQesp0p**J&pfdB
zEu(LmP1{iI#eGP-T4nEv1Z~gjx?VMVQD>`+qN!2R87xZyN9ZjpPPgI%(uF=(a60F3
z9|WkL3@GW32Y*N=?kcX9AM%93cl<|2F)NrCdF}z9lWbjYJ8oRMQC4n>Ph#s}l{ABE
z>L918rB`|pKD@p1R-YROoqHt5^J+?pPMl(@RWoX{OE0-$Uwznd3!G&kFi5^hEYx_(
zOTd7{39(CGERAf$&P%A2&5zRZrE57rYbq6o5?wr@kqPPpe#@u7<SOJAwlAx}n4#aH
z>wR(So^y(_mBZyE?9iKYhsB>V{c3ODu}Kw&Zhkj7<_eUR=Y-mc2dr@K_YUBh@7sc0
z;s&pRI*Tu583~QAyKyM{ax%}$>-%+HxZUIM{7$@rf29qS&+;dBjX(3&|K!0A-y|3h
zN)M#iu0HPh5+zo^AN)vaC+oQ&vDWRj^F0hNeph_+5|r|I22ol(wHof9*7un@qT;m7
zJ;vfp2kULGxom?8R??(4JhUaL{fP%?t`#41zUB4P2Wxp|DX(;!^=P#^&S~j_*{`!N
z&8;r=XdsaGP`mXL%TN8sSR_ITvRzfJ6;1iDYHq>>htktlBgbuzE!;t}E~q-Gqo4o$
zbdZH<o87eOg?Ys5{zbxo*`U8PXLkqVt72wCoGX3iScsU|#Ob`3Nb}BZzg~vz?bQDV
z&k3MZlK)Glt88Jy{dea%7H+EhINwQDgXIkGU@^-($uAcKPuyDviY|xD!hlWm!MMgT
z<v!OHoX@nb!a;|%zTK<a4Ld&Spos`-fX#3pI8v$k(eP%gF||Q<Em=@1pPDQj#4l~a
z1fsYJ4p3Z;Bnlgi)$BSXlIAc*^q9edVbCblTQ``%-Sf$j<9%%LOHqU}R-tZkSN{Am
z{>qUkMFkgH<806Tz@Pxy_`q*<swn)z&J(hCLJL^oDwSx)S}KD*7fLY-r!~|))h*hu
zQK{LBz2w<T^|Li7ihaRfeV`MM-Vv0L+gdzGoR_jV(uCRUoePZ}&Jc3RM7?6kmySJu
zw<kmGYH72LDAcYn#1yd`Tjk&{2uoSuoT_bRo1!AZ^YggDF#6KP35#HMu)PkA*Mba!
z3&&g7R17|M7Zd4)OREoUy&b3xgw(Uf&Y82Pps|?&{Wz{L8*iU%h3+u=QAK6w;E}Y~
zNmClU0{zF=Be0v(=Hpr#JJff1W$;2L`_V2xgkk~##KXt#oiPY}KYpNrJ5ToPuJ5Hd
zc;Cg^<@MBcKGS!%3IqBZoDy$P93!v4)Bo)561x?#->k!8dC#{1yZwg0=;!XX5wr2L
zPIFpbMlk*R^UD_^Cy>QE_x~Lu4y?pxP1ga=bFy6YNmnVpJApU9<M_MlbHRZ|?7>!w
z74%py@!k@f?VTw6?0sx4#3ni#!);*&)A!3qLw3T+Bz=BZS5uSBC;ik>WXy$Yip-yI
z{5oeJ8n*^JZIaP$#4>8GT)KD(e~<GY%vRI}7Ls4P$e$R+3yc)|y_%bzOmB^_OI>6r
zl-n_d?F2as|0eO%vce9UHV;1x912&J&9vq~Gg_ijKlRP#oV9x8<)0F(OgW06+R(4&
zK4;=ICyjD|;ps>QLd!+Nrl%9f1ox*`%dQcbLDRH*KYz!5R!Igp-th|>eMFA?Y!9$t
zG#j06azl>s2l-Qn+e4ff&<ezab4X7{()d~9U<nRRHXJyjlsUANQt7yVE|vV;ZpSwo
zW62gM0pM6|Kq!Y$Ql7E`ZVMxf`-dGoT3_0j(j%rbWu()B#Um6(aB3uSfjSQF8+3xV
zUv2|V+S~TqZLXm|)Be`pH|b1-bE`q#wmfZ2VBy|v^vvz4EQ=Qlyv>_9@5m{&Z^t2I
zA-t24^tS3P5m{s<2#>U6h2FYTqkkv8KkX@HJ1jTkSW8*{IXhnGvDhYA@K|!~=~DKb
z#A22&!~8rZtI?QwjGL7+;x>ozyCbS0Us*|blo5IFYZP~>!g<Y=r}Ib@^-Dn83U_%+
z8FCdto3ZGG-xhnMUq@V3coB?ph>=>OS-91pb~XPfV+Rv@zr&C@M*B+EPmAx$6mcZ%
zL?vo!*@&yDwX!I6%3bv|#t9+>22kf>=ncES-aos4{lT+y#jqz~Yzy{j`<}RL5@Yzo
z+$`^RwhMi+czGPk1edljmGO$Myc_ag7TZ(rfw*eMv|(!qe3{xSg`T|5&!)sv?T9wM
zjh>d&VtKM9Y8NyffR)LK=I(|w8AzjowOkv!V~7q8KAhneWXk%vc-tfWaoA5~Jf2`T
z{Ye}lRBqO5xJ>dt?6J1D<`_%2Tp@R<*7!Bd`n~OGRK&w^#7gU~FioET%N$X>P{l5c
z^qZClSUoLVdwuf9!|vdtmj&Ld*G(MA`&O_*=7ksm%g+}@pvG9*4#8Ed$G8g1L_WG!
zCi-Mj<N_n1o?xEsqQCcc&P4{erDiUKpvCh^wg!C8dp_N<eg2(j7r*7&%C=@K0D;>y
z@~uFNpqxYXG8!`IY_$WeFeoOb<pJHDZ|fEz{n7OS=bJ;h*fpQ&S!*?HWfGkPR3Gaj
z=ww$}J|B7%&qr7}t&DY6)zw`L1%d~5B7fBRMNRVd-LDm9czP56NF3+AY<)Sfo&$nI
zj@!7`Jc<wH@^=<@-9L^4mQ;rWz-{)D;g(TJBa{6EE)fq``5~Jc=4^Z_cARrG;p>6W
z_opeVSeNGec_(a*NjJ{XMkb4kNB*b2sLyM5A3o?XMeVTmcchf`o%IWMe7^loIq*}(
ziHd!uOKgFWgQS}`Iv!Y`7>dfosK)G&MROJd-{b?AwR=PtZpV?IG{{9hj?13CO=X(c
zgr=?0R}C_wxp*a_UtE6KZi0uW>-#4A7(sF#lX-UJl&p=<!we<6O&5N0jA<j#vx9k6
zSN>vdu5NlXSMTDtd9JwAQcyeCSK0Gdg!8`=*^W&ypedCN%9W*RP3<mJBlCjev|~q@
zpoZ{FzkcPN(e3P6g$KJob+Y&6VC_uMGa(yGJ^aFTuim`ykR1?qVA*vFzt9^cad`C1
zd%;K;52O7C0u$q_9i&18ji-Jnz~n4VFL)|l^WS_u%UlVgX;@)zE)(>6jB$irKf@2B
zz6Xg{K=LN8L!j|4bUd2oMJQk0Im3l_PH{6Sfb0D?IP?#?iLrP+D|cwT_$`9UP#ln2
znM6EA>cpG%xbpXdXH1oa203!binFuATN9q-YosY3Zs}%H-Zk6J0z2n!6%fAfWjef~
zYi+>?5hf2;PZ>JoeT|m8;kh8Y5cdhW3qTiIMX#`)uZDP1F^*8bKSeRh_d&>K%oJ44
zqIJ&io8t$1zMEv{oZp`wagZ&HuQS#k!gSj*bF3nb`SMNVuG-V*cWYZflln>I<v1C;
zm70|{lS+3O#EJ4*hf7dB`R#1uOlxi@oG3YY;XZKT2v0kQfikN5-N_!K$__pv`);|g
zb=rn|TC8a-l2**Blv|%Mp#SYN8AEKhq5MFRdu;pu?)917o`Ij9%bA4PDk6lgbLhz4
z+OKcF$SJp3?5ZruqD{z%N^$%aZ4`nbH&z(`19?l!uP<d^S;gKq6ZbYKf8|riE<TF8
z;IKzTs3pQ}3@dSP-3OYuc}BvDEsoOFKHj3zb~k#Wrp5cA5J>WnjvpPDMt@sAzf6bE
zpcy~p76l4#zY&;M9b!#N<v6SSXmHmys(+&3U{Th=<`H!eHgYp4Iz|Yr31vaI;A+9J
zCdYzv*V7$|XFZ4JJdd}ehqn<-MS7Xwz(wPSad+YS(f;Qk8A^9*9iO?rNiR2Iv{L_<
z27*3QvV6(p`VYiY;em$uS66Y43^1`8>AgGyw4I_Yn?>8BecXQerJajN+kfxW#m5r4
zwlSY{2UA^<F<Z_|2`Mn*GGqYRF+qBqS~)MIy|R_PR7zqbbd*)fMG|WbIAd}j)>#7K
zGjb97zvV!bFSj28G7mi|cnAfFGPyHib-yIMj~zJ24*di0%6Hlp2;7{etjXC)CgUNf
z!Pbf!UuK2U&z>o;T-xKT^|nUAncZB-O_M5&$o&S@y^_NwtYBc9Sz9cWd@NdUKDk%v
zQFN^Uyh^OfqCDT>_{%tx_$Ku_YjRH69Rc&b%uhZedtHn`PU~?*V8G1g(vO~__zdQ!
z8FUB1yaD4MlNAw1EozQnn{nWB6pPn8fkuY@m;1TV=n|JVv8|3+wWm5IHq_|LWh_Lg
zaDpQJyhua9b%#PsR(_lJsvgc<lC&%sd9rvMTYDnHHXw6|9S0p6_{8A(7I#ip_sKSQ
zWrdh)cUhdKqIH@vLz_9rnK0jST4t*`PyWQ$<3s!CujfTo{*<a*>*C6n76S}YXyu7j
zx}V&}-$Q`spqM8E#GcW^=AKp#$%(0hInr2gG2(Sp?jdbl7E}H}(~;vp#(0q0?#0gh
zsINBelJM-*@1h(H(DYs6B&yW=Mr3tIrTQVyZ|B5iuI`SAO&fLow32*$c7apP<xL1&
z@Oavi_XGM{do|YIDYoxS^*9jzgK+|xey8oQ9A#kKJin_Ka}R=Z!455#Z7-Tuev$(G
zi=r&WJ)8S~B=u^<jT#7KEip`cTC6J^-LDVdOKmQQnWwenv-9u6d4p4U^eXl}0U7Ay
z`|WF!R%DPb(LLV>pyqt~E==<sI`ex>65E#e)j1@YjV^%FV+w7ODzf%4e2`7N<!`@f
zhkMg_xjL1;tKdM<IladD-3`xpWyfgk2pSucQ)C~{Oi|*=mFQ)G#rtOzi7TBS&foi*
zd@SbT78UtTK%+%65?;TQEGaGJg{Md3Ac`f*4EL=sB-QQReooS97M`tDt{SLmzVp+M
z$n(IEOKn<b1lboq99WMO?J5ob%P+e!=SK?c*7`5lxt|Ua<tEJG)@x<Wg-A6Ud-ht%
z1*WgVCkW{SFYGC=CG&WE72M8T5^3)gfUG@tx(fVT7Ct@9{3D3UmWK8;7jPJ?k@2W<
z9~U~U!;hOE$K}=d{raJP?qLQH`fiad*7@K*{=ytq{vJztF?o1?4yK2?>5~jkb`U8?
z-DY}AicM|Oc0i-XRyjd3p0Ew+f~bRcqOba%m3y%efJkz5xNx<9YX41pyf{1=Y+rPL
z*Nq)dUbPATXs|xI+wzqo3~22i%2Skhm)l6d!Q(UAV0YO`gmN2x#{`vKVr|@QTWkKD
z3H{DP`i$KhyWtqC8#ijQzUPP)L^aj0ff8ONf1>4_F&f*Xe@A2w6y1THP`jJH)?YU`
zzZaZXDQ9bJlq}9!_NsqmIlp3U^RUubkC0IH$_!d3H|tsf<+8q|6#uoC4bpJoq+E{n
z%k!MzI%DbEExhf?kmEUn#JSgpK^n1LSH9q$TM{KgE8Fh!oWARV<X9LPtrW_&Z}~`7
z8)Eq&W+`4PntC|=_IN_1HcpbY5fA%&qGH|L2lAi7@!724tyl4J?|&4O&3S;@7f@+?
z8tLzCMyb%OaX?fqHO3<lwzEPQ2gluQu*pQqpUGrnmZFz`Dnx-(6-<1yfkz7Mg@5HN
zu`2y1U;cl^N5PXAwS2jtWymf4MwDrt?2Sr3#N3lx(U+6w^^MdXc}d$0cp@*8`D#*<
za1)An!QpZGW}GBMc|JDq#qA#@7b?EzsnKdbV^C^IC^A7*EVFT>hu}{0l!WzzvFBOf
zgXduPf{D{!rsXc1O{c@oB)Yx+S6oY^(GcAZk~jhFchhzG&70#ET<DR{CFznZjM8sZ
zJ|GrH!>o_)^v|C`>KqlfE9>(HZ;JfnW4e!#bQccJB{PFVFa3EL&?F^4zpV+&Ti8o+
ziMzL+4D_qkQL#O(jnm`-Q@rFeY(Gq2ybnB|kRY+09}vp$$y&jYXx4WF<)VurO>E=5
zl-FQ*{L#3Nk%8xv1-DKkMaInw?3=*XD0zaPC;Ei^w*-A+a6XSDjufc%ws47!zEV0K
zCMny#Me!_nAvm&df@aU$@RthA#y@S|>d0qf&oeSpf;c;2ct*?jUos1JbId?lK#9;V
zbd#S2Sb!I2x)yMx=IM!o!uyPqZyZ>mZu_-1?F#4bLZ{>-_Rhks?Xaio@E9W5SE>YF
ztDdL0MmQiXB(-Oa4{n8|PJ-M5QIFDagVw^1w-=<pb`ekiXL9?$BYUy2$Pe9j-7+dU
zqMI|>Y&`Hq{_8;;>4;tFPV!s&f~2HR9rAiLGKtV_f~q4toCgS8ysrM-&%Tc8N)cjk
zw%+>$@UB!x9w&3R>eH6l5_96Wj_#GbNz?d-9~mJkR!T`;^N;%-ei=^cK3k>OVnTS~
z)-JD;F=OQw%qb_hYDw6ARYU|KjBr=5i58~$okF5Ai%JWRnO&hp1iX8Z{*yF)rywWI
zT-xzyYCS>nLq|OjTvv!DE$`=rLmt2_!2?^9EOWOkUD?y<!Vk7JnpK~lGt{LXat_!*
zFT5OFvnL7}Jn>xLR+F&}PS==+xmXtRRINXHpeceh%72_O6&Ew#v`3`d_;e$Em79=X
z1AlZi{uJ<n+)JLLS3k>aKiR<!)r8dM^}I87wygT;QSHtu>B(io87gAPG%v@P1h2W`
zG6^U7ZF`;+>YC872}U034Pl4L(rR)0>x4osY=u5EcPVh3N`Y(4Obd}Lq*&r(;Bn!%
z=B32tOyW`T%@#EBoU#6u&(8yS!#3fjsjb^_(+lGC7558t*T&K5!Jh|c7H`Q<#@@L{
zS*0g(n<oqJr36{XZwvORA2N(=kMh(KhC?f|sbJ1exZrR(b{)x|JIED=LoaS7**>tY
z%;yT=Qpr3Zzb)r__0SWbd;(?$iX4U@mcfUOAjQ9C@8SIr#+?C9woF;EzbvP6s*@PL
zj7HVfX8-WoyB(%?QGNo;_g2;|S7aV7mtQ%ebF1-PYHB<mwa3Z)ToX%JT;owFxKP2t
z2|Mv4Z0M%vK*<*f(bz<QlLCqCAP1L>=C9n;yDXu+=f=qE3+oy@s3KdeQoj|>hmjC*
z4En9ZDWdEo`Pd0=AuxxI=#gQjn*%xyuJ|VVre%7kVI!buPszn=GJ(${5%iH)oaTUU
z?(ypb_f0VU=ka#4pOlKj(_@3K?XbvJ{_bdL7JPQufB_^%?08{}gGUs1R+RmN2~Wkx
zU+Z%v^i^*{{Cx6W*=qf-Ve9rw&r`0?Zo9wQz~BE2%w15ro2mPx<oO%@vdXl*pq~^b
zf-gFPJ-xD9vGrbUpRcY+wybV*7PcRGzyu1%ww9ha=YK{#QRuDooECldTa$;mJF6X7
zI2TmIe0*GWq<Y_w@$SPA7`ONuUio0FYP_ZIRdrd498O&i(N}L$2qP0OwqtL1J#&cY
zo%|g-%eNqFSiNs&T&q6(zVd((O<!xzyjz<ny`o22=xSycPyxw6!j{=S8LT?t=b|3E
zZtjpu!(Y6XIrPYug%bEJ1t4s<oYGKX_*{;)W}ycTu&W{wbw-NH;ghS5c2~8&SR45W
zLIE3cCd)e=po+hPJd`m|CCk#tg)T@a{vm|Zl4y<&dDUp<fQsXeCQFp+xD{o$%-akU
zKipdJerXn55rY$znE?!&`dYC1dSBsbi!HwuWXjlHVG4M!l)7}J|5R1<AA#rR@IxQV
z;#gxhAz@Rag;)0>5M+`*+q2K#&+F<QO<!L}vZ;OcZZ<<LVkW4pimQoh%oXk-R4%(5
z5y`T?){Vd?IEK-sdTrBZXQ2JuJ%>17c&L``+WC}Wte;rro2)T6XAr+Nd3%4ZG=&Q^
znZj1-3kf4u@-dOjB}&foWgqx>jy%tfP25XL1kfnpoxSVib3^o%ru7+LiH{LXmJ{?L
zbB=9B`av<E6ss9^>x;bdiVkQ0B^Cf@p4DhQ&#RBluCxqK@u7PPza0h~Z<u(O44>ha
zC<GR0j|4z^MF@w!-D}%<OJl%2uUQIDl6=IAt}F*_r8r>xb6zL#k~|>;23_`t7@>8|
z_&7ujI<i35?+fRoxBd7nzf&J1l@zwY+{~IjS_#u^CtrTFQuBy7sH;7#`?$R1MuIwv
zMWD4<U3KNwB&*h~gDZ2+J(@|df47zSN5P9ganQs=$%4aXK>-0%42O&s7jM0tUyN;~
zhr(8TR%Rd_2J;@7y^EnTlx<uLBXatit<w;v7i;DaILlvPxXmCbcpLMFN1QlH5ORD?
z;t>tQJ24X?fmE{DdxF~--M57a7{T4{ArqSZryB7}-nn@5kkg@`3fq020_iAj9N<rh
z7%U8U>u=5aaX*Di!l2(p-|+^fr+ZAkFgnqGtw<1F&QKXRa0LkUw25xzar4U3v)7sc
ztXiLHWTg(>XI;?iea$X$ca+bheI|AbkEDL%ddDbH=|Ew&nvjT>eRU@qtgCU)hP~*A
z-R_DD019JYL@k<Txo)kJ{&d(Yc~N!0S?;p`bjq86vgpknm?5*m1-(0JoEq{+-=r}-
z??%<?3OH`HGFGrdd4>yXu1^*?m7!YtB;7}LoUNH71ub)3`K-{ks$CUy_AWU1(Y>Pc
zFUP(ui=^P7Sj)9nRnb27Ao@miFYR}|i>xEv{gd`^i7bO#ejy6aGF&YEDD5nQ@T6XW
znfo?NNI8?t4EKzNqs~5mS^5tEi1+J%8}}8tre|h*j`#XrZ3`UQqtGNtPPGw=uRS#|
zcDPBVvp#&rV5U{yl;>D~{ZFTxUKb-E49^3UL_LXIUN1?wT11a?Dlw28D}F+|Qjqp)
zH{*`=BMZG#*Qjhhe>^aHq*2Rd9KwuqI=q(5fS$sq21kshZZ~FAI1%+e*`km7pgo^3
z>`J4zbFmQpcY3v>2Op~LWZa1d9f1&&`S<&t(f-&ag}Ap)CEOw;I&NzCWRuQad#GLi
zt$EWqpzjNB5YuIX<5eHeSjaM;C^(9}S~dHwmniWg`%Pc*TJ@#ExY1u*9kWJu!-e2q
zl3=(Z5^*eXi^*p#YW0{d>-MqrX{%gnRj<VP_#i_G?iGCld!RhflkIzKb@k?T!ySiV
zYjoJ=9p29bR6lILFn^TlIj-xGWvzLy{4W16k2lE#pZ>Br20^zG1R18G)&-{ql)HmR
zslz}>`t~Q15<Q&#qAaNT*@4k-vodn#Pw8&ErKA4^tG#{qU{R`&=DB;b>bedAxR_3M
zP+}NF2%ng4c&YAx@t`S(vUkRqylb<J(Xq-^*_Oe0cFFm<)>QYzmQFqSmYAbT+s`-B
zbW^xVn_()*kDvetsSU>o4%El)0@I1>JmXGxkTx6QpTX;!TY70i^W<&tBc}eg2qHN~
z+||WYclTr&I)z7v%4WHxBftNH@kATuf|LC6L(o#Ja<Gi4QKnzVHSk=z&-WYo{1nMg
zqTk}iUkyII7D(7U8?~AA3z59kA%~OHBSozT8b)a|-fBH&TO4|#b<@n-B;|I!-w($^
zbib6E-`RhbY2+HPsD3&K(kudxlDS#C8kx=6tB%6?8--Uzw8(;BqN}ex9lBSjE-Lg3
zyg7=0Zuz5l;{}b(-I}C4f1!DTvC$?=U;guARmR{f$)p$m-q5$T`oR~xr2O;sK22W3
zF0_*FL$tbWd<4)l;^@V#ECrSMJNCAR<RoMy=C|pYs;Tm!SuaC3dU5H62BZJTrt!#f
zFK41>xJhe0P8A8O^TBe0fSV6m)wO2scyUS349jQ7K8ebxy|aIri8_4cpw)_C-Q6Z;
z)s$=1g7bh1GrW4f<wZf+@-~)=^N9KR6$7|s=U+}c;D#gTg|rc`@77x#9IItSBtOC>
z{XRCvO*q}xP`e%H1}vqsSE<7n&&4?Ytm8QK;M`#)P6!q-cL8Cp?>Wu%H~Rs47}@Ix
z%J=(<?R`FDg$xuAsxl9}q(y9&B-?J;*_9eTJDdO6FZ)J5;ih3s?sX67$i*0OXdCee
zt#_5=A-^f*eyUg9zAf=Z?R?KvGGp_V>3cg`xalGNs)T(Ynfqw_mxnQeRi-2jf#cKL
zgx<QO7=}7X;<A=}qO};lo7M3218D?nSQv9N9ANCUh%NcS4W;3(TAfxfKSK;<A^m7M
zHpUS~Yu{jN{}(oI%QZxjpY-e~eN)ONY#f}t2^8)XT|u}M%*MV0fpVI<Q2!0C0KwVS
z1H(9iB)SJD8D>5?mo$zY5D4+*M%}?FZaPqa0emBkcjCRCW@=kTCzjH^xCC&+6L?a(
zhPB&?6WCWE3H8l%$&KdAVb@vucbnCvkM1E^3o$`@!8)4s0Q!p=j_NBTXxx|k+C?e1
zwrp!$V~rDX;^qxcU3|)sh({$_of!$Hw~9UY;-iHUhi;0T57Dk{&?sR<z8CL3^;VCk
za9Ki+T`F3{n_$V0sQrwTy*f*e0czzdOZYlpz(>nONK6oT^AwMhwhg1><4U#{OxHc1
z-GD_k^F6!-e%iIvcNi1wC*;oS)yEGbMTu9ofJvQ#KuF+w_mwKWv>_?VdR|f(`)=AL
z`qC)hwy&ueeIvx91_8*fKQv160G`%v0NMVDu)v_?qDWhwD1@TUOUnC&$4<>B1Io<e
zuQiE%gMI`0^XnIUStC{oy~&LrsaJpXx$`4qT8gw{1QpM0__8{bfxAh}XB1(hZ|uEm
zogaSadbOd^9DbJ*1M-~UW+R!w?Cb}PN|5jWe3P-HS|SrYmU*>6j9~(5`_Fa<H*o;D
za&!AV4Ud?Y=R%ra=2anta*Q}|-&Qe%zBmVJxRaO$BI$Os`>mrI1K1_nsX7P|pBeef
zyqNul(AT{N-$(o&c$E5e`+VnVf_E!LjQ9Kt%iQ1k2E{MDEyE5HLPJttUlnpEy{KGU
zz?@*j8Lh1h*#j^84yeMIWx|!t!S>!=M>I~+-8S>z&T@zN&Lp3uha}TE_4HnAyyB#9
z6Z#5rr~1<^=EnbwtWN1e*^f;ihd1OoDTEz)YmI5(B+sv3)(IOGi$X}US3meoALm)h
zsN`dPbFNTha$BJ7s?ZtM@@R&$DTnHhXY}F;Krn#we8QO+9ydb&DW!-Dc(g1`l$@k5
z3UZs<$1gne_WGQmmiaXs8wQdTl<TVG(peAEV?qfPCjhlKOW}m*d*h?Yn|3hAT{61T
z^>Ve37mhi%=P2EJJ0|92HS;cXT%0ik6qVi^5n7Mj`hN)f?yx4luG=$7fY5srks#80
zFDgW^ASfLH=|xeB6a|!G21G$XL8XdFRFqy6DWX6W5JaR&?<yco>78Wm{NC@r_j{jP
zp8NN#Ig^|zXP>>-TKhg<sbIxRUfVbkjWazJ@mp-})Ot~d5pK})6RE_z)bcQcmaJB$
zppj<?9Vl3Pc(cx~F~rss*~Ed0Es~S%T0I>|rllFkhRl#4Sf(~-wtj4F(e)&fiKd%V
zBW%q|8|jmMe%lg4d9GuUj=|piho6-LN+l0RK63n?o9^ZLg9f$5+2Ab)EI7ETLx2Yn
zW|Y`6fCs}C#FJFT_t(Ep=<89HdYk*Zz9SbgN@8Jds@a2xY&^$tbn%CMr3o)+^|C`-
z7yO^iA*u{S9#X$bJHH<Y6wQ`dw_KOP1M>BN#5+UWaHn|Ml{xO_?%b92XN(M~jqTDq
zC?{>h3HFJ`GXbZ1z7WtJ1$60_l41a=klC%^k15(gBOWth8!oVhgKPN-t9m;7)Se1k
z#2Mhc@h%LY+&L_ur2tWfKyQFJL<s;=F+WC5b!`%t1Sn4kCTf4g5{$64DP5syJI`lK
z(r?##x?3IBv|e;ieWBPqk62R<<^w7i5BVEBK&~l$&r}%Ka+Y|B9%T5I8eq!zEOD{(
zOZFzZ$7mf`;z>YI7yfDNY9T12uv;$(u9^C74=JFm(Vsed1$%l|LC?Fa6RX`a>o;^H
z=T-B9bi!;75uJ`4B1QFB+vPbhW`vWR?i}dM=#@R^wb)mCji15?<>4oUZp`~-R4)VD
zdvugI;9PhJuzv#+8|OQm)V`3;!W_E;?X^WTzZKHUo%X(Ql?#(l**<2N7m`4#Fz~SV
z(Xg&V=>PAmF|fg)uS2Fz<m}j}LkN5ZQT=_f_Yy9a@2cLc<?6gL>vo%^P7N&$S0?j%
z?@NrG4J4%xVh?wpd!F_((2V|)wlN1O5za;AkyuO;-h~dlND5o4pTS=_vOWlr@etv!
zA@j>XeTkW4a--hI_Nao!8M!2$e}05{%h4U@Yq+Yxax9Svnpw_zx5Pmg{YZ7Ra#m0M
z7}LvGquc65^DJ%m7Z{+41Sgl-#7psjSSdkzoNSdl9Ka>j#3%ux4T+rK5=x1mimQrO
zP8?l?VAasb-CdD+6xMilg_^vN`fRWiOL+2f8x693(qzXJK5NkGxk393oyKmxCK!+g
zakTp9ngS9FkxxbAH;vR}g7AlAE-Gn$X9bdtAd7ASVt_9B?vrAuoxHWPETij&##y8j
z;J`kJ67P{r+MO&$38A9&S`_qytV`4mlrUYHIC`LI&D4bT8{&(8a8+9C12DFV;0XtI
zKNeiM7n7%BO>1TYuIK%pArC<1><0`0RAasg$Yt0v{STkk6O?8OO3#47vQv5e;f6q|
z5=rApQpOFi0wPjrw50&{o5ENKwvm8+7Chuvh<mRf%6`lOJs^|p*Gc@~z9i8Z9PwAZ
zu6iM-$}_?9JfQqhf+tDuR9V4b`>g)B+|a37K|s%1($T8BZ8on6<RA>DB`6{l$MJRs
z8De#rrz?8}ZyhrG7w-KUvURAFlje!%;2^3m_y4~^Xhd?P#dm9<Cna@FIR}2C=Cx7^
z5f<4wn8w6J|FVIL^iYjq@tva*G`e*h<*U-(1LyJaMBX=Z_4d-|>$n8LI$qdG@)s8~
zy4X9i?GUMpOfb9amYCkB@lvW!FUjWr3erQvXD7}OEPzKn<yw)3TRmQir*O-3tK~g4
z$*$y2`TQ-IEC#sj=-syg=^B9Nt6p?=cM6OH&)tW}>EAGQk3jRq$aXAo;OX%ptusR4
ze7F8Qeo32fGJ1X?;h49n2{foM7YCLI5&?bGNao%`Ku*NO{c(FP`$KfsXbI#^<3@y5
z*V|mreNNH2aV<yoC>s>W?DYa1$GpW%L>M#p?^%D~;sh18n+%k{921=a69mK$N3{I+
z0d>wDtV;;q{}M~*1W6VgNT-eF_*07722oz`{jX<>x)+0^TNI~tW$(Q#E$AC_^mb;7
z+V<a2Nf($<qTi3E3eVo;0)cp!ZwP@amcN?=N}m*om1bqY5*M<njX<>e_G!=}3ZF$R
zO(Um~J9x?=gm~t%mH=>DY~;nj4%{UG{_s2#1LR^%mT%e5y>~tJH;K7f5T_b0XYaml
z!hmXnd@2nf;-cAmF`VsKd-w62@8!(1EHD~!VO)x*37Gv;hzuwLL}sY(soN8Y?tggl
zqNP`5KwshESa1<#pHphJ(rg&O757_xu@?Zbgk`9k_Y6IB&4<8@Ql}X%MBP6PX@#A}
z5)Z*;OiA3dy+1*gCzdVtSr8wXeQ<cC{dHq~Vh2o+&vZVZA;f=RN-QmmB$|el@u#D)
zz(wuc91~l?SlIyw5wJg*vBn6r$li3zTFVHVJwL*5uI7}J{fv!L8)IcvOBggki&cKc
zFa;a`S%koxR<&cuOXDAac>4Ojyv8r$HEre4(lUxTwT)n14?{#@=L@zQdJKRN>iL~0
zZlds@B%2j3O%&h`J;P-97gv{d%KtG~k`WsFjy~ieN>wlUs>TeQ%&RdCN~ZaS++gPv
zv?5hgj9DUJUAhL&0i|KAmSb{BG#!vHGoi@?{MCKedjH12f6Xc8G=9imQX+JwD*X@i
zq|wOc69(q9l|=Xepou~*h!){mWEN-V1R5?bi4v0(eZ8HZg8b5;Ud7zF?w5@Za-$YL
z%NX#Tq9@MaQ@=hh&uKK_1~m*&Galq4imHDC6O;bZlOO7xv6`?lU(;g*CzC&FBB;Yi
z{grjLR5P*|6v_ZGY-e{P>>0twQd@0up3>bJ*CGBV^mpo^ifD{5W9MOfH4m6{C1aq@
zz!&Ch6<5$Gw`lQQ+^wnK&mM`!>w9FRjCpq>V>m4-Ix^~-MZth)&bFpdF)j}fP6xJP
zd%uv~pu^q@d163^8+|M0!4ePp6yf>Tcsh-M+lO4j>$|4bDpKRG2bzHl2)!7I!qRy<
zrNQ+S`oG?*AMYM@R0BEBrwYA3<ceaF#(ley-FAHSaS@^fQ5_q1#p#A8Y|Wigm=6dV
zUzorAhFt!#%;X~?hs7qiB0vV<{1Z{Q*F4&g{ND((y(6cPFtG`;iHonY7OL5(RBSrA
z`kJ-Gq5S}`ns2fWE%x+Hu9|vDXi*Igcd$#@X6___^CBQOUmPsKrWUkyU6_FjJg?*H
zZ^nQGFjIu=gB~yWCnLpx92#AI`&f$di^WQa*wg=W#}-73K9iiUKM6}5*{{Kle)rDX
zvXszLbRT~9&^=<P*-Z}@_|T$S1}?=FazDR$B=AOMd{mqLvSYKc`6~Ye0rcQN{8s6S
zD1r>l4@0cL=3Fo4!#rUCI)3Xd!NMZHNr!<KrcwRCTRT_uKWw4vU@u$Jeo$aGv4U!6
z&V~5&2RuUl0GH-v*a-HyalkD;M8E9O((8W9=>V9`e8eOr#gNZ)u7%)nPO(d^E=DS=
z7c?E-uR1}w>k@4TafG_@QWL>e-WIBA%sUG9gLEfv>(VeW_<H&vR^k0{*ZJV7+N@dh
zyB6*mbk5((sR?mT<*s{s0I-3zBoSV4^l)T@Fvnru7s9_~w{t~w_dmqAH7^tUTC72t
zTIH(a<lXMuxIliZ1^nl;CthLU@EP=FSj%pjuhCQarK|XXZsv*At%ukl1;ENlJPjXm
zzX+~dPb$!3UCe*I0$_l-0z)RTfW+#|nme*}(`9k$I?ZWI9$JkEikDvdJc|(kPM+`L
zKLXpHYH2`Z5O}Fq%RS*;-7wmt?y#&LV_npxT^B8Rs~5S4K1H`lFC`*BJtNx~3zC~i
zLg2Z@5R`<}ae~@Yi}uVeD#uNV^u*K@*kOI!u4|EhL8s6!3;IikL1+l}s_B~#UT5yK
z++FvK{yYVlNgY*c4g*BL1azoBU}luH?dX@40%gI2l6~2n`$i#{-ivGKsic+B@exIN
zq=(#FNh-A*og6*X+Z=f5JL&C$6dLK}JTTNa_SgN6Y4kv2zwy3$APIpgC-G&JLqUhw
zPi40N@h*>xrFK2Fih!j7CTJ|LKRmUCJ{7RGQyk*<vh5A6s#Wg+Wc2(?+x8ndrY?SP
z$Cb#DxfOc)1*%Ht;MUAzbygc<R{r)#@G-5vAalM=`~>jN7GBRbJA+qcEMWkZDxa$j
zw&;EMK^%C+lVpdSzA#zxS!w4{$~nAh0}7}q(tC3Q6_zh7A$|Wko;6h>f&a~S`L>ek
zLMR}A-4V{*^g}byfahn2+K@rM(TEkOZjGPI+dX#K->NdtDCwNxjn%V2>nIuy(G1ML
z^OH}277nr)5IA;$>eoXuIUh0h<O|3eWpLpNww!ksqp%?&Xu3?WVS79edGa>ut?&m3
z<T8NIedw!p0FZ|UGhBHY%wJr7GeQ11Re9I@`S;!4px2KxWb$GnF-Z-91?6FbcV$2Q
z;Q&!U2Qc+=T?FObEnCjQ)W!DS>MHe}8er`YMl0Y%^-<b52G*~L7Nk7k8&{?|-@aN%
z`?~wl{v1}v5y@<uMpETPZ-}K$d#0SVQ!V)v_vq)8Ow_Li>ru-&w#x~eSE0t+soWpI
zqu6-DWN79>?1^W)%zzhj3FM{R%VMO+PpxjXY>mG{;@)0igGxfA@g#SKt$JZl@rH4j
z;k!{-Nb~=86jhZ$Kz;bGjq}YqB~?i|7N4Rz(00@LW`cRJXp~7!0z0kKEAV^}6Fxrv
zN|`%qS5^mkqOAJ-vHh4M-L&xsz=;0^8}^_^2JXVh<rl)`(iDj1M+a0bYPE6IFR1lm
zP_n{FVR|cG|A^-P_W};p%D0e2EZpgu-@&gizy8AcN&okIgY=C9Ol0V6<D^<F_Kv<`
zXVU#dk%p{*&b}lDJn<~J%){}*dqIX=l(W;N7>%(0EMR(x0fu}|MTgxrFkmbF2f0`@
zaf$R@ig2=jz?wLCvPy)izco%MDKL`(L>jwdUzV~E1j4HW(IJ0B@L+aU@8Lq)DNMBg
zC(T;XN;)}}yxQzLk3uhdDjqUssK^i2$FH9>KFgYY0|sgUb{;0ngV=+AMSh5_)StMn
zo{<bqOpXaoDn6dnI~X16{^FB&NHC0`WU*4;PCjrQ<OrI!AbdZ1JuK+qM`4~x^_L!!
z{MLkoc%9y>q7#4vif4o%v(u<$S@Mg7*6m7%aQ!n9O5rt%jE$xDQq+boSQ5MW5{e<>
z(Fd|yh!%*hALuVqUl7Ug4RQF;OP=u!9^^@SOXuzlmP#JC@b00at0;uz_RR#eR326s
z^D<l0n9smioPwSyF@B16c1myC>0p^ORd%scT@Sdy=$33ATv<1x?pW^9Bqg;T7iQ-N
zaZIBzgWl&0i~_D+?4UKM^Cxf0lm-AnHty8lxAizFMaY8hfjoqYMv(`=2IA<D3Uj{N
z0AvRSc_(w}w?cr!k|@ZC`(cVxnkNNkO3sq{QE3NJ+RNhni>KGcXX;H`)2z+3$y2Hk
zrC?Gd#>p&>jZ+0;KZ&vZ?Xg_??#hC0A4)5vhRklC3F&-@OO{jKDZL0UNpgr1myqTo
z{Z}%a=O@QsUhla>x{5dRz5Qqwc_2#kLo9a|yH_**lEoRN?A+Fzzkwg71buh{DP47V
zf8l2FBU0K=b0OL{QDOzJ$t&d49YBwWsIwF2pcxFj#R|_EJ}79;<+XnC!05+j>ag0J
z9*<q_LE%Fm1G9zM;m+w?tBMK+;w)A{#*}6{x0qO@=m9)zYB3avZTo|8sG?f597%o{
z=T!a+;uzXXE~wl9QW2CBQ(utNRO*BE+br+`D%thm`!dc2^@KeW_1N|vlvsL<ro+xN
z(g8E?4Sa#|#*<gZSc>9TYE+kBLe8(-DZ{{p>#xkbRjKRpnUhco7^u8`diA)He!~Ss
zkq%8KtYpcc=7XQ{<QnJL(XX>iXQIZuPGMb!`6Rw^f0Uutzkfun=P?6iEg=P{!Jv>B
zaC2Q4*h{o=;aWR4&j=oXHW$;&G^?YX4~w5Xy(r<!8_5V;r4~h~XVNT<odm3^OMrh{
z<N+hUc{y-_AJ+I7XCL_t3mTi+RWM52oJT-7b8seY_+%89yHmtd8T*GlIWzbAMv>2d
zo$Y!<0nuSWP7J7We#BCCN&muGymzlTVqJMC|8$qoA30Fw{RbaYcw+caulPZ*o%vYT
z!9jY>da$|ZY)BrStW2J>j4e!h+9lYwm*V3GRnF+idbM6$s>BoP+R^w_A2Em{WjRjY
z4v*g}wU%PB)s6dLF7<b=EyHD)I{q9f%9GCgIE)Ugvv?5TsqE6Upx_Mt75SC=bI+7q
zwxw21KEt1Ff5KSF3XVY0vuD@V0Mft$E-roW&tG;|qbeRkcfDq8%W`2a2W48{>-=j=
zt-I<hBY#6JmaL9(Iqp#1UV-bU#pI18W~S)f0f_=oQjo6yoQPnObBcAZ{Q?0jWgr%p
zzq~kxE9L}ZKR*SPh*xju9bc~-F4|MZRX5<_qSZ)Cqy^q9C@L6pbA%{d#D@wpH?A)3
z9?ic;cL^l%%7W_VjI6L<GwrDKB6njiV&Tk5Y1*rNRt5sO3RST`T8V!{Z$c%r(d|<q
znzDw|fkGv2d%2TcF&vBw2Z>ubhMA4v!m9hv?i%|Lgrp>0FXcVa!#-z57R6p;=zhBF
zT8x}W`pq?!N!T!G$#U;MP8gO3Nkb(b!@@5;HLz&ev^7zW18fGwspv2@>S7Oqq5f2}
z;t-~ZXXZ3%b9)cvzdjd?AmzgCf7}jer<Wc~E~X*_4;-S8D>RfYgn#z6_}+DYnG_Gq
zeK&I=c%d0Iis{``2WBG3p)JFekguc#Lk0bVX+La&b$@B(&t8hKB*yPbZ}VdT2IP_Y
z)YJNF4>p;&Ja>D?pRV%@m6C57CI;!JbOzib`JCj*W6qj$h9#g&;%H6R3CR$E8Bsfg
zJkzhe?}b1?;rGV~4>;gX@woYUPCqwhtNujfoWTd0sxsgP0>CUgwJ<~zB#XSzK%~J)
z6Z~Z_q4%~)5Q0_}QC2{YIvp4>yE72Xmx>oJ^u@u9N(HoGM#4<}+uurCqWL#f4AgD&
z<ia(;$gc`97(?`uDt$+g$DukC*V2g?)qiemFNq7dp4wDOD|zZ+!=oz%#t@AgH7_iP
zNxtmPZy)7zprV!N+9;8B954pf$Y~HQJlfz;6Z+86e9H&$9D|=$or5?o6rq1kV7u^;
zLgVw<Q9z&vYa^A{B<AWAER0+B;`-yT_c>vDOdjx8k(h?_)VfbS04KqIe$0~nftDR4
z-Rfwtl)p^<2jsQ>6afF#Bj8zEqZS^p;>@54k27tM`Q@CDgHQs{Qov1A9Z6b86!JqC
z%qFaE-uQLz=Up0DDt!HUc{MKJr*H*Zz7sRpJG~&zWfRDP*8O#C0nzF>ThvO&NeFDm
z1~XG`sdFCRK#h=%>tFAfLX;T#h2Gcw--W=RtHNp^nfGWnHkxAEY6kqt$cd@D2gQYr
zQm)f0MSvh-T{V}|`?XKUz@_YYGDI$#xqpE0HV<)Q0@n~tEMaT>kV}(cbJV`=Gg2C^
z?GP-?(9=WLNe{2MMXx113G$j-lFzOz6TW)m)ehajA<#!43(VTS^<2#`E380E#SDig
z&(vUHMCt@Gywg2@!2OrUhhKYsDWzxLssv7|K0D_Pfx~QuEg9Ds0Ae0Tt6G2AfAq88
zm;fNgfL*9e_rfFpDaEf<@o5P<+&ql+1vY#S-0goATS}IN<px~IyriwUTGQxseVw^%
z5Rv%N>YVD=KNSQBCjK-<<6Ny5UiBjMK%V~6{v}IMLi-oX)L&Zd|6d%MbU=5~zyM=-
z!?Et0p*Y`++o1V&>nBA8`}VlyLfe@mz(-&?qsC+*MK~F|VQObBKcy~uHJOH0NGg3P
z=PXFR{c~i#5Te}S%%<yqv%WQOm2JJg;C!pM{<IX8!GR$AaYs)vt9#A{3$u#pGMChz
z#&K9U)u0nj;lQe4VEZE0v-_n?$*5z7j#>G`53dYnqLTWeUO|M7DUEgS89tpDd;dTO
z=1vriop=xr;G3D7h&vR&ZYI9j9E2%E-*!54_w*q8-sfk0aWhj0-<Ri3+@4CDpwn*^
zP4m0FK2R`8t2S}r1#>S5UM%J9WqY#blt@mvM%ZRO*z3NH?2l;GyxUhTnxPWqg<Yqc
z3?s66dSh?7BQ!xY>zyzRoNX`BC_2aQl8CT|-ex}{0loN*S6!v(bEh3RWVBPSkT4BG
zdPscW-go%y^i!etlI%BHpV2gDcy;~La0ySv+S;(pXB|S5q-K#CrN`J2bHom)nP4?C
z!mjvvasTA#MGgaUG{`x3Qra|QuZUQC?P5~*0*?5?r7xsAEs&ZuaPfp8GzbyLts>@M
zAGoqweil^!J}CH1_B<7{uv{-^(*xlfBJvvPYI%;2#AewA-&@mz;wwgOfSD|4rI#u5
z&4VWP_5Z+?tGf@Grrpe5`A=BtJ(3_ebq^C~YTqOC6L{2Si(~b}^zgI@g_qa(_D6NT
zL$E@w{x1@uZE9$$z)WW3^)%K_RNHRn=^yb$3DmwyEMVd^4f^WRRsR)B*!yfdMSAmQ
zKj3BWw0{qkIUPsE8a5*UZlEf9@%{&rB41)qx7b*_q-STx2FEeX6psR1#phSSgzObS
zTzpB0^@9o4L7$#pO2sZ8^vR}!=#S01k1ITTb!>|hQ^4H4?kozdrGtK-zkL`Gokgzp
z*J|SOsfwqqU!Dwd$`QaDsSPe`)OUaSdTi_0BaZm(KO$oEDttvTW*=G6&%{+Eh#ob;
zQ2f=DYH*uvv;L5E%D&zk58Mb+T^^*E%?&q*qsrejj61$*ZzGWtE6ChukT*e(wh?%T
z=%AYpMDq)B!u1vs0ucq6j$b}nTeKQ+^cY34+`;HF0P<gFrHSh15L3Dj7L58myR6n*
zQJaM>BcI++HO)H1wY1;S1%0GI=+coNyz|#CZFrtSNdms?G*9N86k=ANVrJwsVb?zX
zdF9PJcfiGZL0domYAKi9H-2g$-E4vdxvFnHulEk9Jza_m+8KRc_H?x$r33%>0PnfS
zf2iv_UU+>{5RAmJO{_R%SrS?PId=&UCqk{0Y?3$HHkJ?I*DlI@*n3t=q?fESu5|S_
zTK$|R1JW}!?6|@G{q+0x{JKf!nBu8nSCvcI<8fQI+u3x)<i*XdPh(1p%-`L>KHxMx
zh=(OTO~HO`7PYPM9HfZn(_xE(EbjR~*2gg)3imoNgjP-6cSjxy`!Pe5uSbNSrO5?G
z_*P70jUtd-*a`_asycm*4Y)~O+M#pYKQ3;(nfH(@GlJ<l#IASZUWsNsOReyT!Gnc4
zK$#@I8Q;E!mc`6ix2pj7CdiCd_menX)ak*6#ba$EjNrQLE4Wg0;y<xh?vl>|vbOt2
zWFJ_0@SG<BBk<-NiHVSoCya??V}|a)-dLc@gP(ssFeIMaNdKb*BD3CVQy+2`{(DNv
zN53IqEU{rJ!cVQS&`Rww4qPp`!US3=#t3F%Lr>arJ5KLYo$VRVKcNSg?+BvCfL4E4
zfYEHnN4OF3+}i$~-S3>5{nkVl_-hV`fD02rQON0xR+~M}jV3o8?|$yPtbE@9o|fz7
z2`IgS>$<T>+R{{-b4k6N-sP-wVB$)d-al8{L_|TXSn%;>cJTs(*<y?7bh_YAQUW9K
zOW=wvaWD~FPUg&ine2gXu}V^VFTMGC@W_Gf9~=^i7@c?A*Vpy(5x?(b(z(5N9E9Q#
zv-m1=B(1V^vtA#ZT)&Dd(q}h8ND2vm=z>F<qdHPh?~vz9f;7o>#B$$SN1Pr%CMQMc
z@m1msR}{jFY2n@BKKG0v7jfqMyn%WD-u>fmqjh?s`M?B11!S9f+=vlh5gX($Ti2-_
z{F+|M#Id47{E|#;wE4-OMy%_cdaUs^w^m>r93|Fj#T2C(h_gBl?kEx&kbaq|;p!S1
zw<x&MWYawgK&7MrM9D$efL^IN@g<@H*-{ge9`!y=mpzt%ZThPJgdJS`p4RzJc3zJY
zGjT559hU^be;7{!rP+EcCC!`1Y_|RkIERQ$dQ?bG8*%(1F2CXUjV0fQ2qleVP5)<n
z$BKTYFl9pii_I7gfcO6inH2<U+<j+tK^!Ob#$-yn)o^I8!7Yg6R)){f?;qa&VD9{g
zRGfVGsy4uUGH^|@B>yy0e&N>#<cpg!2`&Fe&BYWY(t*FyEf6d#0Zm-E3kNa77D!j*
zDrD9SOxF3A-^j-~+^03F`?i7N-?~cRdfLinB_QP8Y(W#V6HlX1J+K=W7)!?6R-tTl
z5#ee)P(lNRxo^lWk6dS*?JM*vU}d1^9Xk?p?A6MXQbOsCQ-0#r6*GKke^AF6-$K9i
z#e<29xr}Uefk(<1<5Vrap_9vwc)sBmqK2*_#p9e3HoqNCWCAmJTr1BimgsvjzfK(G
zG(uC)O>UcUg2K96^M)a*6<hIu3@Ddr9Uh7rJL}VkWWCrKg{pUPsK?xSe6sX313Z*q
z5n+s{uwhzHWHCKE2+l<?^gsA3=e^7i5h3sh2?GR9^3i<9N$UbWKZTdRFI=kely!4~
zKI$_5^t$+wWEID7e{-ca-xnfWdKm}DPHLRS#PB95%06%w_*F87S%Tka)J*of*(waB
z#tWRgLI)aKyY@qED<UdHR27c94>$5KG6KaHOSuxHzL|~}Q25Sen(4zA#y92fOg;B~
z7wfx^jz>LR47Q^g(C6`j5DI5f`aw}tmCHlxne5m{y`cu1qMlMh;L}L)xrW@{dp{hE
zP)dT$jnM}SiJ56PONNk{T7QOh$El{)(^q;OyV>t+KQ8uVy>KM*W<@v@3Q>G74x`?m
zc%u3pdq6DGYrco8z!I6!)Q!tG{<Um&Ov{0B3g7~Y<v(n4x5o=@-_w4Jf?k0u5O_`7
zugTTJ2IRp61gkrDl63Keuy8Ea5PbM@$JuUg`~^E<TFS82LXI`g^%agFO&7qEaQ)`X
zxdNJ`t(p3lI46zaU(A=fLp4-fN^+_nKf+O_q<jQLxPa4ChUofJ799}1diTu+OVV>h
z@9JC@1iEFeUz^ncIc=m-u_P0{Z-{<aKL8?FC4)J~6$UxW$S<oI|AluB{6F#NJT*uW
zzF!h)|CuM?YJQiHy>eX1#O`#(2mp@{RUcpe*tD2*B|3slpLa_sOq|yD$q$v(-$V}E
z4IiYvKKh|#+knaadWSD|yaX*vz?UupDN6`5rC&SZsDYu-L1yesMj`<Zk*p$L)aLSl
zQ@<PGcEDMTJoSqgTIneA1%@<DEHQ(LLyCWH>K_e)0v--EGuw%^1RO$@Z_mx1T#x69
z<5N9z1XS<bZ9AK_?;ymHf7O}fuL^kP>EY<dsyKp%k0yqqba3p102u>oXUgq9hKQ}3
zIDDQUK^E|M(-Q~zlSK47kUCdX`gn(PS>Y4l1#N>KgV_UPkv%00^)hCXK&p=gexpdx
zyRv~Yu4cOX6vD4*>lG#2Gsosh6+O(5u6bnmoqp*C{}LY{I>lTkeR_Q)uoG~6wW|YR
z)OzbJp|@Sk+S=Z>^hEW~QuIIsEde~+n2+->pcw=I*AJ!+oB(AOirAklh#xPF-uIf@
zmioWZb4Rq7`I#!5ZK5sLoiT9yJ-JOO44e`w$ias!{v%NH{qyNmYJ6?eh!^=pg~|4)
z)@gld`37Qn@>x~jHsZ#d7^^>Xa0v1@V)n114MUW>+N>bk?tFsumD$DHT#Tsu!d3Un
zr+%{H3~9NWQ0LEE+<WylXtidd@d-WLA@{?<#N5FLd7<Q@3i?KDhaOzVLJyJI2=I1`
z@)Nmr4qK5~L7$cwP|s`O*n>T`_uc=r2!8Tbz;SBgP>nWSw1l=F9sIt%Af^Ea`lwm_
z*kM*62Epm7shV@<r<V%mZGtN?aO<Xz2_#SbsqgOw!7=b|R}u1ii=+t>aKNqIR$(mf
z(DmMR)$SrdUOAd+Ni?q4`XX@{9KnqwUZhrSqs*(xdzW6tI-GE-wxFolsy-yVj7WF+
zq01HZ0102ZOns&Sh&38ti=`78spp;Km(%GGXMQl$_xU&fcH(Hu{0rNrJ>}RV@5bKV
zXz7>^AV(hgj3?Uh>38mg7Qi`3KOJ0IvAlhP)?eaQntoFz@chGjQtfMy*-jm*M&4p^
z$C2fjMK47hwI+5Ws=J^iqde+u{<(yo3EzJ8IL3#?4Hjd!w40`Gz`Ds@Bwfs<_XfL`
z1$|XlGhN+3oYtL}0>XjBv%~JM-9w+ZKmT!<f`Nr`Msd`0ASbbWboeAVgv<|S(`e(Y
z@T)(s2b7P_6GU@g+?A690}fo$8>mLetKxsbhLBSjI753_BK$%MjlUkXM>@8jrO^-E
z(n+`hl8sCcMXG4`0hf-zFQ(kor?aFfmM&_C5b#J-=(F>R{2gkoeG<vwAa;>h!G>H~
zwGziYxDEL+aF?bh2t4L=+qmtG$#L9Ft*Qc4PknF#Q3nI%4nIE;)i5eZj5}&Xt3ua^
zf0g4?V7_{3S+P3PHbaHN2@l<-kb-qyIY)Sd3GZLbo+6J+a#rqqLcEP3^=UX-{kcJ3
zJ=c1F@0ErlfTb4L^(*O-o+$$}K_c6>;-23n#Mz!HPnqF(&egh;fLxOMcvJS8gncOV
zro{CoP2U}mRp9+A&RgRs7uk;|NzGYZ@e+T_n`^1NY>GdlGIDBiEd?<6h$6dj|Ix!=
z9X!8N86zZ)qp6d_Je$sgQsk;)`y77b=4ZNNNmNMynxxUXT`d;Q?3?<CYQ#&J8%~0s
z?7}R65LqF*wfvy?HMdzU!$P{-3wjV7_`CED%07iCXXjU3W|%?$ZC5ccMKah$)PU`&
z!bOOfpJMm*shvjbpFVW}HY@cbMQAFSr;GwBreCC!Y4ln&)DY~cI%vHP&kjc1(+8SQ
zlIe&i;2Nq($uDI#4GV?x8^io1eQu|<J_#%FfmUH`davg4CuGRKyXKwq0epV|KZB5T
z+Te#j%r@Sy51~YfM-ahe;wT<;yY27+vP?SH&)aE=&#nt5gbw;AvOxZfpGD7u0ZS0-
z0iQ?R2l^^U>g=h4g#mNIW{-$ZXs6C9yd1XYeD!wppynaG2NkuCE<rj_X2p4%!=K9l
z>|=P*sDm3PC2>o6M@0Qy@)bY3d*AFyvxN--H2!9UgGRc^Nqn%@F&^O9pab+*(Oq`Z
z=YE|;m6P|XT8fooNS?Gq)`;FJ9&DEI?I6n92h-MqumaAMS=slD;eyy?PVkz_`er36
z7za%r3wrW<kcO6ilfwHm=^4Jx#Z*%j8!KX}&rW<5ASZy>KYmHC15W&sSMkQ?gG-yp
zRUFZW^2o2Q8{(+Q9&>qpJ>&A>u;Syt)h1*##>B$TY?l9FUSfeb@RTpU6`i-n+c(|!
zC1DpEJ}2=)u}|vB$dvl)w4U(99_1%c4IAQ&0g+(+=|>2ALJ9<6x5$MYns<s~V*9j7
z$B?hyKSAfse?jLa5m`gXH~lP&)`Nx!1qS%cx;3Uz>tntaJFK(+i|(~y`8Ulh<f;fL
zc&9#wrWyb1MUBoiPK=yB63Ykz+$Ut{2^$fb5K)x4D{s+!hP$?Xjl@p%<2#kz_#2d|
zka6(%KEgLX=3$JD!EtX)Iv{h9seJkFukJdXrHwO!(;wMzVBd;#xPmHEo))-_G)ryo
zC*-6aiEiWyLTd3G<HLVxC78}*XnvBSUfq-u8F-eVf0Nn#ZrA4}Y2Qf~!X5BQ>RaN?
zscbRE&SSLqJN2k#D+GJ{GlQ*~7ASIl_jX?6CHJl5`ela)`oJ}L`f#?b&O;zPi9YJ-
zF_BlgklnCz7QDcU!JL`2{a};Ts!9C*g)h%TYwv6vKBU`#jQm0hvBW|(`r4GM3W88y
zis*r^t$l_#yg{^nHY|WKY*=f$53{<mtqZ<i)r+8x(}Ch{fwgm;hzib7h#iMIsz%G1
zwfu}1h1JeDFW?6_rp>ZnA4V%V2oa=9MyVUW;BWBdg#8Jpwe(UF#=FGTJIq=0yaE#R
z?8KKv=YK@d>e1AFpph{|X@(4~PlIq=6)UX7V`T_I_cddgxtg~gS#yc31Ul~g_Sz$9
z10JEzU(r%D_8;sA?7y+k?#buRdJ*m~OBNo|o%~j_W_k*BJcnt<#{}BL#5u`co&B=$
zHPTK=xwqfwuhmYM&eg_>7JJrg(_>HS+=QOWgXB?YuIs2M6FxT$*tQ3HnSP^M1GD>w
z5B6t!v*233-C|XZFkM6FP^Qi)Fe!P#{#6=S8qC&eLX}ZcphY}e0;thrCZ|8%$*4O^
z(?i|(_Io^P7hHd^FN&1Sa3GFm`SrHNI?92e&*_$|hz4y8f7Ve}GG&AzDTu!DyCAT_
zl2X(B3_K{syOt4LLK$i!gdiV32BI_K%mb!%!Ex}`OAQNqO?0fRSjMsx?cQH5{HFdt
zL9=Lf&c%)`R29UX5PcZ+i!Y+&lMKfa8zzDF2xrUwgKlm>cc~Vo%dx`t5PDzBu0~t{
zWMNTN>ZVQWEC1MN?hsej%~Qhf6%c1G;D)C-Ww3y^Vjiy$b-g&_{FJ9+#0IK)Giv`_
z?Ml9wF%Q8$ZAT@Sy>|7+8DTnb4Df45GutM1=BkaztMdDl?w0xr%)B~AG-2TdN#!46
zO~3~)Y{o{{<rC{#ox7a_i>VpR!H%>=G7<y9H97<xXsLkJW9U?F%8lm8JMS+{M+I#l
zO(D4913)P(hlg64#J<u6i1l`pYx&|*Z#D}}V0l4;1ZDtT0qj|?mDA8?;$k=H!{hzE
zoAwa-;l-a<Tb@o-GP<gPk~Y+Us8epwoTbTRqW8>BVxMojh29TqI@sv(T~>yF!*q6$
zpP8S~gp&4jo!Pqe{d~@&KO>V_qPQ?q8p-001$D7!HH|SY^+>6Y9_$V{c(eMD=1>l^
zG1{qLde1%#r8637iE^K{GWGwCPE^S^#D)ouh0Y_3bH|8_d4k|2jT9&w`FYku4vY+k
zaiQrTbTU5ym{m2W`^$2g#gcb%6$@j*bZo$x>%74P<4oOD_0e(5TjXE{P=zYn!h$k)
z^v<JF*F_fMAHRK|XRAZ5CE%8}qw|uELo7XU!eA3j^r0Hg(kqt8VP+854ti*>AmTkF
z`pun}tAha(^KakaUaqPGbijTFxEQyD^<{}@v=IK0W)UG@9Dz#4J|5A{=Gh6O&T-%z
z{&GX)nu*HchGw0u`a<9%4vK2#_UZ)zA7(=M(_^U2gt<jwm-CYbnE0Gf6ZA})S_<_B
z7fxDD%&#KnrZ$Bt%c%wQx8HJrHyu7WO4@~ejGxx9a5bwqYC&DrS$&X0o45Ks>L}|X
z1nn8_%GbntGwR7M7vB!!2I-H?>Z8hQ24vMT!T5UWuyJn4GRYYlI0^iPGGcDCR&tR;
zaAtF)2Z-HWYi<k^X#Dbd7nt1!HgkyYPW=^6UOtThBY2FHn2(&Gd0sF~@i-rxExAsT
z1O*(Z>tqO^XkaE=D_=6bRnZ^aDdBrQfB_OIR%@Hxs`N@fS~4|89N7|e#}w;<@Lv60
zuswE82y!6+mu=J2yZyspDRo4-XyI~fsN-Lo@7F`@S^{fn<HzA}zruS!33Y)RJ=mjs
z8TqaO!VB~QPUDq<6lZ51Vt4IYGD?bcvBaC5{W)Y7gX*U_n!jGsL#@MW+a7bL+^PD@
z`i>TKVt$G?hAETA<ppaVIRLJU<B9Q+MuG%p)IFI8MBVYjQC64HZU>4X|NCKf*K2hG
z%suIlP7{&_f%4X~SLM0DUus*CjRLQM7iu&&x8H50?1LNbN|WZOqh2C^@C{%!oav_z
zYy*k&`?6olvo5!VvY{I;D?ny6lf!*9FJJ``S@#!KKwhQhcr+-RgeM+lH_w|gdiGrf
zd4P-oXJI$dSp61F47v3CgCGWC_HBjC_Dx2<H{7s;=qC-O*enAH;oejhj2b@Ab)T(s
zuKT<^_=C%Xmflp5dZxx$Q9}!9MyweGGoi$}t#`JJdDXUt{eg5l<Ku`hSbFuJsP&sl
z=;MPU9>DYrAOEbm?^Wdbx^|^3>eaQ6F^RT%N{h;`38zU$37Wc|J~lFp1MG0BIv0WF
z35Yk{1RM<jY!!U1>&l3QC7V>ZT#zz1ur~l{-<%OuK+sc8C=mt386<6x@ElG20Bd6r
z&IvxK^D(yI@TttE*E{zdud78frcQ@zkek!hRUm@JjLcen6?i)hcQ0iZ<A|q&9g)}j
z-@ESp)eI2C??clJgk&rRLgSVGX9$%#o<{>Xa2^joT&SVBYX>)Mjr#pm;ZOqw%0#X9
zB%LtodlZLqPSej04Y*y5$e}-{!kqZ27Tt8^6Jiy0FcY*&h@&kJiQcIa1)FcYK+BZY
z%UhSg_1iI08%YY8+z1RHkch5|E+?syJ@u?mb(%GnsL(7ed>l*3jU4&ofp)Fddw8;C
zeOwDX+%IHX_D8<bwvOG{`W8JLx~xgUqN=kzGsi#!e#!&dq9U+$vgRw>@%zir5_dUl
znJ>_xgf4j<D!LjbdK?T!;ENF*W-I2STkO^J)Wt=TT&WDREmd<9>(Qj<s4!XWz$`V7
zwXMRy9FWJR=v&%%N#!i`2eLYX-`hwY4@Xt<%Qkv<7FTWQBEVxmt_F3_v86K^=Po+|
zE1NS8QjA5ry2f?O!2&?V@!~_haNxoQ4VY`tgT_ZPAg4+1MPE#&?fnl5RrtKz=w%#u
zMKw+OB(gZS^ob2ieD(FrN(?(_6D1Bd4`JZz7Ig62Ey+gf34-Hh%$~a!0hNro3?Vq_
zz2y=%#Ued0W9?mV*$kW)8}B(;d8QO|#HL@^6-+#$_G%pr<42b{v+-g5j2I>R0q1gr
zYKw>@VF(v$JSYX!sJ&905&^cdvDo`~55v2rH_V>iI$zC9qFQ|baN+G_M2B&*Dqhjg
zeVO!l5oP(jrHM?CEM6JY7Y!-4AVvU-kqMeAS3yNQyu4%qdZyFs<q9tT{4_{68B~AO
ze3|n*>SagaFk&pSaZ99~XG3<QK6@590472sA54CcC++O_hP({TC6;<cA4Bg#H6hrE
zS?c}F@#k9&9c%d0R!A!nN?u1rEVvd<Le-u<hZ#S?#?i@F5HY<txvbA&viq*<sI<TI
zxwv3n&TWx>z<gTdd*bl2UT%*a{fXq8s+c(p4(zQ4$FEqj`l+!GT-MX3?+JmnhE~{H
z^d390vN>N%+J3+GOJ;AJ0R+~UaO;K9-v4nt*qKMaIr0_c<-()mS69O>1GB=&>HcK(
zC2Gf0C*Lv}h7uQie&y`t-OMmdHK)eAt=|nRvK}8kONej&a&l?H!JUuJRH4Ou57uy`
zJl9fa0U)b^!Z@pcoe;~Z5xwQ<<{<V<(kEfV^A=1_2OOafXE*fd;G)Py(#AEfTk8z4
z8kbsZmNo6&7?uqL>F1sMg&KP=Q7{ypAWA9gdD8Q1iL_ICxs|pdkc&Iqx#hU|reaPn
ztNb@Go7H>GX)BI0dRHoS$v8ebxYLdt?iO?y#b;LzaMFI$4acJ+&)$avWzxvVV(f{5
zR!bZzCI`w)Jca-WgG*O$Hq27PhunT+;4a_%OFlCEr&{9TIx$i|Or$pqBiC-x11yuo
zsB?IM`pCOGij*#Zf9Oe1`PyUEPI#y|oiw(Ke@Ej!cWB(%7y{M75!LvM9A^8@yk!JG
z7H;bLzP5xo4t21=n)%9)LRkLI1;~GL?2vPtXziwg&9p_Fw|4tfJqzHoZHgohUZLOs
z209OMwEzA6o$q}xsAdhGpLJR@YqjvnsK|)_b!_}s$MbMYNlGZ=^?R3g;l7*beUfFM
zJd``X8~^>w?6^#}B?dl7ylKJ+%T$SQsnb?J89!$y9E#LH+f(7H1A*L^=N0u@Sx;!i
zE85~f3N!gT8MF)|A+D&OovQuGeV6UJj)H0qsN?`JZ(V&PdN_4V6(SpUB`fBcxU8;l
zz8?QbC&*eAM&}I6;)n@2FJLCN@Wb66PXGk_oA0*ve>l6>!Ld{(Pp1aC#QoRd_#fI{
z|33btA_NLjtJX)AX}=(sTQtwBANJV2D5l5g494XvzS$gQS*tUVfO>D6No0|yZYr*@
zq7I-MGpJ$Ael3H0GuIl9@`4G=+Xujt-~wIzH=g^iF@LoO0Q{9>0(BlEBe5W0f<^uL
z)yorwfRf8}6lndiibxuU<l-SEj%d1Lr3oMgQ2OQvFGc<JyzqvGDHt@7+cv9nR6w^5
z;Ef2LNnC;+2lvgtqXUX`qs^cNPs9)m--uNwK|djm-*+xt_|^6ERt)yPAbz<2hOE~A
z3o^8GdbRw8sfdyqD#&vY0_jEU=Bjgwoq%#ExOHl>Ad=Wvz*(9;3QACA5gz8l_+Tl<
zI`fv$gqRUl8u+i)Jl`1>13d$!20*jJ`<~h!A;(*SB1%JrHGVTirgU(K6l)G}`O|rJ
z&My&|x!1EnBS#cB6Pf8sGC&8KCa6iiSYG%SWpJoZn%{=6>TaLs{2}?>+{K|6bN}h;
zv7uFnq7RCvwPtPTDKcNKn6YCh+?;S9X<Wzw3sCQ)p#WFf$L96=&7MHwWYhS4g#BM9
zT+IH}1<H)x2=&|oWj=fc^Yx3YB@m3~(4hn2k1wZ?kk&&;+9ul9N(whH#K00rlk9y`
z!^{KlU!!#1nGQWUP3rR7zZ+)v)b`5jG~?j~JY<G1%V*zuDa7Rk5m}%Xb0Q;1f?T>t
zYM;snbbv#>pYrcb&kwfOj6m;dl04ex=!I`^0uqLG$<lcuzDNf?xaWFI0hHD=uhcOm
zR-oXLCLegvc?PLr_8(hxxI$&#x$xd7?8e(~_aXQUxcM4?P9|b?c%asY4%8p&+%css
zpYHgQ;pVOUs`3XQaJz7WGy3N-@OM%+wiPO?3yf%-l7z0z$bv1~VSkXsSjGq>MCBpM
zY<&kb1@Mo;@0wypI&A<kVh9GEHC}gL+<ts6SHS8m4o0m>=qa*CmSS7BC$K9R?*23I
zEgW&7U=+Zo)T!UmK4z-{0UheV);WnW^Mf}iNSooP6&U5^o{&O9=qXu`X_qmucY2JS
zqXOEZW^=os;2V#~KOpJ@8+0f@xD6)l7ZjX6Y5OS05(emC!xzsFxK(Ir+TAN|$Cb)%
zVXm!_Y^a)kY#eLnP@;VC-w#S)R__?>Hq_q{jkXCXTL2_?+F}7R{SAs5D?q&rd$aiI
z2~<hE*_qv)$4XOTXXhVp1YCL{Ophv>v{qb7a$jBDa#MEip#wpW>ghqnf|(fD(R$l^
zAEjNLt!{vp9?%iD+~o2PywzB@$1@U`z|;q4v~ftOckG*CPFv8~oLwCJ1W{ywLyGpD
zLP`gpR=-V5qqRg^JPrcktY3wEa&OUrh`m9tQxGv0GK?(6_4;!;%b+f^?`mpjo;bqL
z#vzdI=<aZXx}w+vv`{UTfXncaGSr<{fP6kxbvTy}ODJBkoF&!vGqVECIZst^r2{z%
zxf}wAp5>xhvHY9V!bLpaWHtjZlkFIU{CR1MOdu8XusG?PGvDw5#8i`l>A5#LCaDLp
zj5>6OtkLL{!Sl-N1{^F-d4(r)0uidqnMbtxCON6JI4KL7UjJyF6Qcd63PZl7STzty
zTf~F;4Hv`t`V!5Hu50x!$Lg$(KUhI({%)-AbX>0I1;XL)n(pJkc=j+8SUpqlrcy>3
zivvpn*-Sv&e9oxb!IcvX3A{4iMhqdc^&*9ZV~mY{j`1CQ7e0~A0FSdAxb}}t@O{^s
z)5zv`(xW~1f08Y9wy%&y4ybGf^~uZpc#93#A-&3H`hTE3YVe{k_rNMJQ~3M2WDib@
zR3N}B$IVuum09#IR{s`VPjEiLOfE+h8R2S9fo`+~kOXJ}N&Apq3CP+7Epr}a&-dIz
zd#RlUxUQxhWG#^kcmP|I%}1Cx4^xdLbPe7-lJj)Aa0!6`1@m4Q$Y)W4YUsNiMptT?
z@N0gJ)g5c^1p)hC(avWS>u{)q7Zhhv1nHA#-@*0xkkDn}rV^c;ZEH>9eTW$xaA>+F
z<sVO5M7{S+CRnhB$Ys<pz*QwZd+D~uo%|Xoki`}(O~|}5h%8(pkpM^5`^<yz9R;A`
zyqLM{Cc{um|Cd<vVW4Bb5Y9r<|N6oBu76+kn<EH1G_jU_AB^x!sIjRLfg+3fCS45s
zS(IP3O+p)oA@=XVoFVF=Dh$DkG-~pnZA{2@*Vr0Gt?)}Ktl$fB3&7|1t+w!Ru!9xe
zia>h^6!`2Hdi;Ffio#L^cj7BD#X12~eIBH*Wz$nmz14B(MgmzlJ~&9?a-zGKA`1o+
zow!6g*f9kM&L*gIf7un;;tN9)DYJU4aL6TJ6UyW4*I*2Ux4y@dM-HekfaT>q0(q{h
zQA#Z90}|=?8kPMSK0Csi-i5dWqT+}_zyvQF->1~S%a#$>&3~|EwH?Xc`?;yNBp<8+
z+P{I6NFpzgd$WkzO}4(gW%Q*Z43b&@Z2;Pl8+89%`>+uBeGzUYlF=R-gCXELHfid1
z>gEbnbkzwqqHc4*t0bq7G={n+G+kP*vhT&{Lz=xMaVI?j?ZQbt#W0%G@s?&<SLM$Q
zR<?dHUBo!agCg9-IX75;ba|t0Vhx$KJWe&WBa3TWedE0<id|i9Ta~7N@>%mHT$;Bs
z9!`r`HfBI4po|N)zY8%1byyrVL9%sE^dQM}=N}sMIw%vVti8>u9k~MjHOO7RvO)-c
z!xNnaP}N@Gy-=n+aT2*YH9^WDWq})`c}uJ3{q6(5GEWH3!sTgRW}()3H;{f1S%KRp
ze%PKTdCP%h5>GpffftWca4vwuR|_m0B0gJ~N3Bl3TC6``R|iJa&CG@u3wksM<e2;p
z`Zm{b|FFPmv4JQ1-VDjtjVp0jwXI?|>194b6fp^VaW%zbs;1XZ25`eEAWUSN@30^^
zyn!j>q+r1K!YSaN^o7}aM}$C(@F^0ED0l(_O{KO)#3Qc={2K=Ipt)MDmdV>PRCW#y
zT|TVTfk#ixRuK6=_{#J$CAQ(v($JHd(1erMG^%~zUB3G1jqJ2n6^39gGQo5n#9)B}
z1bf-TLCcz+ilY|aUjc&9-mkwBR6di2%aX$2Ey54>wrmvZAlnq$VYKD??nDqtdyAw{
ze?<5;KfBetrPMF&bO7x<a^VW{y=E)3T=Po)WlKQx;ZC|KYlS$@aa})2Lel79nT1z@
zNx6^a5=-Ceg!9j7N`b}>(ML3^`Vf9S;fuLwy}z)+94&_u@TeDB-&D4H@6tm&K*>Zx
zdl{*$`VBEjbMN1I{$X#2CT6qsXw&hM+9Zqh#hc5;Sc;};eR$OjHE?aSKJ-`$vtP!7
z8mRWI(3nG&H8^OFrL$)5YSF$i4hV2V9=G(qt8`qd6SRoX-1I?i9qCrU0;S?aG-k77
zA-?ixJutRaGq)oSCL{x)_cT4_%hmDOY~>Bm#8n9xTFQBMPpS+9KVdmJgLvm4HvpI?
zox!2lmkJli5PXs5Lr)nRL-uy9N06;d{`vTE#OpL$alIS{$=M8gx0O0u&c*<DWB_`~
zqiK!j6ebX;BJd2+6Qy=wLA{xjFtl~oA^$!9C9trHWCZhooc+5;A0O=%2G^5s)(sg*
z%=cQAS|x}Q3kGh%5a3bV-I`T8Yz7XDe2!O)D4}zs$Nyw=zQ~dexx}I##zpoYOZhW)
z82T!Y4%1D%g319b_ow^|%KR}6eX53htlhfuZ8>~%dsDBd{z$D&TD)I|?z|aN`U!E3
zcrKz#Yy;Z{$3ov@DCkBX*j7a`Tz|B|V4Lt26jLel?0g{UWyI6|aZ(5MAEW6)eKq|1
z4BqXy&SSmGxW4h&`%c%bG4Nv=Z|U!+gI8FVJU0Tm9|Y$BIh;Rsq4rLUhjDj=EJQiN
z*3wC51`*_W=I&g_jMMEWeZj+Nf^@DUiQmvo*Pk6p5dNDk84$z2uGuy3AgA}~h1*Vz
zLxi{Q^l;@|pzRmT;)o`<y7ix3iIrS(q%5Z;fI*pSpQ^Lx%Tbam*TPMlzx<j7B|i12
zde1mFsQ8gDPWrjuWrweS<};L=7{gY{4LH>IIQyc*BzCBbW`A3qHb4&QbP29gk*W}d
z4-fXAdMa}J^Hbqg?_*Au2E$9Pk&f-L8wdQgD4NEzAp50xgRI>B$N!_bH;;$%d;iC;
zduA~9u@qS{v``WyAu(eqS`kVmv=W7iY%#Y~L`AF0HkHa66;WBHMS8WNY}ttt#!~h%
zbN`N4ecqq%=llIVet-P_`u<nuy3c*?bFOo3=en+^ca`-u<2yV-YUir9i#IOj_Gb2G
zKbWwbw=yd$b^A22T;rE|#n4Vmk$j0HrLnUp32l4XHr*Iezy3B>07XyYb@14O#X11r
zMn(2s6%7pZoJ~6Q{87{_*hT^&T$6bP_rR}3$T9r%+I^lKVRXbkxZUPaFc<RKBn!>B
z{v=d?iWk;+=<&tv!qmz5!NvnJsL|F}tphDd_K^Nn&RGtYA^gTNad6zzdtMBoC~!u4
zB!QDHI^S^m<r2T}!LqlnA^vID<W3i|QBc^4l#;C8g4rZ|`qGDI#&^K(v1Z;vyiizc
zJ1PA0E7l5-N<QvDt}>lM(5z?>|8@i@;g<_@{kKk!m(jq&Blp<oyRYs`O;TNZD_YY4
zR|t5Vv3`a4l6{sFvLyL0`5!fI)&pmMn4>Z7H}($NQDw)<-Nez8z8bu5KsTSSA<J*l
z_GO?@vU3`KUd&}xbdb-w)O8qLWYoqa;ST;<m+ecfy#MJ-pwq$cWAy+|rlTf=4#h4m
z_Yv#H+jaX;+131LE34ZqUf};2M$3>IR?t{R+>POEqQDQn0p;x^%duUD3{J7J$0Ta1
z12vml_MbXnfWIJdCbYV_3;IO#<%-V0@!Y`6g0p+TVa%yghfhQ%D!LnYR!%;O;E3o7
zM?X=~K0lp%NgDT@%lS<l_>L8;r2qb~%jxD*z9gKBdxHYT%+W8Sa*inH^4F#*%^1x8
z>$YR-ricWeJ$QFC<Hvhpl3U0!W`6he9ol;?4f@RaD1@WV?%Q|Pd*`YvUI{v~0*21S
zw?5fTlNeq{f;u_jPu>vuWCyoRG*;K2pR8*+2W!{)J#Y2b{t<CSpz6Mvj=Ue?`Dq&k
zs9T8kUz?i+>l?iaSaM@-8u(@vW90{Dq2Dhh^#kKICJNiG=RJOT^1tbEh1kUJyu@9m
zK(BsWe@$6+i7cH<bPN%SfCG4nM_7HNhlGfVj;>sIF!ig!F=@N47+o6QHliAypfdV8
zOVr&klv2`FcF9n3qa#KS&!AG(Pzr$sC$4%GvsqyA*|5!WE)4#xX8)xhl2d9rC>)fz
znGvpSKbRV#YJB^u;;d6Z8&J^uN5Sa%Ghpty3{w}5O2iMNkf;@<eWM!cxA`LSr(4TQ
zcAq+@*_2sx<I}k*O$W<2L5#IqlQcPj!9TOhq;IM@rQv$a;zxEmP-lTZZBh%kcNy4`
zp!bHi<Wc8pEV`IsPi9Wo?|x}(CLFzOcBT+#2USlQe#O36lN|c8=W^ef(hb6-uVQ*D
z57#<qMn!nF86G(`erP)cJ^t95b5~Zc5QCLf8}CI?VT<XB+mQn;+sKe4w1wtpLTSi&
zU$bW|LN@v>eQ#3OqpqJDC%HltRikD+D7|UFu`O#L3xiLjMbw7pIuG9NXE;D~VT{{u
zp6)}H{Ju2a3uaf(-8J8+6s9SB(DBkxY-|>qW}*}Bx!X<{mtUH8kDqEoUJyF<EOm2(
z{tAq<S?J4hf$!E64z(iFw`Bmw>}3BBBIwuFo<kUFmuB>m!>g&lfwx)?^VY1qv3xq_
z=-_kuCB4vqtKc3&2-vLOZ|jfqsoQBBgASt~mamwM7RpEcvhOQ#EGhWAsGS1Pp9kvY
z@mXD6>GBc}iKeHVU*S(zoi0_DBvvdteNW6v9XFg#bzr7(Zg`|X00xgjMaWHr_2vuf
zU(k4EO#CrRMpzNp9jOcNRXIjzQHIVC$HcVc4QOhk1b0xBB#*flyAk>GP9GJ-t$+Tk
zt8a8vXI}QJA6R^hWLI(pD^lF^I9c(-&G&cjGA$7`ZN7KEjk-ohoWp8G1av}$_A~e%
zu(CAomebS#AC^v)@wF2anjD*o)3@)n7LyTWC3U`lydzB1u9G59rYngpPBoIjvLEs_
zg*i+gvD9WF@HJ&w{=Ilf$}bGWFyMcGMnvS2(|D6XE%v>q7fuNOsJ8$c$x&kxs2#ag
zCr*hzQJF{s_S1c2sU-52?>;FFz<dqWHgwdhTk_dIr7w&NXmG0jJ0IP?Rr>vX!hs4^
zE*8P`g#UWtft<{F@<}V<Xa}ansjpFXHgm#jC3c@g)%JFE1Azl)9hP9SfpdoR;8$i+
zpR&LegVl}|k=T0dhQN#h96sx*qCbG6Se|2q=S4dkQhWM$R?%YJ?&E~`)ArwUN3wN8
z_p+t?l;aFrH)9*}SuZBn5xF}Fx%5P%ALM(l;_hQseB#xn=brJ(J&_)%8Bvz`Hd^yB
zy}nf9Rc*)V?w5GTAT^_L6GDU+=C~jG6)qhn3=Nh6P!(w=E+AH=o!VArcRA9H%wOH-
zEa@XkPS@Z(gdr)1IcjR6?NRgH>yB{d#!+c+M0y3%#}D=##Aw%7WJGCu!_gLzP|L+;
zhkPgewx{tE01v$WZeqd)81u2`nbN<4tZ+RuyK&aRgfp(QA@t|yo`0nC17GK5xj@~Q
zW>9>cNdr%QlownPg&O0oD>|QBF27NoUVmZCKUC>@hR3knrm<O{(uE}4(;Ec~5C8_m
z8(T~E1tMOxY}m*b1GaB?G?jhYi=x(Fhsxn=7T0`hV!5@B1m=d|UJIztwUV}zmYSU#
zXzTEBOXIg~qtpKkA~N!+40cn%$NDY6)b|7#EZ^>Y`-bNRxCUVOoLKO3@O&R23H&>o
z#KB!}Eke3#3}DHkt25?`<N6prv~21NSYZ4u-gJ(JDTi~|8|(@OY(=H6fzhIoccsd_
zFJz8(?q%Q9O*-nQFuV^&4vfqz(|bzPzp5>B`I+9@KOD-FHVi3Hd)RfqS(&NB51uG1
z**zd7b%)peMOmj_a2V2ejNhk-Y=9*BEe_{uy?Yi!tVY=2t0u?3*2r2YLXi}+2EL1v
z^1h5qgWXQG1PuQ@xv$Oa=+s?kubiFtm34|Tb@$$s*pHfiVfUso3N))#j&d(nB-k#S
zXZ|YUmKcd<Q&yDPRiC?`BpMjCP4s#d;l$u~^bXzEk!%_m4(;0?YyegbtUUiv%T@)o
zH{)#@cbp&aHvsetoCIz%^R8cHcW~^4BJ%j7%EOnZrwTUGI|hapW8zZ;yDrkePzUBd
z2%*6BMfP`51;XzgJcbf<p-x`$UlR?vKQ1YP=(<!V!%R`TgM@D{w2OyZB{Dkeg%+dK
zYc>s9*Evj;E%&@y$tWsr`ZiwI^kW;zUHV<UTch%?(h0p%R@9i7Gn?PmH<r7Qd6&<q
z#W)Ft%=mBvek2wAl(Z;#;OE<dT(PN4ndiA!(f%WEY4}a#yAc0Kk{+$WJxjOF0+;V?
z#eFdW=5xTpEC2k{tD5*Ip~OpAbYmI95)EAFYG#G6!!oMx*b~U#pP;a(Lbnz)TI#ir
zO_Yp=1bxHutT!(U<!$gbEX=&b3>edOSiTpvyTlkj_nFIUaMJLap6YbMmh3)28B(|K
zU*kTDb8d*(4@0N{l9$Hy#DAQ=5p$PQ!BJx9Aco&iI)vGsP?{?=|L&#!v8_U|_&M?U
zLL7oj4OlB<L!%Tw+<TVUGH3aocfhRmHh}g<?(hb1cNC-gDx&ReHN@DDc)HvPMR@Jx
zp%8oOcS%aWvxZ&ZnRCtvTqC5|*acfjQoIT~<_pP_LHh1Fuqzx)7>}IKRE4*TiWhjt
zRmA;TjbEubp&gusE^K(=C3DEI{q-g?w2g83=gIiMbfq|GkZ2khTeYP%e!M(tm>;_q
zs;Kz0u(Fglz?^;L3vhhP3&%A@pt^uz02{RjyT|+%3i-3_pNrD!`ay9I#K*oU=%4Do
zwC3z{hkF}UH7;3XWR&F|rqeziIRI&nlAyo*ek*~R4Fvrj-v~4rup``VvXU0uTrQM$
zl%M(7#~V81l7Vx5H#@ct&UnG~i^ijZHYyk_OjkiB2h<P>b%Onh8cUK$%g>goUVvvg
zm=UmNt-cy3D{wQwBr*{T%C`oN^rVfvDO;-Mc%s)yg0u_O=k*_@9d}9*Bh=89qyCf3
zX*XS21&rx&s#EmE<=GLVTJ*1F&#gicc!lCJnL}UgnJ57nJ+g3~TPk=_a3yhylOR{&
zY%I91ov@ZWnV>_;vS<G499oM7M^buMn1J6bBg1F+_w{yVWE?yEptNQ~oX1p1cuM{x
z6?WUZ>j=v1DCns65VL^!-ed*P8%pb!kPjaq$M5`n$^b&BRW*y~`qJ&O;=AhgL#MZZ
zr>mI8b+OefURj}&``g2!dpB?-XBuSCmG>Q2abOV1jSpJSU;{!qPZKabVhe5g1xw)E
zvCJxvfd0mbgYP$gqRtJ-TmVH^wQLC1`Qxl3jL4h15%G$!oBjgqjykog>(7>Va?j$I
z9Z=MoKkfFmPN)lA*-yCF%LnZ5Fvj%yrCSF!)!%e{|A}(^5A}I0XN<VHn;k#Ig0O@O
z;yv8n5)~S|T41n<ol(jOE&!++aQ=q|s=9-dJC9@*p7dy(PQL10W>_k1?@7BEu6Ikq
z+#1`xfcIjFJFFB*TPP$yT}Fk~^Y2p;4oBP|QQc1OP5#+oxQa6Lp7fZ+%obXq46|Lu
z-*)3QY4}M(0cB2i$zyokkZ2ahIBmsly}Fr_@%42|i9UFp*1-LxsI?R^c-yc3Ej23X
zX75M2%@-<yW#iU;W7@8>jCgG#jLXEpXJh*13ya7w6rZ#lB(Re}S5jSkEjqgGs`BK|
zkC;OMJ_n<33|R_GN|dzz-^fQ;N6rOp^Xa-j{qt(j2Duk?6XOhBpz8;U6AWAY!|dhi
zi?VY<8DGG!?B{N?U<iubUc0lp!7kN5Q`gT`2L-XSe#Z-Pi+4Px`}X+W1ojrwaH32G
zKJ(g6sdJ(vFlM&I3vTW{47>v7ekQJNtCt|J5x6N}6MI=}ff+)eOy3h%)$tFravt)3
zP;hR$gLqI#7-~?Ti5?ZTUuM9`Qj|yiN*_<{{GzyNRP|H(U4Y~Es+k13d7`5Z#{M4s
zXw)xYiz0SvJDoF7$&E|H{s+N1RW%{}z7~o4n2EQr3b>5E)p(bd+9~1R<#$b6p69Oc
zpnvL=*E|^!xWh+YCdjvLKx(hlg9TJ)3OwSUUm*8WEmHV5w|muyBFu7f@2e7m_%-el
zut)bg4JJOm_w&dc^joWgpic#FE}b2TTN}A6NvHl+1*E5wcDgM^p%T(wu<9$B+(|YX
zG#nfm@|~goD2<yN?+)o-n4--5x;nr|6>eYs@lHSDMdhshol%}!$(|>-uhxS!CJDF=
zHs4u84=x;}xbt$AgkzRGGe%$=L+V!&HRC~{u#9Gda`lw|nU-#?U3MN05l*j|7u^g+
z0E5mYWy%ZJM|uZv8K`H<9Pzsq19nSY=PtQotj#6L%ki2edF!F!a{)Pm^`>_zZrs%N
zbq@k}4p=z78sSF~B|0ZMY`~5JSKS_!>4V0NvA`$S0ryB2Wgu<-i|}x58MA@-&{AAw
z{yvrm`qL9K)n#?{S6i&znb52|PF<atq_{Ro?0b$0(28yhY)IPhdmPE^c?z1p7+1k_
zl*MY_jQXgA2F+80YS|-;2O~2vRG){FaXQ7uf6U>3BcW}LFi#-4q@2a#X}C39>A&^c
z=&Vy~dvf3L`VWd)WcWym{}z6`nrJ;oswB8OXALe~R+CTA-7&JFBX8bLVLu_aOORh^
zh^kBXHYwu5_?$C0H)9v~yD`gg8nhG&E^*@y%{kXH_rfI#yQE|pP*t1Wpw2KK!u5X2
z$1`dwrl(~uf%8sYr3fA*hW{SE@<nsHP0{Zu$*%BQuF1WR4Apr-^B4u)W#oKqy%%_E
zZp3~GjwXJWxxCgkO6dG7Jl#v#3R?a3j9s*Z;BxN^8_clxhb0M+k#>@+_Uzcg|3TMo
zXWXKV#C!`&m+BX+=D#GQ;!Aj}zULy4X!T-mPh}-6!h(2u*A7THp5qyog!7V+1w~or
zH;+-R-Znb##72SX=B(2a?i?q)xRRB<1WTK|IK(n#leWX(z5pVi7ZwhB42CDE{V-;i
zjeTEd0n?^rd=}09#aQmhq{r0-_zH%sU=ZM5r8Ip1k#G}&cA{DwJopj~-1b8riIgM@
zH>y)+rAVDtp<TTws=7*rYkN*$O#|-<!6WI(TlcEQ*Z5h$zO|wEE`+Kx%|xy&X`Bl~
z)u+{5Q?vjs7*s{8wGqVTe)YlD$eJ#<1$BJg(yM*NKP9`Oc;ZjjH*{FnzH`^4Fc0K=
z^cE?Qx{fjbxy^ksmHKpuTwD?s2JO!C`iClR!42}wGXCS23UB77i|;i@YWD5<aa$Fs
zBm;4HB&<TFpQFlpuT9e_TTwHTpTJ!Aeh$+LZw^AGr}78Rtr7U@sFdMu3&*xCut*v%
z#0lImVqBa2`u_C-K39noI_i);@;FqG<7~5M+hg;$m$+)%{k5?jN0~KZ9~)l|iw8wc
zV!SdTpcol9kA;t>Bu&U`3V8JjZ}=X*<sXM$8Z7{7qM>TPm5kBxIu*<Hz?L<uc6Gbb
zeSh(*k&C4sr;?E$_p$FCvt>2zG7I_ToHSDp5&C*yCjH2nrhQ&8b>epcAyqnY+8|tA
zhPHb8dyc?9{G=QS&kNo)Cp}RlK1*XCAh$;fPIb!St+QHV=NJDF|0x?*>LB2MD<Go9
zzvV;pUXrPgQOD0)k4Y(Jbz(5Y`befvhHkob1Ea6m_x29?8UONwxm~#9LKL4lAyILB
zA+$${v1~DPFCQ0rQ}DiKs$;+v<75v{2OTr*cWcfegJbmy@4nqqHv50YVVuW)yf%~!
zv`9$sJGjiK-uhe0Jz{y*X$7LST;a_npo%iVJmqSCt=ukezR}T$TiM3<$4+D%8L5|9
zs|W^S`d!OtUE7~trMFs9?7Cfgo0q{v`=%{6R$vVAUrshPs=c%D&<1MTwvb}%>6(dv
zme~=pPgw5Ne;-THAf+E&8Zdw+|MTx-MFsef_r__{l`iywmx=?rU3EtVr>o@vH_MU0
zdom#R9nEBQX{@u@?U#g%jTclc!&Z@?>VAiQYdjdy=_^>#9vH&E9ZZu4rpLt#JLGTY
z2R~|Zv$jE<_c1TSWe>MC@P($Q4(vjX+KLlz<V3-~PV$3V=XS6r(f3Z?;#E9OywB%J
z7d}4M?ON%oXu+F!X`~M6({ZbGjHz0ppdi*`aDNs_>)4q?qJ^_ymgOclvcRw8r$5+8
z-K^XwZG*Kxr{@yMYazXZH;P)v!x7;gOFJ@C`E<$pLta&%1$)80FGTD0ppKBdQRvaC
z69+<==-yi>n4h|W#FT8y6@k|ft<QX+-+BJ!$cmG}6_HPXqb$mFQRD-Jt=S7u_jLg!
z?dQEZ(z_bJAHXp&jR-#DI}#K?hGxMcI3<V!n7AQNtLafad(s}Np2PKy+c#+N()w~Y
zw>S47a#VGzbEl-6`=;;Kpdx<WeV|RDgpqcSElk|jY|`opp=lmhA`2l3pzpFGVe|+D
zA*bW>Ev60>l{XPIg|&tV6(P%UyJ64svft2dl2<BcV#@x+ih&WUymSB5LwkXg?TANW
zN35wu39{f>jmXH$qtGgUCzJ6oPci77OUK-&-K=F7LHiB&182p1xqX#e1veWpd;=^O
znlGsFHBlD6DTKEP@(B-wk48`VfqVcR8>zZ&cW|7753^L)q4=`LNpmq+D7m7%jfFn`
zwE7oDYTIdrH$Q=v(|`6kF!g|BSz&82(l`rVx-c3wKlmsN&M~w%NfCns=Uz#)^#>(O
zK*wjATI5*nFky&`vb(leym&t+bu4wqBtr<9{&AV2OkSCedX>}9cVlV@BBnsD#ne>h
zkaWo=ia5}gN)9jaB$NmiX(KF1khK82TllhrgWIoi<$%d2(r>oMO}{Q{Ft`vs&ZwQ4
zWYy`1WSTzd<c!dhuRA(crdW9Tx-=9k#f4ql_oz){p3A_C<jywhPeNw1!RM=IPp(Q{
z5@vNlZR$?oqZW%L;<#bWGoRVe^~-YY7`yPbtvqNEaqp-<&6$o=wwqmv*F%02_@!Mt
zL~w>JStFaD?2O)z4O!*%9l&5N$!xf(Z4Go9-WHZf2bHTbpMTO9Q>t{+T}LO%h->n8
z>%>WHNAl97+)&<egSmlAmIaO%=!ozZsXdHW{#oztTm^WhJ@bXDk+KjoL)gWr429kx
ze)k#1TnEjO>a563zieb6I*V!yJqx<4{DG4AT2s<&JowM3ZZXIlimo`(Y0o5%8pVA4
z`rs=%9yY1=(omA7a#IR-zdVta<JQ%SG4BT59+&Wc^Va|VyoGiUPoXCGL??(Y&#^U`
zsD`(1R%zC)14I-(ru!9fSD9r>qMPrkpjrKoe5iJgi#OYn<Coz(98Ly>houjhCYwUK
zymYmoTfllpuq;x<!&TVp+EeO7ulh;Ehox*3rEiqZ7@dD;*l3zv5d|KASMk?DP|A&)
z1BqiS`Gu#VMjatZL5zNJ7gt0rOBkl867cTQm-{S<G15{Gyma0(z9>vYIl$WwWNIW?
zZe7o>2upkJJDM^u_r=J=>dLffMlv?_56e#q1c^2na=YjfQXA*rdM_fi=5mh2k!wKL
zVES(j@o|1bsA7A-xhbwVRd2YT|8)Dy-hVa~oW$Z$({n+O>t}(u0lwPz<PO~II)!<3
z5jEu5oZ{u8ER)qgO@x^Uu$p%#bR7?6yfoj*pwZKXJTGr1(VxmwOj{&c6Hk??ri{oT
z%mtLDq_+=a_hmc<HU+QWZQI5W@7KGvntmzrOcg#)nA3hAUpzxXw>)`NOv@5_OM_-Z
zNacLEUEalMzVd3*=*s01_zPRi3Ebb3m}e;6@^)uH{v48|J*JoMsV$KeIZ)vFa9{e%
zGY5c7_wK1N`IM4-b(EDDc2?>h*W?WIppWyOyLP^uOE+%30UM*`Uj=jE`WRy_2>c`H
zz}YD^AHj~gm3oi9kCGOKU-fZ#Yt46zxrFR!#291U{f6Of8;a#sN-qn;6V~Jd?ruNn
zlOBj>D;6(~klxxeITa+j0;TBrV+V4N>Wkt<;vqDx5ko0YbMo8M2>3wndFXy?tXmY>
z?TOi9%VNOqG5)bhSQ5;^WSpbB=||Z;eIe#jiYE%Hj&DKUc`zv+g4C=4h2Rr~4z;el
zuFt_>`t!)ewr>b_#lxH};MoInwB`<G_m+I|{=~IGqbsNc>%rDrpUvf1Ppv%{k>k08
z(*$ZB_}t`zFw;)Bs(Yt3<X-E4HZ{E3oqBKC9B?M32k!rDKAGFAg3+7WCW#}UCrDk$
zTmUDR<4fCCk%9{LE$-VJ9@|J{(J6L=@6sYKOfTIg1~rG{maiJwi&Ds?b1`Q7_!MLk
z3qMb17(||UUw_rrCS`6s#=alH7FU8DIqFCEPAyvjN&M%Mt%(?Ze`4V~P=`ZqZ9Azw
zgT167v&_U}65&+#xbE9R0+k!&)X^GPFJ&(3e;L!I>LJB&?!rxecXG^SrojDn5iz)&
zXtfSFcHxCIHX;zR7VvXXVxVgG?7{nL@=M0P_7k~n<rF=0bG-|U^wBqW-40E5&T%#Q
zmM~~wWO739SxapQQ+y77h`7Sn#M&*+Tp{X7^tGR?#Su6PJ|A3GiI8}4tt%IcHza;P
zFIhh7{z(RY?Y-a6K-zeD+H~1$kikY0A1X&Y?YOxJiu|Q0V`?Rb{qL6?Y;EwH4q<9j
z@EyXD@4oMwR{L=dMQljS)w7tDs=w=4oCm%kBVCs>LOBP1AL&cjdgBeH$L75v?nPL6
ztWK7_1?@c60_ePJeYHDL-Nf@Wy<l0f%G*@HTjL{-vqldxtX`tdg4=(Hpp*G-?OvYk
zJu5Ak5V(ordKA5Dx$}TV(7<sa@*i3R`MfM!p3{5@{7%`&QOw=1@A*ZCXR^KxW)!<A
zPkESLF#qV+o3}rduCf2-aZie};MCc&roH)g(p5QwYi&PlGJUJGQi-omf{O&tU`LV&
zX@4FCHWs@xY#*uaC9&o0CbL#CK*A@?@MuQmK3>z@)qkn`K1jFH6v^#FpO--jws>rI
zBjXn<fpoL|xr;u$m9Sey@oPC!&-DRlT>inVRh+t(M(1~Tx}U__-vj;uW?8_n^NI;#
zg33t~@Xe>yxUoMsyHa7YDDzD$6<@hji%~QeLMP31KOTN4k?ty)zjXuo|9DQdBlWAo
z7p@wKDa(Gum%})}fEi1?Pkb@@P!WWatISP<U!UA3O<&=rD1!UR+kZ;gAV~E#4<0TK
z-=!sbNCqO0A3OB8yIf}EP-EP3(X?fHYbdk>J@!=gs^h&})K4~mH*M&Xf-I==y{OIL
z!z!NncxuTk!|s&a%CftuH>xgibxq~J9tu7}F-;u1v5|C8VxtV^`F?z5<dMNcdR#S(
zUCNI<`H;+!ciSfpJ}u>RpELCpTL2t{^o$k5R*1t<&&@>_H@4;+Mt2!4F}=?>LHb1c
zZSjl25t1a>IEyp#bF`WS!g@SjqgJ~OXx%<FIp@@!{wEa4rjQ%=rH(Q$lbO?NnwrXj
zV~<m^K0o660t(KdySfj8(v@OHvf!@IEczYicctYT`xbwgZhwWmLkW1PU#ZMiiQKrm
zz|Mu|c$rD|H>_7CAKMFQv%SzgSCneC<qptue8S$g9|5I|6}}p5*<Ihad9{T9c-z*9
zFsP!?JxER8rGM*x_j&p4#ZFs)3N(ts{#%a&JwxMO9eyZOQ|hIycz1u38=2lbt=%Sg
z#`DeMm?3nAc>M@&{rG;ApfGT%LR+AME;FcAei5q$!<E9&dmt!mi8L&en5#B^=5xEr
z`UiqfM!~`)csr^p`G(AHBuXNzB|rprr%y~&Sn(2{Gr}d-MhKjx!LK?}<LrAPsD+4&
zhU!rBxWi*C;{#f6Nmni3dUo9LRF?>R)b!i8sEqbcOGV<d98Ugh5nRvl#Ps%3{?)-w
zdv;qrf}a^-+h|C?X(2qK;p~{&58~*Ds;+PN(5d}9#te=pJP~I53fEWc0lPt$!K#ze
z)!fv<`idsxEZi}-Y-N5PhV;Xx`I`gs_w2G2l=W<Z&s@gVg0fI64E&{R0>5|XXKBr+
zI}q34?4h*AmG=afcNAZ58r|Q%5Q0p~-YaqT=NdrwSY=~l83k5}q?!Ca+UO)N8=t}2
zfbZiO>U6~^MB^FnIinCX!B2k59Qimj<*W#_k0;lkP%W<sUu_#}CjCR8ioGGR5o&q=
z3QTUIJusxJ&?w`Y0p2@S7#Jl`i$W2NG&jwo7V98-pZ(G~)xXx|5Z)wqOYDZY!x%?u
zaJto3l6laI_rK9f)H-r~`EGK+b#)<DoYl+~=5PzR>OF~?Sy+CCQE{q~y4lE5A^c`f
zhZdnWa_!BNI_`o~AsU?9!c`AY|HT_*5^-TY?0Y98d7dE=VoLoYXdq(MnQ}9(!@N)t
z=JP$k+%H9)Hd&0tFS1@ySf;AK*oPGET@k*h0D_7x?W*$je@upbjM9PS2}##itFON9
z!hGqrCS*3DwsD}Ur7riH%5Q%q9bY)?rXhpXoPx7yw2S1J^%RGK%~gVl68X6efYM-S
zcgzPFWue7CjfCdc)(McKDMy-r$-+uXYq89S8bqhU`!H&N(l3~Z8KrQ45yf*G8kMa{
z99y1<IuyviP7|n|Fe+9VxrS9KtwWK%cbLpDa}h=F#|K&VWVKC4voQ30N{S{QM|}vM
ze>v;EHixT5W-k`8dQHAd<0R?Z@<Io{H)whb<1uo!rZOALLZ`$(RVL>Q6GM5a@aulu
zE!o34e6?=kKyg<1<lYp|Jvy!AL(AYZ@nwH|vp}yV(@Y&c&})Ou#+HE5j^si{2k~>c
zpASos<%G&}4#fAaR^wTLmS-?j1*8_KrR=<0)_K9bx+-wc0<I6=dOtznYX^Olq5PTJ
zDtqN)?cp+z^cm%tQ}CsvN_06PXcA^_;Cb(rnr4u22PLSCfvPp_Hvn&B{RX<@)z1f?
z&P&og^!=QSP{iqJwXlZsWcCi`BugGBTInQsC|uPKern#|Abqx-09{mIVwtG@4u)<Q
zn$h8*w3%lrr>u4*L64}rt0c3{Jln=`FJXFP?8>V1SWQ?m8c7ASiag0Aq_+T?h^3K)
z|2++6<VwKbjoqJST!7o==4?V_5ug}sZTK<>A$GbML+1(`?`@30(!@#cYZs+-TI=@e
zsK-#Q=keMSuNlH*d414zrT1;$iQ5`*kDVpA^y2&HUtg$Me%vPfp#BD#89r?5#BCe+
zpFdYxpr2FhyhWJK)Q=OsJH2eA>Ax;Bjwq=0XMX<Pb%N$s+Cp^97q;u$orZ$?L-S6#
z<{qHjnblEqNm?zVAY*63iR+d>q@erTEX^$fHwtH*7E*Fk=G>Fp_8ZJr&l_JD{saZk
z=D^JgUKcQ(PRQL4uI*Ss`qU_RE`;yAgf8_NYxyB|-|#~TY8J2J!aX2K5q#DO4!{Yu
z(LVF@<VU;0sgjJTl0n8~0U2fsfvVN(SCLjLXg642*ac3#6oh{%{rKmcMp0`Lxai<m
zyMN4>E^zL7P<fRK5y#Mh5O)WoWB{LJmC>D_h;@aP_fVe+bU!=0Oli<J>G7j2=tRZ9
zKe`G-o$u3l1>N`xurp{#mHz<FrTo;I)(dAt?K96%m^-CxQ0h}8f87fS+yOXx?#-Ff
zPc{6yukEfm{`<*3wn3X=)y2(Zcm=(#m2r#omt2dO2NSO%ZXZdl&UGPQp95#GnvxVX
z2ddWp`b#pw%~gd+<urX$aJ6jFVkJzEWA2>%S;-vOc)W}Rcc@Is0dt@V3mjfCgXOEH
zxo$$ZJ%ueiP6rB^$k@$JCiuB?!Q$OP4-8s^OHsatYtP}FCtm}^$h0l$5Mb?Dbp^Y2
ziP>>12-s88iX!)Yh{qy$ycm{lVi7slUN}1C6&Y%OR2Ufr@Du_Tf*m_q1)kAdlse-w
z!E-&da~B)l`hwy8o)L{_TXHIYACQ2PTAZCR#s-?4s`e2sx)VujBt&oIPaNK;+7L%7
zzI)x_7)e5MbDLmIvIz8gaW)|}6Z8IE%dzYsImYo|_6<g$@2VSERa<_BbmXV<`4V{&
zupG1cBvx1I>#q0v#{)ZM=s#LEu5h$_yh7R2S@PNQvHH>7RZkU<s@S2rSqjZq+nHAy
z@!~^jsF(q2!zeGp?Jf*Cd%*?;8hfq(A(W|Xsdtr=&*V`G{F<hXRf})3b|im-o;$v+
z4Pr-%#gdFy7=T%L{~octt;*n2(86%pCC#&KlPc6LXVv!R@KaL`oi=h6`lNCbNr;r3
zy@>ABwfL#qRhM?239;T>s@VJ*AWz<t!kHaPSlnL@Ti&$EJ<)VH<NJ1$`FJK%L9>K)
zYa#Tr?#;vbu_g~q&o$6FO`1jQPmOMqp|{&~n^G5(<eWOJ#I!{5f)T;#UW~0P#!p<q
z8hm>YvvVRpaFZfU-&vm92Dr{~BI>ddbK-Q<Qr0`HTSyMwP4A_V;e%jl0Q98s80>(^
zFOPnhAv5DGSDMwK-6(s>lemvk`!G84bPQ$xk~(h~XL&wnUg2tUrM?fU883n^o{Bi`
zdDrgZSVX(c@q$Vt(sjPvc>0$)%$n{@GP7$8a$U=*H0%E3ab_qsr`dRsknYy`)V#B0
zSLcABL-&L!LKi@6da>!%ElZVoOqI!Z`DM~Te{=T1KSWf`cx34!|0fT_>W2%h&wL@Z
z@0x{e(WGoRA?sn`Q?Hv#E#5^i?qWqpnBUK=Wy-=-Qr=@?z1FIjglTEXd=J7G<GdOi
zq`_;~Ty0cFRVzTg^0AknO5cT?vMzfRvr?4Z%i-s<>^GtEcu3SPZ(2U}8WfGidJ3G!
zCJTNx_oeO@h&<v6)?%Fg)I!_j*)VKwV7_D*Suy=Y**WaxUbW8@HUd)nk+T({Rpr{h
zWNCVZ_K}z;>^9Lh2t(&Nqc+{W_)x>PgCsk+&i}pn{%q)Xc@a3ieD(6A)k0U^Rmx*S
zpPWL^`k0-vjsa%}5%(?0Rq%4(U9+30=6va!pL4~5K20!j<N|sTA+XxzpFz7dW0`vk
zQ#AZC`ACp()$WEa0epxcW9y+OgCFaKKzq4a$sK_LdWRgz-AEW{lEZ;z7G1>a$EV;r
z@og;Q%N!0<i4&j4Vz@-hutg#FkZQIh{AM+K71V%>JBzr{+mN$Qu_yi@v5{y?kuQf{
zT5%z_O&FhK4ESe?;7_$qIf{as%#KBHX5u2Pd420gL0oMzCJ~Zh^a$Eb73)LYN<M!g
z*3Y7}?z6;$o)%3q4wtNj_Nu4PYhQ5G7dyYQ%2RI<*pB>?u8urXGR_a>PKPLVIjp2a
zC&VTaUpA+Q!1Y)Qe}U7UDwSoc7C@%($%WG_s+!^y3so1w@>RF6`3K08#&nbA(KfSH
z6oK*XA|>;i?u9u}EDAtdBG%$fLT&S`GhdC3A7vijNBb&hdo`ZPZ%Z6Agdj0!KQ9z>
z9P7zM3#Ke|rT!;YRjU4>qlacH^-_5gICs7p%aD?U{&RVT4>Xdl8}+`4yFPCPYUZF=
zGoYs`0*NBfFlV>z0}YoJ!GHbPTM9m*)WnZKPq>JH)?l0{*z5(TKG;dilOUdaMi!M*
z>E4emr}*_25@id3wwxPh0dSOK*E#%|==Ohj9X4wZ5UHxL!|=2k9^y`h{u8oyy3M>;
zy&n;n&TS3mUgfXUcF9xwVKDzf6YC39apQ_n2Hhsg5M}oqj!Dk9G2Px~h+hcCk>YPF
zYRT>aT+^&)`ndUFk%4SAS!I#5xd{I9D)v3}{TDA}nsW#Lx4(+_O+)++uDY4ogo>t$
znFbdAz~EQ7Yk&us*Kd5x?iluB##5qGi5pxU+w8++x(~6?Qh5ZYi_#c`e$!6Z9Ucfw
zM>u|0#0wLPY_+Sxc*5v1xhMs`qqkk4uwD@(obRm-%nRb8TbSBYzuQ(q=a{b$a{uW<
z`M1&B(VaL2yQkz|Wzx-`|N5I00(Cv*tl;yt^0CsW2fS)O9sChFh-=)z(Nl<vGDh^A
zD8kIsA*h)xh3(C@%fJ#_&V~wtV)NFRy`HMMiv@Y<kQ%Im)j2VZsaShP0o7ft`!r~K
z5w}0d!Mh%}zU`&7=8Iuzp9UJ{(|RYfsGUi&xLg*CtX0VRWv{&iBqVUVZ%u@XIK28w
zV#XZme>WDp2cGLsZ#N+FcSK+{PgwrX)H(0a@HEd8JY^#F+pgrzKO|sB!JUA}2ZTEb
z|Jv3bQXouD_hE&u3|Gls#Gm&Xr~xj#RHrFx&qM?RRE+}HW-G?kR^F>s<P?cWX&)kH
zL$h1M)e<Sg^3ArL)W+eA`98#GhA13AJXE2KzweoH7J=y_*!GN1jJX5B$GMD*t-C>z
zYrES2Ft_c|yz33$cOD)Z_6t~4INe~FEoAD)%eB`*Zo+c!SFNQ*a^B`5^%XmyD($iN
z@SFl!vghY_O=TGHEZsKyj(R;IIW&bk#x}9SyuQ+eORHq?uM3wJnSGLl?2zO;ShmY~
z1CSAtm<@5P^fsw2(KCd=kv?AO$=5G7Qv_uNWoF>XM?*hNu2#=dX?QXE%2yy`cGw*X
ziK!a@2u0|3J27uuT<n3gFy~FVa8+{Wu0hM)&|vC1sM}s|Sg-MsH`L^t<#rAYEVi;}
zK5`J3u6e5UpP{`-9I3z`{weioq28~#Wo9U`Nn4?#FA~c;@(}Z%5wXR5)~K2ZxxLsx
z3_3N@g>8%^+XSh3%E*qRl&bf;S@f6uA08{E@$Q52@OmiqRk@6-ngo76_FuC0ty`xb
zbT^ci+-!eL4svxPwU4>oYDA4!rI*R{uX^@hU+ASxQd{(ATZERu%B3suf!E-^zZ~2*
zE&RXa-!&v0-4VaOQ}yk<^Y<gV^&&ZKiYaJSl?qkzpP7A-Mq%fFH$VyKD@m<=rZ0Tl
zVu({?l6~gKc)7O!GK@lGsaf-WjdExxYJg`BWH=cnaP+mcyS1ZP(1-qeeCYHA7#ZzY
zD!1V8VC*F)o{fbLZ_62*YAQ)@qoHj)?N!7KFM74pV(tU!z#CeBSBt{Z{fCT?h4K<|
z=AB%B1if)6Y~5MYh&hmLcL-WCB;ml$AYQ_G^7Nx3e!ZqJcrTyXUt|;ci#A~H<CnsB
z%uGU#j2qmTnVUEqKhBBE8EC1C!&K1|>GsgBp%*KQxDoLu-{XPq{fhB|t5C$>HuKYN
z_LB88uR#b<N8eTy^p7%J{+VNDRGLeh;ZrF%G53qg7=U#DIxBO>FqdH~y=!taL#YV)
zC!x{NJmg>hSrs&ctF!*j;{S$!J19d{=fJP;{L{{J^Z)MCT;Kl2)Tl&yVa(8zb9>>C
z%gm>Xg7h|@BW+EuHa%Q3E%-7u>(*2BVZy+!C4AkQ|KZLXn)M1Aif0!0%LVtL)7(lf
z>v+*q){**rO$oG0j?$=pE#a#s$!!^#?EZTXxo5N8HPi7Z6XhxfvLz3UmuU-gjI#tJ
za}!AHqwHE{@%NCuh`RJvi8JuIxmoo#zT@AmcUnh*G2PPYa&=*Ne-<6Y^JHYaZL0T)
zI##@3hT<DQ!ZV}S;2bsgfz&M*OE;e+G_fy6(Cpfm`1}ki4<M8b5Ht%KfU`JXZts)1
zzBdIot)pj#LTP?WqZP|Ch)QnR+FCNqiYQ0IC&ZtnUeRyn@==AHhZyUk0R%W)81bIj
zfAnR(iap(V3CUz(j*>sGS)N<2yJ}88WBN)(AbVjz1NqL3<U%G*-KU|awGqsm8I}+R
z71FC8Q&Tj#7e&<K*}<m7&Ksqn!O=+6F{I0)SL9M<`Xh#Cmgz7UZTWM6V)npDMpRb9
z*ps|q<0pG_O?Zn<Pf4k$|3`!vv37&R;uE0)F8_2)$B5^HSnp%)RCE&1iO@#tJNbS?
zf3w)Q!W|Qe$ZMvwY0F@vijf7{-m@6zT@03o-Ow14dN9t`H|rda>~;%{4LeJ=E|x;9
zya)0g?SVtg5XJOpN?IGEwSmMbcvk7oyh?pDBQckO^Y&%%gl;I)FX+5GF*;fJ`ByoW
z-SmoKzaUTK&5X4CL$Xr+;p3<sVixDdSi|*^m9brA`JqR?-4z5kyX^kYcl`eoi%5i3
zC_h(ZE3Tj`oZr$%*&6e&x`AhAV@HeMx^7kvP@t0Czs;<v4obS@57bsRDFo_lu$Ylx
zcdkXwRygfyBB87P=05_g>Wo^*I?ocqp<rgq?3G_$cPn4D*Yms9-(e(yxl>>&=*Tht
ztbxS)!J2FF7AD3yo>BF29)He_=)2|jZ!?CX+NSS(7%rW-cQBYaqXz_}Ven(A|2UT!
zrhfjv)L`5Kd!QM&Mzw`&Z<T5`+$i;9%q_M3{Uuo$e4~K3OyloMQ8AW((bEKSM9_w}
z$Lc)cZK8?qeVPA=XPUy~YhMZc_f~YTsxg#fXmkCqvO{NeceqAz88N+iI;^l?{vFbX
zwWwK`*~wOn>~47}EW-UZZANM#Pv~k=&%BTTlX$~5yrVJ`*|mUAOi|y6>cf*eQQE;e
z6LP2jNYM+kX9OVNw-v$LsoYtQ^|oEAbZCRcmjCb+Cv%(?sx$4UxrNzb_1~P@@Pv9S
z_p%=0_wOtJa@V$(qi!Yz=BQ7{b*<Ov$S6W~Hd>skz5*)gYTPy%oFRMezZq%KXTBsk
zGv!4M0;Sm%`-g$e_xG16VUIv%qx{S^OTgBx5;%8}FCmL{Yd)MgYR!-TjJng|7O(A!
zh}i$~9*6V%ZNk_^^ksh}v-{4>QNo_${-1$1Wwa6%H2gnPc#?)9rsjay_FvZ1vwSwP
z$v<uFpTk;Ji#FJr)uXmn0{>L|o#6gE(6=$No?-Pxr5P!8XN(+F^lbJ9=usPcst93O
zwS+#!h)tC5^1p)KalT1rW1GYnzIcX>l?vuvcO}uE%L18gSioalLgF~##c}q`LTBtg
zy{&jr@v~stC6mc=GZKjvaVnJLw(E}C776^pRgBqpv`W-t<~xRn_2?Au7+SaPEMqEp
zJ=SlB>S(JT-y33~O4%8c#9%g<I7zp5n3E*%3s--!`nWpl=rZHn&Xzr2|Ex=`4fH#5
z1IHJYu2KY5?S~WkRb}!(kKvS+?uL<EVepd)ip>;(Ql)eOgUt4jY27?wdK#~>p>M`=
z%q3@(=}t#eK+8jX-8u3q2CK@YKEAJSRtxlJXJ)=e2z}bo+m+nAB^j)mKSvmUZsxQ9
z^TZA!ud*C^wqDG=e@rl(G5qChE2G+A-@oVC=&$lZGSWY*s`l71((Pkse>9P8DLYU9
z+4019-`;Z77csz|5yyYIz^=V#J1_2&VrK5lHvTcn8cx!G4j53}A$!{&2GWVf@|^xl
z!r26e&cYO-4{33v$=%6b<E+8rUJdwPgyb>QT0rB!*<>Z19#)b9H4FSUY?RsmA8wMQ
zYHjnS!x7Pb)*Bg)(%*OEG2q!E?H)A!Ep-lf)Be8XWHwRnEAkEUo_8s67XKINXUIbh
z?w?~tQKxMuhIl4Onf;N0WA{tXUa0wFZR3FkJ!Py)RMC~ZSP1v4P8}MUj{*=VzPIW%
z0_S<8RG@}CEA4pLey#A7ON1<Fab?`YW6wmGxd@3zc+cpLR+)2GYu~EAXcrHDuO|Ky
zdK{UPCMDSX0#8aM**RCKcU7_G&}=7GM0-|;$W@Zmo0EF5YL*b*bw*DDKPEe!ipoC{
zXRp>i+br+O=Zow$SA-I=3kZu_DBpEvRaMEj-x4aBy{#N<Dygxyd;Ttb1<+MyUgsnO
zy-!X#76w^fpM^^ETqv!#d$D#m$<ANY3iPTFv<q1%lp#%S`SbVH((X>Awnp(#63;Nm
zwtZHX5Jb&QR;&#RJ?Pu3R?vy0suJKcF2y@!m8I_hzx+QM8AUI8wpt@dE;5n|sed@6
zDc%-e1^dX5B9bTemj~3P;qESM=-^pYXe-n?V}ShCZ5nSec9^ke$?Ry||K_IXOOU>j
zC4s928TSN4|B+L()Jb;lO<ymf+i2p#53p?1m3c-|eWX&MsFpFjian6+|4kpZA_Hee
zZy&HiO=5bP1{jdtRsRZ0Yh+6cW3A^;qV%o0zjS9P7|8Bq-gJ26z)^&(zudE7IYo=i
z?jj`c|9btRNeUaY>n76vNO5HFefFJNxN6J18Qp|IIdYJy%Gk4E-gK%Yn=yQ}Dm(j)
zj>slA<oL{@%Hb4F5aB`Yu`O1Y(9S|yasJF&DpBYa(<lYEbE%@c<ALjFQHHO@XJ@ZH
zEPA5|`9Xd0`GgTg597QYAUMKRx0J4pyTc*-QKXXF56zDR>K<4_QEcI>H9(yX`f5#K
z&YX30=Kj!ZLVK>tZsHL1%|?eoj@+J|cH4y26PF;Ph}4NeY%C``sfc>Q=UrE1#aT)B
z+RokV?4%&Yo;hC2e=F=EI~UA-(3PLkv?0`iNS{?mY|jb`)BD#2JB-}cCL|4!dE124
z*pqTF(lu=bmrfzZT;B(erQOL!+DCZ4J1YtpWcSf$VMhXyz;gV#o7`}vh+mlV4f*kT
z$A8L{dS)vqbFLxp^04YxfdpQ#p>WkruKH5k)WxiI`nOPVF=JYM?h9eR&7EUyPc9sq
zk+cP@VM$JaAJ)$Z3!ND59OzhI9+lDnpVl=Cn(8icQ-wLMj<d4`V{K6tjC~%7jA<#?
z=ATV*#BWl2>cG+aj~8C@yl)vAs=#5yu2fLPepfmqW5{o}{QEeC^X((+#jRJ|?xCTk
z{(YC5-dC{n6Fv--yPYX(S+Q~RzVmg0A&)@My@RBn;g9e4O5#nd1%GBo%!jc`V*06N
zQP3q`<uMyZaZ%WUfIItxW$Qf8=1vZs=B=R*HyuG&mSwUti(~zSB?fVZ36~~#37x5m
zULhq!RBp$Qs2_Z#_HBVtk!}oP%<uOP-;d;QeiUnY+-y_4W0=wM^w-%gOF;;hD(D-U
z_;^}Erdlp<ZEuxv6N6Z(D15v}L1jP6m&}qu+k(O$_rWh{{UoR5?zCpZBi@K@=XY*w
z+3LBj2giRl?IwP|ve)Oex7mFfsv0VrcIzzpd93zwbX0!|vA>Au&nf!${c|X(&gP%8
z&Bg6eUZV-tb5L}_>)-vV7l=Z1-NpB!Ew1lbCp&(9zbm0Hb;90TlK;zg3L8)5zaR9g
z?jgd%hC4r{WTjYj$>ct${p!0v6-+VjWloA{pgA*Kl!>Z*m#&`Na&4B?C{cC1v!Ww4
z-B?9wl$8}z#hM=Y5wogOV{(KmwTm3({Wb{=bn42g4F&bKaVdDg^~Dl+6LGE_@sATQ
zBc`gtZx0=t@bF?rt&|VLs%4C(7dDM=)!219b|@p$B5Qb0VM0&yE5<l2paM_D3zFWU
zy<mNs**ydle|cWWnqy@}yrw}%YvziZo^LEi#_Da`-nA_i1WY8x{Cs^<KF%#Mf>U@~
zc%;6v_2$1Tg;JnxU%92Sv<D{Q+`?m1@!IT|^SA#wyl-acGU1tRzMPK|dXh6t;-`m&
z!$&`=Pd~TsNS+w47oV7P>&h{A8o4`{(B|X{eoGUU{9mI&99?41r&?PLwMPloBdQak
z&N*I(S)oGmGn^(lGuL|uS*~JxN|e3|isd;skfv(7nZ}<3O>)YdCo@a&$M63?kLXNj
z;fan9aX9v0tM<@N#PYNMHH;gcpi`;yuNj<ocxKKAA<ucqY;O}JFP)dvtwq6>htApO
zV=&I1htA4KdzbHdxN@;D#Fp<l?1&oo#g;dwE5ef5u?6->nxhBr{C_=|Nl1SS*mrH*
T?I8-w0<2rJ+3JCX`^o<YL2S8$
literal 0
HcmV?d00001
diff --git a/public/07-basic_statistics_files/figure-html/kd_test-1.png b/public/07-basic_statistics_files/figure-html/kd_test-1.png
new file mode 100644
index 0000000000000000000000000000000000000000..8e05d61307549f7121374353c75bf3eef9cf719c
GIT binary patch
literal 15737
zcmeHucUTkKx9Chl6G1=_6e$r91O!AvFUe655h*G~iqb<Bq)Q3Jjvx>LsZu;5AXNxO
zTCmZiO7BtWUAiGa-bBv%-S)kI-gm!S-n~g?C$rmHd-b*V<cXoaHY+nPGXMarIu|vs
z0stKj0O0SL;80EAlhtql01p~oHqwG_0YC)+Fo22*paPY60D}QAP+1PuLRGYC+6$wi
zf>*&{R4`Cku7by_;D<4^VNewSwLuLS6+Eq-_JV$tWAJzk9x8`1<>i=isHEam06a7c
z2EhOB3N_QF`Td2*m*ern`0{dmIaE^d!^8MtYB>fd$EcL!p$`UXhT3Q|{r)O1ABNuL
z!%#^rr&7DSyNB^A!+6YaIrPEPTA(&)j^AIy!&ImjR18z8Q~-eHrIzEV!_cSvcO5hV
zt>vwYN)bei1Gg`lc>@6dW7-8qPp&us00Pj_{KM$Zi^b6(J5ICY#FfK|k@AVieEy3K
zsW#jLFXgIZG2F84S#9TvhD2Sr9$aw~#!?MpRD9KqH{vtBMQXEsc6RnadmZ26xtB|q
zxB>QyhXd(=5i2?-^qK$Bms44aXH3uy_4UQfHGE10NmYG!Gd-%cQ$Pbdt&r%ZroG%B
zw0gSuX%vyV@JmCz+rHM%WsH2gw%ED$O?RA9O1ip&2X!Jeq)cFB715vc>j{Nr$eYfo
zOai?j_R8F37v@7&Q}zoA<bPx;4PRx$dm5f}irkt_&C-Jz)y?X|jdmXiav&U_5p(0@
zZ_}$Un?=DYYzp!AF3^TT5`Hes&-KSC95jrHE3+VL=w>ye(3>esXVJaeZr&qIco?kI
z{78m`;)YnC7<w?<Z4qcAmFE3)+J)WX&G6bbA$G(#Lr{0Ks#y%xzekEA(9BGoF21-Z
z)#wEcH2F*4%w$nS{pjGk>crEN0vWba%PPa-C3~*@DOs$rQr&K^OVg2$5Bvs`n&LHT
zH+1v-?H{F<ZM<-zda+P3!!jWC<%y-Y^8gj_?U&r|D3H;;-JN*r2>%<p8H+q6^1J+6
zL-)fO!D{`%vY@%gDY~48Kta6BdfjnT-TP#FjbC<>Xj6~23lZ3iV3X4*Q;+V1sI-tm
zLAOE;2b4in>jjg>{M5=PwQomK9ggv-2bf8#cLyidWsa|&!M?3!@zpL-KP`ziSx8>?
zCJ(z&7IK19`j8vZ=POxm5-(DNuSP!L#|0<!&$p)(rXBY5^Dnb<V#}_a*<#F5C5e%*
zO%Jk#i??L0=8*Gd^@BHB9~Ti7;64189zcX5-}^PER~DDpvGA%6*>(Gxpg77YxHQ@$
zFP+bnZ3wI?@IQO7u|l-q)M?DC<-PSccgAFT%Wcj|=qEJu?6FN!6cbK3i%2a3lTuBh
zgCXgG5lC#x)<+t0L>3e8iEp*?UHYJTke`1@LMl%n-NnS^09;7%p=nd$vnAOjsw)xO
zNsQ@>z=88m*g<nCs~<NFa_hTy7Vnr#^IoXE*0eq2D7d)X(AGE%mhen3VbDbSK7zh9
zD>CRbNd+l9eEreqXQicZ``(Vg^d$9<WV@@l&z?;oUbnk~%d~NQ>7#j$NkO>GmyV!H
zt{`?@a3hS1Q0n+&(ct}zr#g3Dh{ZDmI`0UWd?e!B-iP2@j5%0<ay=MH5xLZ2Ogj8F
zIKe>p#$@Bj-hcqK&;SvsRKQsKasHNb<n2CIar6%*Bv0<tMOC^c8^43s1_EDt<35u$
zbmHIcdCU+?f|BcPmJNk8aVC<mxLwcdJCqL{ePc<%FZq)6HX;@(g@al?=g(P1%{wY?
z7EGxIb{9~8_<ZWqUu>5~=x$#1F7YBVlgvK1!TZkk$i*z)l~>rxec8Vpi<-6Ssv8}&
zb2GR`RpLU)3S&2FZYtCRQh^<CuNR|bM6++@oaQf<wQy;>Rf*KsiJSKgCaqU1ZYrz{
zUQaka{<wCZ*peMH*m9@DN$+HAR=&c(<A_zZfX!!w=#1f$#qp99IcffrW`_~;ueDC(
zDZbefH8Yqy*1Y-Ngx<+T%VzZ_MKD5r`W)_oXQH{ch>V_sQX`<;zGO~1eVZAtMiTSA
z5?*KFajWP>x!71T>!c)G(Bs1=AXVnb*co3@p*HbVB(%FkU`()I7GJ*)i7K;f%b&3~
za4v9>v4AIslE2S%26{`Pdq4J!`OHPx2U)w)JM|1c9A(9yIn<|c!;WtRHlb22Sxb0-
zi}m7*<;@TG+8Zj5WVC-)T#ccQzx6-GA%xC*4oXC=VW`2kuwy9)-HCL@K|BlB9#=t<
zRJ<Tw&_O8ydR4%{(O*x>W_$R5FD++8apfl^dh_rw4N%+3S^?Jzpt5}_ZI+PsBS^qd
z6<u#}-BrEUG28#gapC9D-G4I}r8$^RE;rqN@+P6ZZ@NMy&Ly;b0`T=mmuon=(m91}
z7(~xI%I~Et=2tQa4+;$A0)wyIQr)@_;E{*g3R(l>-_bYu`k4kg-ZjM~uZ^aqZ-$k^
zdy;-ly;ZG?pV}89lxDre7ZK{`QkYSwOKzwFx07d?HdCjkf9GzawMWOz9!A|cpqIm0
zs{G?c^F9^k@?V=H0;8)@{HcJ>cqgyR25&T=+`2?`E~L)#Wh@0R)8*W$CIZI71AKnt
z%A+qe!+-)4Y*<NjBPo3%{e?W-D5QJ`)}zigGu2$Z+8y{+?WzT1&dvC8_KeK{bObp`
zedNaneO#ueArt;gH6?3M72Op~3W2okubD8LjW5T7-ua|hM*<s#-%6vN*|)x5l}i6%
zH2!KCwO3ZgmZOMvPq9{aJSWqt1&huz^BhR4F$N_<g*@&J2C1njd@x~fTGKn@Nh~@}
z<88xG;Bn92taT6+B3PS<eNPJQ0b~5!O`>I3JLg)YEL438geEDLgilu%Q#-ppk`!a&
z%Zlh*EU862I=isP!1MEX|8qr$@be2xNgA%)O7s`gmggCA<W|&GUrz4hO`kJldp5mL
z1+5!>P=?L0L%Xhz$g9EDWwUmp?*P8h=8mglNg3z%+(Ny_n1!5Z=)Lne-o_WII<v|)
zE~B4*w!lhLKmA+{wo*i=KJl1%t-&J0cJkbBf7z={Y>ZekbE+5X9dadHz%8V<62AJ&
zpnT)+P3g!h_8zF&>`U4Bx@7e$=t5T)bEno-)SJNc2Fdwj<6H>JVY+#)kNq333dMw^
zQ-5pu;fypg(GNGo>EU6|!x=iD8pp(u(K|PpKXSmxN^83+@LWe3hy?@J13Wie1D56q
zMG<5fJIZX?&auH19v+mv;QEfRi~E((t(O9CP96;HxM<GXSX?wFx>zqy3DQuBZoQea
zbCXPdzu*kH;GHV?yvqaIo-yP8Qv;yHn9oLB{vkt1-`NZuiADSne>#Su`@lJt->X$Y
z*Xw62z#Y;*4iVcsRSue57s_=M^e<HA(s0CXJy^0FzGJB_A-$t6>^y7PW`=r0we8vD
zo8cQU3zW^p+I(D9yrF(F58k7AFrGd~jtJ2ch0YV(d%IO}oMuM&Gk$!E!FusdcN)BA
z(<L3gqSd%V2=G5RYuC4D^0Z-WXyi&j>Ou+7EbPny^BKXWo1Bd<2r$|S(!%M_^CS!h
z_2ISa3LNuxv+}a-A?a*|WdqG?*iqmBr$_qrjT_`gtG|_w;OE;z!C6ok3W}C;myo^H
znsHjqW7)*}Cd>XI&7^}SqZY2~xx}Y#W;n<Z`M^X%Wd;^4oZa%BAxqcadrW$R($7|#
zZcgY8?C!l*qK}&}`^JR`faDqB{A0S8MZIw89pblq$V;MAgKqZ>%T}N!Dz<lw)Vu05
zCn~<}6u!%ptJ9gu(fIUse(v!C##B2p=uNv!>;0+1>{VrK#FG2dC5UezuX?cu$8d1^
zYLNMHJ4=J^TtME#GP#=a^IamnA1<FpPFMPiFX-LD!_$-@Fh(@Q^SK^I<<mUygys%l
z>@5GYucg|$U8x@Y0ruO=90=e8`@h@e@g%wP8uJ1(xSE+D2zzjc17V=Ex_pU={f8D#
zjRRrrP1nQ;!W6Xs^-ad4G)Y50X5xFdf3L9O_(bQ5-jqiSBdUnH?yP__i{Vo}lwEEw
zQkN<cO=OPF7A6n*o=K2tZ4Ds%4hknZuicqh=@QEpURD!*34x?@N{a9-Ykhk2Nc5r_
zT5)`#c?gtvTut;T2@hDST5F<AU3(4qTHTC9faW9tX%hulkH_B2;vTMu#X`7I;gcN3
zQw5qGZ1%?Jn6pPmwdX39=yJB2W83q#0B}_kx1Ds-W_>|rcNhw^B|4!I7&Hn!Yhd{(
z@q&ZBLi*l#fU@glOj^jz)9&5n>-x91GtZMJE6o(Gf^a~95W2SY$9lfy*^;uCZYv|6
zxLkh3Hh3v}z()9VYL4xBNo?bS2WI%q(Mg@<rjGCt9|%nW(5u)Z!uTLKXD6kf<Xr4%
z*9a!Z1u(HAvW*e0?A<j-34z9<Sh0ZcydfW}G+Dx2G+on&G%1r?bU7WRl@9nt!kLK6
z<r5>sw``<VnW&Oa%5|GH#{3xpe&42>tLGv;2%({cxp-pGS3n%??}$Oa5+lo2E@-Vq
zH0pR+3nZp2ett|QdfABZRCu&;Pxh;z+x%OyE0ZG4y!-Wn`n{ZEc<fvvS2CxYyK=vN
zW{!IDH4ac7Ak^nV*5*vDvoynOmlL-E!Hx8Ek$yEx#iWn0XGlM@8L;yCeh1m$ODY8Z
z>f!})9?KKxjlz+IX3>+>Ej{Il)mpZQD=v}t<R99h>cyJ_NWY?Ca$bW?B=9^>wcF(4
zgY5R0rMZOK^0-I<B9T>uF(WwlOq#hMGR$`V#O?=D>VWP<MQk9)bDkGx(S34jTje}I
zbH(dnL#%l0so8gTRt3Mvk`v}Ky5=9AiP?yt79Q24jB-aTO%1AmUrcIl^4!nKvKl*J
zwET<XW*SwEUt=GNHXXQ~QuKOxXt%EFy4V+!)2+Num35l(-7{NSK4fc!ENG8aUuAHL
z5&YF0ue^4NGjla{HNiX&kqRU^qU0<BOzS;g<vU_JE6iM5Rc}P)Eq<Q5=*Q3-P;r?Q
zf2~M|JIi$PXhOB`kZLD$cV?OEmyiJYJFp4cX)xI;R2hY$-dXetZ`j^Mp~rU3j%94R
zkL-l{65LEFuC1$Qi}mk6+p6J4ol3K+^Kz-ZR%U)xIw%$BwKK|3O?q9UVsAxl+j%V)
zllq76nACX9f+KyvFNq*mIgO&+Ee=?Z+E_0Ht(mT=-W~3<(Ps`1*><MDp?q-h;xx)t
z5<Ph}4rLv`*r7|xW5RF5lO^YCiyQ>=<?$!AKZMtcZis){h`F(oqaM>&ZV)sbXean|
z{$&LjB~Y7V@a(LztgCT_2d6ALHAm5EZ!z=Q_gW4|TrM{LHN0YDT%J8cprsF&KZ<-@
z9~JY}KXlGYOA2Pszt|jg)l4^JC2Lc~$m-w{aR)C=(87f~`tS7#G%sbSESp3pNUq7M
zpJuqJa-`wr0KDf8IrAtRM6kyZy{A>5dio>>y}-6t?53PRt3Mc*kM$BXtbEEHni@xO
zqC|a~zEPY|mk;ZcCjBUqgdyvKuL#_>;Lm8d=*QR_pcoXMpY+yCZ2hA-C`oPPtBqM5
zylgc+Y3$F0j~JCQnWDyiRh_@9OQGgUL9@s6(-YzsPak)bjQV5>=8nnc;mXj3M>4i=
z*V*ARA&R%9{n?ca=5_#I+As0GPO-VFnT1^wqx_-%1)}&8cb>DDqIx5@!XLQ6)9P$F
zcQW_p9V(0TcQ)J{Sx=GP2mG3#2vP$}$h?NrqvqF)qCS~}a}8IOUi1;@O^7wVwR7dD
z8C7l@T$L^^SfC%nWSD-^@tooocw{LgFlBuwu!@2U^lLrM+F7a+x-zT+nisR>thrCJ
zjc$R>#S8g)Tet3VWJE5w6~}};u1y%YBaFtjO5CeGW8Q!7dENc|Qzppm5OsC!5BXHv
zJ|$*M0h(*xwguiJ&^(n<wJdtb=gHJVp87Fa*|v`dA0%)hP;{rd0I5n|;`MhJod5yD
z;<x!shSUIb?=f}Vc6e^AO}nZkf5z0sa>ib4g;#R_=&mjQtc)Lb&-3c%OX7Va67$5G
zj~WP`>Jhqmx3h!;S>n}#ox0yc&^oK@{oBD9!mCV`?CT@AXYCK9w?4&9%M@vF2F9S2
zNt3rUcqL&yN1NRY)AJ#+7aVOEay*wZ^0Za_!JrvxFh_rlkUY&}XLF%cznkmkO(C?j
zU&VF3&k<m-!q)@@T6cYvqqwS7!s<`a4eu|y#N>$L<uYrX@yO$BP#EYcl4r`(U+Xt^
z>nq=mOGTgj?Z=ZXDcz18;hRDJR)0<AAl5dVJ&+s`$tTlm_5_gfHcLM+^iIsjlc{<j
z!h&RpL|rLWL>HQVQiL0A++IIR>NE4?%2$q=+%3q<`#!vE!qRQiuZvA{t9(5KMeim)
zn}7IQ5pyuip!x72p1g%_WtH8Pkze8{PS4@$DW*;@)71*w#D|Slz3sgg1fPTo@+_O7
zFDheByM7m!`^q4a0+vC!RD>om+P~N4SKr04EMaF7Th4}iLuT>wQu94-gL&%7X~*c}
z-Tf?vL5sC(t9+2PYpMUTef3da=qHQwIEI%uRm6tJTBhHxWOe4$A45?1hDAtsD{s-A
z%Gmy#v3=3JNv7VbN(|}tjNz1goeD}-T^$>+=PX8*J)D6PtuIsX7d%Y4cqhjgVS?MK
zKc2xaj0Oi2?2IEqlJBDP(BHc%s7!b<7+2RrpCfr|igE7EZFhzrUtfMU07p{2_KKHP
zc@)m!?p3u!@s<${?5Y-HYx{nzjs84Ue>9_de$~$GMbz2A27M>%Fd-I0U-!owM<y-m
z1doBRa>NwikRXEf4|HiC8rn8L3&kKjo;XZz<=oU&mZdNz7K6`Va!>zUQbg1{VWBfh
zD-1cFcAD;uAj_2+&}C%8h0NL<Q~3P+3G{o2*5_C{zZ45YKYy?qj*I$^E{B^%0U)ms
zD_%Sr8+)oBi>71hWOu~1nr+un))^^<@$T9mm<-tqh6O$DSEgJ)J2z6TyLV;!8F}#8
zop~8I-BPe*>9HcUo}6;!fFb)Zn_)oj+{~8iPR`mzY}-7cAnJ$&2Sd{c^GyD)&84~c
zsi=NQ&J0Ak0AhYK|D(Tgc}P#dXJVymSc~QI{ZsI`W(gyPnfIRj$pC%vBJkXbWJlc6
z{#Cv-6|E8-M{0^y|H!ZCCp-r9PEqG-4jAC>4fx@5J&r7-F_U&7thUqERDYR^O)Q<q
zsj)*~_z?4w62qih-Md$|IOZj1DRpW5kS!I0O-NB~Q+TGNFE6To(5u#6zu}kYY!oc0
z$AOULTRXVcx_UfVqD|(zv%9#N)olM>)yPtGyxQPO1mkxc@PrAkIG?vWMA6Ilcqd_w
zEco(FilhrO8fB;|Q}r;zVfr3*XI37sqP#k3Ad0T$bjD3N%0v+<*LI(og@|9^0axSW
zf1qlgd3F9u`>^A2O_IMc!T~ICKTq1xDr7P&8+RN!U^uU>n>LcqSuWlV>|Whrv&0G>
z1+T`w{+OSY80%!Nd#lWPdj8zhnQP^#m_u?$C^i#-17qe`(&F2tl+6@{<;S;c)@d{B
zelc;=jRRc@24tA<LYx^cd2h-FOopu&3(|g=*Ftnm=z3RbZ2=}5TnC4qABEd<-@WhO
z-!IsjzPJonv4N`?2gfe+XJ;ImRl3N&JzKY9;PyAJkK9x>v(*L9?tV`(@E2(SjKzFL
zG-M8H;(D%Y=T`^mX9ZkLKKN@iK``9aVH;+@3@_ibFDijzh*;bJF#MbeZa>QWb;o#5
z#-AQG(Z;N~*+18%Mqtm5PCQv{{xZpmcxp?!hzZ}OfhcnmTQ`CEv^aNGbJ^e)2I8{c
z9!AKw0qWaBOol{OlY-6xtKyo|=*=}gSZU-dYn}~1H9y2E@Lcf+0__rC2u==LPnO&q
zQJQStLhbpIH8M_$2`&FpLwKv%F<QAkxw-&KY(9ae)ZGG;(usxT@3VTHA4>Y2tKQpY
zPDwwodtz|A|4qh;kAOV!kgx@_K(Hv<CBK^Fr+=zFMEUXLpYB>8c4FoLGsfCgICFv3
zY?VR{_vzy*)uDcpAAzLkHk-9{w!KKex$=$v5iXC<>Ush@%aCan3JvNyWVpgT#h67u
z<^QWP`2I$}jzTrB2DQ$0@xbHg-<-(qdx+=!&a!ue318v%c%{1oD<<WLk`CdC4d!$U
zQ7GKH;)s&itg-jFl6pWr@cG{4(*2f8Isw}0L<)$V8)2KdwibfUr!JU31;1$2ZB8%3
z!LC^Dsh3!%+WP#PaW|67`~?%hT()ZJ`Ql0ps@Ep_^0eq<Un3I|$5-Oj$XmtyPtKyJ
z2AszUq2B|qIYF%A+m_&VSoyh8dh^E`^;ql2-Ls_TYc~p1BoF&pF7l=sYyU{~W2Sah
zwGqlpy7#V7o&^NxNP$BymEfg`Rv{!MKNad3QM5{l-Lm2=ruCC47F85_BtfQ2i}Jmt
zs2(J2dy!SW`P*Xs`-<QEI4E(m+~aKNx%mj`g|^%yr0}mQlxM)AW+phq1+GrrenW@G
zY0@<v2k*gQB0}gfCU!n{1P8c!0rzcRNnv!1bQd*oH5>>f1f=tHPXBr3pEmRtBOCJR
zPty<rSm`bz^MN<47w!6B+%(*A4F9R+qcAwKZqF+uWN&3VuhI1Yd&Y@A;6`m3(PMd5
ztRD)8(C1%3he2c8Upnq@xqG0Y6<lF(Qc(D+tkR~gKs{RP7sv>aH%t~y((n3KLlAg(
z`TqJh$Ak(58u#cZ9H}={DXXL67jTf)=?r>JQKxI{Tk^?f;e=N<G=F1*>*`Hy-;7@$
zI1Am<xVm4d_x1`UM>WOTm9^>C1^DrZGw2ANYz0h3=gSrgb_l7bVAZi~`fWG$+bNsb
zgsY`oAPo8WD8idhL#ll?db+`YoD`<7{T*75&=){Tx}iW<_CnFf7!LAyKUg|#Loi}a
z>s=e+cW7uK(QnAT<iXk5*_Jf}fvs^G>UZF!9RCoTFeUT|$JYR~fH(7iW<K~MDog{u
zn$nM}P=bHv=h$VKP^|+Et}ukD3I!f&3W|b<*s`$uYp(O-*YX(@IPGxng#TQ|@i`*j
zzG0#bsAZf`cy%{Y>nLLDc+AOr#(z2Jdw?-~$fpk;CG>l=0Dkx>g8~#6L!-C$M<1n)
z#xhQ*<=t(A7P}NSql#EoKJ*LHRR}+CG;!_tPcBE=01{4ZTH%`{6v#q19k}2rxwm)!
z#gg{*0b2SRfk&IP`(}(x*tz;tnnn&eblp=6?K-ATb7+ynxQbJ7WWk~L2?_S>8D$I;
z%5|WXEJKrJxaZHM?d|(yxsF4ixhtCJ&G(bb4wp5V99^l1y@`O8_TkhVmA*ly(9B;G
z8QNy9iR<IVlUNvQpmnP%Ok$OO14t&}>YCt2V^L{9fjpv!%=#-r9gT@zpHYX7>ChU4
z;{)gipbJ*A;j|9T07K$n=MGPSBx&l@z+VQoKn}4L!0HA$qog%l+MYQzC?+-bBF==Z
z$qoZ`l|>IGb^3W|uxD&AOvo19)zdtN@Ye0S;2~{U$CviEJdm;D8ewZ}cCgYwbo<(|
zfy=*54Gc*$EB~EK7IE}iG<f0s1xRtvGj~?RPBdo&c0x1}ze|5=!-t6#GC_|{&^vjO
zN4QQMQ{T-;spvsEcqRvs;$9;(2Hd~7m#eP9N~?McNX=cFU<?5OJ|^0;01WEEWMki8
zUMBVon>*m8(bPx+1AooIUIZjXN9}Rk#`iDWHMvh~%>b){Q@AcHmtAQ3jR;HUWP~kz
zVeVEAj01uG^bKZ|PvIKA30ViP9Ay)F+ISOOVYpP$wq{0(=ju1d`eF%4>p$UPap?zA
z-2>$Xh0!kXuEa8&gA?c?xOqu1i0d2rD8wliN%Tkgqy4<&U4QJa7zd4mgNOIQAgL%!
zLPrI4I~!+u52|W>5A&f2p=LG~MUL&>40zy1TV_7c)}V7FLqvJZ4Op9(nVy~&EW(<+
zrme#etkR*#1;*2lFMY!B*jO6##0HGoKZAsb;Yfy#ZR)z*;5VVC!_zw5ckNne11^He
zb;YKEUA-qr*Vr8g3)G_Yy$5&OE)<PkfP!!4M_d_G4m^82HujE2!~Nct@zwEtg32(u
zQ;^hlXYO8#70JFaM8hc)NDA`kvA9I|?9G`^RtWLf=O^CG_l+McN!T`|@%w9IvHo6h
z8tII1C4|s4Vl|PtXB+ir(9(TT^cdVL<?H(f2uruJ>>okAhHKX5QF?D7eWqC=R!MZk
z@b=D!>@lAEdMag}M1mxZl&8_olEj_cfq~n*q9i6v-z$MZf9@*mc$J10MBDoZI~6Vy
zq~3K4c0{JH%5jYPInlgD9B6JiK#3{gt@R3m@0*hdvYDNK`Px?AVTgsDu((A~0$bOt
z*F0r9?Km4$qeh)rk=`f#C{i)?T<{44T4Dm>Y7)w1_?5m4bZ#|&e>Mk5dSz-5Qd787
zMK+wWYDWduu+p#;M-Oic{i@EjOdv-#hgY9gp~?0M`lgX5A@{4_ntQ~0RJWme8b6FI
zX+uOi0*BDv+&1!%lbs|lt*<}Sfh@J99XbuNU-Fs2>lEu@md?{{`ou*C>H2R`VXiDq
z-cfMkBQ6AibI9|W&Q*q{s=V64YRC|qvNbvS!H+}aE+?>>)aZ^kgpEYm6@US49`8vR
zFnfJE-rAb6pOF!Oyi2*-ttZyKhD_{lD^Jj$sy^{!N=)c5Vi_d2x?96n7@TB_56xxg
znT*8vZs3A3if`}!K|fP}rJHjZNLp>p=kHj6LpGLX4d3Hor6<YZJ)cO}?ek^KpSSK6
zC?e{P9l8^tfbP36vcp3>=35H}ba=lvcmSTQfT;w@7Q*AO#)M&c0UC{KfYH?S(4DG8
zkKmKRCNIyT8PiQQ>Xg0cm<-R90yos!`z?s6?-X8<cC1oK;WRdIXRu8^>W(jbx<%vq
zCuV%5@Zbkj3agm+iHFmsavpFR6C}`6@%cqv&(qsqTh8rk%9kRm4!C_g|473k$L?Rs
zTezOM3kgqG@5|f6*86g8Z2Byov4d>#wC3QxMn8nItlye5)Fpa-`p>{<-Fe81Lz;9}
z^<{J(pojH8#|csHFDfH-SH0QwBr)wI`zw`LecTSigkl}&ai1BlyydvwPUp0jV1J*J
zBX#)?5<g9`AZ{gF7#z0@FJ3Wwx-WDNlc(H#WaqLTchcZmgXX8*Ny+oywGB|WHkSx(
z3Lk0Jx51$p);fph5JhZRJAX{AuXpSfi9(X*1TQ^CQ@X3TDbx!EY)5?#RUgMrfGn!6
z)#Z0IySX3KKq@S?RH%!p)w@tssJMq=@t{G^0S4V0nk7>?p3x{|4aLfjcFb95^SR@?
zj1fx*QvLt9h2|x2zhzN`e0=fTy&)VDBV~OIYL-X9;{I7{H=cC)BE%s$Yv<0;$g`(d
zbO28eL#C`N*n)@kXmC7xWv%sh1rCn<p_cLIUleyR1Oq*df>zIt1av}3$z}qqOb}E5
zt?Q#X6Pf9lXi#5UWZ!EXx0)jsJQGIaU@(zrJ`lzQb(s|%7*x_BQdV|$(z{UUB?nA=
z{$7JPI-=g~g_@+7oL-D$?szvXoV?F$I4)oxD-uwk^tb2HTbMWK=JiyK`dcO(E`ly&
z@Mo$*CN~U^<Nqm`hCJF%WbLqH13yQLbk6UfIv!GeK60)}pu0iL#C6|&lb!>NK8>|s
zZ{N8UB73M32F2k=APE^<I2*Mpmx0QQzV;B}>!TwX^^@<aVB=Tb??K$Ce-DcjovFzB
zgDw40D;o&&VUb3Eq9ME=$A3E5dBbm)qBh}g3w3Vng!!x})xjYL3->#h@Hdu_v3b18
zZBNoa7a}VG!i*sA)Lp8<NLAB^+e^26)BOC;Sa8<yT-_zpkk*Z(Z3jP<()?8h45`z~
z+Pn%R5&mSWHn?&Q0)C#^u&T>$lfni5cw}$<H$U+(qY*HNiG2&6Ta}@Jh%`HRoe3XC
zTN4*T;X~lxb-%6H_B-azxYSOEzsEvQe(MmfwcxH2OZq<~3R3Bj^slO%8Dy)&`kMKF
z&jFd`sfthD;ui-0Hq7~e!#tW^`a;1!x^QRI|JW?36bM;gk6julrHS@8$Vlu9JXYyW
zHcEh&lR-KY&dE{X5VAYDv$Hc^)=`YyuPqN)sqeLzzmrTkbaKC@OFl!2cJ|Wc^X(mm
zW``io_Z1Qo9jrX=(00mGjVAm|<o7L6M1-f;&+(0{WjB3CzQJlj+g3qUfd!4Aco>rU
zeZ3-*Rjh-x#CiI;s7|B4ur>~$hp0M!j)e;7_{XLx-!!8+*Za(!5wEhuZh|p~vML3v
zArYrVNxDq<E!+qO`L>t|E|S{OBsyTe?^%Ud@Rh~3c~FLe?*>C4q#+MJMPU^jR9t(9
z9S`(BL0iWKT=@>`(e8zwPk%ej)Tob;)2#mn^YP!EpIXMsy7PAm)_U>%HdW@h@=|Fe
ziol5soDI}cgI1@>o6)l~x3jRmzCKA7i>7!&q&;5)4*iq5YVy(20yRXmGQFEnAK<C2
znGTZMT;E%~prtJ#@YPfjF8dTMk5FfvP;UfLvb3~i`%qJW2|VSAEG>`lM@Px=4)j>V
zkP?L>ya}Ol+HZpoSwk~X!OAu#YrFdg@Si<yH0?gJ?|N$*r2*|qUchnF<?!M=78n%H
zJO$e7Ug*{+e)ye*{3ewRol`Y*_g4z^@1Df`-%@)hNf>@t!T8&f1x!Fj9PttGt&4jM
z6ewq~VpP5fHvkS5RL|<|TIe8-_fHo59jibwNJgPOP=!4|K^hN{=qb_86t@SE@SM*F
zFDZUhFr%l%%h%zh@08Vd3Di7V!aM}rdIZg|uW|od{zp<k=uqd*b_<zIZk#U?C_4F@
zH9i{(Z`5}uw!LT^ltWi^#Af{u+q#%QaO8(XUgc(D7y3&z8(JAo7c)BTP40{rEy>V~
z*-^NU{|(XUvvsnAGsje4_VeN?H4F-eZE(5s#3{kKaclQ2VW?ktA{_Z|BjqE|F@&?<
z>Ma>>afW|{&rqf427S(yt<h50yTJY2opug!^x3dy{$IJhB04e%?|HriN<8H2z|ehH
z`aAwz0)6D5{GR1^ObsbsmYSSvqa1~{X+X0pkWyY{3*DM!>y=<99V{Qi?O>F?Neuy$
zC5we*nP9oOK=^9fG%g+5V0NeX*|fD}JVnXHWLrS7B3dgB{9=DZ0`BuOU~=s^WC%{|
zpCTkeIzICb+Ufo$um1NQ-TqG9|Cax~DBxoN&(t1I2vetp++n~UP~Jb<4T!UbMXJaB
zYfGUj5YxC!CmSvgJ@;L(v74Q4X{C?zQxmBpN&Ly_h;vV`@Kffi@rQEQ((x1IJq$+@
zv=4SXWri<xN+2cl=}pyII5@O|uL-RP(|rnV`^7L!r*6D=;LT)2RoBqdnqGvy3A^?b
zOcq@nNfhD#tCBDDHIv=ewB634$IJGXfkDKyM@(kz2YKBXZE5XKOr24WCpIOu*sD7X
z;=oI${wl*3U3PsrOeU;a;|cK3QGgT^JNu;vkSqFdVe!>cVTv_?{QQnHu<K3app?%$
z!gr9i3+LY8d{@JQZ6s@VHlGV*l7@E1#(z3{>W8W+hJ5MJ^ig4EqbY^C<x`95stZMa
zN=P8>AG@M4{GIRFwf;q*F$ZTcssUkV?)*RfO`|EL!Jh%}jQD9G>+@i@4D>{x(}Z@s
zI+(=78=S*$$K1Qzoz~I7gks>(zxuSB>$?aC!k;6AMd(H5(QNULIzs3rp`D|eN;<Oo
z*B-=b;zqQ7$%fsIv3-%nB=!WTjQDBC{#~SANsmMSFzChey%F(IC)_hx=!FPuLi%I$
z9}i-=#*tb|I&@7p9tht58zvLJ`o9uDV2KAthdBBla3x|7buJEj#ym|6IixNyys|j)
zp<|<NGh}GWQClZQtu)(uIeT{XVNzy-)x7p*NQ@WsT$}F(+o<!<IB+9#t@-G##(JXL
zryV_8dZ*>=f)_ZEfW8nXt8DRI)+3yTQu!1OorfM`I)`17Hx<!@%+<gR!ee(0oqS+%
zx73Ui&*vvF)Z(1Gea+xK(cr4HtsZU@xp)hAxs0u=_jBI#W=wTaiGjcTu^`l~LAqe`
ziEC#9t<+09x{-R>pWU##+A3glNx|FN^vsW~xsltnp;?oS?@w1ZzHG#tPZ)IZ*f>a{
zIHwrTt7Di;>Xs<T*RN6&dQQJ0lQyw2%vs9DxSnihE4WdpK&wEhwp9WuXu!RjdMhTo
zBM(@lmg>!IY}qnzh9q|tODDT<UzPI>Lg^?I)>fh?mvuvvH|5dJ<t>ADZKb>RCQDXk
zsxR%5%e`!Ele2`1o?VV<o-Jj;?;#gmadXdi8mJXP&MJYMy&BBi-KEb3XT!3@Q~z90
zJklugT2iGkLIS<rUD^odmK$aVQHDE4lc?UwU^r&zOSBKN8;Ls3^GdK@<h5Y+I+als
z{iVCK2rQXycT4vN<MV-f<gH18;fq<$F{vlkBq%{#vB>5S_1?@G15S`PObKqU?;*i<
zul|gl8BT!s#V_{r8J+q&oCrtRoz3HavKV3m9r(JD)W%mlQ%|3`Y2TuYHCpl(MYjw6
zT2!ou&QPRvJVj0>JAdg&KI7`kak(pVmjnmRP3h`(vzXvM7O4#U9mr$#AqBhXneP5f
zomGD-(b+^SpGvIEUCB_ZRE=@|qDOc#NYTmdD3~~vNKn%M_*T<jptHyFfK}?H<BiB8
z7zf;DP)wH2HN5jsKcMBs>mpSy_Yx%%DgWzK)|)s+r)4o6CU(bjMUpWGJzY$2wu$A=
zT|2*)c9D7oX;bqIvX`%_qAd@WmtU0DDjZN08Kyex_HzgzJ>FC-cgIOb_Z`|;FfCh-
zHOlkfx-Gv`^~Iunfzo#Uk{=Ed^juXFq`=U;^A~;bGmeNcqLiZa7B&X@KN2Jv9&oO<
z#Tn*Ei;^Wusl4gZ8uuavIhxkP$=<9dAlV1XK#@(k)sJ^4JYEJE%<QHqP?laB<2Hkn
z!-o|da_<L0(tnZ?R=tW`^u*bcFWs}0LsQgmk@Pcx#VzD9a)qtthL&JugE%T!k^vWV
z4*;2<#NogA^~cwpPxDLnsmp_=yRsk7up?$Ff3>NSznc!(-MfoGcb=u*{%N+?-1h6b
zztI^kI;Klg9s)ZfTZELA6Dc-ZhrxRl<dn=hasJrM5vtsAu?}<8i<6Hnj!P{-=W8DN
zV6w@R%41?WT|-lsNZ|!<DPh2e6kW)Jz1pg`66+wgqe`umbaT_k1x}!UPO)dKzljd7
zRa>L3^zKl6mpN}ovm@?!Gj-;V&1`Ry2#iCN;4B@X7s3ykI1qO%pa)##EG({*_AFen
zVtQP8=q)w~9ToIi3lC)L0!)ugC{VVhJ;VZx-5VB-+Ni~4En--Spu0;@VCZ2C#Q<WJ
ztCv4HuPoQez>tfDW0$K`?<%qTQ6ZR;@VLU7xK%`3%+RZ%0Lw$eMYopelHaoWu|a^L
z#w@$_)p^?xg?3fDd-i<~r5m(xt?+`f6tirF?$48@7e3zwK3H%-hZ~h!S-&jGJ~-$r
zBSYmv1uCqD#>Qib;i>4YLlCY)=<Yy@OUy&eRsJh7SCR8Cw%r7r7wMAy1kbHAvDX{{
zbA#+md=IrTm{v+X->YWnoZpnB4h)_W-e0O3db7`n`^D-2MQE5T%+T~A;m%rmit1ga
zPOK*GTLH6S*_zTp{o<i(yVb+-3nxi?y50$LU{y3UwQ>PCc-(UE;jzV*4}W#9W^;-U
zqu|W7KYU5;Z%ak<(O1)YZt&5|W%DaU--C|d^4AVUNM5t(f8{0c8^o>20JNyusNBmu
z&KyE2T5+<CLz#11LkRs-H1)uZ!k>w9FJ)TfUZ(Wld!3}xZk1NR$ZzV=P-gv`QPBTF
zTyL_X#HkwmwH703To$gDtf4YA#!_8=^)-jrC+l+;dbKsF+=-^#hse1Vg6@qDr+^NQ
z7mmvXY5SI)jeC^0oqJ{}><%<)!SDz|RaI!|02al8aJx}kEC0stbhfy8)jd0`E5i~8
z>_LH?c71E#z$oK<PudbI&b;V5`v63zx4wglY}|AC!Pn!D5|3@9384pw5uOz&=eygA
zCB)RX@R<;(>TWfm(HSd1+$md`DJ_Ds&h)S8lqbL+9g|-rSH6?N*v17AXhS55;=T3Z
kSRQJN=l_F;`CF-sNrUfjlV0cL0qCWprLS3d&idZ}0XFkv*8l(j
literal 0
HcmV?d00001
diff --git a/public/07-basic_statistics_files/figure-html/plt_clusters-1.png b/public/07-basic_statistics_files/figure-html/plt_clusters-1.png
new file mode 100644
index 0000000000000000000000000000000000000000..66d429c209e185ebdc7b11d0a81921602f078263
GIT binary patch
literal 44495
zcmcHhWk6J4_W+EZ83q_ix~02QLO@0V>5?w#kQNXLfgzNZkY=P6kdSg{83btrq&oyb
zr33_(nD@ZX=YQ|Vdq2G6co^oawf5@0*53ONtEZz%LdZY}004=)n({pWzym+xVBk35
zkM5N_8UO$x*V8gok+^)BNk{}sn3+kKfmf77F!*lOY90c=1-~+r2)?{?`2s(n%z}f>
zg28L6847&Q247(YUjczPg3VCD!4j7s!Kh#q_-+jbVOm>*TfyrI%1i=vMFJHpfw}@k
zq0BC!P_5uUR4aI$MS)<mt*F_P)?kU&V6)cXV30&B%B&R?{12oRe9c}0&VtvI)|1xO
zliAjjlUbD6EGl>w1!4zZ5&(f_QI{Z>uM-duyv&}Q%)fjJl0IogUE!fFQ7^x~Bye(a
zg2iHGZ7KFZ9T9k|nfU?$Q}pG3NYchnM*v_2)Rk`=2B5avi5i8PQ@BflB&Rb&iFeD*
zJ#B`w9tL9MNvfS}ZN{Fx@yvb5=qhZm(Xx4lW%)2GXB`w(5~HV9IF#^q{?UlBMxoj(
zs(h+K!xodsP8-n$3LOi`<%cZ{9AhI&=Sj!`fWJ2JB>=>Dk*lvop`vue&vHNfzk4$V
zK&>9rEs>Mpbp_Bt=vayOV(=nu<v||Eo;_BM>=b3b3*f=K<cd0N=twyLoTyc%F&oi@
zXmTXv!~Sy@QM#TkI0mo{P?e-3{$dNWL5j9<Fc3fc338A4|DP;=25{@oH^nC>2L}fu
z9p@E7tI{Hhp|K6z`B;q}{uF`xKfg(fEO+$6wH>B4Z)sxBbVWp1!gLMdlAibqn;Zxk
zwuajL$4WQ{QaALX=7K1+gHE}P>0+H$WVuLuO_T-FmL9Z%qs=FLFx+g_|4whGCFwtr
z@Z$huqDH&gm;kx6-HkQazUKql{#?Q7jPeJqscwaHk68X`ffypcgC*?<k_o%`%7QMh
zW`Kx}W&`g7I)BHO=<xtS{Z#)4_+&%Z3wylNJN*fc>7vz)CypRTcG{3ZBY=ywR*ZM$
zp%n*`2~=?8Y8rwJvA!BmAFFsVB%RF?)@&KT5qCp=zY%+e*7|)|XY2APS%llC`JmUj
zYVCcH!2Y;mJJ*?e=KXZqneUFL!z{;Z`HJ#}VP|IU=#ynq=c(uu1Q!A1$;FS}_jxDL
zCAy)1NejMXLG>ZvtcHKG$z1==j<C?*y7+0*tME}8XMiwAg3QNqc8}fQplQ&w0_Q&&
zl5Rre6P!dl&)pQ^#B|#oGmnWw7|klr2S^p?E4R9e8#KM)f$ys>M&2JrwelD#{M4m~
zn(in@0LJRe*bVM)hs%zJSP?d8jA5vzX?$3MWXLSFrYBy;hO{#;=Z*d5)KjY-b9x9J
z@yVT+z|s(W{YO6qrgVAR|C{Y=`S?e4B}Qu|B4MH2A@J^ujX-J^)3~<7d#uoz?XZ`C
z|M*`PW9WWbj3Jha6=~`yVq1P9x~M6;;v`<z_BA1j6YrLVPwSwm02o)RPGyuBxqu|i
z3}9*dGilh#@!{ceC9d@JVb{{xens^1YU|`z#iGGwtRRg=$|fbIw<8QYv-sX{KMl*h
z!^X^xT)Z$LU`;=I{jGQTz4cPGnxU>8piU_thdr-L_+8`r_jL31o8_Goszt5)8Ox~f
z<bYgf^!i;O#TfE0jt*e^lTO#9<?3f&Dvjpu1kwEEr?$%6B*(Of|FILZ39ekL{j5f?
z^5U)3sWlf;`SW~-TlkKM^{*(vF1_(|@gktnV&PF>`jVD0NWU<72IH*h)Ij(z+z{lz
z(Q~&4xMZKcOSc|Q+B!{@y#4IK_b8AV@`TahY#<4@1m-=1Wq<@^nyBX)UGN(*nL}Xw
zEZTI=A<7e-x%~ss<AcgONNT{+r#)|a;L;?G$TPx~Z*CXA!?2Be3XqCur_95QU$(*T
zHAr-=?pLo36Sqvn+<J4tVx5<pDV`34C2Jf|;Tr00J6HNR<!?D-`?33rn*Jh2ca61x
zXfh0@i;Fa(Z|^?Sf7zxW0>cRnXz9&IJ1@cl$&g7OtGTPATiT!y_aNvzBL8=C6(=`R
zFEtZe5T*2MBK0nR=}B{5)d}J$;4_>}82;qUrhic-tta&Hznt|QmK+eH$Tw%ZnSZ@e
zwxZ)vCo?MpMESsnIyi%p6N%j)_AC{EC954QlUg`t60qKrZPx7&a)l*7_++Sd2WU>c
z3PggQV8F|N{p2HUC+hUuTZJxPGDKS{h8)3})C~Q-f3e8yvhyDF=jVIAW+`WXlCbk(
z=b6if1gztza<Z)&>6((u5D$pB;NEAz3Q}MgZ=ITSgw8JOnOh-#p2A$9`x|2RKs*mt
z={3a@VjGf|#snA>*-!f)FK*42@<Ne064a@(I}$<<#K75LA9gNS@K_|T>PTpnRwSj>
z;fB`U^URkNCV@Bcs|E(ikvuF5xD5+^(>7fF!Ubv+4Me=UK<q&0^I_8W-}hXF3-0;e
zy~B=^FO<CtHOHC1_0JWv#t|I>Kj~JyI*2TP_BQ-I^pfhm$dIj*v%Y@n{l4#akJv%n
zsqXUIKP$zo$Jf=lvQGdh_0eG9DK(<<K>sXoL+@Na#1S{y?UNyVpBXq~o%)et%=VA?
z)*eJYiONDpc|Pgwtd92Y^V5xAOCj@LFP?qJf4t2RVmjVCU%gvz-Bw~eQUBU8&<r}W
zw0!>HtG10-Ysfu<eeV6`KdEQZ;nPu22&Z<<d*9Q5k;gZNNmVjgca(G-8F^<=vB~Fg
zjU-fp^z8&~4;*3OTuM?V5)sn!GU~XS)cWQ~-1SyD?55WTkKFmMX^xF?j~RyF3*oXO
z-?Tm1FZ8Dw75k>mPe8Dee5CuQ9w|DHXxzU45NnC%;fE!Ad{XWU<yyjH$kbx73er0I
zZ;r$HqrGB%9nA?Ewe`{4)y50?;7-yGztcUh_R8E&$VuVEI(5;=yKw~RrjDh$GBC)8
z*ceB|&m)StW#UAn-{08mT^3$_wk9=d>DzPXSm0D@RIC47n4{{+Ki~C+?aKsR{P{el
zxW}`=BGxk!`g8G1!IP1pi{ZB{fhYBcih=G*f6foz=HvIScQKL+9B9lZP3=LtZx1Vd
zw*P!8q^GV0>>f7qckV%&3?I43X-~ig`%inLN%KBjoXwxOaiZIZc&AY*$>#$PX}$Zu
z1eK&m|C{$R03BQ#llbsw|NY+k6uvT3NxJPSHu^8QG|@nwJPB~Q73u$u&gI{vZW#ld
z)jxEHjK=&Qmd$*N{joLhZ{iRjN1kqPh8;-L)BpY-P8>jN_y22A;8M~-cUcFS|G!iR
zx$pp+JrCT#8VgTMjSMLU2CXQHY#6rkU-^|r#s=75)?+d(<^-6_bcoj_%ccbMfRlBn
z_f1I(q{LNy_To+qkN~-4)ZK*xa0Y#mj@bDr6@(7w5~F`q833n#@Jk&cF{misWku&(
z_!K~0<_J*~tq;tG_!6V^4h}@-s{E4?gAripE-^mAZb3MYm#?rt!PNg@Q-*5;$aCqd
zu_<q-U5(upB|4u5$pjFmUWx9ablg$FHx6NUGJwihu&VP5$datrA<Kd#*J7u-!P-tr
zUMPp22mS$Oa|PUW2XI0G`*2n_Y*iu%?_R@&xc2$Kn_nYlv4W;By&CM)0Ej6}2XO#P
zJW)E~#E%8p4<azW5c*5C)XYlQ1He`GZ1HZDm4E^^mr&J2BRTXqC0F*NeR@a(LXcf5
zw~M-VTjS?;4mskg;`LUE@*f&fjG=-4URmJj2t50F9(?jm+Wwams4OVEgwrvLG6$sT
zagyQ{vSke}fL8@uc^?ESl#Y0u%^RD09zCW7g#CPZsnx7&(M%GD`6?2SCXp*sQuy>N
zE&~q7it+x?0Eu&u&8}Z!^AD|mNa>n#EXNHOANaX|v%^+q5*HFA;2qf1e9h?aQvlLX
z9EvDR0hZclFLXogL5VDx>R*-{#QwxHcBe?^Q5Jx-J!!AG!f_n(FUuhkdQy~D1?ahO
zBc;FWUA(&__MmC@cw%Ddu#Ora9ER;5?9dQ`VogWoj-u|01d)p{(lk(FlB^j(|1x=&
zJDQVf4EUDGbIcLg%#yfX4oN922A9YhH{~;FlaK5%xPt_4U3><8qKW_B>02+ImzwYu
zZNANRY9}J#It;!-k1qvkMVJ6{-DTbYpMme>cSj;L0q{;{MfMu&T^2&ASucPC)3jVM
zcLfgfOXsp=Is6F3!S)%#2(+x1W3LPxmn8%Tl(_~(p?z2VheJ)v1dl!N26VhWu->;3
zby%75^-opEbY@4&E?MSLT^b+K6LeM@A0j-!ovs1A8PK_Q>Cga&^Ml188mxmWJ<jMA
zZ5syy8#Br>dSeEhtaFj8-p4_2)~om(Tog(cd1=DFLMK;MhUwDr{*=ezIp-psm-6zF
zQT{H613|rm@B)%cBWka{>8W*f!#6iM*bU<VV4$(VZplc>kNxZ1U4RGdP&&O0<Vhz5
ze}|KCPs3N%FCB3=_PfcF824jT;0@>&<We7bW#j<=+)Yo8GI9hd*Z~orbl(QT6QdN%
zQybq#;Gua3;05>?8l2A!zrYr!&YKyhNx@^;J@!VEn<stZf!)x>W5|pHA_tv^7kQg*
z2@z&~|A6MS%d#(P_K8|fX%5OMQ{_1J?&#EbLDYt%jhy~T+&=!zbKHtP7d5{W!OZ<f
z_0KKvW}Gf5JYx%Z@4k1oJW?oh15=85v|B>1jmJ{Q==pO^S|-Ye7-KS-_lVvm7xG{(
zhyl;0_UL^T>DQQ?H?`!9#UJ~tN`?$wa({MB`JV<5XF@FJ#xrCItkQR^V_&z3YItla
zS?DTx{T4=sT%+aW7wA)R*=4e^-6ae>?eKs3jOH19C7m|glxVhC7{^_XRT~600a!xj
zsyX?1kc|~wO|;I3A8<n8Hf}aLM6FTz`RA#sfPnAJi~j>xME+EywU$lUJfl15^pl)9
zs(b65<~N~g0$rh7O3PzxGaRWR5|IvVQ$u>-mpu6KU<*GW?PK2bL$4=NL;;K6zW*-s
z(DD)JwBl{jR&j>1O1s^hb{XBTCQT=<`H7VDP#`%^rgx^#*9-HQb2aBV|Ad`?b@C;|
zbp18eXeQ97JBCZt&?{fSr4cfsIsnWBTxm2ElUOgN<QhWxP6hL3*Y`wi)&EYUZ^u(a
zv^GNMoGZ^$)CxN^w@37EggUs?>4-!T!-;28UnQ*<??s42?%3=FB}<_w)8dZp0R+vQ
z{JN_2HpQng9FKV2SB-X|jz^z8j2%KY|1hJA8_#+0Oq3^^`#Go}Goe>bal3Nw#52rJ
zHQl%BBG8l`KUv@AR!utEJZ18MAJOSp2n6A#s{Y9H=UGW|pg#fVWPP1Xn~zgAhklxo
zSN?q=UH>`r+K1^BeQLr0a&*X+v?v=694Ts%Yz6qaqX*eew(VSgJV^fF%Zz<8w88tp
zKj7nWmb>svTEAaQXX;X}EgXUUEG*<?FYR?ZGS9T{Sv;cP3_9KOJ8ce%Mp{46<h$+R
ziC9YQQ)s0FeX3-|E7pOf_6L+w$M59t+u)#Jf1k<UigtXV?O#;@om)W)#z9N-V~fLB
zfmKAzl&{*CoTs@*Yd|iU+W6EsM)?WqP`uES+3}Px|4EY$-6of7sxnboZgwB_OCsTt
z>Msg1dwDI4SZAv(C%<<)<`X%slG~2@0Ra$DZnD*o)h_IS!IufeZJuaEK+m?6LWFXM
zC=XsOi)`~`+s;x-Q>m5v3H}7`&sFIk<FmQn9g&ATWfY}#F2f<_$8UJ$+W=4o7w@qO
zofy?2M$i2o?ZzE?4QSKqPl_RpF7JnbjAxBdWS<mqyP5;gBSn@@r-k$SS-_`1D@S@k
z0k=RVlJywB`X~u|j|DS6o>E@^wf$K}r2f+do0cKtNua;bOwnn4p)>BErwrbwjdN;s
zFws?sY{pm7SFuH2_^WDOH4q9<2$309Bu-6ZSlkI)bXTC28PCoQ=vi)lc_7n*TjIF>
znqoU~Tp?vv|49HdIA&Un+}gNfm}h}xLft)QvsgG^s4=umhx4cKZtZCOZ*mRT%KhSx
zMXZnn_ifFB-}~~Q!TUPrKke<y@psd)rYr4BjA#Ipu_fdP+-UX(j5}V1?i~rhkzQy3
zK1kjHv#2ti1mIDjsS$XT6v&a+gXC4Wk){qN;)a=!rvqK{g;k}HXM+kgfAwssBGz4~
zcHK8c*^pdcVpO%li>4JLMu67o<)=ToJPcBC!++@o`paFBWtP8#z7q*>&)`V%L1H>c
zJD<J%c<ix+a!Q4XE^}lv&TL*1RvuS<@mu9piIxTsLx-t^?ME!&jxyC!aJ4Hh<7Dk;
z4-s!4g2|CA;)K~l($HLE?;aK5NuxKlL~7u<2L*@~_)eKR?;vG}=s!5bvVS~$m73Xh
zC61WvZ)0f}3MRVNeq>?+(F+e@2JL?h{wGkk6-s9ZR&sL){SU@K5at#sm_6iz+Phw{
zuA^XNqMK32PI00&<QQ4x6^_4FZKU<x0d)c(TbIO{1CS%pA)V<3*|&|H!3*U;`UuV9
zlWpXVtf8I*oVr3edk?ipY6!wFa}wj%I_xwTvXV>P-1FuOiAd6zGH{WHqJ|Vqw_S1l
z+a2VXC~jxy>D#-&xI#jIc*td((G0CLrM!^50a?H0n_;Y&J(k^h@gf9aH|g4V(T}_W
zVI~V6!7jiGT48Dx`9oXa%ruI*MGOu|I<$I;yOWF2ywO~W94?EZzXQ15Dj={wFu*w#
z1WhAv3mdiMDa;v?5QSne5kM($YzF#FfVyJ&yr@Rh`a&}BH3_mXi|;@Lu-A;-0U0Ga
zGqYL}B~SS*?CJ^adon_ksY`7jio6DKkv^YAhS1CfEiunSy2ZPcl{H$+`U!w6-48}1
zPX11;z?$nM9DzUMTv)Zavr0%BeM^fo3LcXa%(zuwz0bB@Ip^T-{EQbc!YwRM^dHYB
znNbBHJywfeV7Yo?x5fm%5Rty~e6P}PBL8x6%oz}ez{}jp0r8q79gC4xXp9VD!V7<L
z@w!h4KzHKPO5Ugat+$XqLU@_{qJ0+2jB07srj;#>jCM@aV^U+YUVf7UfZ%2AiD{8;
z7mrUJW*|HM&fL;6$BiNQLS@|O&iYzH;kzbqt+~;-d~u5hb}Z}iBTyH~Q52YkLIDjz
zj0xWok_PVednH4->>zU<p?7RpqR@Gb%1&^w<Fu_8y@e;rgEQpvB<elWfIA3Ov?g&Y
zayC4K3{(+$Gh|F&kMrR#R#Ao*<}5cT=(K@d$Im>X(lw-aEJozm<yf7}p_YGDL<zs%
zP~;!JakI@{4iSjCh3}!T7qdN~-L>UU-phrgr?<I}Q=$Y!Mq&=7unSlBy<&wmkwjz|
zlp7#jLAfR<%xVGQ1x~Lw{A%MO^vXNHCv0`V4}1d6N`c&8L>a4<S3MKQpoGGpHY|~s
z{4WhHz66|JAx%`-!f!`CWQW?QRt{fCgopTmj8ibd5euGgK5}q70ue$%t&wcR-ptUI
zOmV0U^pqGJf`gFTlX<h*4iR(@55Z9UsP6RlknUb+$t2kqjqLMH=qVfoVv94d+%0%d
z0nr)+%1T?E{W%-SOF16A>x#KIqHjk8NYx}EEJhfM<SDY4lLg2zl{&0ZvIiq4_qDRj
zRlm=Yp~M^RJg4&)Q^wqq1{D%Lhp@?349tBX%nCS0!k*p?_GB~S7}ynw^vLi3G37Un
ze@qV=Ptj2I!<LB$f_g4N(_-}n1yJTcjoi=90Mgi_8HX{r{{c;?Lc5@ZSrM4PRjS93
zcZLg$xb}Ht^S>JGOU<DLL`+Pz7F|{>Grg~?HqVjt`0)h(sM`i<^r271HJ0AWpfKDX
zbzD4oSVcer;rQ|BY(LA``g=s4P60>$N8mT+76jxM|47E$f|K}5a(HD+*l^|w_FF`n
zGh3+!AT;?LaCpI=)Y~pdRXCm5-8nxVJGkL2fwuxZ1wg$q-SjvxBMFpwu^bAi58caG
z)9EG%nHZ))<pIYvyYJoKME_#ZU1Xv(mlc*Vp`%j=^w|nuw=mY|YFmuthM(Vkas$Wp
zCE3@J5)L;(4HipJPN|ALDQo%<r|5^><2mYgaX%gD1JBPJZveD2rJ#Vrqk|XLUlfoM
zGg#_wtDW8)ciU^7Dv0RZt_5;g#gU771|-3@5*R%9x1=TBLm{ZXi^FLd5sN65IM}CJ
zSb-`siPIjyt0BE@F%rBgPXurv<#U!&;YB~ii3`R&yKgdXcgTjDV$jv-ypsrWMD6Gq
zn~iH3E}L$FiS`I!N+Mxfe$3s%QZrmpwb?#8A{`n^J6enL=)T{IS$61+w$&K1<P3Kw
ztSkoo7Nl^eccrWW7YwD~tcF)hOIhha&s(Sq5#S&d0AZcDBaL$v!y@~Z9A)=-c!10^
zF}9mq+|EnSq!#*ckzxS;4Bph#q45?yV>=;as2(q-{oIO50$R2qemVk0KYjPBjW(-O
z-%`p<wT1yQREuY-dw7!5kYw)jHtLbSNa>^K?dByn7zX-p7%j;l+z=9IRygDspE|E>
zqL96|dQzo5;WJYm?fVx(lgf?I<J+KLiX1Jmh&11R=(2k8o`xY6S6$@gr{8x(n}tMM
zXAZ!=9*MK<J34jfwABn{-Pjg*lL&B|LZgT%Z1>FdQk;6%z6)Bj=XY)^lFk@|>^p&}
zoGL3G`1^*#VHr<~J}gOOvt>4nxn{VsYI6}ouh1;M^5E0GQBEKPkFFFsk!#a+v?ChL
z*WW-5kj|7AfQrWWa5?NKdT*4#lGmr5kSUa|DWNy+8leR$O)Gn@K}q}+Z5YihMoy6m
zK|b?e5`Y%l?YsdRBAyT#ef^PVK^neiuI+aA`*$(u26UeE?XCsB4q(ew<`DrRkY{ve
zAQx_f%J5KNmrE><zX7!Y+||G)Vk8);=zq}qWo6I~&z2K{nDtTyNPHK<k2_QYw@uj3
zlf2_d2HbG2at!`D0j6_$q#4>rhkxT5owe9_Wui;bzTEf|v90b(ib3l-j>9^PR3n(p
zkZpSt8`aiMxcgd}wF(ZrqNH8bzdW+5HiG?mGcI}nURIWHazvOUi9u84pi>hSWP7@|
z4mmIo={|kat@%?U?mUwnkbz>3Jn})@f^Z<0T$pa(z%~uuPkGyDVr$5l_yu5s7R<eS
zZ|?8n&Vfw10($SlqB;pYxQGsDUnJx>BwYhu&ESmHJmLmyAFi-J|8vhQzc5G)DRkM}
z1bV0u7k_uco&^=K*5y1Dgpd`5E06hYeausTUFD?-|HS$Hw?|McSIx9bI~6A5vb$`P
zY9T|2?Z*4PZaQx}CH%miZpkUs^rv;+xt*k}LHoJ0DHIl><T6r64&d1gUbcYu8N^>S
z^bJ~DlC$zJocI@9=Why;5hJ&moUu>*br!0w;d%22?CR_mb;bxc;OXQD#fkhLsE2|G
zNugNK%w&QPw-{nYjN%=8b<M-^W~<YX;KD{SHe)}EJ^Tv)h7h?<!h$-LVR!)xS<)8*
z4~4hHokH0aRYPhe%8;VH1vDQ`{Baq7x!=p5dz>rOMQ*FdxKT3nTXSJh9I#qBK*&Gm
z0i_aDeynFwbyLc#D7}Qb|DL8c&sTrUBMAB5?89(^N>e9UF&p}oConQus^(~pW2Por
z$k&JRpt~A{KhIqIE6=9H_jW?3?F~ieTXUuzO9Cmcx9D9`RO}Be0J<i?gAsEB0|RiE
zz4WyT_W5QrWj!7w>X7S2JSzif7Vy21zu6Ru`(kbZZZlp~8kMSA&yPNwX@}K}D1itO
z;?Ammfyx<+bJRYP0{4vBCgF|aWyND8(mb}K+SHPk1zYvfvKSFb1<2?JeOR+Urwh{z
zeo@t?O1OA%lyK6}SHeK6ulJ;(GdJwgsi3ocWt0etSAi0b=fCo~vbY(P1P6wq?mjTh
zhtKd_VihU@ue^?_tI4SNrmOYtSsuWl1=Wb-SBtgW0cKrV3h%b9m*54AHN#bxz{<c=
zb)$Y3&CwE5>BfaB8sJGqh_X>0r=IyPfz9P2;1<5SuiKA6eYKNNC=N1KrGmo|$+Hk3
zy9`Bab+yb>?x^Q2YSx1qDud21f&N0}3ag=y+RSYnj3xag>zu?P@Hg`Zdy67Ojdu4g
zWG!dF$Ofi|i|zzdBDbDZ>lZ?d5LR_2di*)Ta$8Y_BnF4`ehVX{uhJ;zU_H*2bpKDd
z$3xIB2!6JUlu!c-GQ4+yv()h++fqgMAVJ7JXYu3ThxT{pzMR4^QcdW*X;{!a_muG$
z0^|)(YJ!3<_cI8X5LMSDKH+y?FxM!#Ik2rf{|DH4-@YR{Cat&rbq<VG?_HXUzLk$|
z5e`lRe8{kC$xgXR!82)$d9f7uk6AS<#$Lcwf5FT`BI^Pgp7Y8<^ZPxSuPv`~<{qp-
zWilKVTPf-XU6OVUfGb5%FbR_S<02}XtFn*@u{6Niv0`$dAUp?-OrEpEQ4;hB>^f!u
z1*H53p0I*LPdxs=vjFz*;op)Ow4r(y!F@5ib}C&-ta{hisXJ}or0v>@{9snHt?(cQ
z_1F&Tk$rt(|NUYnF?9hy3%f%OZ8q#zOr^{3om?~=@wy@5pr5n&BzS^^vA3c3_YnpS
zCO6usC=rK8A6lMViz4&fuylEv&&4_TZOmOovo7`<)!2&JY6v~X7&u3Ic!9c){;J+I
z|2mPJ=ZF({#f2CdA6m!x8Oa5y3pUCLx#lYj5rpgEqnklanCIXak6V#_Oz{%w+mKf(
z0L3I>AG4_Xo}l>?H*#G;dtALAPrez|W8pUW&(V3AO2xFVJ-Bqr<mJOn*Kv?aar+K0
z5{X-<o@?f?LnM(_e915KS{F`Pe+^x5AVY3~?nUyX(dn4}SHL^&l=9m^2<iR(sMdjI
zwM}clPhO{(182foR_%J>TPN&8%&qGn?|5kGkGDgy3kHLPw~Z%_H4QfE9<4>miN1^H
zHiwN0q3-<pF7XFyw;6Kij;dDZ8$sH+1%orD9iT1aBZ!fhxJD_;`vM9fwg6b~d#28-
zi*QDBw5TpR+<y?;9@$ZFqxM)-5mGa9*J32TFdPtPr2y>OB4jxmnCo$)gyl~jn<DNq
zX+yX4o0Yr}D_g+OpCnTACdr4|qs$x5!0{|NhYMjer?~qpCe`5u73U+2=kho)(*nf1
z#pz{K+E7kr?Zwl#!7_3|QJthawxM_hbEjY{MDrbn>|gB1>DGIfPstlra{Il;Qz<f<
zMQ7Zab0fv1sP7_g)Z!iX!X6|Y{PRY_>ZOW)m!IWpxUOWtX?Nfoehz{H7MwCcz%FI>
zT9544qEv-zWZUuN;2?xHjFuK7nyZyCjJz@fTeA{*-9q;>$HXk}k9B%xz>2w7NV@Wz
zMYb~BST{`!fX>iNPaT?%`a^!+!Q45{-x&L5FFNRZffBLzWEs5<Tluq<6lKy=uez_o
zz`leXW!^f(8809OMHlM}zLDc^WK*}r94Ucu=`;fHTs)y=8oS-En!gfV6m>k+lg2*1
zPKx)L`TGl;`LCe;;h3+u5VG#VyKHl8cW`y@kybpFQ@){1`w&u2j!E{8%iJy+tb0q$
zF@=8@!euiL%0XmHde2Bs5yE+@n^Ed<VT}(H7QoXoO%FZpKs!5$Lfqf8Ruk@&O3*{n
zkRFEM%!Tt-DM<#xJf!Ie+}<PYC}~=ao0iGadWzCc*DRW~^Dn#ciMZFefb|6?sAmem
zwP7>@vpj3I+4xfa(DB2c+l9f(P6VUeDp^py<Bn-4A`zgnANja&ZGnyR5nj1If~KtW
z&=tlS>0VNqg5S;IHabPPiOnqbbXzHQn<!c7+$wxFaANbd7CZY5mtXJ;weobC!jUuX
zjOpcCA1&ftYh5DL-pfjX$Z+6Kak>W1aLQgDOfNOjfzWP;pIG!M4zJmLr)tC8nDvth
z=8G55`Rci#JZ70*IX5KKZPWb5BYaY0=J#Jcc928YGH6vk?Nc4T{3}1|d7QrkXw3QM
z8&6o|n3kh)vnXetO->!IV=VgDXw@U+$G#L*M!yI&Hs^Zas!J$PKP@}t6Br(?T)B*T
zm<%cMf4B~1u&=1t9C-)v^mqVc1>Cz_e+0TB=NV^S21}P<S~FxS)@;Tz73oRX>O$Mo
zft$h*{*=44Z-mi!TdI(3Q-jihKA#tvIH|<EeBB!FhB0XvsY-MnPtWK1SH!Lg$;h()
z@UY#dvSLd<q0xDsnNde}z_vqu_J@`4!2rc#)y<X_h8GNw1Ss0}-7k5e56OIU4PV7$
zl_?1K*tZGmoFDCfy!SHdW)rUF!Dzxa7B|+Seib;9<79R?hXzP^6pa?jBA@vR`f>>}
zi0`xJ3-w;AYWlLFYPq{AeNf@H!Uu3*Pck@>CAORBx;=qS5iZ8O`YAxiL&*REFj5`p
zyi(XgR|*Zjl<3xdYjNFZU5hxt)z*y-N+xCZdnN&A{`*YL2P33ewQv9{L~`E-%{!bJ
zTdgzCss(o+2UT@PQhUvW=Ru3+HG`%MYRWUt#J8y=YE|x$TojUaR3_7|n}^d*_Q-JN
z0%5PmjF)mg0Oe#ccajc$ZEqnt{6i0wB8O%1d1z-u!g;qmmc3_r)*v(Xf$(dmkjewI
zZAHbYkB1%fIGh-%_aL)Mot^3nrM^^!!vhtxZuc4ew7V@Pxqu!<QhXDeGgnCunWv_A
z<n*<RXU=kgcM+9y4OJhWV9-_QJZGiFGvgNiWKL%+Ih)q!dtYRj*(;0n>)dCZ1E2ZI
z&tS~&Z;wtg-UYs7FepQYbnIZPIPUYHgyNEnCcJB=A}VFYLwZyu<Etz`7Zh+K^f{5&
zx!4vQWk^bv^H*#Q;ifhc?!uv;qrt653Y&RjixJ<#5PuRfL_66nY5!c_!q>yc8^<DS
zH@b{^1W=ESs0Wneb6OlzEz8Bm=7L3yV%msS@B6|=KjJ#Tl7V?N=>J68U!@O;V_<ry
z*y$sC!*#BPmX4e0+**f8%C1c|LNQ@Gdng#|(LMiAU!%AF5_mC44+{?kUEFTL+MLMy
zFv0!nwkh;)^0;r8MY_70hscnql!FUz)~WID^!Rto<A>I<lY2$qUb&h%rO%;lrLLGZ
zfQWVS=z5!?d*^@VGqc3K%}slF56Wsm<+9p+B<FV+Q}~o{irwKXzbGOMDe$ZA=;ph`
zE{7`(mqK6r-g929yq2GLA7dU;Q1XSa(VX-+H297Bsw}s6U2W!XL``<u7LC3cUh<C;
zby<%uqVzQ$V6WSZ@j1v8Axe~M_MHmMmCyBxlqFDgJn(TOteM=a=i|4w>bTiW3$!Ia
zB}WopVf2s6M}BLJ$)vZi43?6B{GKf#SV<qu8fy7#G!_oXv@gODcr$1)6ZpA2YB(|P
z=2(|>EGI{}ks&t;i=BpOlI@Tj+~eUuQDcRJ+twZ6Xvy<`_P(h`iA0f><-OvHHjSbe
z79u0$b0)bUf3qyGD=+qx@~g7zY$&1T9((L|y*M-(g7yIYnaMSHqwf~`8m%J(|E>n$
zfmc$2v(-262&vJ4AKQ!Ryi+wC^M#BK(yA*I^#6~wgtEL8>)rD0RF(1=lNan{)LR2U
z2opln^LOhWbRxH0+tT4@X+wb6?YjW~m4Y{wiExhCk*?Q*psW1ck$(EFd|Nx{NoNkP
zw}}8|c``%lfBXm#GG#A!{jn$WP1AnY@`4;_*DECGrZ12#9vU>g0d?7SnvIy_wiUiI
z`JwGkdMY~B7w_AvC!YeQc{~)5qu{5}7HPMESzSE8{I{A!D3jF%aktY}pR$7gS>Rhu
zeq#2Gqo?Z$EG_q_B3<1X{K6<*6@%e6;Ne8dvr@9ZgeVhhz2_${(VQw;r1k*IfA;Wx
z^>qlJN}mJmLH1dxsX7NIq}lQN)E_2fQ{QpI2b@A#{)r#ox%RY(kgT(tmI0a(LJ(zS
zh!hwOB-InB;TNZ##L15|17*#P0TNroV?G3l%Dtkzmq5#VC@Wu`IJRH)ljWqGVU_v3
z%n)q5er)Q{otGTZ`na?|@t#j*M(^Uy?JZ6C#7DxJZZ>m=ASgT(l>~UdD-n>mH#yg1
z%WadNh|Z(zY@Z0$`)OHwub1gIFzhocU4Q`Uj;%v^Ty!5WZFi&%p|T#ug}?cTLO`$b
z{ozXUh2SP{3kg39jjF$`rIf2#rRgqH0uP{5{{6_{b4?t>w~J$I4cBtYBEG2%U<ZS)
zK<ACGz{&o~ue3!S^c$!1t;3<bO~^SFKi`5OB_NfUwIwfR8`}+I?Pl)*hJjpsa4*T1
zqI=U_Vd3`bs_=?iNwDackyHS?U0IbgwBNn@tJ$B|50^VLe2EAskXa?SkHfg3;Hd?<
zn&CH9o7dIwse6cn<DdO{YrfP#(YJQUi};F*!yIq<4Ct<`C`dn6`6Yvfm)$kE`{KGi
zl4Qnda?1Cbnzm)kltk`JRe*iX)Jr^p8yV`!@rcrxVshkfN1Th`>pXIV#1(xiy3vO(
ze&3#*=4gc#s7G!{GDirRXPC{;5)_pF$&UjV*6DC6ucS68P=qKC26T@NCk#9_2CkEP
zbh^2274tygvSvZbls736r-_V^AsqKs*B`RDe|s<5{MPTg$o9h3sZL^O$VtUh32t`C
z$x}m)6y6pY(wDX+FnEj;c-V^*)a+aey2Wxj?~0k`+@LR9WQ^#9xt1G_bt*m+;r>kf
zw~{ZI65)pXR}5U6`%gp)Vjrk}LOdCyZze42=Gryb7@2HKmX<Eryb&2;%OC}Yu7G~V
z7}Nz#-=oC{(x*=G{rsJ<QDG=g>7+mBMmdXR*%WJ*TXLG;4`j^3oy36++;uvLe7J{^
zheGLXFFbD_bk@BH7jbiVfe=|jMqh|6?G7ZT2S4g}Os*uu-l8!u4$Qxq3(|>P3b$#o
zV*5IhrCE4WU(Utl(I2jQkBq3N{Q`U)timkW6^yPN16wS(WTijHQWJnYAQ$h_Bbfc1
zfR^*jnnk<H@od0#`XyG?<P_VYhk?B(^VXjbMjN{gu3PAlgsOWeiR0HKf+~_H;{;-x
zn}!Gx?vvr{fF~t;(&Ee~tF_77eP*)L>gbkA7!%ZGK2kQE<}RRnRV)Uw%7)D9C?;9b
z8j20iek*yQ0FNk#RNph?jvgUSFLj_6T^@!;y(T}3Gm0CC6^8~u=ga1TKH<z3z6)91
z{hiBJBqVogs_(}xVPYA>ncF_FmC+m@b)8^X3rKDGnP~%#gVe?WSBPXu)>WtK;C&5p
z8i?GnHBvS|J5;m*SISqq8=|iIq|p55K-37|J8A^Sl_-)kjL|-#+UNTbudSYz96p2*
zAb*7H>H_xLShrRMw}xlJ0)=uoYSoO<Za={;AL`C<xgzp_Y~CljbIeNO@ZHx~R&zv-
zzQ0gXvhgYJwfExLLnI$_x-dJh-oXokliTa%IgmUx9-!7FUA|)q+R1{7;e4DVkOspz
zjR+sVTXVk24_!n35|2C9Wl%>RD-Ylpx)lQVT+nw(7zkJ&SoLSxdCxn<DaIPHj}y`}
zWC-8OKDm?N7`t$mzY6n<O-AhtuiU6>pg@CXAZNrc>*eu+MVn{E?^P_>nH-fq$a@sx
zV`f!2fwRv~OBlF(mFSyssos3U9L(M`5QcQ8i$h(YX!Uo$P<T)YClSt3cH-0|c4Qg6
zLyDK+8<bz8bBa5yxlrqM|8#phGvA%Bi(Fy#$G#hbN5{}aw+&`!BEXE1DhEeJL;zAE
z0r6$-)Hg<2CeB!nv8>ipjxLBX!+i<aqk&Y~l*NNj-nLci9+U-!s5EsWwwPjjjQ{-v
z3a!|?04Y-FKl3R+`Kq0JOY9d_N$WPL9n(ZyCkMkm8xZkEX(!B-<!|RMJ;#UF3r=Tm
zH9gy<afta1Qu-LR|G)6NBVSwTc@wc7K6LBb{~-3wk%G+Gb)ivBZ=pSvguIO;P6fy-
z!3*?D@N&6b4&vEZ7=Q)^7if;fJ7L~3mCe5%TLJL4G0nWEPRj(Hnm|19FX&j*iN)`_
zsV8%<9SHw1N}BTom&8&1mkj|Tl$`V~Ufrvp0Hox$BGXTE-lm9jfSX9(R{o~Q&}fkd
z0R}cBdS#gvVgck@3gwvB^MLOvnIcinz|REL*q_H84YueMfWg@8x~QeGf(;A<LyKLS
z#F+;<;D!1<P<VIM?fu8`KlOPf``Wf=_t~DE^JKaxO<9Fm_V)8lAP0HE)xm>l_-{Ql
zoq&I1A!2}=pKcBwHy<!s;NMRlj<ScTO#BQ|HgWvrD)<?|8V?AXr$@c-X;=Cbzp(>t
z7KPeC=F`ATf<pi`T?SXN8)D6*r(qv7yzEK1k*=|SEz>Dv*JrSWFtR1jv1cY!9F`l4
zY`c>VYZYz=Paz4w{RE(oj1{S^Je~(%R-pJZ6Yt}AC&~`C;`Pkkx%;+bQvt3GZ&Ix(
zwLLpa%bxdS!Km+srf|U}%V@4kX@_BCI#aP0y`6UDs`M<l#yrShZz`PFCa2yJQywW`
ze?Pr$$SB-sky-qHT8MYPj;wr(i_ij614t2rhetLAUFHW+a@QDcsLCxUcpop2>G<_w
z@8FmWIbPuTXt<N-=K=*hx*`#R&CY!9>sL4C>R)FI<h^O(uHp(Jkb(w?K@02{`PO%v
z8{9j|@A(omPrFVwX-hyaZ2wRLx`}!{-Q>XUS|fpxTOKHrP4D&f*TlT{Tn|*#(=deG
zx3oEsv>X7x<@;Dst7<=wjf~G5LAY#W8vDD-PjE4x*{Q_#puh>|%5|;pF|N3Wl$^Bg
z0wHVKL(AHA<d}GJfchM6GlC=ZA-kBEGtwWrvTeAh4YV~s34`(~$T<jzqg2bzes@oQ
zUP~{FBgYtG(8cJy7Z~as`1nThY^qunhS#@d_j(6`)UqDbhWfiU0DsG@L)_@Vrx**=
zB{~Wq4RGe4gT{>zgYCDBEY7BfR|LCwv2euo4w?wQRsn`5jo0JH?sMR%ks(4KvKA0&
z-+5+|2yFc~kPQ#O?V{jU5pDkchI0_wO8IxWEGv$Yz<Qq@p-Q1MZ)E&;?!S0uY4=mU
zJ@w-lNOWkR0R|#Zbe{-l&u3|cTjKPNg0+X_vDNN}@Q>G@uDd>|;cO15!uTDMBTP<{
zWQM|>-ZoJs)19q3MAhms?%+VDYOi;K(Yekj18x)h7EC%134dZmy5cqVrE>vGDomt$
z)~6!Xi0`-`{8U{tg%t1b*M51WH?aBr2DG4f6a$`oLE(CYWLo5iIf$ZHZ~XRYM%tkB
ztsQYkUjW{F$M0g46(oPcNk^^dLh2KtHncQGWwTfwLXzv?R;v1_OrR|#BA*>x(lf@H
z@6lBSz7qj|*9HZU0`og6i}z}x@1byL&j(*TfbA=nhljZQkR=jU0d9vjXl7e{bAT0i
zVJ$wCQs`EcD^HPfm=Ty#EsPLXN5_TC!B+^j$H%688DfU4%0BiCd8LRj`U<=hz!MEW
z_p13c0f@Ham2B;T>-H$0PduVB`f=Xb=hj#2fI2w1P&(u9w_u|uB%+nx=#w^U+%)#V
z*LFeFY36J5kNQ8NFpn~os<}CkxHF~2;Dpm84w3Y-k|l!pp|MOm5<3eMp9EBU15}ud
z)VIINvR`|6{&tq8UzzZDaPFA{g$+v*n8h)0q{VxiCfK%EzxO*69`^RP%;zo0%vN3E
z0Ls>m4>epkKG*#|8W2?vZet0zzks69G$hXcAt<<2FbmUbx|IQNXJf6yfjq9QhtD)(
zKR*7#_;bN{L*a%W$;anK0jv9XU>QN=v%>=J6PSTj@!}Wv(89m-D&S5zhCP!D);j&7
z-_Cc#^5IJp_O2ktcUm_T<z(v4vMq_6rF28bq&Vw=`Ljzu?qQQtfUpuCvm!ObU<d3)
z<6g+fhnzd2{og;W#kmS8Z{%EqB_~o=^8F|dv%<O^hvA_AfJp|%!;YlE^ZsLMKlrDI
zfti)peWoxpqim225Q7=;0Jm_`zI<j}WQ4f)H9EjO6nMg+kfWS_TEdo)YS^dOO-9GW
zQ0Hb`4)afBL?cm*qrqWLN+B^Q5}2NGclJ4HxJL+x)2R+e2DIs_>y_O3*gfqyHdvT!
zR>g{|X=Yc1s)mU+(7kez*64A!HT89!PYFa`;e-!~87mB`Wrw~E3Nsq!Le?4YFepKl
zH%k<{{Wt;t_+w|l5dHo_0DQ1%#(x5IAjw(&yJk5C&0W`2Y1{VuIgzi2U-5E6OLSyB
z^lY`>)uraPNPj|~*aMtH7c3ZbJ38;sMi7$hPko%P?;n34^@ABdSpC?#WL0K+>01hk
z_j*Ix-H_e_^`tm=4@PnF8jrVNp_i2b+}z`Pm`*~2OD&2&J$_?=aK>&1Rd@EcS8nkX
z&V&I5U^d6gIOrWvwfK<)1;y?Z%p$rzOtMCk;9j<x7qw-UMQ|61Uw|iv)6dz@cf{^<
zAjPh@p|oB98`Qv9%zCjQ=INTdt=7Nw1769@Z>{)5t)}*SPa=frgH+tBS7#wiUpVIQ
z9QbYK?^}$-igH1Y@~|wAtq-cZXz^ykT)zA$K>w(ZR5!4Zz?m?4g457PWZb}X2$??u
zy(DU!0ui6j?g^D)#;^nAr_1b(*q+SLUngWU)k(m{iNzQL<Tqdezbu5g6OK*>JStZ5
zmo9QB5F5n)TKv2G#)|J(Xf%t_A!QW^0-Xx^Lr5#MF5*!_57>)<DwVKhg~WKgF?AF>
zpWH7{f3T7U8`Y~wNY6<GTB`cnDmWG*==&q9KCWLaKN;9AxMj#dS^L+v?$b$j>hBOk
zN6}c43U)pYuEPWWUyQth`XqN4z$f2`anL_OjS>~Z0mXMb>vjpd-wXIcE6|449kPC5
z&=ndOu6k7JL$4pJC6BJb%E*zkShAU(=_y}fR1UBuAwP8Tf^c(0TN_}A{)$M=abB#T
zs(q?Hy{K(8dl!gAdOYz^*!;j+%=Yc$H3@xsU{<i^&o><aHL6qrji7O*ocu~)?u?CS
zn@E97z%kolF!wKRKV<1s_cT^-f2)d^UDIk<O=Ob37Nm=T10rwMHM%rYZY$y?2O1!8
zIFRrwPQ)cgCOCb?IX;&7evKKXjM>!$1V;?&p{aNSPl+*Ed}?kDKRydXsPt3je<aA)
zWBD+~P;k2zMQlJ0d~eUWYgES3%kn{ipx`K-o?C3~`vx@!yqKYrS;~MLg<4WK^He<b
z0#~}+xh@Ox{?X4$8;zwCzD_=5ZwjQx#GYFeg{!=B&Bs>gmN?g7XG_OBt<<7S5we80
z!_Cl^i$fi=SSlNd%k5sBXHu<PSw!j5UU*|KgqB9jleTuX%m=#-5Hoij=?l7iQegeb
z;!kvzCC&qft7vaBySZGB%Y8ZS>}VJPf*o0uiF=s6?MfoFGZ6{Y^wbhT)N;!z<>hZ{
zmVY+b_L07yX0I#b<A=gBLI5C_;L_Wq{H&p){JhySf1eYj-CB6&V+BVD-uf`-Es+3>
zJ|fVWYz%T+7^YyR3!b6mw6N#3n!vM!{>SjAXK2rX#5o_I;z~L8IE>euYqxD=r{PNB
zwLHI1h#hev7FH8Cw^ec&oUjJS9oS`4#K?euH^f+&lXT}!*)#IL4U+@}1=0F~t^40U
zZom;5qY0u=H3*vWvW)WE0vqr-?DqWtKFwK4|8*<Gj2+V_rd>OBfy8BFOPv(ou5Cr2
zrttFQaH-Olk_xHS*P5DY$g`z~4;kjBOjU-zC7Vx+8tTn@j5`Y$SgRj)!U14L@3Q`-
zEaJcsb$)eCqa+?8^2k+y8=~e!$<dG3&|YoB%u1C207w$tOMcm2vmrx@Sn@t{GcLJX
zLf2s@evsJDup0u@lXS$JsSPxx&t}8mHkw!ViwS*bv!?I!Ng$>IS!h(sg;0eedI?6;
z{TB=S{0{p(C&ZvljF^lo?;>L&K>BxfPCG9CsOsY3$#_+=eapP0w5<MN<z83B=P0lp
z`af9mMLNU_z$c?D@b`otPdRU@<47F2G)8iYuOPHUr-E>eVl$i^fYrRZQU%QaJ3Pp%
z+ZcF1-yw#l#~UaNWewda_#R4cPxs?pl-Flh7jN^db9{&t^`)BAFuUS`Uy1k%d~T6)
zDX;<;fd}DgkJawqC#0rRys^Re_s0Fw4VIIeg8U7&9j_`%FzU820P4<v>2<Q<S#^KD
zcFFCd?R?<her_ti;V-OtviMN3Ztz_jfu(DeFbqLsE?Z@XGUKe|qyC}Dl>i`++E<$8
zA=8<6ncI`f)O+P%Y$sGYL-za}Jmy=04-s|9IDc4Aj(PNB55FEOia}o~jM72kx&O#I
zeSzIiITG7gYGA^$o(z%la8C*NOL!DP4iMK=UCPg+(x2AVyU5;as$XrbV%a|d14P+%
zbDvd|h*$g7;vDU~eUE2lbF7F{Q+uT@m2Ykq*=UbNf77_b<2tN3hs%8^Z_o6eG9Xbl
z3b_l=BNMOqm58fX6{YS1j^cGh;lwc+F6FLpoGP8wA}WZ@`v-#Yd<lD08fsl|)_;VZ
z@#F&qch}2z?bqEYcTWC1-)woMY0yszG?Ej(p@*QDoUp!t1<_>)x{jh7C+LxZ!di{z
zaTPq4MXwyBgwh{-h?9TkKGa|`da6%NEf!5v1U{_+aTmH&e7U|4%lcd++0B(*^6ygK
zCeW=~au;?eT;r}gCZpdNL0P}WhR=b#j+wgB9ph-|$Q`dCX^GF_V|r<k+P1M7sWT1T
z-brKY{))b(_d3L##*~Piu=POh6+@oh8GxQ#afjbioiwB~?Z@0VI1ouxRILIX0oR|&
zANC9?Q8ut-+!@QuSb7oJ#6~G82`k18VJkR=uKX$W)9j~2#IFol%t;>t?Z?|%45Fv`
z_%rwagH{7hRlG_G#;LB&RIqCTJ4@-;tp76cX|*#@{q^8uBn1zfVUDlZzHaFCT-wV^
zzI8maJ3YK=%_x)rGfMxs_%2YDrJ0KdK3xL1i(X~FlopbKFRGsg1s|UIzIs-6vp-{v
z3~3`g#y?^}N@&104&^{XF?g4!a8OJbih|Dq>dl%FC~T7GitcQ~JHsD%njFa6S(=Qu
z5&%Mg@%uus!2iwy5MLT7NRK1Bj#2w&2s0<gyA%jipSY@9Ja#JJO`Kkn1{DTg0Mv9|
zIg@JLqvX4QwtdI607kZaoDx~~%}3e^sp*X*M?h>MFSA4*(4d_i0Tcaus+X#dWQMWM
zT|cEAyBQiiSW#8~M0`r5>p{gB?Em<cC)meVBlMKobIibed5wGP+N>HdDXy@fIA5wD
zm-~T0s7kI~r0@SY7y-f}WKw~anZ)f)JO}9re^%fDR#$Nq@#sa)oY}7roph|EHSL$Y
z>H?|fnOp$<N%z5@uC?mV&d<L-i-U<b2yU_ta`t^62CQC5uMAOvcK&C%dXBm*VyFxA
z>GnZ%|J&NWmM;y>wdQF(-N^ns1gU?`Kg14i2l8Ry{~N$LnkalLt;~rhoDZqz?i(|x
z65fB)p0F>QUv0GJ@$T!cg}Dve{||Mg56R_%5Z<Yw`E|}oQ_h!T&#N6Yg~y$o8*kT^
z)c(lD<5{HPKj4awhq{Yg+WgyXCVF2ozyopm%%ZH8_m|w+^E1|=eZd}kRl6Vo9UE)i
z0y~%lmJ2C_cbUi)V{mZ%gh!PnX?b$6q62K>#+*=_4XZozo2<xhnE)y3wknGgRuize
zGI%K1e14(GHO?|O$qJE&)X)gHx#ya<-E-{q5<%HK3xQIH&_U7wG~HzeJp<PooP)Z?
z@(jZ?;*VBg2<vJ=uf5&iOd0077V$Ob+Pu!TyxYCt-vRg^Gje@OMXC9YhCyZqh@f2i
z$@=`Z@8q+Y<BV+)sj%d{PJS1P5gV(Kf-i&|NQ(cSO+qofL`&Rzd9&$khlse=1X7c;
zKPzhL0T&uaYcA|)ow=5F()(G0t4GioyURGMFCKTd3b3kOUwv+c)!v-afA`SHq(>vo
zzqJ={v$?zy_;7>VLgmgo%2i2E)_GjRe`w>y(dD6Bq!P-z84m^e0Jr#GtGE61g&|Fn
zc45*`8B$z22o)f8CHB#lGN7!eccWrPsyGG4+GUn7_>|S#M_rUykh@&^Qz5ub_0Q#X
zlF-`e>1_dM-uMTSSe<B~L?%A8odL#e7}aCOJ@wXEfAR?e7fJG;p>9$DY{oh5qiqIa
z#{qo}GiC&=?VJuoBen*QQFkot|1UeRSP>w7VINX>Yqb^rtiRHVe{{{<24yF1q-plS
zz;ptqbVZ;Z8;IPw%-(^}qwMkVgVN@xC4CK^wt1_@8+6Zro6i7#Szg#^MIn!Bs|9&G
zQ^c=>xNe^9YT}x)s}Mo{fg|=wCewfn+ez^jyh?yUK`Vsifg&5nScA%RAs3kr^hi@k
z<>}qu)F~eC;FrO@{o)2L(eG2qS)P>@*T+AE4pnJ&I%uwSWz&?uah&_>PK*h(R|q92
z=8u@qriCUmewkK6PqKsOF`(UhbVisTL%-w;e?Kqm54q^MZqsCic*%r_IL21P5N0k;
zt)Y&mbNZ;V`GcfwL<be&Fb%jyKv{4|2z(Psl1Qx4kS7Gsr_~cx!~%aS$H?q-$W0e(
zd4IeS&iQ|+dhd8RzvmD1*|k``w-CKYCxQg43yG5GbraERqPJLGbU_ep2_br-w^&`2
zAP6E_^h67yv-gpFzV~<Uzxz68pEGmj%$b=p^PV4NMIHl>L_g!l#sYi53<;>z_F?PW
z!V9<(YCdm$Im$ki(4F=N3X&~F>jiIzs3Hx$<O34k{}2@HG|M74|NQCjReJ}=g$72B
z1k@a;OVXv1BE1s!67n3zVr4+g)R4k>nHH!IprfDiW@YWBO1o=%+AG)XJ!fgJ8v|YY
zTNIH4BvYcIZYsbwd`Jv3TRbP4(p6j`Zv4>1JwxmJvMDV+Vdh!K>hkMs4gB(Rm5{37
ztNM$z-Y7wiGS34z6e(CO4r3KN>E#ow$4z;NOf37jUcb3`2(7|`b*m^}N-(QMT0X*w
zfiLx^J+@SlX(_ep-gmd+8?u^`2g2v{5DATECze|s{=_FY04ISf9daTX0?;3}Jq>$&
zR3=9^Kd!s_#kDr(KGt&7o79KW0x}fl@R0l~&C7UUe5@d6%RsTb>_2Pd4#dL>2x%XD
z!#jFyi~;cJOs^C&eX#dPE#l%9T_U=S`SznY070D_3MT#!0}m=`xPf*gcN=eDtf!yz
zBHxPx3CV$B{_CkU7<)M4>w{)eG4JW?s^_?gLBwn|f9~MQP+^c~!@k|Qeo{Igj6=(v
z^NEa)(21K%y3`X49XY4xJt72)JrKTs#^fE`aX8|cxTfaaqYtrS=jt(VRJl_=ffe4)
zYw-6uziZIMqw%8vl5cQU+$pUq?NEfGg-~0+$EWVaYnuF%C}oiO?i;o^WmRZoe+oNh
z*My;Gg-qT1H*$T_e^kYx_8C53C(gn74pACFeI0=iZ8b*}y)Ut?#@5mB;{F@U19`MY
zP=r;qj}m+xTjKUIFZ#Q?H&4;0Rk1ujO;mOI#Mm^}&=iLgV7&4?_5~0L1PoA2oWk~r
zK-c3rt=HeBaNZ(+)7~S9iW0-)?cBuD0CkjC8rE1O1=v+e`~-}jM~cqRa5yj{VNDHg
zw>{v9LATtF8c@4Z_W%?a)hn~%4uNVDs;SLu1PQ&R#KL$^32~E1`C_W7@v!yt?FU#`
z&mU?|T#!K6l<F0MJnd3YdbdNfhZ)`DYIrQ)qwgP!ILWtKcVSd^U7EJiHT{O(JcZIc
zqKAY5Ggtokz5x9)G@nKPtKRj(L^X(z<ngYr!nVGbBA*JNsEOL+(KR?EVrSboojkcY
z*be{ScWfb-zlyUyH(!dcW<d|1wp>~Uw|nm%yLXV{zUTPKrO_2epV<Cv+idqvX|6#Q
zVC#v!gM^Vooj9%pwHobe^h(xnmHJ2g9`A$SAEZLEOyh$r?kMSI-p#$Z!KsRZ>=oVT
zkh7km=}Wj7(k=5&0;&qIVI==DgvgHywMlmrtr7-D%3An7y#9>%t||5VS*bX#u(kx=
zD7(?%GM%h<H2>f4i9`D6SLC>MxyD)*Hv7}Bp$kN=#qC}{cuDV~P!@2Y$kp%Rx9<ug
z$N9IwWb}>@`u*DJLFo;KFn3DeO_&b6z9=s|gP`5ePz0+Ai2k=0e7F*<-y~D=!x|Qc
z1Bk^1$`_UO5O>+4ld@R7t82Nq22w3LFBu`q|1lee7Ca5sZ<x6py8FXrfT0eb+E559
zmQJqc1$i;2$YV7l*46+XI%pJ7M{y-81c+;Fzv-&Rw5=eYmsbNbT8Z-d73LEvn_1wS
z-)`V-Mw6FNSD2_fs5m8E7ovawX}R@y{{&$_)CPOOY<$glriAqjsqX119DV?By{Vdl
zx%ijT`yO03F??Ad^trLDg}JA$eW0ziNT4(kZ}2km-%8z|>)=Hmv6Fk@=U4?6pBsB1
z`BLzC_r>VB>yHTaD@wF-jz@bcl|1QPgm^52p|KDs>i%DsSRQT_x*>^tz8d|o*ztXD
zteiRYN!?r2P|HWejRK!T1=uf%4^!O5Q`qmus;`xKNjXpelIou&Ih8b8)&6Y3E2pBH
zb%43q2QA=uTey<Co~f1AZtu0D@tQTqUFS$r2*%d9K}tdSx*$CS24wyXGCfCc$+zu%
zAoTwJxl<7K4O>V-Ms3nWPrcUtxIe!q^Nt`CkStPY{5$}$!78Dg|E;vDuCnlmloOS+
z{kC^gc9x*aZey<|JKrq{px(?5NbS3PF}Bn~{C{F}BKkNodM?AI!x|Nb2zw=z;cP-x
z_)=1BoT5Ni)a!dxkOgZ_mTuwaeh@m~KVi*cZo!qL!6869nhO%4_H4smu%VVKBUfad
z<c-nPSv7BPv34PdSQO?Hl9(KDV*jhgby+GXl_CT}E$!8yb^(k<<S=vuYAIwCW;8sR
zM0Q{N$>^M}{D(BlVY`PKBt3u}hW78dfbioe+F*z|fzJ^dPI7r~wUk~N;eL%%w&*yu
zOnWlcz8&T8YHZ<_z$*!81N6T+IMHKVd5h0zpmwG>%lXyo1{U(V<c{0iU{(p|ol1(1
z2KTesMd*#?#TN#VqA2{T;D3h1cb`OA6|Oq7+D#5~1WdkqU}wKb!gKR|`wgH}ZVaz?
z@V*~Ie{e_-RrF8SoZ&G&iK(XuW(?lHWq!Htab1hRR8^MEzkqmgm*9f~HO~2Yg7U-8
zpa(ZS#i<Yx&}Rea8ma0_HU&Z4^a~Kph5YYXSYWrBsl<OM=&XmH$#9UUHQ|07{Iq~2
z)jI+gv66A}+Y#Xy%&4HA{;qLX1iJg*EQTtV@ARU)yPs)A<ZYZDj<cotO6prZJo~})
zh2FZ+_ilE7PI!M;bZ`65^|!EX*mTYo4G9<oVL=l86-ww*1P<F2fz6J1^Ft0GNk8tm
z*|5BCS1+QoL-u|sSgtUk?ePe<faAn=wRP@DW1IsPsyHHG^F2^7gDwj+vm!>F;J*L%
z_SL6*#$JXB+|&AEaD6hpJI0-<|2HogQ*L=X;|2_442=BDv!1himzT}=`jLLtP;62H
z(Hc!@l$G`MWddsuS^$4a@$W^ZG<lhD2v|S!W(7Vp+D+s6kwMY?HMOORTRQht)#H@i
zs)-vFo<mTASF-Lab6^fl6!3Wj(V<oLTSR5)OW?8QElm?3UzDwn=R}|{R8XvZ1e-3D
zj7x^V_kKR`-eKc*gGx*7ym~NuXDl2z{KojYPLmiZQy<O`A!qEAN7w~*oP{5ZljLYo
z9@)YcIK~FSa_~EBey^!Q$l%{JDbF+O{R0hvxt7G+v>Ae?f?m&{h?drw_j~0$C%-fk
zXj?d6$v7$mQ+cYWolHaO{%$efXaZCj&U)>geVvfP0xOHVh!+Q{ksf6oN^?W_+mSUF
zhU!8f<G@5H7IFtg@|QBLgAY8%O2e4Q#wI(eJY5sIGhqc_lj^g><k|<UfN2p0RCVCH
zg=U^wJ=amgH)8~|*j6@ZXC~(-n=-gMw`buRmQ;$w0qRdTF6b)t`J%0V;Z-m~q6X|~
za)kJt2v`ZK0<UC#IEIu7v0HBoM;AP#@9Z?}?(ex4(|QL{lmHPKI7mrO`fMs<^PsO*
zGvPNC&g3fSH77FPi$yu6n9PzXl}03*q5wZ%R0R@S=#uaMaF+prxM_vDUd$Z?rhSF%
z+LbuZfe%8lMk!1bw`&Z_oQQ**gz-l_gwQTT*}97TH(5<*UIFI8j?Xwyw8XX8^u=H%
zU)d1MMnJp_eT-#azpGOF_n{}kP+m$*x);WYVC(64?KBn#c?Mkh=nNm;y!(1ldk8UT
z)o2V&e-UR~h0UZ~$T0}cq>mk-!c=o>dAmGu;6UL_NrE}6<B3_u1}dK@P~(K?JEO_Q
z5KdF0B{Q%tzW>tQwuy2+gkhR|g@hm@Mio%RNP<;!w!IC$jjWSVPb$P|Yx(kS(WCv8
zR1vdXPl!dTQflBy-}vX`4zIl%AeZN<8mcH?n-+EP&RJL}jOt(M4zu_a$8i6!+S8v-
zYaRM!A41|1@m-*;&NyQLRHOKR3ty_OzO!xNwBC>M6J=*Q(P6EzE^0-{7?T@0<BGJ<
zgm_uT^D1XEbXlu|EWJvQ+CNBS(2G@QuXE@!M{ges>-RMIMvi59;wLLPie+B3kwKL2
z-Iv-3Gd8W%eJ+R01hcO9l{h6MMXesaaCYT<BWB{VmVJo(GlU}8^?uDuAH4Lz^HK^F
zDH&z@DQ{;*=@LSo?r(M#u85rtZP{D0&pzi$(lKepTMnnjM1U~1I(uQ1;Wv(+xfXwe
zRPgpAu_}Sze00FDL)x4)3K%?R!AOF6W^^db-PMA7iva=E7w2>$qSJ;)&W~n-R0e+#
zK~>k2G5I~phA69;4LGWB)SdwOE_2*A7I+=(YygU5f^PG^*N%^i$YKwDGSKlbY)YZY
zBg$oS<@{?`rLBmXsaXiX$rLxl{<>r*W%9;NpJi<lr)n^77D8+eNh!bci{#v|urevy
ziO%^)fv2#GY{x+(0(o7)lIJ6l2&ULx^%k)agdXDaccE#BrIGw&m!Fwd{A&GqKTDpt
zHd@kk;doVk;r6<aV>PyW8#Yjp#$W4E_v(N#ATV&ncYeyVKcvnTr4J&c;Q#$DNll!f
z1O#2DV`y2;wm!ZTeo<6!JHvc!x_0H-u*!1*=B!+LiAZhy!ic?S!RAQ@!qi&p<#`u3
zz3dN2a!ehB<YXIFN0Cl6WeZkY-5hzsmbhm8_|}6I62`X&GMg6rG<8D0%-cDggF?R-
zQx~q;G@f}STivDj9yTA<J=IQ|<}>?>T+XLS;U@V9f9>2wPOAw%V(^iQI932O`+&a{
zeei2|bdt|Br>{}1aMBA0H4VDwpclTr36i|s3Ii-&>GisPo;B%my{r82)GQ`Kh@)-D
zY>W+;LH74F2Nb!H*AJ8nv38BC%)syAZi<7IAN&hir0)zExWuzqf1In<lzd~rIL95D
zk(4p#)p9Yu();)uZ%np2$7J+?k2~5a=8fbC=dnxiEJK$O)J_a2bm0|#{JTW@vIwWn
z94v?-_8BwC(v09A-=|+v4ctUxsO`EHA-`17fl1G5c!teJzY4r)>>X!a#AByKSuUf6
zRcrmINA3ZC9{7a@DI#Y;At%b~&2Q-@q%`{)sRT344dWuX^ROA)rWv}LZA_X<!b41U
z`np2D%W-r5TI?kZsm01N<prK5#dQQQII3YOzKM<H1g0h#TWAMO&RHGzh@_%ji~h`Q
zIKtVW$X8U57l4!~3UrCU3S%6wU<N0?@~v0)Eu#}WJWHLvSkx;)hY17URHEL`ZxoI`
z?=EOkqT*TXx-MQ{9HFj+x)Mh%0ZM%<|5mJCi0BLvXV4=}i98KJxFA(OPhnrh?qlU-
z6!#*^n!q|x>?YKnlR$w07Y{w!aFy$LRov?sEK{aQ8iVI8m<sS8mOUtdpi?|U$&2*&
zrLCRk96n8A-T2=KjlMiDqj$3~a|H$52)s}0j6vp7ueaW@g4}(E993tyi>4m}*dHOK
z{&2}~UNhGpxB+@x-21%VH)}uk>^;pJr5*{w1w-z@AsZOz;7e51cM;F+8c{xz!0-xu
zj8}b9VxmQ~7a=hzOJ#;!H>~(nDn1VAHw~HdR;hUj;KUk1c;nAc{!xtEPxKmdkaQ-=
zz?*p=2$Q*%^amyAd~z*^VwO|yc@N{gq75yH4|1_G{hoxLH#rwapNMg$Uyz{!!RU+y
zaZUNrqSDjCC40L*0ih2XDan|Z7k3c;)W|bUB<@K2(xT>p<CYrwKqh~W{ds{A%&U8>
zsdLZ_!HLY&0i_{C6_7o&L0Zz_@|ZMq@^#Vj?}ppnZgQqTumdLdos=n$3_5#nTq{|Y
zM)@@`j*fCq{xmB~l{{ksW~#u?lNZyYgMJvjpLa*qs+=(Rl%r!Se4$3F`(COr)72*9
zqR0zv<tD@Y4<0<^ZFY4!zmm;%u4PaNzI^%7;wBW1a#jE<WZ+$cx9LR%Bb%Qrt6{(H
z=~kd&R=PS!dyOVTfj_-RRam!!ECVtt0*rqQ+RWT^sqB<B-a%<~$xEXe%T`5FT)sx5
zn~Nyod$2f<hRQ+oRzF-2U@T!G*8Smn8nv<1@7p{Pt|^MQe+*+#glP`y^Fc~w8v6qs
z&!krr<Qc03!9U<i+9(+{S|=EEE9L)^3voDInfajSlssEq$i-RRFocyr>FJYDF9_E|
z`6w>7wF}2e#;=}ki9ls~f0;cA=N{HXe^!6w13k-om``8@^q5EBkF%p76rF9NT>Qd+
zTaUHFIX>r3p<WJ8eJ_ach>=8J6&H?wv6^o!69XjO)Y_C0vuwK^(NH(;Pc<^iVY}RW
z0a{L<AM&lZnPzDErf-7MhF5n1mZx%~$sfJ59eDG@o$F&6qEQjb?zP_c>g5_2n?W9X
zxP3tqS*ExOgb7>xpt0WvOd*hm{F`<@Vl>MzhAVV>t07|ItuRDqj)eUI!q(Mv$GPe;
zu3b2NeYY$8*mK^Yirrnoze^jxD)q|hseCbe>M~~7y+oJ%n$L6shfbLHBZQhk@0QLa
zcN(SOUBGuny#(dwC@9!&EW2z_^Nr)V43beBtoUO0t9R`Cm<uO8{&f<AHKAGS%FK7F
z<8JtVozXlRfCZkM**e3mi#;XQ;``saQ@MnLK6RBdh>o$c5Xrh<y}ONa_6+SNz$x9j
zHGWk7&IZa`!gDCK@^+^8^;po8tgY-NIICb>Gz+SNW9yOpb&;V96v)&NqSec#p-a*c
z@6M;cBdk~G%d1O+e|g=W>z|W5hQ4NOTDa%=cpB%eg{Q5gLhtvx8+N|^6<<h0qJo{J
zL2AR@qVEtvB*NLC11wE-CL@!g@4JBXuRBwpb4q<3pu6nacRUUT3%e7{DV=YFIA!c8
zlE2l{e9E6`RiII_SZCq0=BeF!{F`__ZyAUITJ`0=aE~rH;zMa1CrTf7LSIPz%_>L|
z$?~c$$58Q!$IY#v^Rk)8p6_?s!nM;0M+s0LsU)z1!MiZBcKjRNKz?8x`@IkVCV4mg
zA_4L*dK8X!{B3ohYjcEOD|B&2>qdMFewlKO17$LIiT|btT7!@Ez(`hu)<uWjVH+J}
zv!_k;RITi#)8Ho=cK-EUEz2>*;(^y;yd=+h$)ut=-aYi+{oi&AhutQ}{F1B5TuvkE
zt&s2vr+(dT`+y6@L0Db(v?)t?=8H?JxVj7&1;U%sxbi~iz=ui|jSYvYLhG4{FGpF>
zl!LWBwefFa=8x_gnJ6>FH?Ye6a3Ad(MY1hWBX3`MR2J|fR^SDL#ftL6uGvZX7dcxb
zyXUt(CLs}q5dz@A`L4XvPfFH6+sDNhlguaLP$%9i$BO8Y5OiG*#<)ypSs6`B|4}!I
zFvBM0Cx@XCbr<5t4B0n2(<Qvn`&fm4&#}JO2Wtt|JpmlI8z|dR7yl#4MCP{9uOF3E
zSevtEvaRhOwlzly<wIBWO4P;n$#AanGcDlW9DoZh!>u~aY^=`pDUI9yv0)}@3IHbX
zlf1nr-jsCRs*nT}6&%QYHF%5ylcI&bN6u#T)d*kp<zA{Md8#lwu1Ai!BSBT`RP)Eh
z%(N$~@?@LhV6B5<dK_RA3w<(Q6dno<*HI{Ek2X-_i)M_{R}xTp+ZCn>d_;8>+rIu*
z7DO;*3zlAogHIoywgI|fFTRH%#*Pnt6y-__5_MtdZUAkJ|0Lr?80SnK)CV9!VSl4l
zk-Q?g)UK!}o2LV>xAWQXi#$$BquLIo8-HM=%-@S}4qt#572Ed&fLD_JdWTR@IWJxk
zc-_G0$g88#k{`&YF1`Im;+`2-Zm;wh2!IH3&??WXXti+I3<Y2vtK@#7M3|>K=zQ}y
z_x5s1iii_fK;vSHPi|3OeEnzECIh2Xl{P_D>eZCW(2Y5qM57*#pGe!8mwlP84kxCP
zX!zQoJY?<-!#$vK?)g27M^4xOEYd8qh~#LKR%QR2cCv~6g(^oE6ZmcnS@txWcSD_p
z?epj)=;c#x1ipwXe4<LNMETyr>&@ej{V1`ukG)k#Iv=46kx3v@%`c=DRHq{UiL?~H
z@mDzdPZ{&2AKv(rGph3_wg+5BHkqunJ}LUb;aS6skVK$P;wqZpDZ&F;7XvOiZWJ^T
zri7H#>a(fR%gEJd+<f!Z1dy1}<5xaOe>3S}-uqhx6-W(kIUZF6z^uasbZsW+8@^4^
zyhJP6rP)87?##L8UP}>*o_A<eW<X{s9^oF|1^LbJ{p)2K9G&OH=RZXA#bc6E!*ICS
z2Hn9IikWUQS!Ydw*bpNiQ{S)7QCfQz4BZb9YZFNNcfXrUg}_{5DlDgW<ClTFG`bu*
zBc;JjdAuon5Q@keTzBkyqVqr@GiY%ZCH`pWlrJ_r4Ne+{$bPWUxP`gV#kML{=t8)e
z44R-~4dRe-?&Z{wb~W4^C*qzxYs4q*Ux&i#T543A;+s6DKG$zHuF)1uDwp!N0j!zN
zG)9hBF>)Y$f-qR@g-kJ4FKutbS(ZLDpU6m(MzBwN;P3@I#Td}ZR}W?8j+YU$u0Z_a
z#f~1sP|*LV&IBH0Vv2oCaZ|*D^%Zl|?y9g!6C@X{C#mUkJnW|vDWc=8e3h{mkCBtS
z`U)Qba(QmNs>H>0>GTE)1^wdm>9Jxw5Z&mL86XwjrE*Z*4@clk@%%?Rad{bKgvx+|
zh3BVA1cQiB@atKQy*?@wrdoypl76d=r%D?Xhyn23mUvWBoev+<(e})ezVxF&#Jk{(
zxVr!kAvCcj-2L^*4$)r*@u%;rER1Tbl!@vR_P2lBVSM&GH9xW8&U-%u`6<+p)uN;C
zCeS40!}nGeSxLHk_sXBPz;*wIT{PJ;_4`(k;uux0X~X`pF{5ZEzIb4(S&tKi8d?vD
zsDNC1_WELnbdv*&vGao{mg7G+)c|xO{_x}{)AfQ)M>nT;+>n-6jW5de@E6j6yC8V!
zHbzbqJVGJT1PF!Fi5$YdVr#;ALXJ%(&kbR^K1{9Y*YGet;#Buu|EJWloIh7lRj?>J
z+i!3F;QimkB7;dY@n|658BGA8{-~Vz#3OhNcb|sJ7mCs<jmjapp!r`ez!H-_#rG!Z
z1tG}bB^huS42FqlK#y-ilI4Cxop%OZ=)hy7_^-x=r@g9hD!^z(<Gz$?^v~@e1XJ>>
zSO5<=YXKDy{A~>utbX72XQvj{PbI=x6Bmxe)9-o=8%<iF>c@v2k{><ikZos06`6qR
zB*n-HgPR`0M}Tm3bg&w#`GRXJ@AJ;4zP?x_-^S>9D=X_eukYd(dYRnR<g^ZIMxE>!
zB~+jV$a9!GCC1p1o3=N?-~L@OM|%5^jI89&?jh{Y7KC%7)cw9cdJa4x;K^1&!dOkJ
zsd02{*6p87Ja?H~I-=z79^oIYq2O0a{M_e6ECT;KP+x=thnEtOxstc@eDGePsR2-V
z^Nhi~@S~c}WK=SrkT?m>X51Uu2d>b~{V!LW2nL23&_jDw{dJUp0NRaZ!-m~ulg1EH
zrr(9&0?u*<q>#C3;LRRPfkMu<5}+`^0Y~U*Yujx`oWyO9>45^-dpkJ04F6<E6$tU%
z7r4IMsjwzsQ{;TOp$X`1$P%E^rw6eJBuo00RtO_Tm%M~SbXL=S&a^3#CPLZ5S!L4_
z=*>3Hgy^Sn3S?DxV4FCgfQh9i03O=KuUG*!^3eLxvUmPJcYAHiA<o#lxpgcfkSH*W
zEkZuER(PfOX6Yavf9$z{{u_;MlCSr3c5j}(+}$gTfX2$I&fW&%fWgZI*r6{d4{Y~T
zf&Q>@@bx08Z>G`@5`tG_<ocE=9-uUU%rkaMOe96_a?v`e3fU<jw|@Hy|0BP{jM(il
z6ivvXV*f4}B0}`pG)39DT|{W;l7mQR@2LWjnq9)@Ovo7qlpo4fb`(`J3b5zI-r>lw
z3#a(GDGXCi_EwZ&6M$bLUTr|XKoS0Kb0mLvELDUA(y+jyf4!@VCZysG95a(0*0<c!
zb{=F5BR@w_0{n(JgAfVvD(!oq4f==@PrWFIUxWB%+6=uCA%vU(Py?QZ>|^uBH>2gn
ztxx3x14KFov2Opk9rAicRyroOD(EehDh05v&qv*N9WRco`)j<5R+oz9r+adVMx_!j
zI1K+VDP67`g&j7ua8!|jA97Uqw2HU-JkwUjoRGYtxe5TG8+4z)Ecdb^ts32Zns;{8
z>#!HyCSHhl$BzT`A~+BU$}=%P_oTOA7-3CN)_X|)O*%zjx0~HcXIbr}ghBNFN8?L3
zd!2qw9n{Nm5_SC={1w6AzsG>Y50*G6-WjtbYD17{3OQg0k^}}u?JA8A`J+0G4@FxN
z?1^t<AL9Sr>J>E7E!mC3=c$w)0lMKaYn1JBr`G5g5~9KMvtdK@kY&#+oMG_T5fZ?B
zbqh^~a^s-rCfLU=3LDE9W!nHWjMzx}#gVzM+=~nRHpRQie4)2~UDoUxJ4pVjgzvui
zE6C)XBrZc?yrL+lR+Z-aZUMD|fDQ~{4fN>Ox7ez--oLwf7%1Ps@$Ixg2JTAcR0Q5i
zA@t6!8x~<~<ni)KF3f3{wUZ>znOTddR-*1F2^?=qhY#?C#`_SluJ5~C*xEnZzbM8D
z_={Of*Jb1$GecAHBkiX;@cxgxy#+>4nV8t!ozk@V8KHfnKxI1cfqSmwBM4Oi#;{vh
z@u<MOsk^L)^*SqCLEJ2JxSK)#X6U!7R@_crw6g2dL7hyPLqbp`MdkI-wh9L9va?o8
z7wNJFyuNl12*UshqtkHYjP|#;5HP`w2mg5F$}19%dJh|6vt_(<LvR4tUO+8hJHWXQ
zP~X&5)@a?qW6=?s8_n1mx*R6mefQVmCHDqRXps%KorVX6bV7>qRYeuL^3^eYN)$!|
z2`_d#A+Gtfuyh<dzvU(k5HhhcDv22J+u~r{k)+?nQ_3F78%e$3Bk~F;j@GM=q68{>
z-n+0?W5;j;oUV4wuuBJ;9tL^o%HoHmNwR!N3yaDdzo#hLXknPX?I2CB_!}B5jyRQd
zHU$RBb{qe$h@umYy7q1BE|7ggpn{jQh^&R0*O5aNC{FWW;9r0aR~$T~wZX38AAkSr
z1x6{{cA=k$wE^Cr@)Hs6ipk(%MqnB)jni*=fs}z&>@Bs{7y)o!qunZJo>Y~Nh3glm
zX*3!-6?UZ+wx=-?00CiJm6U5Y1}r-7B2yl<!xxB)y_0akQ$P{S!XEOScbP8r3xq@O
z?FR?tb_F7Keuy$9dRDo0GYE};s>o;9OM^N*7Gp)NvulHf71%@}hnh|zg;@g-bBy;>
zXOQxN{(^ohXjV7g5l-V&p&3E|Z2o^t1Fk``APdQV!K&C3l`8FHB?W*UN=#{(XbBbI
zM!^D`Bal9hw-Nb0+!}iRI*=hPUJ?&J;XKK0nm~bJ(Ai)IfkRt3M>-Sab+ms#C`-nk
zb|LA2-<dcwA*^1Pwu2>x+&nCegbvZrhQawSB4<IQ<EMRipnMQ?00l0~PcjsB!gwRd
z0bRmS;Oo3}3`sd3p(9QkeKcT{hGLqE_%ZTw8tab!swN3ib(h?>qyV?GX+BF2^a-+X
z{DShLwSbZPt9Oo%548zhCdLWS%x8R&QX@@yEIa!#7U@oqdU{9}PPg2TtJs&~f%364
zz0904eacs%jx+<Z5Djv`-aK5VW5xZ|crliD(v(zX=}C$hE60}^9<#$-X|lBa=IRVE
zOLFD~NGESG9@)OG@F(Bq&1<MtG#Y-$Gv&k3Xjd8YJjr|K$+<wP^sQ*XB-?I|5dF&C
zxT);A=Zi<TE5}sNUUh2vDfJ_ubyVPup*upt{3!~Kh=uAf<A1*6Ka*ZPe1EjUxhvfI
z7ilepqHWYnnQewT=HbhJ-~O9xxD8FkwYs67e+CYZ;--0(811+(z{P4Hf0x8BwMs*J
zN5-&P<X&GFH1X1=rR6+B#>jJj`cCo?6g}p66He@#Q}XPcblsT=4plqu!hOjCzMu#K
zNxyX|6XG8jFLv-W5$1#kL(}xIx5_&dpjFc%W0PO|ulWf3ui7v|)CKaszp~9kZ4Gk>
zCR%+x|M}mPLniS(v4iRhO%f&8IHOf&M$Gu+PpwBOPVB%7e?Q#Si>H=*4`U%hq)t4b
zVbHYjI>V=P;X4dfZ80Hza>MVj(1PGQ^I^v?;Xs&6CU*yX;on+>iP;8blL5O-)~CX1
z3dRmF#Av=(tEiH%rF@pfYQ^z2c5YO81EdF-#QV$4M_DK!K3h^s1>Gm`7TLYZ&aY<M
zBQ@~LkPoIaiwj#;`=vCXf}+6G25%{YhlyUys;=}RXm;qdAIFzPjZ*7Qzg0=GS??Q9
zQQc{0Mk*AM>@xt;@ku2W#6h(}IpX}~vdCuzAoH%b%Dfu6<)B6XgwCg%FM&kIB)74_
z9>VAJH>b3}DFU63f%nQ=zaOm={H3@f(RZTcHU$0CeY!2_wzsMv<TacXEj|1#Qv5J5
zw@~vK`qJ1llaB(dNh$odHik4FV429_18jtwu#NI}3*sgpP2~gUp)hA9Fc-y)VM?o@
zd@c2<1{8H8to5t<td=6+xno#}l#8GgWb3<muz}YD(Ea0zbyf<1$ri$p)x_NJNLzk}
zR`}-rLO8QIB<5M$YDm|6;yG1*Qz*S1=8z5C{#Y=5!_4{z9uHG-6<&rt4K1#X<D?NF
zkkMbZ&V|F^M1V}ht0My?*Ba~*@f!NAf;)tR=}>Qi7C6w9g6@(8tln!o5Uy0t){O&*
z!N_VNsBwG1B)-{=>9<{r9F<QN;IfqDr7z`RD8~w?Wlp)`xN`jKJwO`nzkkho1$5k(
zADS@^bylkVN&mpIbzgYYx+*P^4ds`&NeNhE!T;s_`@d-sU1)ta6s9SfuyjW>Uz5aQ
zSdl-ZEn*&5?`}VXp9<Jhp+TT3P#rXFl#nAor?4TN`6>olW;Y<L%H_f9E}5v866<56
zZeD4eq4VYMxlqBtu076`!@`(fy_Sc$uWA1wC+HWLg07Y<H(Xg6{*y7N;|BxT$oqPG
zjvJAU)p$}Is9)^+7%EU7IfHPX%boPkbWy|*4Dk{vC7O?X%J#vi#MH0AvKu1;=Nn@6
z9NNHPM(;0Zz{1~PklH?4p99d-q2VJUH|tlVH9ZpD@=CoHF&9<krpNr^;RAzWp5+8~
z=a3BS4V-`<f9FIlkiKpwuaW-5bgR7dz7Thx&Y?Yx70zWEb@15EwS4?AJfV|HA5gbi
zKRML_!2m1c4e;pi0YV<q2T~(?gO{C}sGlvjFBWW`zHz)4YF}DI4qSdt!r!4l!rZJ;
z+Dum&PJ2=`kYh`mBBn!~B$H!Yt`S_rJ1g%V2G*Vp69hW{vU}ZrvNc{46!mQ93uq?0
zSz}~*!$Ir2w-Js!5#B0hDbPEnOTm!Ga-&{PXbsrB>0g+HE|^S9|B&H&^nYJDC6`jQ
zr9ai1j057yoztoBhJ9XSyKZgLlwzx4X#K$YYWGAiJfv68@%S~S4Z1pPC~iD;fihD8
zVcwkIkM*Zz_2QX*K1xXO{OJ*dBQemKAW$#kfDxY5Do5P<30JM>3;wO550NEE%X{v(
z<{QcZVk6`kSY7Ciq5!sT-4`+Y=G<)a_$V<K*BIv)JG=bFN0r=!X^`17fmi=@44G&@
z40;ZgYT+LtmhWqH8UOSxNH4`81t|F_l8=&1zi5-FnpL|(!PJDjAwbA{ZXguoVg2R7
zd_Lu9Po=f)H{26ZtuJXIyu9`Y4t7_goZ1HKA@5_D8aoNlnsJD!H0HQJk{6Q&bR{JB
z+{!zCu31aLP$#E`x+ro1sGBpg8C>kG;7gQY8O1m3gWW-l*fT-(?@wNwog2JUyf;Cj
z816WzA$At@Z)AP&VYKCY4R!7pki#gU2R<8w@xYHa>F&N!cFyJs&=F>`h>sXA77)u8
zXC<AbqC@Cr$HS)q<>5neoMbvWrqV5$POSM8<`u8W-uGG&p-TU;fsC3vHhJ7IC))6r
zU{;qIziFdRG1bLKk@8lU)+C}#Gclw_Ei_MDY?db&Tx`byY{d35mkZ#;(ev^*h_;Sd
zFjISZhL|xuqPX*%Lb~`9eBmdMD{~c6ibF8h&=~{NS)yk%CQ%&|p0GW|aNvuu$BIIA
z=hlAEuv5J*$`>U>w)_6-RL&7(nTINgdf--Blm__pq!OU6LFG8Vrg7C?i$8BD&)$NK
zjAugcsse`i$5U59vYjxn9#lIn>Ux^=zVR8SP$aN7$;RdI2w1bGc>Yw1V&rQ!VLovh
z&hhxa(HjKlhjHrfP$%Wx1UgA(4R8~tMbD}~z`9w_hb(@|H`fUYl<{JL3eZmdx1J+T
zp#KBAsQroKbj{vP*HE&mZOmzSzrM^A7bi=DXXG=@0D9p8`h_3=5u7a|3psFujQ%KC
zG$v6nri3ipbfRK<wS~e;-EXFbo%PZ+Ua-Q$3S!S|)C8MD>NM+MB2Ea;5knB8l$G>C
zQvg^ms1JHqFDKor3^;Ip$PqAnJ`HroP1v=2#hU9s&{C|kl72=f4sDRaME*TEJoFGG
zVZ%L<SDfd&2j^W&FY_ad#H1^=XGi1NUBo$JB~J^a_aWv?3rhG`7^PG;JSZUwRL(OU
z*e<Gb<4a9K@{b^eHR6~&ndyD`sQd2%&zck%rk;cE4%u#CvK3k2>IFA1*+@H(J&Y~t
zYBG*fygA(ic;g-S{bT7g0V0r!T<?5>g1yPqlNoaUgbj7@t6e>K{TJx(Z`Qo)=4?86
z+Q|v9NMA`rHiGeRX$$M5iJDDFqJV^ZOn&;9TO|hch<<L!ncgR$m6wExUJG}rawc%I
z`cGRKpq*b7JfT%&!9%~kU2qq-{@@PJ*;6<s2B&7@1+kVbVKrDolkA^Kfr-=o70h@=
zC0_3J9z<m|t6y0lX5-jl0|G4`BY10aIb;4O?HYf#^mS65`J4R`SvW|Zs}!sjD!W6=
zP{40Ao)#hnzRAyuB@w8k`rfbQs)LW|MOHqLFFZbFgqYE#YaN5HD&A1*ksH%kK6)Tk
z+T%~9Jq5&v6fFZGKbWziI?vASnm}5mnMyv`dQqWY_Q($@vxsvg+ngLq@5x?D5kRE+
zY}<BDHZ=iF{Vp9BA{+^NhkAa-GPXmyrPs|hj|`Bf3s(~e&k2^Kh|dMwG;NM*w%;qs
zefzBhhq&i|sM+*^Ailm8N|Q;fOBR0ZSN+IlLFN?&Mkgy61oJ0~{#Lb7cX6TidjBv$
zC^w^hCP-E9RXR)R0d>|kt(`IS$q)SBB^WnB)-yB(MqQ*nHa7et8N9Y|u72}Z-Dv0c
z=2ToiY19)9RBo;@N3HG$ui=|nBvV=-{8c$-PF##!!xEQc^-o-@>-y37v9}6SAS96@
zIVckHy*34oYKk5jCwYRr4FZ|fcksaxmO^m=<q}ze0hfl9M@W@h6D|u|PkUhZW?L}v
zlggV=dia5a-st5~X=a-(bN>TwfR3Ap2}iF#{`8VA1jtYLIAe1khvm<99hjkH$|lO#
zKD-3!t}9p(f1vD9b~h1lIGhisBPRm3U*&9O&=ea+ydkCdLpxJqg?#gE)&RV<Z*<K|
z&DY;>v6{U;*|D~I=xbvuw$96RqsbRi^&Do?25S+nIzKw5CSH`hLu1Za?7^5JD1SMx
z6Df*q3l2ANodJ_8TFL!=q17yJBN7CwL}iT^&S6y_Nn5a~Lcmul>FThUhok=R1!+Y}
zu-}h}?l0#n31n0hPKZfZ`;kGauucX1M6TR{NMTv<DKH&PGxB}csJNE2X>m+th}zIk
zz$P|K{MpWtpj;^_1Eb%6i)eVxjP~l4Mgk&5&zidCY~jckcnH6;+g<@`OppcA%V!!D
zFRktu&)y_4RD56Q3;LN}ynfdKXkW9xj40w3mQt0!;wL4fix}`hy^21pv-vKl7uE=y
zngBa4!J#uC5LnCgKCqt@<BI0}^)7%Hin&`d6O;h?LSJ>n(+3C*85vfu!ulyu)zfVX
zOj9o4)^DLWfk*<KLlc|>8Hx)2R0piA`_7LP4q_cvpbvlf`k~pMnUsgRuqx#@watZ#
zk1<{#!rM;72Xp!Fl%|OvoG6=z#{I+7Rkrb20dJ?1Jg{qGujD=H4jiOti?$HSu2T2l
zg%vq|MJNa{sM>RRCbTiJht|s4c~rcpUX!vOp#DZ=DgK!vY&SU!c>Zh?|9;JGDeh*=
zevX=18RD@HEB)`&2nv(}6H@K3cgrYwq<Db*?%+YIw0N$9VAzYeHm;+(>!K)L%l_-0
zBGCIaNCv{GiTX|!iGHH>Mz+wwTeEWlwUq;&JF<~+vAyGmn^6sUa~$X|FNwCvf8bNf
zQth<vWm2MMv?7G`@m#uPg|_EujSTT<CU$TAs3ZoP7j*#5Ojj!I0vPnnw)OnP?DOb$
z+;5Y8So8M;H&d<FuL}a}BXg05K~|Bn#hC`zD*&;a*Gn1Wom1<oL_WRr7*?W&fkJRI
zBh=r-^j5x1zT<k=WKo~t^@h!-=hyFMs}(A|ZAv0>evbTokz0zjT?#Rrq6s2Lv^OSL
zX0mnCC$WQFm5h;RZ^26%M(_2V1gG=pi$hWNjNr=w(TC!!Z9xx6gf2JZ2`;tS3t$W9
zfryNaKp$#LZfyfZil_6SqE=Km*a<Da&tnM&vVr3Ltw!H3vrmcw_f22Ft!KyPrx0zq
zS206ydQi1wv=D!t<CFd0Se0&c8srC)LhM_(9geP_^nHu72$x9-Gh8=$E%1fnI>lN3
zOskNf%{PwxEUYOW0D;}+q{`Llc?sPKP~oiF#!jzcQ_FAv853rY?qE%>uIe|+o4rkv
z2Gs3?W}y;iGaJ|U?bv6iVf;a^IzrxS@^(i<hu$eaNi}nW+n~i;9YKX*<}#F+R|?Jk
z*MuNWYoK`>ze^It^ykTpiAMVncRoojId00VK;g4siiCtSJ_^jCX%u8+EAbC7q3PhQ
z-ARMm3b>+IZCCteM}Vd#FTu_U1?8M&tQue}Jn|9uU?DW0g+)8OfrcXYs$Clt<0a=T
z>q@Yy++ZWsB`!&`!QF%XYSlwj)5g|<j{~(p-3tBT8mtWzJAk8yFo)piofkhMlq6-e
z*1~@PVv4{+GAhh(cA!StZiINT4?^{{mL8(Ml+fmfJ;Y#FCkHB7+Rm46r9$P;E1I>k
zgSWuP*g0xr&5^n{4@C^$Q74fySyA1;Yi9Rzak#^OvYogxN!p@*=Z)ur`7P)O25jy6
zH859x%P$q|HP(9O5M^^cc<VX%7c>l}V|Hv$nImYYOR-@cz#J(H_z1$ldPe|y>@Zki
zjOLzmV}xYk&$oH!Ui{E@wYjL@nH}3RBv|Mb27R(t$ZY~0+I-~g^v?t-cJr=^=>pA$
zx=>(HI%T;#c<d;g>=CMNLlLuemKc9l$$M8L-re4NNON)MHMZM(AXi=>2y9;p%6HxR
z2Po3NXe0mqrBgk%=O=?85%I?f_n&s;7U;uSTjQ3|@rKx2;EPuz;lv{t>x)Y7Gwj}8
zyR1Mnm^ugYGDePAM^LyXm!~TF^X>ca&tXsB@3_JYf2xop8gOcq0XI*fqv|TJ;!kC1
z-}dZ|1~u74R#~uHZKt!U0L%BHc^|NA?qOw})bGh*`@Uwu-_^N6^~+}m*i-*CIc!|6
zrv=hK7i?P)?k~$k^z6}>r!aE*qrvwi1uCJpnuVUK!~y3Z#A8Co69T{?>715r8N{$-
zw)wK1k=9|eCX0aW{!aTP6#({yO>jIo-gnJ8k-He4zq~wPl>gO&@shtH;Fv_@s{*<q
z^4<Wd(!n=LP^*9VWfE-H<QZ)+52n3`<t`9z_4A9R`rFUh#|8p5D}VpIJ_p|pR~eXZ
z(q<MvotN+In#o^C+fKFwV?fQh<w-bemn+^ZShhhKK}^oynmDTiX+L*X$g+T^Uldu%
zPd801Ats%<eH_b}H(fgG^#%4HjNxO0?@rh2<7)j^Q+GXObR*%ceRY(W$cZjt`FT(a
z^E_2VUB4<B-v68^(cKL$m{rGeJ4-rxzN`Htc{*TMS0oDf5{HHtX(L-ZxAOno4&H$W
zZAW<Zwos11b~kofh)WIa1W&idSPlx$9;Y5}5Li%^9`%Be&be!{^hiRedcx87vAZut
zV2O(%B17FTMs6AJdG5nmz4q9m1-fg_R#H)%D6(yet&6c&kFxhF7njJ$SVk_z`~F`t
zT|JPfQ5b^6hqmRcxP<|#o`qff<1q`U3w1?=t^l76(^`zc?s_DwR$w0Lv6MhZ;GV?h
zZOEq2fZuL#uBQn~_Ah~R;7#^v_)b3mJsQkI90}b>I$$L^FPRHa4E?fs-4P5*j8kkw
zPqEK)X7En;eg_3^pGb#bjG?>LT0~X0S3%@CrafYjAwrZHES{T_0DeYly=y?&cT|HO
z%Jo<L<5??fwSqSWHmQ9HxBPkP_jL6bwtI2L(aG|Bh16C1K*s36eMm;IWY!;awQog2
zA+ZEdy?zX1fXEjJw67@$>fkoVtoxn6YkovydURQA`4J2ana4k{*=&<C00xNXcu=Xd
zhpfAFIa$kpkP9TCFLbtMZ-AzVw2KBX{48oH9W^UEc<~+~9Ka-I0onXSU;b*6No1!X
z+z@51w8EZ5_^oyCL0>j*4Z~$6ORv&q&m0Hp)=wkB^ZMuHQlL~V<Ya&k$(cAcf`SPD
zqVN(&@;WD)Kl34~^wV2Z!Y-NT!f#vmd>3+oM+=+R!>>8n;&fN?*m}!19>3PSEN*AO
zhyUn2<3gUT?MjT?3ccLeVdjx<{-aW5+48iL<ttamSWnx<zR$|9r0yd)u5l6WROMBu
z-IcUH-n-1cc!o4d;N`^1!1h<M{r9RqEE|g>1e^Y^pklfqima^Wubtk>nYLRKLHV4m
zVXRR*2|JK7VJ}(Vh0d3Ut{rb!nKi@K61?XkVFofrpp451R<(j?Z2nf#my29yzJN@R
zAF5#DbKCP;9%%B}5*-3(TDXrc0Bpt}E$_?)0b3et!l7X9`-_C2<J;>o$RMBUom{Nn
z?W4t`po^(_Yz$X#n|a2<)6E$kd2@M=>TV#UtQtCV8?>~fzspTieJK26j?O1#eR_As
zOt7f<D0N=y@K;D>=jI|r27(|?^zqbi4_ttz0v@38bkKLuadiXJ4v^2cwrcS+n^A`P
zgWIW(KRNM{wr|<g3ENL5w7Vm)xG;OGrn*ZUnJ7RS-9)Dy(N|))Ow9pwB9LcApgGw+
zw%5$@ZLRASaI*fk>ZIti!@!r_X?A&vDzZM6RpxKpdglBpZREcRzUZoTm)T%R;xJxd
z3gS-mt(XtWKs<HcO+?QvHirt!dUSD?l%gaOYbVo2_8buj(=Uy-!^^9rhwysc>%58D
z3c0#nBB?sHsUY;XQz@<!Q4>QYYzErkiF=U#%d=F-Cc(CjVDmir%?jf`O@)j6yk2%>
z;2i4SH@jC*>2NC46#k%BaQO*83^9fK`YT>o!Pu9nYBus(u(jsv;H}WB!6Fc}vvPL`
zIwv6XyhE+6f!%apmjLa?q-<usIv&l>#d=d)?B^eiPEXXo@gIX2G@PId9CR<UG#Fc8
zecL1@Q$fcy4SvnbNB*kRsHCt^K>)nZ53h(Ov?ECFVEgvJT!4`cXOTr5w6CS~I}PVg
z1~;+OONyoOnfD?%VeD!E=(fXw8GLYiZ`>Ih^(Am4JWCKk@8Y3tAJ1Oe4#!l~XnARu
zS5j+XO(JC9Jg$^5!<&)=Gb_y(F<ih`b-jC00~h3p<|l$&w?4L<KE_<vO2<W9Ry8=Z
z`Z}LAps4)|7sdWA%QfaXY-H@Rlmc_g!pj_!fu$3B`U;r&?NSF7xku>4GX8bHV!fUu
zs!qD_ZUYimMfCFu0ea$c@^e^Usk@n~D{luT1cL`bo`D&b-rdp!z#KUrTLY&}ePv>v
z^B&e|@`z)dydK{vq@xCsm;KLP`OA$&fRi3W6BOM~TL%1kq3zvJH-lw$G=DDzkH7Qy
z6C5K#`IjK)r&AL06s|fSzP`B}EPO&_keK>1Gs874@K<*APrEa+hENAN;e#Y~RUjhi
zA3;Qkz~Mv1-(T7Ny5K}Tc*|@XJ^?DCfvrD>X0yFlXS`JHZbJY^(hsku1WdIGne7`W
zs{+B?+!^R0q<b=Io%YR8)X(SiW<xiZ1KEAV&r3gfpG`hmhGV)3a@YqM!=CXUs9ss}
zR{}$~M-23+8^1(s^hxCG{&;?7me;+?qb48u3rdMY%{W5y@f{L|Oeg$HNuVw}K#P;u
z_FzKDJki3<)U9KnG)dURV^ST+q3q7qm|!fkmU<Sy6B982`MdMN1q7_OZf-FYZZSRX
z!2|k<LBT!XMDcDjfiMT(#wu7Cdc9RT|NOTUV<=KJ*x16O#*GA;ScQ!-?p^!tjBSUA
zX#!3UGcIna{}U(SJs4&N{?pITzUjk&P@Knz84EP(fS?W628NU(`p1cmBY^_C^;Z+l
z^J+ZLi(y=u^>>raNUGM}CN|%Ol$rRzbadYJfGt%2$MG0qh!ZKipb^L|KYlS}OtA+;
zWxB{$f^||pF}CPOD|qR27Xc3DU)<P`&7hbZ;VwgE&Ohr3>&&gzGj6oNrs+}poCZ6&
zHO+0|K$Y&oWV-ME<9<czvjR{^uM~zWksB_i?mJh#c6F+dw48~xe|}5taOZh$A~2;8
zGUUCMm5s|!)Eip&ZR_9om@t6yNcPd1&-9OalMMw})x|FzmnsD|z%t>qB(@$VCCPj}
zP@&q<f*{2=WRk3A!Uew$AIvT`_2Ds7Z7aolbBLsZ+TD3?D*#~)Pv8OWafrcL1EhK%
zAR2=#V5&eWGkDgVDW-!KW`%2>#?g{q#(J6>NQj`KtQd7kbY-kv<>egj-W+euXC#`d
z_SAd(O}Y|?1EsMB9;dq9AFZYu=M8SO_;W{}j(C!4)&s7Y*>452421<->X3LBNkI_;
zpM;R1HX!Inp*y%ND`j`tg$=il66qO6AMSg0Q_ZIVgnPe(&HFLJ?;@T6J~uYrcM@zQ
zHls*hgNQTsYNTLLA&!C)*uQDvRX}fkuh`G#=CsE-lGX%*+@X<qIpHgm8%o&!*yHw^
zJ_yj^wG8&foTK{%mat(N#C2{_dzyCiHPPwTVNXW*9!XGrc%_FCD|UYol)E_l|NBPv
zVtinbG+uFYbTcKwbB4p1-CXDGBlw$)#M)xWhw=;FfNfd<P?dokvj8K0t&3ZSOBBGT
z%1&040uhQGf?0gjVaNSMkU#RzTyM~a{M&R@3gRFV*LKEL2T1{R?&=PC<-ph6Ak7zS
zhw|>Ve^ije+Dk>LCA~5`$!*4?*+f%l1~74R!vpM@nA4YApD~ZOe{MNRgF)jWE^tj*
zUr6L6fB$@OMuJb(a$#OFYpwU&mD7Z?h8%+%I|2jy-gwA>9TSE9??~AaEF@e!u1`+M
z4N?kzbjb33Q$rLxOiMg=DH{cbS>t>!Rrj(U=`M(pv!N=nt8Hi7C%wHvr_I98ZeI9a
z94!fBe>86eJ!R%Cf4(*B_6&Sp>rHYdj{qC!Od9%LWOJ2OUoW;US$q0L9~li<PY`<@
z%npOX>-SO&0VFgT^!qqjm4MHIf6kXe-KC+&y=~_<CrVj>*C$To?dwW43QWUDk;@^=
zxmV90oe3)g0%y782>UD+Q8Q+UQ$h2^;4P9WFn{%N$sE{L8ukRfklf~1fBt*=j0qBO
z@lFl6Y?CvBRcUfVW;W>aNwQJ(#T;<72_g*eIh5x{MMkb|tU#7p5o|vQS-+3xo*diQ
zH1lKv0>rEU1N8Wy&G*_O=rT@%XWj+VW*;^X>2prPB|!%eKsNJU{^{tzB@&cEQ{Mw{
z$#en;eoZO}(_-%R0OjQDDD2WjC;q|W);vDse7E%I^TmO;Yf#|%S$*5(s<-Rcv+`WQ
z(l89}!BSf8<#y71qxSR5*=JjwV=>?_I|hsL=Yx$wznkBD*T8-MM7yWibymp%<Sozi
zRD|k+6aVC%7#z*C=XA&VlrQX^N>$Lll%Z?$kHesj2Xo|+yeI@P;>6;`y6DPZ-k}xl
z5>5^|&$W~*JDd#qy~BKE9^0<@-5YFse);E<s~Bt-T*SG}FxI89F8z|sQSVXfG4~C2
zl==tZrRpQ0w!|sGyO_FT%h?Xv!yj9X{UcTmLs{%$W^UxU??f|}w6Mj;1IrTk`9F_m
zj1_*Q@c4ANPW$a*uLWd->&NF>Yi-Au3V>yETj1cxeA({=OF4nxJ1p*}7~Go69qh$Q
z=VjXpHf{Lavi$AECnm?kTW6Qu1HD-5Rxfgdz;s#?iSildP-XP1q(lcCoiaUxTU$7y
ze7X~`2*=Pk5I(GqkSiq?>-w>ICPI?Pjv{k?d%hJ!1~qcp&t$ti$gF3$)W#mkJNv#G
z1f%GN+Gp5{GjGk)=5T;H89R&P(Gc<&3g^TZ(-DO@SvuL9g-Yl!Qz$dP3wcO^G3d!W
z7=vTnuYnEjg-$s1ZO%B--k`NFDak!VC>IdXz?=<M*tHae4+&_)3uy}!-<g-YkRY49
zg8*EnC7S$Pvu2jScnsNyWOjlXB5&D9_4*Vk&uAZ>s9WF<-Y9W|J2AR5JB4(3stBtN
zb;DRz359Fi;3A*{aa%!BZdIRQ0~+arasi9W<I-*cCD`sK>~bW)9DmvE6Lhw5%YRz{
z684gcK_7WLOZ^680cwUR<P(fKnFq*W--1Rz&pA*1ao%<h=vK;TFvu|)gri9Lz+Uf1
z*o&a^%(On-gO<}Z`SZ=8&q_k*9l1OCb&+wF_s@=YutVF&FU%2Se2%yumz7m%rnI{4
z^^|TMOyN^Ye|}+In#Ont{eOD<?x-f8XYWl25CTg0Qba)MAc9gwia<bm7nI(Wst8E$
zp(7w-qe)eeA{~SP0-^UN2tuTZNKuMZX~}*3{@(k(@BjCldrr=ib8>cOKeIc#J2TH_
zX3w<mrM9;%(V7Rl-4`zNs@n<0>vAweuap3qLrIgbIpxFgb1k6<1t}@)7b|DWvx&r%
zBq(sQeg4Dg_ZB~d*Ic<Mc3D2_GubY3mH2IGiI(u8oSk#Qx*?`qASt5<D$O;=!%7&T
zk%mhRC7KNXv$k`z6{4#`yD;#GxADm7Ny4cxJvL9cAm9qU=fp-Pe<U;PW7?9dWXsXr
zi%g+YC5O1}D}OHH4<LtPYP-Da*xa|nBPE{jf%YkTHtE3}MT3^^y>aaN!*EwuG&YsC
zhn#CFaDS9i$=zjTC-d8y{RxW01TG?&XFWjql2P`D2B#`;V>*04n7I=q@Y9Vw&<l!o
z42p#AOU8sA{&w8(Bm1+ptnhAk_+<E8x6xwL#;WO-AKkB=(`kifUs7n`@-%CA>8wXz
z3M&3?UM1J(kXz$LrCic0@$<^6^b!RkHsn5@&bMI(HSae`ibF{m)V&K!3--~~;v{yP
z`@YdP<s19`iQn7%Kc3taLWn<-+(9aqy4p88=*JnrbF|O*vKF7QD$$Kfn0324!ScyI
z7fELd<J*K4?j*=$?sukNHX7ize@0L|@Wk>(nlbWUM<^?rbF%2ZSvs$~Ilw=WA$7*Y
zh}I?#bckY0u84o%(r)yb%4UG0hyNj;&zguHj`)|T;}!;}igy)U$iFab^7N8TTxG=k
z!3!w+ouz11$?B)b78DXA(NB+!p+3m^M4oHZxq1b53;h-IF+0_%=JT`IjnDKkd}4t>
zm*j>79taLYaHMPap!+P^1WExUJT(<L<*Wbx8_hc`vz^_>z3ZaoK)>NqJK__9U{DZN
zyZi#dQBOH<u2SOapv*EAhUlog0ZXNF(J67|7s(lF_?=gAPiB;XBSs~X>8PTBD01sn
zKyYENWg+FfQN$(B9>ZWK>wQ$vSOx~bua(qh;(5gJuD*1S;YsP2+30Pj%_j~}7um@K
z?^8wVaDv|WCX0f_W1S}6YU5sR3OKsZ_QN`Y&;R$Clu&ilhXQI$MN<hi=AhUx>|-}w
z3LP-g2Tm*+r%#OLvmD5v<~Dzur@=PzEXMk_c|EOUS$^|Ss5{kD>d71M!_t_v=g4xN
zMwj3f2FamfZmli^D(!8vx}jp$a`2s^Xa=1U_CsYqlAfkvf0_GK!BYVt)t&R5d4!t*
zd-lKEi;?4{Z}AwxddRx((LS8(ofFsKD^vDuRSjn*%?%l&?xl$-XGo#G@_i1SK3}}_
ztnE{wtB?G6x(Pwo2E9d!bn>Kw#ir(Ldbz8jXGBN44HNs3c2ZrHeRu(|_G;0%M(pm;
zlQ-IQmf+p`UM0m-@;If^I7loC|5Ed3J<mK|!aI2OJB|nIH<Irw#X0`e94V>1K4U4X
zC}PgkA>1Ztx7+^)k#n56RCpM~$iPNE?qWvJ&1r)ZvwyH=)Dwa|R82=Uu1rR@3%>1c
z9&6@t7{0*<i!*<LR%aNK=AfLJro6#MVHyJmXIw0yN!CaDI~p7-{6eWKuAe98u$ZXu
zGBKBQc)C?6yaLDndj9f#@-1$enoV2gZ2d-WeUPJ6ngF4_oQn+YQAD4D{BvmfB))<g
z%XTDn%TeSS>*PwwQ38u3&%;*{B9uKy3cBXf+c1%HtcXwP0l5?BkU&4zsB78>{wfWD
ztymZdlEePlR#Fixy(jmB_p5&b5YbWlR)Wl0(;S%{{bX96iF+9SHr(v|eFD|(H*ksx
z9u-ua=W3MX?t{f?^0@t&(Ki9$C0jKDuT7UK_jAzcQ!!N{wTt~<$tvfT1LhlJ>5=5D
zZM^w;cZ93&DW4?FT7=*1xJqh4!$ew!Q&(~NVC3e1L`r;}`Rr6k6n=Y%#NQcOl2W<v
z=|GXK)GVU`K22U6BgasgciM~aWa50nx&MPmg3S`!CXb&}P4rqNk2n~W?rL-?ARSO+
zs+wL}nJd&eGUH<VbBCS2O;aUO{tIfP@G799%j6-y!~-fvSw8JxsZkgM_5K97=_7BN
z5N!+D*5C7GRx;2Kv!uZ>u4Dmxul3_KMV|)f7@%Wo2CmdoCNcleSk;+&*O>TxDg~o$
zF5OC}So-8IK|MUlcnDE?n0NmhMedpIP1pC0r=jZL(~qNW6o!@3t}n2EGM8^OQP1>R
z>#hIL$W)dND^t#2bWL;&x4JoT$?G}vrs6>iz%}Z45mfyX)q<|Um_MZ@V*r-c#Ty#c
zk=`}<I2zl*YmwV4b6z^13L_Qq96qvdHemgR9$^SBUMsaJ`^X7$BFrv8bLN!@RRYSd
zt-1eAvyTo~r*w>wA<tdBaNW}i&(_jWxa4M4z*chxtEbP|>Y-Hn6p}(l8jkiLIYRjr
z;rYK_BpLl9XK1eVW&OE$02s<rtg*p`#NA@(JF?J>kx3AvFpoCl{M(J);;`A9uXauk
z>*nHKoY6!N=E3KEnj$%EtlQ;=j3(VyPXxN!(TfY#n<nH8phjQto~vw_u2(AO`o^$;
zgICT8hr9MWdj$T&1qoh4p|GdWm}cwZRs4#J8w?FbluDESBHKY?yvCI@Y@L0hUE^E$
zw7}O<mNq5q7g0;SfPRJ$g5FS<N@F81BQAVxmCT(OhqOF1{{Z}=PWmPbGelzQ7F&F!
zQw_<Ew7AGQDh@LiD%Tad{F++~pCp{5`XJ!ItZ=WcHZw;>7v)t#cB$op`!omU0mIi9
zhG7g2V(*w&f*Hy!$({#*R%_J{!+SM9CcIqP+UUqw^k_aAw=NkgSD<3|&cQ1f%r<S@
zY-DHR(=S)u2;?Jji5>Be8uL(r-`nAEOig*_-saJju7C96V0)C5GyO#oHgf2n!U!9I
z8s9SBHr<`bO5c!hkXI6=)52v1b|;&EuEXbDypA8dL1HHl<LBDsl3ZtyJvZ8px;1VB
zY@|^zC(vqFSZ}|%o5?Qj$5M4K3_jm9D^D~3s6I=(oh~P7=ir2CAiYTiOlv#Yhv{I7
znlh$+!f&z@rBhv7Q@a&;Uuu?cEf{JsV0}zJZ>TiE(RUd<&lc2mI-W3<(fRi0{$Xb?
zVbfe+8n2~iV}Kzy5S#a0V8{XQTvpBI@T3Cixo-VoD@4~hmP+;pz^s6NVZG=#OBa9t
zshalNHYT)ag@nuN%%>mLOcFoW(if&$MgC&sW5Ond7W0B{3Z5x73nk)(!xVGE8$POx
zpgK0fOO$dZir+7(B+5;2%h+&%0KN{Qn)U5IhXEl<$vTk4{{eCH)-`e)Kie7U?sR(b
zja_A!&Cz79iC4dM{f!e3%WMkxJoG7-L1R1dRfrt@bNI`s0ZARvDg8A@QGt^(!hYIw
zatyWf`MG6Iejm)m^*T09VefSeIJrX!&0*K;cG(co6l-+>&y0S*iCpo-=MMabaa$)W
z;-!Yb0y;j9L*sx`mErb5!DVc4o4%=*5du2Ie4#_nOz0<eQPQMm11{ou7s?&CM1^1Z
z5Qqp2Qf>&n1JpGS3WIn%V^9KfTqmJyXe?%_2-+@13o7;HFvaIaGFGILhPp~0s7+;g
z78xs3VVuZvMqx{QDKD@T`P@u5T5mr~wWVFR@z63NgF5twI=tOgYPJ-N@3%+c{mx~^
zN*6IAILg%fQ>25aN=XGiu!df>r4XO~;RPYqn*cI+Zur6qYBMoW^*67!8^F3sTJAju
zsXI<DQ*M!c8bx7tsya2<f>}x_M|5UJ*?WFo2}m#cmTbbf;8~8h)S*D&t)Y-mJjV6u
zG$FSu;U=N{^=)@wkL5knIXv&}i)&Lasryja`YSsmSvH)O<zN;6HhPHDZ!?z>_r4bk
zoc4UQq1BJQaFi42D%RIyX{w~?49_{&)i6kp)EUJZqmq8kX^j4JVejQKljDMl=?f}6
z&M6LFV!N<*8v|+rWZyxH)ZYEFB&;G&_#1_nuNy59CrEqh<rNUm&GyyL-PSBHN?a`)
zn6y}kZ$_4<|A|P@tm+I>W%m{fOuT@^7R<UsgT~`xF}2&Cn4ho8&gpSl#In1EYx;CQ
zY_ZDlM?rw&v7gq6>c<G{1mB&pNVjxie5$=7Obj|UvaPQ(ev98U5W*2MpO0+_XU}~Z
zK3Q$rSooIdAM2%cLkT2@H$-7M!BC_5p3^BAxn2L6@uyn?c5t_V#mt3ZHQ5T@mpPW|
zJ1IlX#)b{%=J%d%X#*rSLJYpuT#9m}Vq&1fW|Ou@J*V0QDPSgaH_flRdkO|e4pe3A
zaR<ev;!~Orsv`Qm5u4no9f^#^i&@TQBF>(KwP`BDupHnMhs4ipL|!L`R{oh1Q9;bF
zJyrwqo6HCsmBLE)wzr5KpK{A^P;)k0e(w^4!lSa3l_<VN^Ym+AJX!URRSqzM7<m7*
zz8mB}JPxH)q}~6ezzKfl&fVS~J%4KaJWfG6pL|X24})kJfAHK1|8lxK2i@9j>6TUb
z2o1SX!P><qkMo1`T=kW~!)v4f(v`dXZjo=BLp#4HgeFnGcKFjz+ZJ<OF6u>jXX|7_
z<|!9qevI0Gl(@Z{E_e7Wlilxo^NZ-K>{o#SqJwmNp!3c;$Z1x>_o&FAYCwe{$nQ_e
z_3L$LEF)*MeWx6ILlLzU_mA?6@+tIX7BwgTc=6waJoh(|!o{z#FHc_`qt2W5KPdRs
z^jhGItXUiqvxv10nY=c*>GLMSf4b%SlbwB=9RsPK(K{RShF8JlOzY{=*o8o1XxrYw
z!^YumG*-}KwD$nIF3Q_)5j_M)*x1*YM+~{^(UWt8%sN~;ObRiAIg#mVSig$xc}0Z&
zR77LAzWj@w7H;!)fMbhjJ~0e$u(SSM>%aJjwdJedE<0|g$<FcHynupVz?f9f?_!NZ
z|H+R*xcR}oM(T}Ol|}1FuLj&u($lMe_T0&5{*W;3@{|$)GvW2r-gt|`;3$)d!EB;h
zy7WTzW5ajvh$;gM4#(1yJv}wG7x?ohV82KQ<-*KvUUi(Or%Ofuv^^_pkpA<Xo5W9B
zBjBduxUfag)1mm<L|r~C=M#FE^i%-w3x^(AX3WELUVi=Yi3|oF>)*s=dG7Lbkqh~y
z9p6i=e9%h2{9*LIL&kRK$NZ4I;+Gc435id~QZ(lx8Z9SjHmxjo+;x^)2oY^fb;jNs
zmTb4VFqZPFNOeS_@`yDGV_hX}LId$-U?o#Gz>XA`IU_KaFzdpzPpZTSLElqJi&y@L
z-+3DeYSsg%+BRoILNyp6e`|l~bqgs#6u0q{pZz#ZP8TM1a#ZT|rvYp|q(A_MFg7@<
z@xTd&gaVOmJ&J-NOwZEn{dgmEnRQ^y3YBWdx4jcAB~$`{G5=hAivc)VY2-#oATjLl
z=Vy-;>9CD6ErP~BIdiT?^PD|BJiKGrz<_POhr~;!%Ihn##=n{!50%fjiPEqH!Q^Qf
zy0W@rd&aNhy~8MX1g+1=rs(84=Ww0%3>Ap>(QE#3vszZP?>JewUFI`o*ei`2GaOr2
z*qNI{^AT=;Ze$HP(;n8O{O(oa>hL;}6@EpH+0hd`53dOMLh}r@&BGBFC@c&_X%Dxv
zyo4%b<Uh&;<z+i-_9eh-s->o?ZM*n48G2IM1^K>u34`tV6j?gBSj6?o2h82;J9Lh2
zDjMZS&N<q;+;SHf#UM@Lu3DAxr?Xt@$zHX-4ZbVkI@%t<Z4$4uy|3GSZ0AZyR?AhK
zx3<1Mbl}{06i@lXx^Kz4oW=MwSJv;*{;?t>@X)`CSft8sZd!{*p6!A!TxIv)U%n7{
z7-NFm=NA63dSPoOB>f<`7md}iIRk$=n7yL!tiiT3)_$HKyz>;@jlw(ijs6bMN`Q}<
z{_+`N%C=-!lM^qZv+1qSpW(Qj?T!i^muafOasCX!;H7)FQ{98#b{{|HyITZz-~9Tg
z9z7oDV8D%$ACn8zynmMdqb%>^s1A8d7Vy(%v(nui911)9$-C)Z>60t~g0$yvWC&5N
zxr&xDa=cg##{@vfvNO@&SQomGThHyA64w=1*G+o-&L$0B(V`ttgP|EG*x8BWl|(6&
zgJ)}WszhMw)~E?6o5?9XLv)4zJca2yFaY*y3tjmO5!AO6E@iXeBr0aFm)`Kr>R9R&
z#Pxe8x76B(aDcGDV(1|HM^h-{N9Ild@F~cU=~sK_&P#R0`6qFLNEKJztoQN^g2VkT
zWH#Ln|A>$hGnFD!q5c{iF@Edu{Jv5jGamI2N?i>{<7}Y=Nu7b6W+F>ggDW)6xaC?z
zLwSC?^@}$K+B!_LW<vx1<aN?W07HJg4cWpW(E=CkPZ@Xapc<<ORZZjbOLso3PpGmc
zC&$xJOtN23^+2$~!?ZcTM6rTCL3cjtjN+5$vzPz4(`kNwtY%4{b8Yg&AmKYx*1|x5
zz~f_)quqi>a{?w@6ZrzRkfo+qu~r9R_DgeGD6U$((dn2>kHz>kk2Q2}q3q0&f{MV%
z{XLlopUIv%g!`k@i);PMS_eO)7_jmS>dsS!%e46e4&eZM=by5p=a3mLJchz3+q5JA
z<)al&J_#0n_dyUR2}6MiWbPU@#3G2{sj;tr59b)N+)5L?c_R_=>cRLUy&-le`6T#1
zO`O8EGW@(-Y_)e%ymi)?3#`-uSNrbTfbMh9;bw}0-UUVmctWWE%x^TrzPD?)=v~=r
z(Uy0liG{8W!vU6ZZSWRB7o8Ie@@UiE@eTKNWvS1>q@_cV;0qXk{kArf1Iq;0eEsH^
z$$fJbm>2?MzW?*1gb6kcN(FC(+-oj&<wxeowa0bJ3h5Op4CSX#!IzN0x$_(X03<%3
zLaKy0d&x7_L%yj2BpC&Dq998k?3z;3bx1%Zuf~~67X`bVqb6pfPwZXnj4yUP|M-^4
z>Q;Oe*kCWAUu*gcPMLxjvzioBsHQ;9_U%_DHlcuacMf|!UY}^D?%H5|2Ai($_5>Qx
z%Pz-t8DOA=O~@RkbbK1a<ED-z(N3WDvLKK-&v86L->3u-eF<b0HiEO~$l{#79qYEA
zMljxN5{JO_6ut!>#^e;?jvMeBwg1d3tY5vM1)_Bd_>VI|A?@A}r28CW{$;rR&>r6C
zTFbM>xe_1q1E7FGM3iIe7m*}5K0SBV2+~8Z={w*S83=*J5@>r;3?-<<{imIbI_%~~
zCEqv^BU~{}<xqbs6;8wX<T|Qhdrk+|rl3cXM$boVjQUK}G3EQ1fMsaTMjodV1%y{Z
z{et;%6FL-f0;OkpMe_k}ta~sAK5vpcEB&`KJ912>WJiKb(#VnTom`2_R3M#XL$ALH
zIWusX%2_Q&aLT(rYWmAVBBmw-<hd;;aRPUe4fnq-!jb=QW1a@!V!r%wES(oIltYQO
z0Q_mhAf^c_dPK#?)wn9}r=<ekc>eyL?RB{`_TgG+r!^VY|3976+v;M6^|6;=911Rv
z<Y7)~t@nv6V1Rm$X~?k%0Gdl0%8Iv#AVWTuZ>3Lpo^Q@Ik(>iZF)8-@(+imenqC?L
zF9gL<-|esG<<thxk<*l#yKg{_6=Dd!?1^cho<R5Kl96a@$@jYca)~16#j`|dr0>qz
ztM}ie1DYI8Chzli*^u{x7f7)4$*Qi^JO4rEffjVKg)tjFKOFN7)nJuOed=(2-<cW-
z{8MdlcHgYYg<jP-QwtUfPdv4kHiDEa=Ds+qA!A%5_T^Xg*U`mtQ6{hv-6Wqt<hhZ8
z%!L?OJOZ8*BGg|A0lj3h{Au8_%o@{o;ROS+Jl$WSK9)#c{w4b0J*g!c1sW4RG!}ow
z5MrvvDprvHIXTpRhJ5_}+ld7Kcd(^hc2%l^Lteb--)&0_nn90>!nL9sn(`sA^+Jn2
zmA5)EL5~Fv^DJEN-8s4rx*>PQy&uwsj@EB$jtV6#O^1X_UCK>EhEr@B>-<`S<d&_2
zG|$5TVj~U0CUtZXT%%!F5(=&Zx0D+s9HvJ<q+QGsQnzmjb+>>5q6d(hp~zDbEJWka
z#?fYa`A+9ESrxLQ)eO}o@wu3)UKzPO!Gq5ci%?_}=Lo5Q9i8X)svafxP;bE;?E9#t
zr*4uMhvJGh0}Gi+YblKw79bw}?bzh#L-qKs{V6Go1EzgE)^d@_tTsNX$^V{Ur1mRP
zRK(xND$f2d!&M)>SR6+Kk=}=O+iGrk%nfCGo(_4*kPc?jno0BMzZv>P9wca8JV(KG
z?_mnyvur*hj-0h1xY*hB$3Rz4Xse=S&wq!^>9VQ%KY?|!-mmUv9aW#GJ&p+YJ6Jqu
zey~2ksrG)R){RY+aO-_mQOqm3_*7Gr27oJaeR5go5oRiRq6Bx}mLqAM`|DbG#6j0@
z_L7Sp@Tqfc{NBp6l0w*crQT@Bq1`Dq?>?WFO3da1K0kv#_<MPG)FCF+Ibk-#Zf8Z|
z?t4&_gpd1C`*cWG(lr-x8J1TcyeTau|G89MJzth|m+V5(B{=%G2L7@DH{d7r&0gRD
z^Xj4pdz1I0ruwcfNOr&eY<k}=5vs)=e`!k*?_sD8h(4`y4ZGV1a~sTohq(%Yr1Z*a
z>y9ElVP;u>&+3*38%1Np^%8bm`%$G(cQG^NWm|UKg?GuiE0Q1H#5gO}9D7vUd9A^M
zb4jO#Cq7n!Z=GIYr(}Y=*U|5lyM60F&^s);Z+dOm9JVq$M9h_*Jyy?+^RST|7)dBK
z>xt?V3V55Vt~LHo@SR5wtmo8jJ)kb*jUZ7jA?DpbpU}hIJBJ>gJw7Nob0{%HeE+(A
z*>Z=t@J(Y(7}w|*!mWhqBcMzal9x=*5b!}OaCGtJv$6PZLX{KBE<AHbJQ8zg(GvwJ
z1_sF5++l@G`cJu=!i1|B){~Z3;gBUB8r*6IB@{El|CP<<3&oFiQfkGlxzDV3TX(M6
zT}*C$R&wKL&z+wpU%K;JeFXSG%>DgD+2h8UL-$|qE3*m~G^4q?Ai9pR;_rfGsSVS_
z{TQohB|UC>ca7qEVRBaE=m4WUJ5GQfawqhN-NMk<um0<yByS{a&rQ(g)Fk=twFhL?
z;zGUag6(KCc874?HRU@n<Q=Wy86?Pj1b4?VayMn6M@mx#k4C7l+qLk2w~=;95y3}(
zDWdjWp>tNrW6m$>4W}0hALs7j>C+Jtx{5F<i^uhuT^#N^&8&!r%JV<mNt%(^bitSZ
z53027%niMXhm^Jmt)o>1!$txR3}Zw2UEcs~;8HfZj$ILjfu#Huwu*<*E8cGz|G$wg
z>9Mb0N3b7zA{;hgg@#gTZif1}&?GetnA6t=$T`80s^^ZYPn!PvDF;(ybszUgcvfON
z0fhmWm}zpUFP1I}NRj;W#m1Ah32$d(fwBQ~i;WJ7jXM|gn%v(nxeHFu=FSja&Bf+i
zMgt^3LplCjFb-za;|rAGa1J;^EDS)rfUD@|gw9&xTy=)8{9U}vzdt6WH2{aAr^!v~
z#y;%f4H&=yIJ7UokaA2m<OiIE)KJYNfb@bLn!XQFpzrZuEt{7|c>kpY<VJ62tD!XC
zTO=D64uA$2+Y{#Qv^a0MJR9=soP}rqQaXvu-5!0EpODSu>@ReR+Q3vG{%z_IZG~M=
z6Tb^fokmsAnXr5q9HNASZ?=7^x%97W21CA_gA>`Ya0s--BLC))(WA+Y=Mil?tN>q(
z1z4w!t_<%P;n&-h9pC{u62!&~iqf!&z%Bq#6$Y>j#kAPZX-`o22B<BM3pI8zj2y6u
z1`^R}b=yl%Wqr2a1!{jMK6=Biss!*#VKJ1fZ-Zs>{1Uc4Z*2n@Ado?3To+>?F-$?7
zIJ4m1pA|emoEXGE3<(Wv25(p(g<D!4Krh(oT74U9sUZr0y|&}dIdl4X=k>(GL5TH7
zKb+rouJmDd-LLQWMJ?Qug;8jT)&vC8&i8g(QD+4)gw}%_7F$-WpLg8;%;O1KM3TQx
z+P{t9#vgTBLWfJ>TiyAwsK*}R!?HvYe=<Atzaaqd|KJF}9Zq|x--96TlNL6%`OHW$
zGP3jV5fj;~p(N`kwv(T3vm7`G-6t)^|IqR~<RrF3RKFiV`;@S}#S|ik`j5q#vX&}f
z;gK(vsPUpqwR@(gsC@ZHm@1r088QtgV7_k_6`^|^mObbZ1H^oCruCDI8g!X%lls@H
zvDe4cOA!{;)pN8l3UlXT-CzJe%3(fK_fhUa8byF$a?}+S;K#7mVE%5zvrg8H^tP>C
zWsUOLXz9&^GY}3*+(WbWm|<C{asqYhe#*&=0Rr1UUMiti`=|ceWI`oB`|I{>pP=Hk
zFttCvuCb(}UbWd`QU}?I+c*VDwtlztt>?+{TupzBQbR^Zeady$Vo5#mKmer9PH)vE
z>^-du#}TfPu0RD|ZZ^5DX<eAVn9e$AKd*AGBc*+sE8TPNB<9E48L@TG-~GBi27+ek
zT1POOrS04#$$|xo<F(tVcK2ujP=i~~?A6TBY{dL_a5sJ;DFpG$C_b~_uc1(9Ny=L-
z%J}$7)=VO9LSk;ye==Wsde`~hF_HL&o%e?)mZ(8u&}oU0J5FpdxN3}gCVg$Wxk36@
zi}Yc0Ft0;z`V<)e?$0iPN4L@~>L=FF2P5mu6<eQAPCxt_+{#U8%-rgmEOm3MCuE)w
zIxl@0zO!&XTUW-SjDgFuVZ-t4UeS=+zbu|#0+V9nZ8$-rH#@$KzNbAOzKkeIcKXK=
zCTv3kT6K?{NwnvlWVb9)&sqHp2^@|%SzFTN<SGa$F&Ro)zv*bU52@4FJSxm}<Lutw
zE*CS;JtX<~Dfqdb7iM9Kxwd|M)r<Fq<lw&X%+&p*sDOHdp1qO7kq6F<s=XH>g?}vp
zTlo=cMLT*ZDC&PF;dYI<$#BfzlXPyoUvJjgcE{8R&dSCm*%ag640(Vi<$YAo!x$Q>
zO5eU>vcD4s9zKVPyoSvAoUM2Ei9b9kI8DNr`VGf8ZdzBCiEp{LX8ZbtPF>sC^x>a-
z?3ld=JLMy1Kb$3TC}B<^F)T%5n_d;Mv^sB}>~znpUi!Zr?fOmAW++s-SjIl|5SU0J
zcXlkSriOnq^z@bu69XrYf0^^*@^rb@saKb?%nZ_?k;E{5vAb2OO$RD3Dsr$JZpBqr
zEBGyvwwizUd{V4C1<m!NV|Awz#8IUyqelvj(qFUo>f`q;_3WP$ALS=qEf^l8tGB@p
zvj)d`+W>5*KB50ue?WT;+7!UnEkb|et<uQ9>sB@FfAGvjLB!ZI|L!zT;D7g<|E1?P
Yt*(gMGTx)<7X$!ksOTz}DcOYo7k-!rZ~y=R
literal 0
HcmV?d00001
diff --git a/public/search.json b/public/search.json
index 2a918a7..f3cad48 100644
--- a/public/search.json
+++ b/public/search.json
@@ -1,10 +1,24 @@
[
{
- "objectID": "index.html",
- "href": "index.html",
- "title": "Mapping and spatial analyses in R for One Health studies",
+ "objectID": "07-basic_statistics.html",
+ "href": "07-basic_statistics.html",
+ "title": "7Â Basic statistics for spatial analysis",
"section": "",
- "text": "This manual is tended both for R users wishing to set up spatial data peocessing and for users wishing to use R to carry out the tasks that they usually carry out with GIS. The main steps in the processing of geographic information are covered. Emphasis is placed on the processing of vector data but a part is still dedicated to raster data.\nHow to use the manual\nThe RStudio project containing all the data used in the manual is available here. Once the file is unzipped it is possible to test all the manipulations proposed in the RStudion project.\nContext\nThis manual has been designed from the courses “Géomatique avec R†and “Cartographie avec R†by Timothée Giraud and Hugues Pecout. It has been translated and its examples have been adapted to the geographical distribution of the audience.\n\n\n\n\nCreative Commons License\n\n\nThe online version of this document licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0."
+ "text": "This section aims at providing some basic statistical tools to study the spatial distribution of epidemiological data."
+ },
+ {
+ "objectID": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
+ "href": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
+ "title": "7Â Basic statistics for spatial analysis",
+ "section": "7.1 Import and visualize epidemiological data",
+ "text": "7.1 Import and visualize epidemiological data\nIn this section, we load data that reference the cases of an imaginary disease throughout Cambodia. Each point correspond to the geolocalisation of a case.\n\nlibrary(dplyr)\nlibrary(sf)\n\n#Import Cambodia country border\ncountry <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n\n# Import locations of cases from an imaginary disease\ncases <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases <- subset(cases, Disease == \"W fever\")\n\nThe first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.\n\n# View the cases object\nhead(cases)\n\nSimple feature collection with 6 features and 2 fields\nGeometry type: MULTIPOINT\nDimension: XY\nBounding box: xmin: 255891 ymin: 1179092 xmax: 506647.4 ymax: 1467441\nProjected CRS: WGS 84 / UTM zone 48N\n id Disease geom\n1 0 W fever MULTIPOINT ((280036.2 12841...\n2 1 W fever MULTIPOINT ((451859.5 11790...\n3 2 W fever MULTIPOINT ((255891 1467441))\n4 5 W fever MULTIPOINT ((506647.4 12322...\n5 6 W fever MULTIPOINT ((440668 1197958))\n6 7 W fever MULTIPOINT ((481594.5 12714...\n\n# Map the cases\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = cases, lwd = .5, col = \"#990000\", pch = 20, add = TRUE)\n\n\n\n\nIn epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, …) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use the district as the areal unit of the study.\n\n# Aggregate cases over districts\ndistrict$cases <- lengths(st_intersects(district, cases))\n\nThe incidence (\\(\\frac{cases}{population}\\)) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as \\(SIR = \\frac{Y_i}{E_i}\\) with \\(Y_i\\), the observed number of cases and \\(E_i\\), the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district. The SIR therefore represents the deviation of incidence compared to the averaged average incidence across Cambodia.\n\n# Compute incidence in each district (per 100 000 population)\ndistrict$incidence <- district$cases/district$T_POP * 100000\n\n# Compute the global risk\nrate <- sum(district$cases)/sum(district$T_POP)\n\n# Compute expected number of cases \ndistrict$expected <- district$T_POP * rate\n\n# Compute SIR\ndistrict$SIR <- district$cases / district$expected\n\n\npar(mfrow = c(1, 3))\n# Plot number of cases using proportional symbol \nmf_map(x = district) \nmf_map(\n x = district, \n var = \"cases\",\n val_max = 50,\n type = \"prop\",\n col = \"#990000\", \n leg_title = \"Cases\")\nmf_layout(title = \"Number of cases of W Fever\")\n\n# Plot incidence \nmf_map(x = district,\n var = \"incidence\",\n type = \"choro\",\n pal = \"Reds 3\",\n leg_title = \"Incidence \\n(per 100 000)\")\nmf_layout(title = \"Incidence of W Fever\")\n\n# Plot SIRs\n# create breaks and associated color palette\nbreak_SIR <- c(0, exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = \"pretty\")))\ncol_pal <- c(\"#273871\", \"#3267AD\", \"#6496C8\", \"#9BBFDD\", \"#CDE3F0\", \"#FFCEBC\", \"#FF967E\", \"#F64D41\", \"#B90E36\")\n\nmf_map(x = district,\n var = \"SIR\",\n type = \"choro\",\n breaks = break_SIR, \n pal = col_pal, \n cex = 2,\n leg_title = \"SIR\")\nmf_layout(title = \"Standardized Incidence Ratio of W Fever\")\n\n\n\n\nThese maps illustrates the spatial heterogenity of the cases. The incidence shows how the disease vary from one district to another while the SIR highlight districts that have :\n\nhigher risk than average (SIR > 1) when standardized for population\nlower risk than average (SIR < 1) when standardized for population\naverage risk (SIR ~ 1) when standardized for population\n\nIn this example, we standardized the cases distribution for population count. This simple standardization assume that the risk of contracting the disease is similar for each person. However, assumption does not hold for all diseases and for all observed events since confounding effects can create nuisance into the interpretations (e.g. the number of childhood illness and death outcomes in a district are usually related to the age pyramid) and you should keep in mind that other standardization can be performed based on variables known to have an effect but that you don’t want to analyze (e.g. sex ratio, occupations, age pyramid)."
+ },
+ {
+ "objectID": "07-basic_statistics.html#cluster-analysis",
+ "href": "07-basic_statistics.html#cluster-analysis",
+ "title": "7Â Basic statistics for spatial analysis",
+ "section": "7.2 Cluster analysis",
+ "text": "7.2 Cluster analysis\nSince this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The definition of clusters emcompass many XXXXXXX\nThe first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.\n\n7.2.1 Test for spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\n\n\n\n\n\n\nStatistical test\n\n\n\nIn statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nThe Moran’s statistics is :\n\\[I = \\frac{N}{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}}\\frac{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}(Y_i-\\bar{Y})(Y_j - \\bar{Y})}{\\sum_{i=1}^N(Y_i-\\bar{Y})^2}\\] with :\n\n\\(N\\): the number of polygons,\n\\(w_{ij}\\): is a matrix of spatial weight with zeroes on the diagonal (i.e., \\(w_{ii}=0\\)). For example, if polygons are neighbors, the weight takes the value \\(1\\) otherwise it take the value \\(0\\).\n\\(Y_i\\): the variable of interest,\n\\(\\bar{Y}\\): the mean value of \\(Y\\).\n\nUnder the Moran’s test, the statistics hypothesis are :\n\nH0 : the distribution of cases is spatially independent, i.e. \\(I=0\\).\nH1: the distribution of cases is spatially autocorrelated, i.e. \\(I\\ne0\\).\n\n\n\nWe will compute the Moran’s statistics using spdep and Dcluster packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. In this example, we use poly2nb() and nb2listw(). These function respectively detect the neighboring polygons and assign weight corresponding to \\(1/\\#\\ of\\ neighbors\\). Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\nlibrary(spdep) # Functions for creating spatial weight, spatial analysis\nlibrary(DCluster) # Package with functions for spatial cluster analysis\n\nqueen_nb <- poly2nb(district) # Neighbors according to queen case\nq_listw <- nb2listw(queen_nb, style = 'W') # row-standardized weights\n\n# Moran's I test\nm_test <- moranI.test(cases ~ offset(log(expected)), \n data = district,\n model = 'poisson',\n R = 499,\n listw = q_listw,\n n = length(district$cases), # number of regions\n S0 = Szero(q_listw)) # Global sum of weights\nprint(m_test)\n\nMoran's I test of spatial autocorrelation \n\n Type of boots.: parametric \n Model used when sampling: Poisson \n Number of simulations: 499 \n Statistic: 0.1566449 \n p-value : 0.014 \n\nplot(m_test)\n\n\n\n\nThe Moran’s statistics is here \\(I =\\) 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is \\(p_{value} =\\) 0.014. We therefore reject H0 with error risk of \\(\\alpha = 5\\%\\). The distribution of cases is therefore autocorrelated across districts in Cambodia.\n\n\n\n\n\n\nStatistic distributions\n\n\n\nIn mathematics, a probability distribution is a mathematical expression that represents what we would expect due to random chance. The choice of the probability distribution relies on the type of data you use (continuous, count, binary). In general, three distribution a used while studying disease rates, the binomial, the poisson and the Poisson-gamma mixture (a.k.a negative binomial) distributions.\nThe default Global Moran’s I test assume data are normally distributed. It implies that the mean However, in epidemiology, rates and count values are usually not normally distributed and their variance is not homogeneous across the districts since the size of population at risk differs. to be the same since more variability occurs when we study smaller populations.\nWhile many measures may be appropriately assessed under the normality assumptions of the previous Global Moran’s I, in general disease rates are not best assessed this way. This is because the rates themselves may not be normally distributed, but also because the variance of each rate likely differs because of different size population at risk. For example the previous test assumed that we had the same level of certainty about the rate in each county, when in fact some counties have very sparse data (with high variance) and others have adequate data (with relatively lower variance).\n\n# dataset statistics\nm_cases <- mean(district$cases)\nsd_cases <- sd(district$cases)\n\ncurve(dnorm(x, m_cases, sd_cases), from = -5, to = 16, ylim = c(0, 0.4), col = \"blue\", lwd = 1, \n xlab = \"Number of cases\", ylab = \"Probability\", main = \"Histogram of observed data compared\\nto Normal and Poisson distributions\")\npoints(0:max(district$cases), dpois(0:max(district$cases), m_cases),type = 'b ', pch = 20, col = \"red\", ylim = c(0, 0.6), lty = 2)\nhist(district$cases, add = TRUE, probability = TRUE)\n\nlegend(\"topright\", legend = c(\"Normal distribution\", \"Poisson distribution\", \"Observed distribution\"), col = c(\"blue\", \"red\", \"black\"),pch = c(NA, 20, NA), lty = c(1, 2, 1))\n\n\n\n\n\n\n\n\n7.2.2 Spatial scan statistics\nWhile Moran’s indice focuses on testing for autocorrelation between neighboring polygons (under the null assumption of spatial independance), the spatial scan statistic aims at identifying an abnormal higher risk in a given region compared to the risk outside of this region (under the null assumption of homogeneous distribution). The conception of a cluster is therefore different between the two methods.\nThe function kulldorf from the package SpatialEpiis a simple tool to implement spatial-only scan statistics. Briefly, the kulldorf scan statistics scan the area for clusters using several steps:\n\nIt create a circular window of observation by defining a single location and an associated radius of the windows varying from 0 to a large number that depends on population distribution (largest radius could includes 50% of the population).\nIt aggregates the count of events and the population at risk (or an expected count of events) inside and outside the window of observation.\nFinally, it computes the likelihood ratio to test whether the risk is equal inside versus outside the windows (H0) or greater inside the observed window\nThese 3 steps are repeted for each location and each possible windows-radii.\n\n\nlibrary(\"SpatialEpi\")\n\nThe use of R spatial object is not implementes in kulldorf() function. It uses instead matrix of xy coordinates that represents the centroids of the districts. A given district is included into the observed circular window if its centroids falls into the circle.\n\ndistrict_xy <- st_centroid(district) %>% \n st_coordinates()\n\nhead(district_xy)\n\n X Y\n1 330823.3 1464560\n2 749758.3 1541787\n3 468384.0 1277007\n4 494548.2 1215261\n5 459644.2 1194615\n6 360528.3 1516339\n\n\nWe can then call kulldorff function (you are strongly encourage to call ?kulldorf to properly call the function). The alpha.level threshold filter for the secondary clusters that will be retained. The most-likely cluster will be saved whatever its significance.\n\nkd_Wfever <- kulldorff(district_xy, \n cases = district$cases,\n population = district$T_POP,\n expected.cases = district$expected,\n pop.upper.bound = 0.5, # include maximum 50% of the population in a windows\n n.simulations = 499,\n alpha.level = 0.2)\n\n\n\n\nAll outputs are saved into the R object kd_Wfever. Unfortunately the package did not developed any summary and visualization of the results but we can explore the output object.\n\nnames(kd_Wfever)\n\n[1] \"most.likely.cluster\" \"secondary.clusters\" \"type\" \n[4] \"log.lkhd\" \"simulated.log.lkhd\" \n\n\nFirst, we can focus on the most likely cluster and explore its characteristics.\n\n# We can see which districts (r number) belong to this cluster\nkd_Wfever$most.likely.cluster$location.IDs.included\n\n [1] 48 93 66 180 133 29 194 118 50 144 31 141 3 117 22 43 142\n\n# standardized incidence ratio\nkd_Wfever$most.likely.cluster$SMR\n\n[1] 2.303106\n\n# number of observed and expected cases in this cluster\nkd_Wfever$most.likely.cluster$number.of.cases\n\n[1] 122\n\nkd_Wfever$most.likely.cluster$expected.cases\n\n[1] 52.97195\n\n\n17 districts belong to the cluster and its number of cases is 2.3 times higher than the expected number of case.\nSimilarly, we could study the secondary clusters. Results are saved in a list.\n\n# We can see which districts (r number) belong to this cluster\nlength(kd_Wfever$secondary.clusters)\n\n[1] 1\n\n# retrieve data for all secondary clusters into a table\ndf_secondary_clusters <- data.frame(SMR = sapply(kd_Wfever$secondary.clusters, '[[', 5), \n number.of.cases = sapply(kd_Wfever$secondary.clusters, '[[', 3),\n expected.cases = sapply(kd_Wfever$secondary.clusters, '[[', 4),\n p.value = sapply(kd_Wfever$secondary.clusters, '[[', 8))\n\nprint(df_secondary_clusters)\n\n SMR number.of.cases expected.cases p.value\n1 3.767698 16 4.246625 0.012\n\n\nWe only have one secondary cluster composed of one district.\n\n# create empty column to store cluster informations\ndistrict$k_cluster <- NA\n\n# save cluster informations from kulldorff outputs\ndistrict$k_cluster[kd_Wfever$most.likely.cluster$location.IDs.included] <- 'Most likely cluster'\n\nfor(i in 1:length(kd_Wfever$secondary.clusters)){\ndistrict$k_cluster[kd_Wfever$secondary.clusters[[i]]$location.IDs.included] <- paste(\n 'Secondary cluster ', i, sep = '')\n}\n\n# create map\nmf_map(x = district,\n var = \"k_cluster\",\n type = \"typo\",\n cex = 2,\n leg_title = \"Clusters\")\nmf_layout(title = \"Cluster using kulldorf scan statistic\")"
},
{
"objectID": "01-introduction.html",
@@ -33,231 +47,5 @@
"title": "1Â Introduction",
"section": "1.4 The package terra",
"text": "1.4 The package terra\n The package terra was release in early 2020 by Robert J. Hijmans (also author of raster). Its objective is to propose methods of treatment and analysis of raster data. This package is very similar to the package raster; but it has more features, it’s easier to use, and it’s faster.\n\n\n\n\n\n\nWebsite of package terra : Spatial Data Science with R and “terraâ€\n\n\n\n\n\n\n\n\n\nTip\n\n\n\nA benchmark of raster processing libraries is available here.\n\n\n\n\n\n\nBivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. “Rgdal: Bindings for the ’Geospatial’ Data Abstraction Library.†https://CRAN.R-project.org/package=rgdal.\n\n\nBivand, Roger, and Colin Rundel. 2021. “Rgeos: Interface to Geometry Engine - Open Source (’GEOS’).†https://CRAN.R-project.org/package=rgeos.\n\n\nDunnington, Dewey. 2021. “Ggspatial: Spatial Data Framework for Ggplot2.†https://CRAN.R-project.org/package=ggspatial.\n\n\nGDAL/OGR contributors. n.d. GDAL/OGR Geospatial Data Abstraction Software Library. Open Source Geospatial Foundation. https://gdal.org.\n\n\nGiraud, Timothée. 2022. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\nGiraud, Timothée, and Nicolas Lambert. 2016. “Cartography: Create and Integrate Maps in Your r Workflow†1. https://doi.org/10.21105/joss.00054.\n\n\nHijmans, Robert J. 2022a. “Raster: Geographic Data Analysis and Modeling.†https://CRAN.R-project.org/package=raster.\n\n\n———. 2022b. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nPebesma, Edzer. 2018a. “Simple Features for r: Standardized Support for Spatial Vector Data†10. https://doi.org/10.32614/RJ-2018-009.\n\n\n———. 2018b. “Simple Features for R: Standardized Support for Spatial Vector Data.†The R Journal 10 (1): 439. https://doi.org/10.32614/rj-2018-009.\n\n\n———. 2021. “Stars: Spatiotemporal Arrays, Raster and Vector Data Cubes.†https://CRAN.R-project.org/package=stars.\n\n\nPebesma, Edzer J., and Roger S. Bivand. 2005. “Classes and Methods for Spatial Data in r†5. https://CRAN.R-project.org/doc/Rnews/.\n\n\nPROJ contributors. 2021. PROJ Coordinate Transformation Software Library. Open Source Geospatial Foundation. https://proj.org/.\n\n\nTennekes, Martijn. 2018. “Tmap: Thematic Maps in r†84. https://doi.org/10.18637/jss.v084.i06.\n\n\nWickham, Hadley. 2016. “Ggplot2: Elegant Graphics for Data Analysis.†https://ggplot2.tidyverse.org."
- },
- {
- "objectID": "02-data_acquisition.html",
- "href": "02-data_acquisition.html",
- "title": "2Â Data Acquisition",
- "section": "",
- "text": "The function st_as_sf() makes it possible to transform a data.frame container of geographic coordinates into an object sf. Here we use the data.frame places2 created in the previous point.\n\nlibrary(sf)\nplace_sf <- st_as_sf(read.csv(\"data_cambodia/adress.csv\"), coords = c(\"long\", \"lat\"), crs = 4326)\nplace_sf\n\nSimple feature collection with 2 features and 1 field\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 104.8443 ymin: 11.54366 xmax: 104.9047 ymax: 11.55349\nGeodetic CRS: WGS 84\n address\n1 Phnom Penh International Airport, Phnom Penh, Cambodia\n2 Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia\n geometry\n1 POINT (104.8443 11.55349)\n2 POINT (104.9047 11.54366)\n\n\n\n\nSpherical geometry (s2) switched off\n\n\nTo create a sf POINT type object with only one pair of coordinate (WGS84, longitude=0.5, latitude = 45.5) :\n\nlibrary(sf)\ntest_point <- st_as_sf(data.frame(x = 0.5, y = 45.5), coords = c(\"x\", \"y\"), crs = 4326)\ntest_point\n\nSimple feature collection with 1 feature and 0 fields\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 0.5 ymin: 45.5 xmax: 0.5 ymax: 45.5\nGeodetic CRS: WGS 84\n geometry\n1 POINT (0.5 45.5)\n\n\nWe can display this object sf on an OpenStreetMap basesmap with the package maptiles maptiles (Giraud 2021).\n\nlibrary(maptiles)\nosm <- get_tiles(x = place_sf, zoom = 12)\nplot_tiles(osm)\nplot(st_geometry(place_sf), pch = 2, cex = 2, col = \"red\", add = TRUE)"
- },
- {
- "objectID": "02-data_acquisition.html#online-databases",
- "href": "02-data_acquisition.html#online-databases",
- "title": "2Â Data Acquisition",
- "section": "2.2 Online databases",
- "text": "2.2 Online databases"
- },
- {
- "objectID": "02-data_acquisition.html#openstreetmap",
- "href": "02-data_acquisition.html#openstreetmap",
- "title": "2Â Data Acquisition",
- "section": "2.3 OpenStreetMap",
- "text": "2.3 OpenStreetMap\n\n\n\nOpenStreetMap (OSM) is a participatory mapping project that aims to built a free geographic database on a global scale. OpenStreetMap lets you view, edit and use geographic data around the world.\nTerms of use\n\nOpenStreetMap is open data : you are free to use it for ant purpose as long as you credit OpenStreetMap and its contributers. If you modify or rely data in any way, you may distribute the result only under the same license. (…)\n\nContributors\n\n(…) Our contributors incloude enthusiastic mapmakers, GIS professional, engineers running OSM servers, humanitarians mapping disaster-stricken areas and many mmore.(…)\n\n\n2.3.1 Display and interactive map\nThe two main packages that allow to display as interactive map based on OSM are leaflet (Cheng, Karambelkar, and Xie 2022) and mapview (Appelhans et al. 2022).\n\n2.3.1.1 leaflet\n leaflet uses the javascript library Leaflet (Agafonkin 2015) to create interactive maps.\n\nlibrary(sf)\nlibrary(leaflet)\n\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\nhospital <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE)\n\n\nbanan <- district[district$ADM2_PCODE == \"KH0201\", ] #Select one district (Banan district: KH0201)\nhealth_banan <- hospital[hospital$DCODE == \"201\", ] #Select Health centers in Banan\n\nbanan <- st_transform(banan, 4326) #Transform coordinate system to WGS84\nhealth_banan <- st_transform(health_banan, 4326)\n\nbanan_map <- leaflet(banan) %>% #Create interactive map\n addTiles() %>%\n addPolygons() %>%\n addMarkers(data = health_banan)\nbanan_map\n\n\n\n\n\n\n\n\n\n\n\nWebsite of leaflet\nLeaflet for R\n\n\n\n\n\n2.3.1.2 mapview\n mapview relies on leaflet to create interactive maps, its use is easier and its documentation is a bit dense.\n\nlibrary(mapview)\nmapview(banan) + mapview(health_banan)\n\n\n\n\n\n\n\n\n\n\n\n\nWebsite of mapview\nmapview\n\n\n\n\n\n\n2.3.2 Import basemaps\nThe package maptiles (Giraud 2021) allows downlaoding and displaying raster basemaps.\nThe function get_tiles() allow you to download OSM background maps and the function plot_tiles() allows to display them.\nRenders are better if the input data used the same coordinate system as the tiles (EPSG:3857).\n\nlibrary(sf)\nlibrary(maptiles)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\ndistrict <- st_transform(district, 3857)\nosm_tiles <- get_tiles(x = district, zoom = 10, crop = TRUE)\nplot_tiles(osm_tiles)\nplot(st_geometry(district), border = \"grey20\", lwd = .7, add = TRUE)\nmtext(side = 1, line = -2, text = get_credit(\"OpenStreetMap\"), col=\"tomato\")\n\n\n\n\n\n\n2.3.3 Import OSM data\n\n2.3.3.1 osmdata\n The package osmdata (Padgham et al. 2017) allows extracting vector data from OSM using the Overpass turbo API.\n\nlibrary(sf)\nlibrary(osmdata)\nlibrary(sf)\n\ncountry <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\next <- opq(bbox = st_bbox(st_transform(country, 4326))) #Define the bounding box\nquery <- add_osm_feature(opq = ext, key = 'amenity', value = \"hospital\") #Health Center Extraction\nhospital <- osmdata_sf(query)\nhospital <- unique_osmdata(hospital) #Result reduction (points composing polygon are detected)\n\nThe result contains a point layer and a polygon layer. The polygon layer contains polygons that represent fast food-food place. To obtain a coherent point layer we can use the centroids of the polygons.\n\nhospital_point <- hospital$osm_points\nhospital_poly <- hospital$osm_polygons #Extracting centroids of polygons\nhospital_poly_centroid <- st_centroid(hospital_poly)\n\ncambodia_point <- intersect(names(hospital_point), names(hospital_poly_centroid)) #Identify fields in Cambodia boundary\nhospitals <- rbind(hospital_point[, cambodia_point], hospital_poly_centroid[, cambodia_point]) #Gather the 2 objects\n\nResult display\n\nlibrary(mapview)\nmapview(country) + mapview(hospitals)\n\n\n\n\n\n\n\n\n\n\n\n\nWebsite of osmdata\nosmdata\n\n\n\n\n\n2.3.3.2 osmextract\n The package osmextract (Gilardi and Lovelace 2021) allows to extract data from an OSM database directly. This package make it possible to work on very large volumes of data.\n\n\n\n\n\n\nWebsite of osmextract\nosmextract\n\n\n\nFor administrative boundaries, check here the administrative levels by country:\n\nlibrary(osmextract)\nlibrary(mapsf)\nprovince <- oe_get(\n place = \"Cambodia\",\n download_directory = \"data_cambodia/\",\n layer = \"multipolygons\",\n extra_tags = c(\"wikidata\", \"ISO3166-2\", \"wikipedia\", \"name:en\"),\n vectortranslate_options = c(\n \"-t_srs\", \"EPSG:32648\",\n \"-nlt\", \"PROMOTE_TO_MULTI\",\n \"-where\", \"type = 'boundary' AND boundary = 'administrative' AND admin_level = '4'\"\n ))\n\n0...10...20...30...40...50...60...70...80...90...100 - done.\nReading layer `multipolygons' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/geofabrik_cambodia-latest.gpkg' \n using driver `GPKG'\nSimple feature collection with 25 features and 29 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211418.1 ymin: 1047956 xmax: 784614.9 ymax: 1625621\nProjected CRS: WGS 84 / UTM zone 48N\n\nmf_map(x = province)\n\n\n\n\n\nroads <- oe_get(\n place = \"Cambodia\",\n download_directory = \"data_cambodia/\",\n layer = \"lines\",\n extra_tags = c(\"access\", \"service\", \"maxspeed\"),\n vectortranslate_options = c(\n \"-t_srs\", \"EPSG:32648\",\n \"-nlt\", \"PROMOTE_TO_MULTI\",\n \"-where\", \"\n highway IS NOT NULL\n AND\n highway NOT IN (\n 'abandonded', 'bus_guideway', 'byway', 'construction', 'corridor', 'elevator',\n 'fixme', 'escalator', 'gallop', 'historic', 'no', 'planned', 'platform',\n 'proposed', 'cycleway', 'pedestrian', 'bridleway', 'footway',\n 'steps', 'path', 'raceway', 'road', 'service', 'track'\n )\n \"\n),\n boundary = subset(province, name_en == \"Phnom Penh\"),\n boundary_type = \"clipsrc\"\n)\n\n0...10...20...30...40...50...60...70...80...90...100 - done.\nReading layer `lines' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/geofabrik_cambodia-latest.gpkg' \n using driver `GPKG'\nSimple feature collection with 18794 features and 12 fields\nGeometry type: MULTILINESTRING\nDimension: XY\nBounding box: xmin: 469524.2 ymin: 1263268 xmax: 503494.3 ymax: 1296780\nProjected CRS: WGS 84 / UTM zone 48N\n\nmf_map(x = roads)"
- },
- {
- "objectID": "02-data_acquisition.html#geocoding",
- "href": "02-data_acquisition.html#geocoding",
- "title": "2Â Data Acquisition",
- "section": "2.4 Geocoding",
- "text": "2.4 Geocoding\nServeral pakages alow you to geocode addresses. The package tidygeocoder (Cambon et al. 2021) allow the use of a large number of online geocoding sevices. The package banR (Gombin and Chevalier 2022), which is based on the National Address Base, is the particularly suitable for geocoding addresses in France.\n\n2.4.1 tidygeocoder\n\nlibrary(tidygeocoder)\ntest_adresses <- data.frame(\n address = c(\"Phnom Penh International Airport, Phnom Penh, Cambodia\",\n \"Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia\"))\nplaces1 <- geocode(test_adresses, address)\nplaces1\n\n# A tibble: 2 × 3\n address lat long\n <chr> <dbl> <dbl>\n1 Phnom Penh International Airport, Phnom Penh, Cambodia 11.6 105.\n2 Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia 11.5 105.\n\n\n\n\n\n\n\n\nWebsite by tidygeocoder :\ntidygeocoder\n\n\n\n\n\n2.4.2 banR (Base Adresse Nationale)\n\n# remotes::install_github(\"joelgombin/banR\")\nlibrary(banR)\nmes_adresses <- data.frame(\n address = c(\"19 rue Michel Bakounine, 29600 Morlaix, France\",\n \"2 Allee Emile Pouget, 920128 Boulogne-Billancourt\")\n)\nplaces2 <- geocode_tbl(tbl = mes_adresses, adresse = address)\nplaces2\n\n# A tibble: 2 × 18\n address latit…¹ longi…² resul…³ resul…ⴠresul…ⵠresul…ⶠresul…ⷠresul…â¸\n <chr> <dbl> <dbl> <chr> <dbl> <chr> <chr> <chr> <chr> \n1 19 rue Michel… 48.6 -3.82 19 Rue… 0.81 housen… 29151_… 19 Rue Mi…\n2 2 Allee Emile… 48.8 2.24 2 Allé… 0.83 housen… 92012_… 2 Allée …\n# … with 9 more variables: result_street <chr>, result_postcode <chr>,\n# result_city <chr>, result_context <chr>, result_citycode <chr>,\n# result_oldcitycode <chr>, result_oldcity <chr>, result_district <chr>,\n# result_status <chr>, and abbreviated variable names ¹​latitude, ²​longitude,\n# ³​result_label, â´â€‹result_score, âµâ€‹result_type, â¶â€‹result_id,\n# â·â€‹result_housenumber, â¸â€‹result_name\n\n\n\n\n\n\n\n\nWebsite of banR :\nAn R client for the BAN API"
- },
- {
- "objectID": "02-data_acquisition.html#digitization",
- "href": "02-data_acquisition.html#digitization",
- "title": "2Â Data Acquisition",
- "section": "2.5 Digitization",
- "text": "2.5 Digitization\nThe package mapedit (Appelhans, Russell, and Busetto 2020) allows you to digitize base map directly in R. Although it can be practical in some cases, in package cannot replace the functionalities of a GIS for important digitization tasks.\n\n\n\nGif taken from mapedit website\n\n\n\n\n\n\nAgafonkin, Vladimir. 2015. “Leaflet Javascript Libary.â€\n\n\nAppelhans, Tim, Florian Detsch, Christoph Reudenbach, and Stefan Woellauer. 2022. “Mapview: Interactive Viewing of Spatial Data in r.†https://CRAN.R-project.org/package=mapview.\n\n\nAppelhans, Tim, Kenton Russell, and Lorenzo Busetto. 2020. “Mapedit: Interactive Editing of Spatial Data in r.†https://CRAN.R-project.org/package=mapedit.\n\n\nCambon, Jesse, Diego Hernangómez, Christopher Belanger, and Daniel Possenriede. 2021. “Tidygeocoder: An r Package for Geocoding†6: 3544. https://doi.org/10.21105/joss.03544.\n\n\nCheng, Joe, Bhaskar Karambelkar, and Yihui Xie. 2022. “Leaflet: Create Interactive Web Maps with the JavaScript ’Leaflet’ Library.†https://CRAN.R-project.org/package=leaflet.\n\n\nGilardi, Andrea, and Robin Lovelace. 2021. “Osmextract: Download and Import Open Street Map Data Extracts.†https://CRAN.R-project.org/package=osmextract.\n\n\nGiraud, Timothée. 2021. “Maptiles: Download and Display Map Tiles.†https://CRAN.R-project.org/package=maptiles.\n\n\nGombin, Joel, and Paul-Antoine Chevalier. 2022. “banR: R Client for the BAN API.â€\n\n\nPadgham, Mark, Bob Rudis, Robin Lovelace, and Maëlle Salmon. 2017. “Osmdata†2. https://doi.org/10.21105/joss.00305."
- },
- {
- "objectID": "03-vector_data.html",
- "href": "03-vector_data.html",
- "title": "3Â Vector Data",
- "section": "",
- "text": "The st_read() and st_write() function are used to import and export many types of files. The following lines import the administrative data in district level layer located in the cambodia.gpkg geopackage file.\n\nlibrary(sf)\n\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\") #import district data\n\nReading layer `district' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/cambodia.gpkg' \n using driver `GPKG'\nSimple feature collection with 197 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211534.7 ymin: 1149105 xmax: 784612.1 ymax: 1625495\nProjected CRS: WGS 84 / UTM zone 48N\n\n\nThe following lines export the district object to a data folder in geopackage and shapefile format.\n\nst_write(obj = district, dsn = \"data_cambodia/district.gpkg\", delete_layer = TRUE)\n\nDeleting layer `district' using driver `GPKG'\nWriting layer `district' to data source \n `data_cambodia/district.gpkg' using driver `GPKG'\nWriting 197 features with 10 fields and geometry type Multi Polygon.\n\nst_write(obj = district, \"data_cambodia/district.shp\", layer_options = \"ENCODING=UTF-8\", delete_layer = TRUE)\n\nDeleting layer `district' using driver `ESRI Shapefile'\nWriting layer `district' to data source \n `data_cambodia/district.shp' using driver `ESRI Shapefile'\noptions: ENCODING=UTF-8 \nWriting 197 features with 10 fields and geometry type Multi Polygon."
- },
- {
- "objectID": "03-vector_data.html#display",
- "href": "03-vector_data.html#display",
- "title": "3Â Vector Data",
- "section": "3.2 Display",
- "text": "3.2 Display\nPreview of the variables via the function head() and plot().\n\nhead(district)\n\nSimple feature collection with 6 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 300266.9 ymin: 1180566 xmax: 767313.9 ymax: 1563861\nProjected CRS: WGS 84 / UTM zone 48N\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP Area.Km2.\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416 1067.8638\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708 837.7064\n3 Angk Snuol KH0808 Kandal KH08 45436 47141 92577 183.9050\n4 Angkor Borei KH2101 Takeo KH21 26306 27168 53474 301.0502\n5 Angkor Chey KH0701 Kampot KH07 42448 44865 87313 316.7576\n6 Angkor Chum KH1701 Siemreap KH17 34269 34576 68845 478.6988\n Status DENs geom\n1 <4500km2 79.98773 MULTIPOLYGON (((306568.1 14...\n2 <4500km2 17.55747 MULTIPOLYGON (((751459.2 15...\n3 <4500km2 503.39580 MULTIPOLYGON (((471954.3 12...\n4 <4500km2 177.62485 MULTIPOLYGON (((490048.2 12...\n5 <4500km2 275.64610 MULTIPOLYGON (((462702.2 12...\n6 <4500km2 143.81696 MULTIPOLYGON (((363642.5 15...\n\nplot(district)\n\n\n\n\nfor Geometry display only.\n\nplot(st_geometry(district))"
- },
- {
- "objectID": "03-vector_data.html#coordinate-systems",
- "href": "03-vector_data.html#coordinate-systems",
- "title": "3Â Vector Data",
- "section": "3.3 Coordinate systems",
- "text": "3.3 Coordinate systems\n\n3.3.1 Look up the coordinate system of an object\nThe function st_crs() makes it possible to consult the system of coordinates used and object sf.\n\nst_crs(district)\n\nCoordinate Reference System:\n User input: WGS 84 / UTM zone 48N \n wkt:\nPROJCRS[\"WGS 84 / UTM zone 48N\",\n BASEGEOGCRS[\"WGS 84\",\n ENSEMBLE[\"World Geodetic System 1984 ensemble\",\n MEMBER[\"World Geodetic System 1984 (Transit)\"],\n MEMBER[\"World Geodetic System 1984 (G730)\"],\n MEMBER[\"World Geodetic System 1984 (G873)\"],\n MEMBER[\"World Geodetic System 1984 (G1150)\"],\n MEMBER[\"World Geodetic System 1984 (G1674)\"],\n MEMBER[\"World Geodetic System 1984 (G1762)\"],\n MEMBER[\"World Geodetic System 1984 (G2139)\"],\n ELLIPSOID[\"WGS 84\",6378137,298.257223563,\n LENGTHUNIT[\"metre\",1]],\n ENSEMBLEACCURACY[2.0]],\n PRIMEM[\"Greenwich\",0,\n ANGLEUNIT[\"degree\",0.0174532925199433]],\n ID[\"EPSG\",4326]],\n CONVERSION[\"UTM zone 48N\",\n METHOD[\"Transverse Mercator\",\n ID[\"EPSG\",9807]],\n PARAMETER[\"Latitude of natural origin\",0,\n ANGLEUNIT[\"degree\",0.0174532925199433],\n ID[\"EPSG\",8801]],\n PARAMETER[\"Longitude of natural origin\",105,\n ANGLEUNIT[\"degree\",0.0174532925199433],\n ID[\"EPSG\",8802]],\n PARAMETER[\"Scale factor at natural origin\",0.9996,\n SCALEUNIT[\"unity\",1],\n ID[\"EPSG\",8805]],\n PARAMETER[\"False easting\",500000,\n LENGTHUNIT[\"metre\",1],\n ID[\"EPSG\",8806]],\n PARAMETER[\"False northing\",0,\n LENGTHUNIT[\"metre\",1],\n ID[\"EPSG\",8807]]],\n CS[Cartesian,2],\n AXIS[\"(E)\",east,\n ORDER[1],\n LENGTHUNIT[\"metre\",1]],\n AXIS[\"(N)\",north,\n ORDER[2],\n LENGTHUNIT[\"metre\",1]],\n USAGE[\n SCOPE[\"Engineering survey, topographic mapping.\"],\n AREA[\"Between 102°E and 108°E, northern hemisphere between equator and 84°N, onshore and offshore. Cambodia. China. Indonesia. Laos. Malaysia - West Malaysia. Mongolia. Russian Federation. Singapore. Thailand. Vietnam.\"],\n BBOX[0,102,84,108]],\n ID[\"EPSG\",32648]]\n\n\n\n\n3.3.2 Changing the coordinate system of an object\nThe function st_transform() allows to change the coordinate system of an sf object, to re-project it.\n\nplot(st_geometry(district))\ntitle(\"WGS 84 / UTM zone 48N\")\n\n\n\ndist_reproj <- st_transform(district, \"epsg:4326\")\nplot(st_geometry(dist_reproj))\ntitle(\"WGS84\")\n\n\n\n\nThe Spatial Reference site provides reference for a large number of coordinate systems."
- },
- {
- "objectID": "03-vector_data.html#selection-by-attributes",
- "href": "03-vector_data.html#selection-by-attributes",
- "title": "3Â Vector Data",
- "section": "3.4 Selection by attributes",
- "text": "3.4 Selection by attributes\nThe object sf are data.frame, so you can select their rows and columns in the same way as data.frame.\n\n# row Selection\ndistrict[1:2, ]\n\nSimple feature collection with 2 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 300266.9 ymin: 1449408 xmax: 767313.9 ymax: 1563861\nProjected CRS: WGS 84 / UTM zone 48N\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP Area.Km2.\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416 1067.8638\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708 837.7064\n Status DENs geom\n1 <4500km2 79.98773 MULTIPOLYGON (((306568.1 14...\n2 <4500km2 17.55747 MULTIPOLYGON (((751459.2 15...\n\ndistrict[district$ADM1_EN == \"Phnom Penh\", ]\n\nSimple feature collection with 12 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 468677.5 ymin: 1262590 xmax: 505351.9 ymax: 1297419\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n29 Chamkar Mon KH1201 Phnom Penh KH12 52278 54478 106756\n31 Chbar Ampov KH1212 Phnom Penh KH12 64816 68243 133059\n43 Chraoy Chongvar KH1210 Phnom Penh KH12 30920 31087 62007\n48 Dangkao KH1205 Phnom Penh KH12 46999 48525 95524\n50 Doun Penh KH1202 Phnom Penh KH12 33844 36471 70315\n93 Mean Chey KH1206 Phnom Penh KH12 68381 70366 138747\n117 Praek Pnov KH1211 Phnom Penh KH12 27566 27698 55264\n118 Prampir Meakkakra KH1203 Phnom Penh KH12 31091 33687 64778\n133 Pur SenChey KH1209 Phnom Penh KH12 95050 109297 204347\n141 Russey Keo KH1207 Phnom Penh KH12 67357 68419 135776\n Area.Km2. Status DENs geom\n29 11.049600 <4500km2 9661.5265 MULTIPOLYGON (((494709.4 12...\n31 86.780498 <4500km2 1533.2823 MULTIPOLYGON (((498855.3 12...\n43 85.609156 <4500km2 724.3034 MULTIPOLYGON (((491161.3 12...\n48 113.774833 <4500km2 839.5881 MULTIPOLYGON (((489191.1 12...\n50 7.734808 <4500km2 9090.7234 MULTIPOLYGON (((492447.1 12...\n93 28.998026 <4500km2 4784.7051 MULTIPOLYGON (((491068.2 12...\n117 115.384300 <4500km2 478.9560 MULTIPOLYGON (((481483.3 12...\n118 2.224892 <4500km2 29115.1253 MULTIPOLYGON (((491067.6 12...\n133 148.357984 <4500km2 1377.3913 MULTIPOLYGON (((479078.8 12...\n141 23.381517 <4500km2 5806.9800 MULTIPOLYGON (((490264.8 12...\n\n# column selection\ndistrict[district$ADM1_EN == \"Phnom Penh\", 1:4] \n\nSimple feature collection with 12 features and 4 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 468677.5 ymin: 1262590 xmax: 505351.9 ymax: 1297419\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE\n29 Chamkar Mon KH1201 Phnom Penh KH12\n31 Chbar Ampov KH1212 Phnom Penh KH12\n43 Chraoy Chongvar KH1210 Phnom Penh KH12\n48 Dangkao KH1205 Phnom Penh KH12\n50 Doun Penh KH1202 Phnom Penh KH12\n93 Mean Chey KH1206 Phnom Penh KH12\n117 Praek Pnov KH1211 Phnom Penh KH12\n118 Prampir Meakkakra KH1203 Phnom Penh KH12\n133 Pur SenChey KH1209 Phnom Penh KH12\n141 Russey Keo KH1207 Phnom Penh KH12\n geom\n29 MULTIPOLYGON (((494709.4 12...\n31 MULTIPOLYGON (((498855.3 12...\n43 MULTIPOLYGON (((491161.3 12...\n48 MULTIPOLYGON (((489191.1 12...\n50 MULTIPOLYGON (((492447.1 12...\n93 MULTIPOLYGON (((491068.2 12...\n117 MULTIPOLYGON (((481483.3 12...\n118 MULTIPOLYGON (((491067.6 12...\n133 MULTIPOLYGON (((479078.8 12...\n141 MULTIPOLYGON (((490264.8 12..."
- },
- {
- "objectID": "03-vector_data.html#spatial-selection",
- "href": "03-vector_data.html#spatial-selection",
- "title": "3Â Vector Data",
- "section": "3.5 Spatial selection",
- "text": "3.5 Spatial selection\n\n3.5.1 Intersections\nSelection of roads that are intersecting dangkao district\n\nroad <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE) %>% st_cast(\"LINESTRING\")\ndangkao <- district[district$ADM2_EN == \"Dangkao\", ]\ninter <- st_intersects(x = road, y = dangkao, sparse = FALSE)\nhead(inter)\n\n [,1]\n[1,] FALSE\n[2,] FALSE\n[3,] FALSE\n[4,] FALSE\n[5,] FALSE\n[6,] FALSE\n\ndim(inter)\n\n[1] 108285 1\n\n\nThe inter object is a matrix which indicates for each of element of the road object (6 elements) whether it intersects each elements the dangkao object (1 element). The dimension of the matrix is therefore indeed 6 rows * 1 column. Note the use of the parameter sparse = FALSE here. It is then possible to create a column from this object:\n\nroad$intersect_dangkao <- inter\nplot(st_geometry(dangkao), col = \"lightblue\")\nplot(st_geometry(road), add = TRUE)\nplot(st_geometry(road[road$intersect_dangkao, ]),\n col = \"tomato\", lwd = 1.5, add = TRUE)\n\n\n\n\n\n3.5.1.1 Difference between sparse = TRUE and sparse = FALSE\n\n\n\n\n\n\nsparse = TRUE\n\n\ninter <- st_intersects(x = grid, y = pt, sparse = TRUE)\ninter\n\nSparse geometry binary predicate list of length 4, where the predicate\nwas `intersects'\n 1: (empty)\n 2: 6, 7\n 3: 1, 4\n 4: 2, 3, 5, 8\n\n\n\nsparse = FALSE\n\n\ninter <- st_intersects(x = grid, y = pt, sparse = FALSE)\nrownames(inter) <- grid$id\ncolnames(inter) <- pt$id\ninter\n\n a b c d e f g h\n1 FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE\n2 FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE\n3 TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE\n4 FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE\n\n\n\n\n\n3.5.2 Contains / Within\nSelection of roads contained in the municipality of Dangkao. The function st_within() works like the function st_intersects()\n\nroad$within_dangkao <- st_within(road, dangkao, sparse = FALSE)\nplot(st_geometry(dangkao), col = \"lightblue\")\nplot(st_geometry(road), add = TRUE)\nplot(st_geometry(road[road$within_dangkao, ]), col = \"tomato\",\n lwd = 2, add = TRUE)"
- },
- {
- "objectID": "03-vector_data.html#operation-of-geometries",
- "href": "03-vector_data.html#operation-of-geometries",
- "title": "3Â Vector Data",
- "section": "3.6 Operation of geometries",
- "text": "3.6 Operation of geometries\n\n3.6.1 Extract centroids\n\ndist_c <- st_centroid(district)\nplot(st_geometry(district))\nplot(st_geometry(dist_c), add = TRUE, cex = 1.2, col = \"red\", pch = 20)\n\n\n\n\n\n\n3.6.2 Aggregate polygons\n\ncambodia_dist <- st_union(district) \nplot(st_geometry(district), col = \"lightblue\")\nplot(st_geometry(cambodia_dist), add = TRUE, lwd = 2, border = \"red\")\n\n\n\n\n\n\n3.6.3 Aggregate polygons based on a variable\n\ndist_union <- aggregate(x = district[,c(\"T_POP\")],\n by = list(STATUT = district$Status),\n FUN = \"sum\")\nplot(dist_union)\n\n\n\n\n\n\n3.6.4 Create a buffer zone\n\ndangkao_buffer <- st_buffer(x = dangkao, dist = 1000)\nplot(st_geometry(dangkao_buffer), col = \"#E8DAEF\", lwd=2, border = \"#6C3483\")\nplot(st_geometry(dangkao), add = TRUE, lwd = 2)\n\n\n\n\n\n\n3.6.5 Making an intersection\nBy using the function st_intersection() we will cut one layer by another.\n\nlibrary(magrittr)\n# creation of a buffer zone around the centroid of the municipality of Dangkao district\n# using the pipe\nzone <- st_geometry(dangkao) %>%\n st_centroid() %>%\n st_buffer(30000)\nplot(st_geometry(district))\nplot(zone, border = \"#F06292\", lwd = 2, add = TRUE)\n\n\n\ndist_z <- st_intersection(x = district, y = zone)\nplot(st_geometry(district))\nplot(st_geometry(dist_z), col=\"#AF7AC5\", border=\"#F9E79F\", add=T)\n\n\n\nplot(st_geometry(dist_z))\n\n\n\n\n\n\n3.6.6 Create regular grid\nThe function st_make_grid() allows you to create regular grid. The function produce and object sfc, you must then use the function st_sf() to transform the object sfc into and object sf. During this transformation we add here a column of unique identifiers.\n\ngrid <- st_make_grid(x = district, cellsize = 10000)\ngrid <- st_sf(ID = 1:length(grid), geom = grid)\n\nplot(st_geometry(grid), col = \"grey\", border = \"white\")\nplot(st_geometry(district), border = \"grey50\", add = TRUE)\n\n\n\n\n\n\n3.6.7 Counting points in a polygon (in a grid tile)\n\n# selection of grid tiles that intersect the district\n\ninter <- st_intersects(grid, cambodia_dist, sparse = FALSE)\ngrid <- grid[inter, ]\n\ncase_cambodia <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\" , quiet = TRUE)\nplot(st_geometry(grid), col = \"grey\", border = \"white\")\nplot(st_geometry(case_cambodia), pch = 20, col = \"red\", add = TRUE, cex = 0.8)\n\n\n\ninter <- st_intersects(grid, case_cambodia, sparse = TRUE)\nlength(inter)\n\n[1] 1964\n\n\nHere we use the argument sparse = TRUE. The inter object is a list the length of the grid and each item in the list contain the index of the object items of cases and grid intersection.\nFor example grid tile 35th intersect with four cases 97, 138, 189, 522, 624, 696\n\ninter[35]\n\n[[1]]\n[1] 97 138 189 522 624 696\n\nplot(st_geometry(grid[35, ]))\nplot(st_geometry(case_cambodia), add = T)\nplot(st_geometry(case_cambodia[c(97, 138, 189, 522, 624, 696), ]), \n col = \"red\", pch = 19, add = TRUE)\n\n\n\n\nTo count number of case, simply go to the list and report length of the elements.\n\ngrid$nb_case <- sapply(X = inter, FUN = length) # create 'nb_case' column to store number of health centers in each grid tile \nplot(grid[\"nb_case\"])\n\n\n\n\n\n\n3.6.8 Aggregate point values into polygons\nIn this example we import a csv file that contain data from a population grid. Once import we transform it data.frame into an object sf.\nThe objective is to aggregate the values id these points (the population contained in the “DENs†field) in the municipalities of the district.\n\npp_pop_raw <- read.csv(\"data_cambodia/pp_pop_dens.csv\") # import file\npp_pop_raw$id <- 1:nrow(pp_pop_raw) # adding a unique identifier\npp_pop <- st_as_sf(pp_pop_raw, coords = c(\"X\", \"Y\"), crs = 32648) # Transform into object sf\npp_pop <- st_transform(pp_pop, st_crs(district)) # Transform projection\ninter <- st_intersection(pp_pop, district) # Intersection\ninter\n\nSimple feature collection with 1295 features and 12 fields\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 469177.5 ymin: 1263090 xmax: 505177.5 ymax: 1297090\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n DENs id ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n149 NA 149 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n150 NA 150 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n151 NA 151 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n186 NA 186 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n187 NA 187 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n188 NA 188 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n223 NA 223 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n224 NA 224 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n225 NA 225 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n226 3.400075 226 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n Area.Km2. Status DENs.1 geometry\n149 183.905 <4500km2 503.3958 POINT (469177.5 1267090)\n150 183.905 <4500km2 503.3958 POINT (470177.5 1267090)\n151 183.905 <4500km2 503.3958 POINT (471177.5 1267090)\n186 183.905 <4500km2 503.3958 POINT (469177.5 1268090)\n187 183.905 <4500km2 503.3958 POINT (470177.5 1268090)\n188 183.905 <4500km2 503.3958 POINT (471177.5 1268090)\n223 183.905 <4500km2 503.3958 POINT (469177.5 1269090)\n224 183.905 <4500km2 503.3958 POINT (470177.5 1269090)\n225 183.905 <4500km2 503.3958 POINT (471177.5 1269090)\n226 183.905 <4500km2 503.3958 POINT (472177.5 1269090)\n\n\nBy using the function st_intersection() we add to each point of the grid all the information on the municipality in which it is located.\nWe can then use the function aggregate() to aggregate the population by municipalities.\n\nresultat <- aggregate(x = list(pop_from_grid = inter$DENs), \n by = list(ADM2_EN = inter$ADM2_EN), \n FUN = \"sum\")\nhead(resultat)\n\n ADM2_EN pop_from_grid\n1 Angk Snuol NA\n2 Chamkar Mon 10492.7159\n3 Chbar Ampov 1593.9593\n4 Chraoy Chongvar 1434.1785\n5 Dangkao 942.3595\n6 Doun Penh 10781.8026\n\n\nWe can then create a new object with this result.\n\ndist_result <- merge(district, resultat, by = \"ADM2_EN\", all.x = TRUE)\ndist_result\n\nSimple feature collection with 197 features and 11 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211534.7 ymin: 1149105 xmax: 784612.1 ymax: 1625495\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708\n3 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n4 Angkor Borei KH2101 Takeo KH21 26306 27168 53474\n5 Angkor Chey KH0701 Kampot KH07 42448 44865 87313\n6 Angkor Chum KH1701 Siemreap KH17 34269 34576 68845\n7 Angkor Thum KH1702 Siemreap KH17 13802 14392 28194\n8 Anlong Veaeng KH2201 Oddar Meanchey KH22 24122 23288 47410\n9 Aoral KH0504 Kampong Speu KH05 19874 19956 39830\n10 Ba Phnum KH1401 Prey Veng KH14 46562 49852 96414\n Area.Km2. Status DENs pop_from_grid geometry\n1 1067.8638 <4500km2 79.98773 NA MULTIPOLYGON (((306568.1 14...\n2 837.7064 <4500km2 17.55747 NA MULTIPOLYGON (((751459.2 15...\n3 183.9050 <4500km2 503.39580 NA MULTIPOLYGON (((471954.3 12...\n4 301.0502 <4500km2 177.62485 NA MULTIPOLYGON (((490048.2 12...\n5 316.7576 <4500km2 275.64610 NA MULTIPOLYGON (((462702.2 12...\n6 478.6988 <4500km2 143.81696 NA MULTIPOLYGON (((363642.5 15...\n7 357.8890 <4500km2 78.77862 NA MULTIPOLYGON (((376584.4 15...\n8 1533.5702 <4500km2 30.91479 NA MULTIPOLYGON (((404936.4 15...\n9 2381.7084 <4500km2 16.72329 NA MULTIPOLYGON (((414000.6 13...\n10 342.3439 <4500km2 281.62910 NA MULTIPOLYGON (((545045.4 12..."
- },
- {
- "objectID": "03-vector_data.html#measurements",
- "href": "03-vector_data.html#measurements",
- "title": "3Â Vector Data",
- "section": "3.7 Measurements",
- "text": "3.7 Measurements\n\n3.7.1 Create a distance matrix\nIf the dataset’s projection system is specified, the distance are expressed in the projection measurement unit (most often in meter)\n\nmat <- st_distance(x = dist_c, y = dist_c)\nmat[1:5,1:5]\n\nUnits: [m]\n [,1] [,2] [,3] [,4] [,5]\n[1,] 0.0 425993.7 232592.12 298254.12 299106.92\n[2,] 425993.7 0.0 386367.88 414428.82 452431.87\n[3,] 232592.1 386367.9 0.00 67060.05 82853.88\n[4,] 298254.1 414428.8 67060.05 0.00 40553.15\n[5,] 299106.9 452431.9 82853.88 40553.15 0.00\n\n\n\n\n3.7.2 Calculate routes\n The package osrm (R-osrm?) acts as an interface R and the OSRM (luxen-vetter-2011?). This package allows to calculate time and distance matrices, road routes, isochrones. The package uses the OSRM demo server by default. In case of intensive use it is strongly recommended to use your own instance of OSRM (with Docker).\n\n3.7.2.1 Calculate a route\nThe fonction osrmRoute() allows you to calculate routes.\n\nlibrary(sf)\nlibrary(osrm)\nlibrary(maptiles)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\",layer = \"district\", quiet = TRUE)\ndistrict <- st_transform(district, 32648)\n\nodongk <- district[district$ADM2_PCODE == \"KH0505\", ] # Itinerary between Odongk district and Toul Kouk\ntakmau <- district[district$ADM2_PCODE == \"KH0811\",]\nroute <- osrmRoute(src = odongk, \n dst = takmau, \n returnclass = \"sf\")\nosm <- get_tiles(route, crop = TRUE)\nplot_tiles(osm)\nplot(st_geometry(route), col = \"#b23a5f\", lwd = 6, add = T)\nplot(st_geometry(route), col = \"#eee0e5\", lwd = 1, add = T)\n\n\n\n\n\n\n3.7.2.2 Calculation of a time matrix\nThe function osrmTable() makes it possible to calculate matrices of distances or times by road.\nIn this example we calculate a time matrix between 2 addresses and health centers in Phnom Penh on foot.\n\nlibrary(sf)\nlibrary(tidygeocoder)\nhospital <- st_read(\"data_cambodia/cambodia.gpkg\",layer= \"hospital\", quiet = TRUE)\n\nhospital_pp <- hospital[hospital$PCODE == \"12\", ] # Selection of health centers in Phnom Penh\n\nadresses <- data.frame(adr = c(\"Royal Palace Park, Phnom Penh Phnom, Cambodia\",\n \"Wat Phnom Daun Penh, Phnom Penh, Cambodia\")) # Geocoding of 2 addresses in Phnom Penh\n\nplaces <- tidygeocoder::geocode(.tbl = adresses,address = adr)\nplaces\n\n# A tibble: 2 × 3\n adr lat long\n <chr> <dbl> <dbl>\n1 Royal Palace Park, Phnom Penh Phnom, Cambodia 11.6 105.\n2 Wat Phnom Daun Penh, Phnom Penh, Cambodia 11.6 105.\n\n# Calculation of the distance matrix between the 2 addresses and the health center in Phnom Penh\n\ncal_mat <- osrmTable(src = places[,c(1,3,2)], \n dst = hospital_pp, \n osrm.profile = \"foot\")\n\ncal_mat$durations[1:2, 1:5]\n\n 684 685 686 687 691\nRoyal Palace Park, Phnom Penh Phnom, Cambodia 55.9 71.6 64.4 40.2 76.7\nWat Phnom Daun Penh, Phnom Penh, Cambodia 60.1 80.4 40.1 32.8 53.1\n\n# Which address has better accessibility to health center in Phnom Penh?\n\nboxplot(t(cal_mat$durations[,]), cex.axis = 0.7)"
- },
- {
- "objectID": "04-raster_data.html",
- "href": "04-raster_data.html",
- "title": "4Â Work with Raster Data",
- "section": "",
- "text": "This chapter is largely inspired by two presentation; Madelin (2021) and Nowosad (2021); carried out as part of the SIGR2021 thematic school."
- },
- {
- "objectID": "04-raster_data.html#format-of-objects-spatraster",
- "href": "04-raster_data.html#format-of-objects-spatraster",
- "title": "4Â Work with Raster Data",
- "section": "4.1 Format of objects SpatRaster",
- "text": "4.1 Format of objects SpatRaster\nThe package terra (Hijmans 2022) allows to handle vector and raster data. To manipulate this spatial data, terra store it in object of type SpatVector and SpatRaster. In this chapter, we focus on the manipulation of raster data (SpatRaster) from functions offered by this package.\nAn object SpatRaster allows to handle vector and raster data, in one or more layers (variables). This object also stores a number of fundamental parameters that describe it (number of columns, rows, spatial extent, coordinate reference system, etc.).\n\n\n\nSource : (Racine 2016)"
- },
- {
- "objectID": "04-raster_data.html#importing-and-exporting-data",
- "href": "04-raster_data.html#importing-and-exporting-data",
- "title": "4Â Work with Raster Data",
- "section": "4.2 Importing and exporting data",
- "text": "4.2 Importing and exporting data\nThe package terra allows importing and exporting raster files. It is based on the GDAL library which makes it possible to read and process a very large number of geographic image formats.\n\nlibrary(terra)\n\nThe function rast() allows you to create and/or import raster data. The following lines import the raster file elevation.tif (Tagged Image File Format) into an object of type SpatRaster (default).\n\nelevation <- rast(\"data_cambodia/elevation.tif\") \nelevation\n\nclass : SpatRaster \ndimensions : 5235, 6458, 1 (nrow, ncol, nlyr)\nresolution : 0.0008333394, 0.0008332568 (x, y)\nextent : 102.2935, 107.6752, 10.33984, 14.70194 (xmin, xmax, ymin, ymax)\ncoord. ref. : lon/lat WGS 84 (EPSG:4326) \nsource : elevation.tif \nname : elevation \n\n\nModifying the name of the stored variable (altitude).\n\nnames(elevation) <- \"Altitude\" \n\nThe function writeRaster() allow you to save an object SpatRaster on your machine, in the format of your choice.\n\nwriteRaster(x = elevation, filename = \"data_cambodia/new_elevation.tif\")"
- },
- {
- "objectID": "04-raster_data.html#displaying-a-spatraster-object",
- "href": "04-raster_data.html#displaying-a-spatraster-object",
- "title": "4Â Work with Raster Data",
- "section": "4.3 Displaying a SpatRaster object",
- "text": "4.3 Displaying a SpatRaster object\nThe function plot() is use to display an object SpatRaster.\n\nplot(elevation)\n\n\n\n\n\n\n\n\nA raster always contains numerical data, but it can be both quantitative data and numerically coded qualitative (categorical) data (ex: type of land cover).\nSpecify the type of data stored with the augment type (type = \"continuous\" default), to display them correctly.\nImport and display of raster containing categorical data: Phnom Penh Land Cover 2019 (land cover types) with a resolution of 1.5 meters:\n\nlulc_2019 <- rast(\"data_cambodia/lulc_2019.tif\") #Import Phnom Penh landcover 2019, landcover types\n\nThe landcover data was produced from SPOT7 satellite image with 1.5 meter spatial resolution. An extraction centered on the municipality of Phnom Penh was then carried out.\n\nplot(lulc_2019, type = \"classes\")\n\n\n\n\n\n\n\n\nTo display the actual tiles of landcover types, as well as the official colors of Phnom Penh Landcover nomenclature (available here), you can proceed as follows.\n\nclass_name <- c(\n \"Roads\",\n \"Built-up areas\",\n \"Water Bodies and rivers\",\n \"Wetlands\",\n \"Dry bare area\",\n \"Bare crop fields\",\n \"Low vegetation areas\",\n \"High vegetation areas\",\n \"Forested areas\")\n\nclass_color <- c(\"#070401\", \"#c84639\", \"#1398eb\",\"#8bc2c2\",\n \"#dc7b34\", \"#a6bd5f\",\"#e8e8e8\", \"#4fb040\", \"#35741f\")\nplot(lulc_2019,\n type = \"classes\",\n levels = class_name,\n col = class_color,\n plg = list(cex = 0.7),\n mar = c(3.1, 3.1, 2.1, 10) #The margin are (bottom, left, top, right) respectively\n )"
- },
- {
- "objectID": "04-raster_data.html#change-to-the-study-area",
- "href": "04-raster_data.html#change-to-the-study-area",
- "title": "4Â Work with Raster Data",
- "section": "4.4 Change to the study area",
- "text": "4.4 Change to the study area\n\n4.4.1 (Re)projections\nTo modify the projection system of a raster, use the function project(). It is then necessary to indicate the method for estimating the new cell values.\n\n\n\nSource : Centre Canadien de Télédétection\n\n\nFour interpolation methods are available:\n\nnear : nearest neighbor, fast and default method for qualitative data;\n\nbilinear : bilinear interpolation. Default method for quantitative data;\n\ncubic : cubic interpolation;\n\ncubicspline : cubic spline interpolation.\n\n\n# Re-project data \n\nelevation_utm = project(x = elevation, y = \"EPSG:32648\", method = \"bilinear\") #from WGS84(EPSG:4326) to UTM zone48N(EPSG:32648) \nlulc_2019_utm = project(x = lulc_2019, y = \"EPSG:32648\", method = \"near\") #keep original projection: UTM zone48N(EPSG:32648)\n\n\n\n\n\n\n\n\n\n\n\n\n4.4.2 Crop\nClipping a raster to the extent of another object SpatVector or SpatRaster is achievable with the crop().\n\n\n\n\n\n\n\n\n\n\n\nSource : (Racine 2016)\n\n\n\nImport vector data of (municipal divisions) using function vect. This data will be stored in an SpatVector object.\n\ndistrict <- vect(\"data_cambodia/cambodia.gpkg\", layer=\"district\")\n\nExtraction of district boundaries of Thma Bang district (ADM2_PCODE : KH0907).\n\nthma_bang <- subset(district, district$ADM2_PCODE == \"KH0907\") \n\nUsing the function crop(), Both data layers must be in the same projection.\n\ncrop_thma_bang <- crop(elevation_utm, thma_bang)\n\nplot(crop_thma_bang)\nplot(thma_bang, add=TRUE)\n\n\n\n\n\n\n\n\n\n\n4.4.3 Mask\nTo display only the values of a raster contained in a polygon, use the function mask().\n\n\n\nSource : (Racine 2016)\n\n\nCreation of a mask on the crop_thma_bang raster to the municipal limits (polygon) of Thma Bang district.\n\nmask_thma_bang <- mask(crop_thma_bang, thma_bang)\n\nplot(mask_thma_bang)\nplot(thma_bang, add = TRUE)\n\n\n\n\n\n\n\n\n\n\n4.4.4 Aggregation and disaggregation\nResampling a raster to a different resolution is done in two steps.\n\n\n\n\n\n\n1\n\n\n\n\n\n\n\n2\n\n\n\n\n\n\n\n3\n\n\n\n\n\n\nSource : (Racine 2016)\n\n\n\nDisplay the resolution of a raster with the function res().\n\nres(elevation_utm) #check cell size\n\n[1] 91.19475 91.19475\n\n\nCreate a grid with the same extent, then decrease the spatial resolution (larger cells).\n\nelevation_LowerGrid <- elevation_utm\n# elevation_HigherGrid <- elevation_utm\n\nres(elevation_LowerGrid) <- 1000 #cells size = 1000 meter\n# res(elevation_HigherGrid) <- 10 #cells size = 10 meter\n\nelevation_LowerGrid\n\nclass : SpatRaster \ndimensions : 484, 589, 1 (nrow, ncol, nlyr)\nresolution : 1000, 1000 (x, y)\nextent : 203586.3, 792586.3, 1142954, 1626954 (xmin, xmax, ymin, ymax)\ncoord. ref. : WGS 84 / UTM zone 48N (EPSG:32648) \n\n\nThe function resample() allows to resample the atarting values in the new spatial resolution. Several resampling methods are available (cf. partie 5.4.1).\n\nelevation_LowerGrid <- resample(elevation_utm, \n elevation_LowerGrid, \n method = \"bilinear\") \n\nplot(elevation_LowerGrid, \n main=\"Cell size = 1000m\\nBilinear resampling method\")\n\n\n\n\n\n\n\n\n\n\n4.4.5 Raster fusion\nMerge multiple objects SpatRaster into one with merge() or mosaic().\n\n\n\nSource : https://desktop.arcgis.com/fr/arcmap/10.3/manage-data/raster-and-images/what-is-a-mosaic.htm\n\n\nAfter cutting the elevation raster by the municipal boundary of Thma Bang district (cf partie 5.4.2), we do the same thing for the neighboring municipality of Phnum Kravanh district.\n\nphnum_kravanh <- subset(district, district$ADM2_PCODE == \"KH1504\") # Extraction of the municipal boundaries of Phnum Kravanh district\n\ncrop_phnum_kravanh <- crop(elevation_utm, phnum_kravanh) #clipping the elevation raster according to district boundaries\n\nThe crop_thma_bang and crop_phnum_kravanh elevation raster overlap spatially:\n\n\n\n\n\n\n\n\n\nThe difference between the functions merge() and mosiac() relates to values of the overlapping cells. The function mosaic() calculate the average value while merge() holding the value of the object SpaRaster called n the function.\n\n#in this example, merge() and mosaic() give the same result\nmerge_raster <- merge(crop_thma_bang, crop_phnum_kravanh) \nmosaic_raster <- mosaic(crop_thma_bang, crop_phnum_kravanh)\n\nplot(merge_raster)\n\n\n\n\n\n\n\n# plot(mosaic_raster)\n\n\n\n4.4.6 Segregate\nDecompose a raster by value (or modality) into different rasterlayers with the function segregate.\n\nlulc_2019_class <- segregate(lulc_2019, keep=TRUE, other=NA) #creating a raster layer by modality\nplot(lulc_2019_class)"
- },
- {
- "objectID": "04-raster_data.html#map-algebra",
- "href": "04-raster_data.html#map-algebra",
- "title": "4Â Work with Raster Data",
- "section": "4.5 Map Algebra",
- "text": "4.5 Map Algebra\nMap algebra is classified into four groups of operation (Tomlin 1990):\n\nLocal : operation by cell, on one or more layers;\n\nFocal : neighborhood operation (surrounding cells);\n\nZonal : to summarize the matrix values for certain zones, usually irregular;\nGlobal : to summarize the matrix values of one or more matrices.\n\n\n\n\nSource : (Li 2009)\n\n\n\n4.5.1 Local operations\n\n\n\nSource : (Mennis 2015)\n\n\n\n4.5.1.1 Value replacement\n\nelevation_utm[elevation_utm[[1]]== -9999] <- NA #replaces -9999 values with NA\n\nelevation_utm[elevation_utm < 1500] <- NA #Replace values < 1500 with NA\n\n\nelevation_utm[is.na(elevation_utm)] <- 0 #replace NA values with 0\n\n\n\n4.5.1.2 Operation on each cell\n\nelevation_1000 <- elevation_utm + 1000 # Adding 1000 to the value of each cell\n\nelevation_median <- elevation_utm - global(elevation_utm, median)[[1]] # Removed median elevation to each cell's value\n\n\n\n\n\n\n\n\n\n\n\n\n4.5.1.3 Reclassification\nReclassifying raster values can be used to discretize quantitative data as well as to categorize qualitative categories.\n\nreclassif <- matrix(c(1, 2, 1, \n 2, 4, 2,\n 4, 6, 3,\n 6, 9, 4), \n ncol = 3, byrow = TRUE)\n\nValues between 1 and 2 will be replaced by the value 1.\nValues between 3 and 4 will be replaced by the value 2.\nValues between 5 and 6 will be replaced by the value 3. Values between 7 and 9 will be replaced by the value 4.\n…\n\nreclassif\n\n [,1] [,2] [,3]\n[1,] 1 2 1\n[2,] 2 4 2\n[3,] 4 6 3\n[4,] 6 9 4\n\n\nThe function classify() allows you to perform the reclassification.\n\nlulc_2019_reclass <- classify(lulc_2019, rcl = reclassif)\nplot(lulc_2019_reclass, type =\"classes\")\n\n\n\n\nDisplay with the official titles and colors of the different categories.\n\nplot(lulc_2019_reclass, \n type =\"classes\", \n levels=c(\"Urban areas\",\n \"Water body\",\n \"Bare areas\",\n \"Vegetation areas\"),\n col=c(\"#E6004D\",\n \"#00BFFF\",\n \"#D3D3D3\", \n \"#32CD32\"),\n mar=c(3, 1.5, 1, 11))\n\n\n\n\n\n\n\n\n\n\n4.5.1.4 Operation on several layers (ex: NDVI)\nIt is possible to calculate the value of a cell from its values stored in different layers of an object SpatRaster.\nPerhaps the most common example is the calculation of the Normalized Vegetation Index (NDVI). For each cell, a value is calculated from two layers of raster from a multispectral satellite image.\n\n# Import d'une image satellite multispectrale\nsentinel2a <- rast(\"data_cambodia/Sentinel2A.tif\")\n\nThis multispectral satellite image (10m resolution) dated 25/02/2020, was produced by Sentinel-2 satellite and was retrieved from plateforme Copernicus Open Access Hub. An extraction of Red and near infrared spectral bands, centered on the Phnom Penh city, was then carried out.\n\nplot(sentinel2a)\n\n\n\n\n\n\n\n\nTo lighten the code, we assign the two matrix layers in different SpatRaster objects.\n\nB04_Red <- sentinel2a[[1]] #spectral band Red\n\nB08_NIR <-sentinel2a[[2]] #spectral band near infrared\n\nFrom these two raster objects , we can calculate the normalized vegetation index:\n\\[{NDVI}=\\frac{\\mathrm{NIR} - \\mathrm{Red}} {\\mathrm{NIR} + \\mathrm{Red}}\\]\n\nraster_NDVI <- (B08_NIR - B04_Red ) / (B08_NIR + B04_Red )\n\nplot(raster_NDVI)\n\n\n\n\n\n\n\n\nThe higher the values (close to 1), the denser the vegetation.\n\n\n\n4.5.2 Focal operations\n\n\n\nSource : (Mennis 2015)\n\n\nFocal analysis conisders a cell plus its direct neighbors in contiguous and symmetrical (neighborhood operations). Most often, the value of the output cell is the result of a block of 3 x 3 (odd number) input cells.\nThe first step is to build a matrix that determines the block of cells that will be considered around each cell.\n\n# 5 x 5 matrix, where each cell has the same weight\nmon_focal <- matrix(1, nrow = 5, ncol = 5)\nmon_focal\n\n [,1] [,2] [,3] [,4] [,5]\n[1,] 1 1 1 1 1\n[2,] 1 1 1 1 1\n[3,] 1 1 1 1 1\n[4,] 1 1 1 1 1\n[5,] 1 1 1 1 1\n\n\nThe function focal() Then allows you to perform the desired analysis. For example: calculating the average of the values of all contiguous cells, for each cell in the raster.\n\nelevation_LowerGrid_mean <- focal(elevation_LowerGrid, \n w = mon_focal, \n fun = mean)\n\n\n\n\n\n\n\n\n\n\n\n4.5.2.1 Focal operations for elevation rasters\nThe function terrain() allows to perform focal analyzes specific to elevation rasters. Six operations are available:\n\nslope = calculation of the slope or degree of inclination of the surface;\n\naspect = calculate slope orientation;\n\nroughness = calculate of the variability or irregularity of the elevation;\n\nTPI = calculation of the index of topgraphic positions;\n\nTRI = elevation variability index calculation;\n\nflowdir = calculation of the water flow direction.\n\nExample with calculation of slopes(slope).\n\n#slope calculation\nslope <- terrain(elevation_utm, \"slope\", \n neighbors = 8, #8 (or 4) cells around taken into account\n unit = \"degrees\") #Output unit\n\nplot(slope) #Inclination of the slopes, in degrees\n\n\n\n\n\n\n\n\n\n\n\n4.5.3 Global operations\n\n\n\nSource : https://gisgeography.com/map-algebra-global-zonal-focal-local\n\n\nGlobal operation are used to summarize the matrix values of one or more matrices.\n\nglobal(elevation_utm, fun = \"mean\") #average values\n\n mean\nAltitude 80.01082\n\n\n\nglobal(elevation_utm, fun = \"sd\") #standard deviation\n\n sd\nAltitude 155.885\n\n\n\nfreq(lulc_2019_reclass) #frequency\n\n layer value count\n1 1 1 47485325\n2 1 2 13656289\n3 1 3 14880961\n4 1 4 37194979\n\ntable(lulc_2019_reclass[]) #contingency table\n\n\n 1 2 3 4 \n47485325 13656289 14880961 37194979 \n\n\nStatistical representations that summarize matrix information.\n\nhist(elevation_utm) #histogram\n\nWarning: [hist] a sample of3% of the cells was used\n\n\n\n\n\n\n\n\ndensity(elevation_utm) #density\n\n\n\n\n\n\n\n\n\n\n4.5.4 Zonal operation\n\n\n\nSource : (Mennis 2015)\n\n\nThe zonal operation make it possible to summarize the matrix values of certain zones (group of contiguous cells in space or in value).\n\n4.5.4.1 Zonal operation on an extraction\nAll global operations can be performed on an extraction of cells resulting from the functions crop(), mask(), segregate()…\nExample: average elevation for the city of Thma Bang district (cf partie 5.4.3).\n\n# Average value of the \"mask\" raster over Thma Bang district\nglobal(mask_thma_bang, fun = \"mean\", na.rm=TRUE)\n\n mean\nAltitude 584.7703\n\n\n\n\n4.5.4.2 Zonal operation from a vector layer\nThe function extract() allows you to extract and manipulate the values of cells that intersect vector data.\nExample from polygons:\n\n# Average elevation for each polygon (district)?\nelevation_by_dist <- extract(elevation_LowerGrid, district, fun=mean)\nhead(elevation_by_dist, 10)\n\n ID Altitude\n1 1 8.953352\n2 2 196.422240\n3 3 23.453937\n4 4 3.973118\n5 5 29.545801\n6 6 41.579593\n7 7 50.162749\n8 8 85.128777\n9 9 269.068091\n10 10 8.439041\n\n\n\n\n4.5.4.3 Zonal operation from raster\nZonal operation can be performed by area bounded by the categorical values of a second raster. For this, the two raster must have exaclty the same extent and the same resolution.\n\n#create a second raster with same resolution and extent as \"elevation_clip\"\nelevation_clip <- rast(\"data_cambodia/elevation_clip.tif\")\nelevation_clip_utm <- project(x = elevation_clip, y = \"EPSG:32648\", method = \"bilinear\")\nsecond_raster_CLC <- rast(elevation_clip_utm)\n\n#resampling of lulc_2019_reclass \nsecond_raster_CLC <- resample(lulc_2019_reclass, second_raster_CLC, method = \"near\") \n \n#added a variable name for the second raster\nnames(second_raster_CLC) <- \"lulc_2019_reclass_resample\"\n\n\n\n\n\n\n\n\n\n\nCalculation of the average elevation for the different areas of the second raster.\n\n#average elevation for each area of the \"second_raster\"\nzonal(elevation_clip_utm, second_raster_CLC , \"mean\", na.rm=TRUE)\n\n lulc_2019_reclass_resample elevation_clip\n1 1 12.83846\n2 2 8.31809\n3 3 11.41178\n4 4 11.93546"
- },
- {
- "objectID": "04-raster_data.html#transformation-and-conversion",
- "href": "04-raster_data.html#transformation-and-conversion",
- "title": "4Â Work with Raster Data",
- "section": "4.6 Transformation and conversion",
- "text": "4.6 Transformation and conversion\n\n4.6.1 Rasterization\nConvert polygons to raster format.\n\nchamkarmon = subset(district, district$ADM2_PCODE ==\"KH1201\") \nraster_district <- rasterize(x = chamkarmon, y = elevation_clip_utm)\n\n\nplot(raster_district)\n\n\n\n\n\n\n\n\nConvert points to raster format\n\n#rasterization of the centroids of the municipalities\nraster_dist_centroid <- rasterize(x = centroids(district), \n y = elevation_clip_utm, fun=sum)\nplot(raster_dist_centroid, col = \"red\")\nplot(district, add =TRUE)\n\n\n\n\nConvert lines in raster format\n\n#rasterization of municipal boundaries\nraster_dist_line <- rasterize(x = as.lines(district), y = elevation_clip_utm, fun=sum)\n\n\nplot(raster_dist_line)\n\n\n\n\n\n\n4.6.2 Vectorisation\nTransform a raster to vector polygons.\n\npolygon_elevation <- as.polygons(elevation_clip_utm)\n\n\nplot(polygon_elevation, y = 1, border=\"white\")\n\n\n\n\nTransform a raster to vector points.\n\npoints_elevation <- as.points(elevation_clip_utm)\n\n\nplot(points_elevation, y = 1, cex = 0.3)\n\n\n\n\nTransform a raster into vector lines.\n\nlines_elevation <- as.lines(elevation_clip_utm)\n\n\nplot(lines_elevation)\n\n\n\n\n\n\n4.6.3 terra, raster, sf, stars…\nReference packages for manipulating spatial data all rely o their own object class. It is sometimes necessary to convert these objects from one class to another class to take advance of all the features offered by these different packages.\nConversion functions for raster data:\n\n\n\nFROM/TO\nraster\nterra\nstars\n\n\n\n\nraster\n\nrast()\nst_as_stars()\n\n\nterra\nraster()\n\nst_as_stars()\n\n\nstars\nraster()\nas(x, ‘Raster’) + rast()\n\n\n\n\nConversion functions for vector data:\n\n\n\nFROM/TO\nsf\nsp\nterra\n\n\n\n\nsf\n\nas(x, ‘Spatial’)\nvect()\n\n\nsp\nst_as_sf()\n\nvect()\n\n\nterra\nst_as_sf()\nas(x, ‘Spatial’)\n\n\n\n\n\n\n\n\nHijmans, Robert J. 2022. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nLi, Xingong. 2009. “Map Algebra and Beyond : 1. Map Algebra for Scalar Fields.†https://slideplayer.com/slide/5822638/.\n\n\nMadelin, Malika. 2021. “Analyse d’images Raster (Et Télédétection).†https://mmadelin.github.io/sigr2021/SIGR2021_raster_MM.html.\n\n\nMennis, Jeremy. 2015. “Fundamentals of GIS : Raster Operations.†https://cupdf.com/document/gus-0262-fundamentals-of-gis-lecture-presentation-7-raster-operations-jeremy.html.\n\n\nNowosad, Jakub. 2021. “Image Processing and All Things Raster.†https://nowosad.github.io/SIGR2021/workshop2/workshop2.html.\n\n\nRacine, Etienne B. 2016. “The Visual Raster Cheat Sheet.†https://rpubs.com/etiennebr/visualraster.\n\n\nTomlin, C. Dana. 1990. Geographic Information Systems and Cartographic Modeling. Prentice Hall."
- },
- {
- "objectID": "05-mapping_with_r.html",
- "href": "05-mapping_with_r.html",
- "title": "5Â Mapping With R",
- "section": "",
- "text": "The fonction mf_map() is the central function of the package mapsf (Giraud 2022a). It makes it possible to carry out most of the usual representations in cartography. These main arguments are:\n\nx, an sf object ;\nvar, the name of variable to present ;\ntype, the type of presentation.\n\n\n\nThe following lines import the spatial information layers located in the geopackage cambodia.gpkg file.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n#Import roads data in Cambodia\nroad = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE)\n#Import health center data in Cambodia\nhospital = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE)\n\n\n\n\nWithout using types specification, the function mf_map() simply display the background map.\n\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = road, lwd = .5, col = \"ivory4\", add = TRUE)\nmf_map(x = hospital, pch = 20, cex = 1, col = \"#FE9A2E\", add = TRUE) \n\n\n\n\n\n\n\nProportional symbol maps are used to represent inventory variables (absolute quantitative variables, sum and average make sense). The function mf_map(..., type = \"prop\") proposes this representation.\n\n#District\nmf_map(x = district) \n\n# Proportional symbol \nmf_map(\n x = district, \n var = \"T_POP\",\n val_max = 700000,\n type = \"prop\",\n col = \"#148F77\", \n leg_title = \"Population 2019\"\n)\n\n# Title\nmf_title(\"Distribution of population in provincial level\")\n\n\n\n\n\n\nIt is possible to fix the dimensions of the largest symbol corresponding to a certain value with the arguments inches and val_max. We can use construct maps with comparable proportional symbols.\n\npar(mfrow = c(1,2)) #Displaying two maps facing each other\n\n#district\nmf_map(x = district, border = \"grey90\", lwd = .5) \n# Add male Population\nmf_map(\n x = district, \n var = \"Male\", \n type = \"prop\",\n col = \"#1F618D\",\n inches = 0.2, \n val_max = 300000, \n leg_title = \"Male\", \n leg_val_cex = 0.5,\n)\nmf_title(\"Male Population by Distict\") #Adding map title\n\n#district\nmf_map(x = district, border = \"grey90\", lwd = .5) \n# Add female Population\nmf_map(\n x = district, \n var = \"Female\", \n type = \"prop\",\n col = \"#E74C3C\",\n inches = 0.2, \n val_max = 300000, \n leg_title =\"Female\", \n leg_val_cex = 0.5\n)\nmf_title(\"Female Population by Distict\") #Adding map title\n\n\n\n\nHere we have displayed two maps facing each other, see the point Displaying several maps on the same figure for more details.\n\n\n\n\nChoropleth maps are used to represent ratio variables (relative quantitative variables, mean has meaning, sum has no meaning).\nFor this type of representation, you must first:\n\nchoose a discretization method to transform a continuous statistical series into classes defined by intervals,\nchoose a number of classes,\nchoose a color palette.\n\nThe function mf_map(…, type = “choroâ€)makes it possible to create choroplete maps. The arguments nbreaks and breaks are used to parameterize the discretizations, and the function mf_get_breaks() makes it possible to work on the discretizations outside the function mf_map(). Similarly, the argument palis used to fill in a color palette, but several functions can be used to set the palettes apart from the (mf_get_pal…) function.\n\n# Population density (inhabitants/km2) using the sf::st_area() function\ndistrict$DENS <- 1e6 * district$T_POP / as.numeric(st_area(district)) #Calculate population density \nmf_map(\n x = district,\n var = \"DENS\",\n type = \"choro\",\n breaks = \"quantile\",\n pal = \"BuGn\",\n lwd = 1,\n leg_title = \"Distribution of population\\n(inhabitants per km2)\", \n leg_val_rnd = 0\n)\nmf_title(\"Distribution of the population in (2019)\")\n\n\n\n\n\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\npopulation <- read.csv(\"data_cambodia/khm_admpop_adm2_2016_v2.csv\")\npopulation <- population[, c(\"ADM2_PCODE\", \"T_TL\")]\n# Remove commas\npopulation$T_TL <- as.numeric(gsub(\",\",\"\",population$T_TL))\ndistrict$cases <- lengths(st_intersects(district, cases))\ndistrict <- merge(district,\n population,\n by = \"ADM2_PCODE\")\ndistrict$incidence <- district$cases / district$T_TL * 100000\n\nmf_map(x = district,\n var = \"incidence\",\n type = \"choro\",\n leg_title = \"Incidence (per 100 000)\")\nmf_layout(title = \"Incidence of W Fever in Cambodia\")\n\n\n\n\n\n\nThe fonction mf_get_breaks() provides the methods of discretization of classic variables: quantiles, average/standard deviation, equal amplitudes, nested averages, Fisher-Jenks, geometric, etc.\n\neducation$enrol_g_pct = 100 * education$enrol_girl/education$t_enrol #Calculate percentage of enrolled girl student\n\nd1 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"equal\", freq = TRUE)\nd2 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"quantile\")\nd3 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"geom\")\nd4 = mf_get_breaks(education$enrol_g_pct, breaks = \"msd\", central = FALSE)\n\n\n\n\n\n\n\n\n\nThe argument pal de mf_map() is dedicated to choosing a color palette. The palettes provided by the function hcl.colors() can be used directly.\n\nmf_map(x = education, var = \"enrol_g_pct\", type = \"choro\",\n breaks = d3, pal = \"Reds 3\")\n\n\n\n\n\n\n\n\n\nThe fonction mf_get_pal() allows you to build a color palette. This function is especially useful for creating balanced asymmetrical diverging palettes.\n\nmypal <- mf_get_pal(n = c(4,6), palette = c(\"Burg\", \"Teal\"))\nimage(1:10, 1, as.matrix(1:10), col=mypal, xlab = \"\", ylab = \"\", xaxt = \"n\",\n yaxt = \"n\",bty = \"n\")\n\n\n\n\n\n\n\nIt is possible to use this mode of presentation in specific implementation also.\n\ndist_c <- st_centroid(district)\nmf_map(district)\nmf_map(\n x = dist_c,\n var = \"DENS\",\n type = \"choro\",\n breaks = \"quantile\",\n nbreaks = 5,\n pal = \"PuRd\",\n pch = 23,\n cex = 1.5,\n border = \"white\",\n lwd = .7,\n leg_pos = \"topleft\",\n leg_title = \"Distribution of population\\n(inhabitants per km2)\", \n leg_val_rnd = 0, \n add = TRUE\n)\nmf_title(\"Distribution of population in (2019)\")\n\n\n\n\n\n\n\n\nTypology maps are used to represent qualitative variables. The function mf_map(..., type = \"typo\") proposes this representation.\n\nmf_map(\n x = district,\n var=\"Status\",\n type = \"typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n lwd = .7,\n leg_title = \"\"\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\nThe argument val_order is used to order the categories in the\n\nmf_map(\n x = district,\n var=\"Status\",\n type = \"typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n val_order = c(\"1st largest district\", \"2nd largest district\", \"3rd largest district\",\"<4500km2\"),\n lwd = .7,\n leg_title = \"\"\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\n\nWhen the implantation of the layer is punctual, symbols are used to carry the colors of the typology.\n\n#extract centroid point of the district\ndist_ctr <- st_centroid(district[district$Status != \"<4500km2\", ])\nmf_map(district)\nmf_map(\n x = dist_ctr,\n var = \"Status\",\n type = \"typo\",\n cex = 2,\n pch = 22,\n pal = c('#FF7396','#E4BAD4','#FFE3FE'),\n leg_title = \"\",\n leg_pos = \"bottomright\",\n add = TRUE\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\n\n\n#Selection of roads that intersect the city of Siem Reap\npp <- district[district$ADM1_EN == \"Phnom Penh\", ]\nroad_pp <- road[st_intersects(x = road, y = pp, sparse = FALSE), ]\nmf_map(pp)\nmf_map(\n x = road_pp,\n var = \"fclass\",\n type = \"typo\",\n lwd = 1.2,\n pal = mf_get_pal(n = 6, \"Tropic\"),\n leg_title = \"Types of road\",\n leg_pos = \"topright\",\n leg_frame = T,\n add = TRUE\n)\nmf_title(\"Administrative status\")\n\n\n\n\n\n\n\n\nThe function mf_map(..., var = c(\"var1\", \"var2\"), type = \"prop_choro\") represents proportional symbols whose areas are proportional to the values of one variable and whose color is based on the discretization of a second variable. The function uses the arguments of the functions mf_map(..., type = \"prop\") and mf_map(..., type = \"choro\").\n\nmf_map(x = district)\nmf_map(\n x = district,\n var = c(\"T_POP\", \"DENS\"),\n val_max = 500000,\n type = \"prop_choro\",\n border = \"grey60\",\n lwd = 0.5,\n leg_pos = c(\"bottomright\", \"bottomleft\"),\n leg_title = c(\"Population\", \"Density of\\n population\\n(inhabitants per km2)\"),\n breaks = \"q6\",\n pal = \"Blues 3\",\n leg_val_rnd = c(0,1))\nmf_title(\"Population\")\n\n\n\n\n\n\n\nThe function mf_map(..., var = c(\"var1\", \"var2\"), type = \"prop_typo\") represents proportional symbols whose areas are proportional to the values of one variable and whose color is based on the discretization of a second variable. The function uses the arguments of the mf_map(..., type = \"prop\") and function mf_map(..., type = \"typo\").\n\nmf_map(x = district)\nmf_map(\n x = district,\n var = c(\"Area.Km2.\", \"Status\"),\n type = \"prop_typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n val_order = c(\"<4500km2\",\"1st largest district\", \"2nd largest district\", \"3rd largest district\"),\n leg_pos = c(\"bottomleft\",\"topleft\"),\n leg_title = c(\"Population\\n(2019)\",\n \"Statut administratif\"),\n)\nmf_title(\"Population\")"
- },
- {
- "objectID": "05-mapping_with_r.html#layout",
- "href": "05-mapping_with_r.html#layout",
- "title": "5Â Mapping With R",
- "section": "5.2 Layout",
- "text": "5.2 Layout\nTo be finalized, a thematic map must contain certain additional elements such as: title, author, source, scale, orientation…\n\n5.2.1 Example data\nThe following lines import the spatial information layers located in the geopackage lot46.gpkg file.\n\nlibrary(sf)\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE) #Import Cambodia country border\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE) #Import provincial administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE) #Import district administrative border of Cambodia\nroad = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE) #Import roads data in Cambodia\nhospital = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE) #Import hospital data in Cambodia\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE) #Import example data of fever_cases in Cambodia\n\n\n\n5.2.2 Themes\nThe function mf_theme() defines a cartographic theme. Using a theme allows you to define several graphic parameters which are then applied to the maps created with mapsf. These parameters are: the map margins, the main color, the background color, the position and the aspect of the title. A theme can also be defined with the mf_init() and function mf_export().\n\n5.2.2.1 Use a predefined theme\nA series of predefined themes are available by default (see ?mf_theme).\n\nlibrary(mapsf)\n# use of a background color for the figure, to see the use of margin\nopar <- par(mfrow = c(2,2))\n# Using a predefined theme\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"Theme : 'default'\")\n\nmf_theme(\"darkula\")\nmf_map(district)\nmf_title(\"Theme : 'darkula'\")\n\nmf_theme(\"candy\")\nmf_map(district)\nmf_title(\"Theme : 'candy'\")\n\nmf_theme(\"nevermind\")\nmf_map(district)\nmf_title(\"Theme : 'nevermind'\")\npar(opar)\n\n\n\n\n\n\n5.2.2.2 Modify an existing theme\nIt is possible to modify an existing theme. In this example, we are using the “default†theme and modifying a few settings.\n\nlibrary(mapsf)\nopar <- par(mfrow = c(1,2))\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"default\")\n\nmf_theme(\"default\", tab = FALSE, font = 4, bg = \"grey60\", pos = \"center\")\nmf_map(district)\nmf_title(\"modified default\")\npar(opar)\n\n\n\n\n\n\n5.2.2.3 Create a theme\nIt is also possible to create a theme.\n\nmf_theme(\n bg = \"lightblue\", # background color\n fg = \"tomato1\", # main color\n mar = c(1,0,1.5,0), # margin\n tab = FALSE, # \"tab\" style for the title\n inner = FALSE, # title inside or outside of map area\n line = 1.5, # space dedicated to title\n pos = \"center\", # heading position\n cex = 1.5, # title size\n font = 2 # font types for title\n)\nmf_map(district)\nmf_title(\"New theme\")\n\n\n\n\n\n\n\n5.2.3 Titles\nThe function mf_title() adds a title to a map.\n\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"Map title\")\n\n\n\n\nIt is possible to customize the appearance of the title\n\nmf_map(district)\nmf_title(\n txt = \"Map title\", \n pos = \"center\", \n tab = FALSE, \n bg = \"tomato3\", \n fg = \"lightblue\", \n cex = 1.5, \n line = 1.7, \n font = 1, \n inner = FALSE\n)\n\n\n\n\n\n\n5.2.4 Arrow orientation\nThe function mf_arrow() allows you to choose the position and aspect of orientation arrow.\n\nmf_map(district)\nmf_arrow()\n\n\n\n\n\n\n5.2.5 Scale\nThe function mf_scale() allows you to choose the position and the aspect of the scale.\n\nmf_map(district)\nmf_scale(\n size = 60,\n lwd = 1,\n cex = 0.7\n)\n\n\n\n\n\n\n5.2.6 Credits\nThe function mf_credits() displays a line of credits (sources, author, etc.).\n\nmf_map(district)\nmf_credits(\"IRD\\nInstitut Pasteur du Cambodge, 2022\")\n\n\n\n\n\n\n5.2.7 Complete dressing\nThe function mf_layout() displays all these elements.\n\nmf_map(district)\nmf_layout(\n title = \"Cambodia\",\n credits = \"IRD\\nInstitut Pasteur du Cambodge, 2022\",\n arrow = TRUE\n)\n\n\n\n\n\n\n5.2.8 Annotations\n\nmf_map(district)\nmf_annotation(district[district$ADM2_EN == \"Bakan\",], txt = \"Bakan\", col_txt = \"darkred\", halo = TRUE, cex = 1.5)\n\n\n\n\n\n\n5.2.9 Legends\n\nmf_map(district)\nmf_legend(\n type = \"prop\", \n val = c(1000,500,200,10), \n inches = .2, \n title = \"Population\", \n pos = \"topleft\"\n)\nmf_legend(\n type = \"choro\", \n val = c(0,10,20,30,40),\n pal = \"Greens\", \n pos = \"bottomright\", \n val_rnd = 0\n)\n\n\n\n\n\n\n5.2.10 Labels\nThe function mf_label() is dedicated to displaying labels.\n\ndist_selected <- district[st_intersects(district, district[district$ADM2_EN == \"Bakan\", ], sparse = F), ]\n\nmf_map(dist_selected)\nmf_label(\n x = dist_selected,\n var = \"ADM2_EN\",\n col= \"darkgreen\",\n halo = TRUE,\n overlap = FALSE, \n lines = FALSE\n)\nmf_scale()\n\n\n\n\nThe argument halo = TRUE allows to display a slight halo around the labels and the argument overlap = FALSE allows to create non-overlapping labels.\n\n\n5.2.11 Center the map on a region\nThe function mf_init() allows you to initialize a map by centering it on a spatial object.\n\nmf_init(x = dist_selected)\nmf_map(district, add = TRUE)\nmf_map(dist_selected, col = NA, border = \"#29a3a3\", lwd = 2, add = TRUE)\n\n\n\n\n\n\n5.2.12 Displaying several maps on the sam figure\nHere you have to use mfrow of the function par(). The first digit represents the number of of rows and second the number of columns.\n\n# define the figure layout (1 row, 2 columns)\npar(mfrow = c(1, 2))\n\n# first map\nmf_map(district)\nmf_map(district, \"Male\", \"prop\", val_max = 300000)\nmf_title(\"Population, male\")\n\n# second map\nmf_map(district)\nmf_map(district, \"Female\", \"prop\", val_max = 300000)\nmf_title(\"Population, female\")\n\n\n\n\n\n\n5.2.13 Exporting maps\nIt is quite difficult to export figures (maps or others) whose height/width ratio is satisfactory. The default ratio of figures in png format is 1 (480x480 pixels):\n\ndist_filter <- district[district$ADM2_PCODE == \"KH0808\", ]\npng(\"img/dist_filter_1.png\")\nmf_map(dist_filter)\nmf_title(\"Filtered district\")\ndev.off()\n\n\n\n\n\n\nOn this map a lot of space is lost to the left and right of the district.\nThe function mf_export() allows exports of maps whose height/width ratio is controlled and corresponds to that of a spatial object.\n\nmf_export(dist_filter, \"img/dist_filter_2.png\", width = 480)\nmf_map(dist_filter)\nmf_title(\"Filtered district\")\ndev.off()\n\n\n\n\n\n\nThe extent of this map is exactly that of the displayed region.\n\n\n5.2.14 Adding an image to a map\nThis can be useful for adding a logo, a pictograph. The function readPNG() of package png allows the additional images on the figure.\n\nmf_theme(\"default\", mar = c(0,0,0,0))\nlibrary(png)\n\nlogo <- readPNG(\"img/ird_logo.png\") #Import image\npp <- dim(logo)[2:1]*200 #Image dimension in map unit (width and height of the original image)\n\n#The upper left corner of the department's bounding box\nxy <- st_bbox(district)[c(1,4)]\nmf_map(district, col = \"#D1914D\", border = \"white\")\nrasterImage(\n image = logo,\n xleft = xy[1] ,\n ybottom = xy[2] - pp[2],\n xright = xy[1] + pp[1],\n ytop = xy[2]\n)\n\n\n\n\n\n\n5.2.15 Place an item precisely on the map\nThe function locator() allows clicking on the figure and obtaining the coordinate of a point in the coordinate system of the figure (of the map).\n\n# locator(1) # click to get coordinate on map\n# points(locator(1)) # click to plot point on map\n# text(locator(1), # click to place the item on map\n# labels =\"Located any texts on map\", \n# adj = c(0,0))\n\n\nVideo\nlocator()peut être utilisée sur la plupart des graphiques (pas ceux produits avec ggplot2).\n\n\n\n\n\n\nHow to interactively position legends and layout elements on a map with cartography\n\n\n\n\n\n5.2.16 Add shading to a layer\nThe function mf_shadow() allows to create a shadow to a layer of polygons.\n\nmf_shadow(district)\nmf_map(district, add=TRUE)\n\n\n\n\n\n\n5.2.17 Creating Boxes\nThe function mf_inset_on() allows to start creation a box. You must then “close†the box with mf_inset_off().\n\nmf_init(x = dist_selected, theme = \"agolalight\", expandBB = c(0,.1,0,.5)) \nmf_map(district, add = TRUE)\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = 2, add = TRUE)\n\n# Cambodia inset box\nmf_inset_on(x = country, pos = \"topright\", cex = .3)\nmf_map(country, lwd = .5, border= \"grey90\")\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = .5, add = TRUE)\nmf_scale(size = 100, pos = \"bottomleft\", cex = .6, lwd = .5)\nmf_inset_off()\n\n# District inset box\nmf_inset_on(x = district, pos = \"bottomright\", cex = .3)\nmf_map(district, lwd = 0.5, border= \"grey90\")\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = .5, add = TRUE)\nmf_scale(size = 100, pos = \"bottomright\", cex = .6, lwd = .5)\nmf_inset_off()\n\n# World inset box\nmf_inset_on(x = \"worldmap\", pos = \"topleft\")\nmf_worldmap(dist_selected, land_col = \"#cccccc\", border_col = NA, \n water_col = \"#e3e3e3\", col = \"tomato4\")\n\nmf_inset_off()\nmf_title(\"Bakan district and its surroundings\")\nmf_scale(10, pos = 'bottomleft')"
- },
- {
- "objectID": "05-mapping_with_r.html#d-maps",
- "href": "05-mapping_with_r.html#d-maps",
- "title": "5Â Mapping With R",
- "section": "5.3 3D maps",
- "text": "5.3 3D maps\n\n5.3.1 linemap\nThe package linemap (Giraud 2021) allows you to make maps made up of lines.\n\nlibrary(linemap)\nlibrary(mapsf)\nlibrary(sf)\nlibrary(dplyr)\n\npp = st_read(\"data_cambodia/PP.gpkg\", quiet = TRUE) # import Phnom Penh administrative border\npp_pop_dens <- getgrid(x = pp, cellsize =1000, var = \"DENs\") # create population density in grid format (pop density/1km)\n\nmf_init(pp)\n\nlinemap(\n x = pp_pop_dens, \n var = \"DENs\",\n k = 1,\n threshold = 5, \n lwd = 1,\n col = \"ivory1\",\n border = \"ivory4\",\n add = T)\n\nmf_title(\"Phnom Penh Population Density, 2019\")\nmf_credits(\"Humanitarian Data Exchange, 2022\\nunit data:km2\")\n\n\n\n# url = \"https://data.humdata.org/dataset/1803994d-6218-4b98-ac3a-30c7f85c6dbc/resource/f30b0f4b-1c40-45f3-986d-2820375ea8dd/download/health_facility.zip\"\n# health_facility.zip = \"health_facility.zip\"\n# download.file(url, destfile = health_facility.zip)\n# unzip(health_facility.zip) # Unzipped files are in a new folder named Health\n# list.files(path=\"Health\")\n\n\n\n5.3.2 Relief Tanaka\nWe use the tanaka package (Giraud 2022b) which provides a method (Tanaka 1950) used to improve the perception of relief.\n\nlibrary(tanaka)\nlibrary(terra)\n\nrpop <- rast(\"data_cambodia/khm_pd_2019_1km_utm.tif\") # Import population raster data (in UTM)\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE) # Import Cambodian districts layer\ndistrict <- st_transform(district, st_crs(rpop)) # Transform data into the same coordinate system\n\nmat <- focalMat(x = rpop, d = c(1500), type = \"Gauss\") # Raster smoothing\nrpopl <- focal(x = rpop, w = mat, fun = sum, na.rm = TRUE)\n\n# Mapping\ncols <- hcl.colors(8, \"Reds\", alpha = 1, rev = T)[-1]\nmf_theme(\"agolalight\")\nmf_init(district)\ntanaka(x = rpop, breaks = c(0,10,25,50,100,250,500,64265),\n col = cols, add = T, mask = district, legend.pos = \"n\")\nmf_legend(type = \"choro\", pos = \"bottomright\", \n val = c(0,10,25,50,100,250,500,64265), pal = cols,\n bg = \"#EDF4F5\", fg = NA, frame = T, val_rnd = 0,\n title = \"Population\\nper km2\")\nmf_title(\"Population density of Cambodia, 2019\")\nmf_credits(\"Humanitarian Data Exchange, 2022\",\n bg = \"#EDF4F5\")\n\n\n\n\n\n\n\n\n\n\nThe tanaka package"
- },
- {
- "objectID": "05-mapping_with_r.html#cartographic-transformation",
- "href": "05-mapping_with_r.html#cartographic-transformation",
- "title": "5Â Mapping With R",
- "section": "5.4 Cartographic Transformation",
- "text": "5.4 Cartographic Transformation\n\nclassical anamorphosis is a representation of States(or any cells) by rectangle or any polygons according to a quantities attached to them. (…) We strive to keep the general arrangement of meshes or the silhouette of the continent.â€\nBrunet, Ferras, and Théry (1993)\n\n3 types of anamorphoses or cartograms are presented here:\n\nDorling’s cartograms (Dorling 1996)\nNon-contiguous cartograms (Olson 1976)\nContiguous cartograms (Dougenik, Chrisman, and Niemeyer 1985)\n\n\n\n\n\n\n\nA comprehensive course on anamorphoses : Les anamorphoses cartographiques (Lambert 2015).\n\n\n\n\n\n\n\n\n\nMake cartograms with R\n\n\n\nTo make the cartograms we use the package cartogram (Jeworutzki 2020).\n\n5.4.1 Dorling’s cartograms\nThe territories are represented by figures (circles, squares or rectangles) which do not overlap, the surface of which are proportional to a variable. The proportion of the figures are defined according to the starting positions.\n\n\n\n\n\n\n\n\nSpace is quite poorly identified.\nYou can name the circles to get your bearings and/or use the color to make clusters appear and better identify the geographical blocks.\n\n\n\n\n\nThe perception of quantities is very good. The circle sizes are really comarable.\n\n\n\nlibrary(mapsf)\nlibrary(cartogram)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\" , quiet = TRUE)\ndist_dorling <- cartogram_dorling(x = district, weight = \"T_POP\", k = 0.7)\nmf_map(dist_dorling, col = \"#40E0D0\", border= \"white\")\nmf_label(\n x = dist_dorling[order(dist_dorling$T_POP, decreasing = TRUE), ][1:10,], \n var = \"ADM2_EN\",\n overlap = FALSE, \n # show.lines = FALSE,\n halo = TRUE, \n r = 0.15\n)\nmf_title(\"Population of District - Dorling Cartogram\")\n\n\n\n\nThe parameter k allows to vary the expansion factor of the circles.\n\n\n5.4.2 Non-continuous cartograms\nThe size of the polygons is proportional to a variable. The arrangement of the polygons relative to each other is preserved. The shape of the polygons is similar.\n\n\n\n\n\n(Cauvin, Escobar, and Serradj 2013)\n\n\n\nThe topology of the regions is lost.\n\n\n\n\n\nThe converstion of the polygons shape is optimal.\n\n\n\ndist_ncont <- cartogram_ncont(x = district, weight = \"T_POP\", k = 1.2)\nmf_map(district, col = NA, border = \"#FDFEFE\", lwd = 1.5)\nmf_map(dist_ncont, col = \"#20B2AA\", border= \"white\", add = TRUE)\nmf_title(\"Population of District - Non-continuous cartograms\")\n\n\n\n\nThe parameter k allows to vary the expansion of the polygons.\n\n\n5.4.3 Continuous cartograms\nThe size of the polygons is proportional to variable. The arrangement of the polygons relative to each other is preserved. To maintain contiguity, the sape of the polygons is heavily transformed.\n\n\n\n\n\n(Paull and Hennig 2016)\n\n\n\nThe shape of the polygond is strongly distorted.\n\n\n\n\n\nIt is a “real geographical mapâ€: topology and contiguity are preserved.\n\n\n\ndist_ncont <- cartogram_cont(x = district, weight = \"DENs\", maxSizeError = 6)\n\nMean size error for iteration 1: 15.8686749410166\n\n\nMean size error for iteration 2: 12.1107731631101\n\n\nMean size error for iteration 3: 9.98940057337996\n\n\nMean size error for iteration 4: 8.62323208787643\n\n\nMean size error for iteration 5: 7.60706404894655\n\n\nMean size error for iteration 6: 6.83561617758241\n\n\nMean size error for iteration 7: 10.1399490743501\n\n\nMean size error for iteration 8: 5.79418495291592\n\nmf_map(dist_ncont, col = \"#66CDAA\", border= \"white\", add = FALSE)\nmf_title(\"Population of District - Continuous cartograms\")\nmf_inset_on(district, cex = .2, pos = \"bottomleft\")\nmf_map(district, lwd = .5)\nmf_inset_off()\n\n\n\n\n\n\n5.4.4 Stengths and weaknessses of cartograms\ncartograms are cartographic representations perceived as innovative (although the method is 40 years old). These very generalize images capture quantities and gradients well. These are real communication images that provoke, arouse interest, convey a strong message, challenge.\nBut cartograms induce a loss of visual cues (difficult to find one’s country or region on the map), require a reading effort which can be significant and do not make it possible to manage missing data.\n\n\n\n\nBrunet, Roger, Robert Ferras, and Hervé Théry. 1993. Les Mots de La géographie: Dictionnaire Critique. 03) 911 BRU.\n\n\nCauvin, Colette, Francisco Escobar, and Aziz Serradj. 2013. Thematic Cartography, Cartography and the Impact of the Quantitative Revolution. Vol. 2. John Wiley & Sons.\n\n\nDorling, Daniel. 1996. Area Cartograms: Their Use and Creation, Concepts and Techniques in Modern Geography. Vol. 59. CATMOG: Concepts and Techniques in Modern Geography. Institute of British Geographers.\n\n\nDougenik, James A, Nicholas R Chrisman, and Duane R Niemeyer. 1985. “An Algorithm to Construct Continuous Area Cartograms.†The Professional Geographer 37 (1): 75–81.\n\n\nGiraud, Timothée. 2021. “Linemap: Line Maps.†https://CRAN.R-project.org/package=linemap.\n\n\n———. 2022a. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\n———. 2022b. “Tanaka: Design Shaded Contour Lines (or Tanaka) Maps.†https://CRAN.R-project.org/package=tanaka.\n\n\nJeworutzki, Sebastian. 2020. “Cartogram: Create Cartograms with r.†https://CRAN.R-project.org/package=cartogram.\n\n\nLambert, Nicolas. 2015. “Les Anamorphoses Cartographiques.†Blog. Carnet Néocartographique. https://neocarto.hypotheses.org/366.\n\n\nOlson, Judy M. 1976. “Noncontiguous Area Cartograms.†The Professional Geographer 28 (4): 371–80.\n\n\nPaull, John, and Benjamin Hennig. 2016. “Atlas of Organics: Four Maps of the World of Organic Agriculture.†Journal of Organics 3 (1): 25–32.\n\n\nTanaka, Kitiro. 1950. “The Relief Contour Method of Representing Topography on Maps.†Geographical Review 40 (3): 444. https://doi.org/10.2307/211219."
- },
- {
- "objectID": "06-advanced_spatial_analysis.html",
- "href": "06-advanced_spatial_analysis.html",
- "title": "6Â Advanced Spatial Analysis",
- "section": "",
- "text": "RGeoHealth (Herbreteau, Révillion, and Trimaille 2018)\n\n# remotes::install_git(\"https://framagit.org/espace-dev/geohealth/RGeoHealth\")\n# library(geohealth)\n\n\n\n\n\nHerbreteau, Vincent, Christophe Révillion, and Etienne Trimaille. 2018. “GeoHealth and QuickOSM, two QGIS plugins for health applications.†In Earth Systems - Environmental Sciences : QGIS in Remote Sensing Set, edited by Nicolas Baghdadi, Clément Mallet, and Mehrez Zribi, 1:257–86. QGIS and Generic Tools. ISTE. https://hal.archives-ouvertes.fr/hal-01787435."
- },
- {
- "objectID": "07-basic_statistics.html",
- "href": "07-basic_statistics.html",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "",
- "text": "This section aims at providing some basic statistical tools to study the spatial distribution of the cases."
- },
- {
- "objectID": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "href": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.1 Import and visualize epidemiological data",
- "text": "7.1 Import and visualize epidemiological data\nIn this section, we load data that reference the cases of an imaginary disease throughout Cambodia.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n\n# Import locations of cases from an imaginary disease\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\n\n# Aggregate cases over districts\ndistrict$cases <- lengths(st_intersects(district, cases))\n\nThe first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.\n\n# View the cases object\nhead(cases)\n\nSimple feature collection with 6 features and 2 fields\nGeometry type: MULTIPOINT\nDimension: XY\nBounding box: xmin: 255891 ymin: 1179092 xmax: 506647.4 ymax: 1467441\nProjected CRS: WGS 84 / UTM zone 48N\n id Disease geom\n1 0 W fever MULTIPOINT ((280036.2 12841...\n2 1 W fever MULTIPOINT ((451859.5 11790...\n3 2 W fever MULTIPOINT ((255891 1467441))\n4 5 W fever MULTIPOINT ((506647.4 12322...\n5 6 W fever MULTIPOINT ((440668 1197958))\n6 7 W fever MULTIPOINT ((481594.5 12714...\n\n# Map the cases\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = cases, lwd = .5, col = \"#990000\", pch = 20, add = TRUE)"
- },
- {
- "objectID": "07-basic_statistics.html#basics-statistics",
- "href": "07-basic_statistics.html#basics-statistics",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.2 Basics statistics",
- "text": "7.2 Basics statistics\nThe problem is usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nThe statistical analysis performed relies on the type of data.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test.\nMoran’s I test tells us whether nearby units tend to exhibit similar rates. It ranges from -1 to +1, whith a value of -1 denoting that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nWe will compute the Moran’s statistics using spdep and Dcluster packages. This package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n# Compte incidence in each district (per 100 000 population)\ndistrict$incidence <- district$cases/district$T_POP * 100000\n\n# Plot the incidence histogramm\nhist(log(district$incidence))"
- },
- {
- "objectID": "07-basic_statistics.html#cluster-analysis",
- "href": "07-basic_statistics.html#cluster-analysis",
- "title": "7Â Basic statistics for spatial analysis",
-<<<<<<< HEAD
- "section": "7.2 Cluster analysis",
- "text": "7.2 Cluster analysis\nSince this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.\nIn statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nHere the statistics hypothesis are :\n\nH0 :\nH1: , i.e. Moran’s I value is different than 0.\n\nWe will compute the Moran’s statistics using spdep and Dcluster packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\nlibrary(spdep) # Functions for creating spatial weight, spatial analysis\nlibrary(DCluster) # Package with functions for spatial cluster analysis)\n\nqnb <- poly2nb(district)\nq_listw <- nb2listw(qnb, style = 'W') # row-standardized weights\n\n# Moran's I test\nmoranI.test(cases ~ offset(log(expected)), \n data = district,\n model = 'poisson',\n R = 499,\n listw = q_listw,\n n = 159,\n S0 = Szero(q_listw))\n\nMoran's I test of spatial autocorrelation \n\n Type of boots.: parametric \n Model used when sampling: Poisson \n Number of simulations: 499 \n Statistic: 0.1264291 \n p-value : 0.016 \n\n\n\n\n7.2.2 Spatial scan statistics\nWhile Moran’s indice focuses on finding correlation between neighboring polygons, the spatial scan statistic compare the incidence level of a given windows of observation with the incidence level outside of this windows.\nThe package SpatialEpi\n\n\n7.2.3 Population-based clusters (kulldorf statistic)\nKulldorff ’s spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.\n\n\n7.2.4 Expectation-based cluster\nIn many case, population is not specific enough to\n\n\n7.2.5 To go further …"
-=======
- "section": "7.3 Cluster analysis",
- "text": "7.3 Cluster analysis\nIn epidemiology, the definition of a cluster\n\n7.3.1 Population-based clusters (kulldorf statistic)\nKulldorff ’s spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.\n\n\n7.3.2 Expectation-based cluster\nIn many case, population is not specific enough to\n\n\n7.3.3 To go further …"
->>>>>>> refs/remotes/origin/main
- },
- {
- "objectID": "references.html",
- "href": "references.html",
- "title": "References",
- "section": "",
-<<<<<<< HEAD
- "text": "This section aims at providing some basic statistical tools to study the spatial distribution of epidemiological data."
- },
- {
- "objectID": "07-basic_statistics.html#basics-statistics",
- "href": "07-basic_statistics.html#basics-statistics",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.2 Basics statistics",
- "text": "7.2 Basics statistics\nThe problem is usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nThe statistical analysis performed relies on the type of data.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test.\nMoran’s I test tells us whether nearby units tend to exhibit similar rates. It ranges from -1 to +1, whith a value of -1 denoting that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nWe will compute the Moran’s statistics using spdep and Dcluster packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n# Plot the incidence histogramm\nhist(log(district$incidence))"
- },
- {
- "objectID": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "href": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.1 Import and visualize epidemiological data",
- "text": "7.1 Import and visualize epidemiological data\nIn this section, we load data that reference the cases of an imaginary disease throughout Cambodia. Each point correspond to the geolocalisation of a case.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n\n# Import locations of cases from an imaginary disease\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\n\nThe first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.\n\n# View the cases object\nhead(cases)\n\nSimple feature collection with 6 features and 2 fields\nGeometry type: MULTIPOINT\nDimension: XY\nBounding box: xmin: 255891 ymin: 1179092 xmax: 506647.4 ymax: 1467441\nProjected CRS: WGS 84 / UTM zone 48N\n id Disease geom\n1 0 W fever MULTIPOINT ((280036.2 12841...\n2 1 W fever MULTIPOINT ((451859.5 11790...\n3 2 W fever MULTIPOINT ((255891 1467441))\n4 5 W fever MULTIPOINT ((506647.4 12322...\n5 6 W fever MULTIPOINT ((440668 1197958))\n6 7 W fever MULTIPOINT ((481594.5 12714...\n\n# Map the cases\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = cases, lwd = .5, col = \"#990000\", pch = 20, add = TRUE)\n\n\n\n\nIn epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, …) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use district as the areal unit of the study.\n\n# Aggregate cases over districts\ndistrict$cases <- lengths(st_intersects(district, cases))\n\nThe incidence (\\(\\frac{cases}{population}\\)) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as \\(SIR = \\frac{Y_i}{E_i}\\) with \\(Y_i\\), the observed number of cases and \\(E_i\\), the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district.\n\n# Compute incidence in each district (per 100 000 population)\ndistrict$incidence = district$cases/district$T_POP * 100000\n\n# Compute the global risk\nrate = sum(district$cases)/sum(district$T_POP)\n\n# Compute expected number of cases \ndistrict$expected = district$T_POP * rate\n\n# Compute SIR\ndistrict$SIR = district$cases / district$expected\n\n\npar(mfrow = c(1, 3))\n# Plot number of cases using proportional symbol \nmf_map(x = district) \nmf_map(\n x = district, \n var = \"cases\",\n val_max = 50,\n type = \"prop\",\n col = \"#990000\", \n leg_title = \"Cases\")\nmf_layout(title = \"Number of cases of W Fever\")\n\n# Plot incidence \nmf_map(x = district,\n var = \"incidence\",\n type = \"choro\",\n pal = \"Reds 3\",\n leg_title = \"Incidence \\n(per 100 000)\")\nmf_layout(title = \"Incidence of W Fever\")\n\n# Plot SIRs\n# create breaks and associated color palette\nbreak_SIR = c(0, exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = \"pretty\")))\ncol_pal = c(\"#273871\", \"#3267AD\", \"#6496C8\", \"#9BBFDD\", \"#CDE3F0\", \"#FFCEBC\", \"#FF967E\", \"#F64D41\", \"#B90E36\")\n\nmf_map(x = district,\n var = \"SIR\",\n type = \"choro\",\n breaks = break_SIR, \n pal = col_pal, \n cex = 2,\n leg_title = \"SIR\")\nmf_layout(title = \"Standardized Incidence Ratio of W Fever\")\n\n\n\n\nThese maps illustrates the spatial heterogenity of the cases. The incidence shows how the disease vary from one district to another while the SIR highlight districts that have :\n\nhigher risk than average (SIR > 1) when standardized for population\nlower risk than average (SIR < 1) when standardized for population\naverage risk (SIR ~ 1) when standardized for population\n\nIn this example, we standardized the cases distribution for population count. This simple standardization assume that the risk of contracting the disease is similar for each person. However, assumption does not hold for all diseases and for all observed events since confounding effects can create nuisance into the interpretations (e.g. the number of childhood illness and death outcomes in a district are usually related to the age pyramid) and you should keep in mind that other standardization can be performed based on variables known to have an effect but that you don’t want to analyze (e.g. sex ratio, occupations, age pyramid)."
-=======
- "text": "Agafonkin, Vladimir. 2015. “Leaflet Javascript Libary.â€\n\n\nAppelhans, Tim, Florian Detsch, Christoph Reudenbach, and Stefan\nWoellauer. 2022. “Mapview: Interactive Viewing of Spatial Data in\nr.†https://CRAN.R-project.org/package=mapview.\n\n\nAppelhans, Tim, Kenton Russell, and Lorenzo Busetto. 2020.\n“Mapedit: Interactive Editing of Spatial Data in r.†https://CRAN.R-project.org/package=mapedit.\n\n\nBivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. “Rgdal:\nBindings for the ’Geospatial’ Data Abstraction Library.†https://CRAN.R-project.org/package=rgdal.\n\n\nBivand, Roger, and Colin Rundel. 2021. “Rgeos: Interface to\nGeometry Engine - Open Source (’GEOS’).†https://CRAN.R-project.org/package=rgeos.\n\n\nBrunet, Roger, Robert Ferras, and Hervé Théry. 1993. Les Mots de La\ngéographie: Dictionnaire Critique. 03) 911 BRU.\n\n\nCambon, Jesse, Diego Hernangómez, Christopher Belanger, and Daniel\nPossenriede. 2021. “Tidygeocoder: An r Package for\nGeocoding†6: 3544. https://doi.org/10.21105/joss.03544.\n\n\nCauvin, Colette, Francisco Escobar, and Aziz Serradj. 2013. Thematic\nCartography, Cartography and the Impact of the Quantitative\nRevolution. Vol. 2. John Wiley & Sons.\n\n\nCheng, Joe, Bhaskar Karambelkar, and Yihui Xie. 2022. “Leaflet:\nCreate Interactive Web Maps with the JavaScript ’Leaflet’\nLibrary.†https://CRAN.R-project.org/package=leaflet.\n\n\nDorling, Daniel. 1996. Area Cartograms: Their Use and Creation,\nConcepts and Techniques in Modern Geography. Vol. 59. CATMOG:\nConcepts and Techniques in Modern Geography. Institute of British\nGeographers.\n\n\nDougenik, James A, Nicholas R Chrisman, and Duane R Niemeyer. 1985.\n“An Algorithm to Construct Continuous Area Cartograms.â€\nThe Professional Geographer 37 (1): 75–81.\n\n\nDunnington, Dewey. 2021. “Ggspatial: Spatial Data Framework for\nGgplot2.†https://CRAN.R-project.org/package=ggspatial.\n\n\nGDAL/OGR contributors. n.d. GDAL/OGR Geospatial Data\nAbstraction Software Library. Open Source Geospatial Foundation. https://gdal.org.\n\n\nGilardi, Andrea, and Robin Lovelace. 2021. “Osmextract: Download\nand Import Open Street Map Data Extracts.†https://CRAN.R-project.org/package=osmextract.\n\n\nGiraud, Timothée. 2021a. “Linemap: Line Maps.†https://CRAN.R-project.org/package=linemap.\n\n\n———. 2021b. “Maptiles: Download and Display Map Tiles.†https://CRAN.R-project.org/package=maptiles.\n\n\n———. 2022a. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\n———. 2022b. “Tanaka: Design Shaded Contour Lines (or Tanaka)\nMaps.†https://CRAN.R-project.org/package=tanaka.\n\n\nGiraud, Timothée, and Nicolas Lambert. 2016. “Cartography: Create\nand Integrate Maps in Your r Workflow†1. https://doi.org/10.21105/joss.00054.\n\n\nGombin, Joel, and Paul-Antoine Chevalier. 2022. “banR: R Client\nfor the BAN API.â€\n\n\nHerbreteau, Vincent, Christophe Révillion, and Etienne Trimaille. 2018.\n“GeoHealth and QuickOSM, two QGIS plugins for\nhealth applications.†In Earth\nSystems - Environmental Sciences : QGIS in Remote Sensing\nSet, edited by Nicolas Baghdadi, Clément Mallet, and Mehrez\nZribi, 1:257–86. QGIS and Generic Tools. ISTE. https://hal.archives-ouvertes.fr/hal-01787435.\n\n\nHijmans, Robert J. 2022a. “Raster: Geographic Data Analysis and\nModeling.†https://CRAN.R-project.org/package=raster.\n\n\n———. 2022b. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nJeworutzki, Sebastian. 2020. “Cartogram: Create Cartograms with\nr.†https://CRAN.R-project.org/package=cartogram.\n\n\nLambert, Nicolas. 2015. “Les Anamorphoses Cartographiques.â€\nBlog. Carnet Néocartographique. https://neocarto.hypotheses.org/366.\n\n\nLi, Xingong. 2009. “Map Algebra and Beyond : 1. Map Algebra for\nScalar Fields.†https://slideplayer.com/slide/5822638/.\n\n\nMadelin, Malika. 2021. “Analyse d’images Raster (Et\nTélédétection).†https://mmadelin.github.io/sigr2021/SIGR2021_raster_MM.html.\n\n\nMennis, Jeremy. 2015. “Fundamentals of GIS : Raster\nOperations.†https://cupdf.com/document/gus-0262-fundamentals-of-gis-lecture-presentation-7-raster-operations-jeremy.html.\n\n\nNowosad, Jakub. 2021. “Image Processing and All Things\nRaster.†https://nowosad.github.io/SIGR2021/workshop2/workshop2.html.\n\n\nOlson, Judy M. 1976. “Noncontiguous Area Cartograms.â€\nThe Professional Geographer 28 (4): 371–80.\n\n\nPadgham, Mark, Bob Rudis, Robin Lovelace, and Maëlle Salmon. 2017.\n“Osmdata†2. https://doi.org/10.21105/joss.00305.\n\n\nPaull, John, and Benjamin Hennig. 2016. “Atlas of Organics: Four\nMaps of the World of Organic Agriculture.†Journal of\nOrganics 3 (1): 25–32.\n\n\nPebesma, Edzer. 2018b. “Simple Features for r:\nStandardized Support for Spatial Vector Data†10. https://doi.org/10.32614/RJ-2018-009.\n\n\n———. 2018a. “Simple Features for R: Standardized Support for\nSpatial Vector Data.†The R Journal 10 (1): 439. https://doi.org/10.32614/rj-2018-009.\n\n\n———. 2021. “Stars: Spatiotemporal Arrays, Raster and Vector Data\nCubes.†https://CRAN.R-project.org/package=stars.\n\n\nPebesma, Edzer J., and Roger S. Bivand. 2005. “Classes and Methods\nfor Spatial Data in r†5. https://CRAN.R-project.org/doc/Rnews/.\n\n\nPROJ contributors. 2021. PROJ Coordinate Transformation\nSoftware Library. Open Source Geospatial Foundation. https://proj.org/.\n\n\nRacine, Etienne B. 2016. “The Visual Raster Cheat Sheet.â€\nhttps://rpubs.com/etiennebr/visualraster.\n\n\nTanaka, Kitiro. 1950. “The Relief Contour Method of Representing\nTopography on Maps.†Geographical Review 40 (3): 444. https://doi.org/10.2307/211219.\n\n\nTennekes, Martijn. 2018. “Tmap: Thematic\nMaps in r†84. https://doi.org/10.18637/jss.v084.i06.\n\n\nTomlin, C. Dana. 1990. Geographic Information Systems and\nCartographic Modeling. Prentice Hall.\n\n\nWickham, Hadley. 2016. “Ggplot2: Elegant Graphics for Data\nAnalysis.†https://ggplot2.tidyverse.org."
->>>>>>> refs/remotes/origin/main
}
-]
+]
\ No newline at end of file
diff --git a/public/search.json.orig b/public/search.json.orig
deleted file mode 100644
index 4ead360..0000000
--- a/public/search.json.orig
+++ /dev/null
@@ -1,263 +0,0 @@
-[
- {
- "objectID": "index.html",
- "href": "index.html",
- "title": "Mapping and spatial analyses in R for One Health studies",
- "section": "",
- "text": "This manual is tended both for R users wishing to set up spatial data peocessing and for users wishing to use R to carry out the tasks that they usually carry out with GIS. The main steps in the processing of geographic information are covered. Emphasis is placed on the processing of vector data but a part is still dedicated to raster data.\nHow to use the manual\nThe RStudio project containing all the data used in the manual is available here. Once the file is unzipped it is possible to test all the manipulations proposed in the RStudion project.\nContext\nThis manual has been designed from the courses “Géomatique avec R†and “Cartographie avec R†by Timothée Giraud and Hugues Pecout. It has been translated and its examples have been adapted to the geographical distribution of the audience.\n\n\n\n\nCreative Commons License\n\n\nThe online version of this document licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0."
- },
- {
- "objectID": "01-introduction.html",
- "href": "01-introduction.html",
- "title": "1Â Introduction",
- "section": "",
- "text": "Historically, 4 packages make it possible to import, manipulate and transform spatial data:\n\nThe package rgdal (Bivand, Keitt, and Rowlingson 2022) which is an interface between R and the GDAL (GDAL/OGR contributors, n.d.) and PROJ (PROJ contributors 2021) libraries allow you to import and export spatial data (shapefiles for example) and also to manage cartographic projections\n\nThe package sp (E. J. Pebesma and Bivand 2005) provides class and methods for vector spatial data in R. It allows displaying background maps, inspectiong an attribute table etc.\n\nThe package rgeos (Bivand and Rundel 2021) gives access to the GEOS spatial operations library and therefore makes classic GIS operations available: calculation of surfaces or perimeters, calculation of distances, spatial aggregations, buffer zones, intersections, etc.\n\nThe package raster (Hijmans 2022a) is dedicated to the import, manipulation and modeling of raster data.\n\nToday, the main developments concerning vector data have moved away from the old 3 (sp, rgdal, rgeos) to rely mainly on the package sf ((E. Pebesma 2018a), (E. Pebesma 2018b)). In this manual we will rely exclusively on this package to manipulate vector data.\nThe packages stars (E. Pebesma 2021) and terra (Hijmans 2022b) come to replace the package raster for processing raster data. We have chosen to use the package here terra for its proximity to the raster."
- },
- {
- "objectID": "01-introduction.html#the-package-sf",
- "href": "01-introduction.html#the-package-sf",
- "title": "1Â Introduction",
- "section": "1.2 The package sf",
- "text": "1.2 The package sf\n The package sf was released in late 2016 by Edzer Pebesma (also author of sp). Its goal is to combine the feature of sp, rgeos and rgdal in a single, more ergonomic package. This package offers simple objects (following the simple feature standard) which are easier to manipulate. Particular attention has been paid to the compatibility of the package with the pipe syntax and the operators of the tidyverse.\nsf directly uses the GDAL, GEOS and PROJ libraries.\n\n\n\n\n\nFrom r-spatial.org\n\n\n\n\n\n\nWebsite of package sf : Simple Features for R\n\n\n\n\n1.2.1 Format of spatial objects sf\n\n\n\n\n\nObjectssf are objects in data.frame which one of the columns contains geometries. This column is the class of sfc (simple feature column) and each individual of the column is a sfg (simple feature geometry). This format is very practical insofa as the data and the geometries are intrinsically linked in the same object.\n\n\n\n\n\n\nThumbnail describing the simple feature format: Simple Features for R\n\n\n\n\n\n\n\n\n\nTip\n\n\n\nA benchmark of vector processing libraries is available here."
- },
- {
- "objectID": "01-introduction.html#package-mapsf",
- "href": "01-introduction.html#package-mapsf",
- "title": "1Â Introduction",
- "section": "1.3 Package mapsf",
- "text": "1.3 Package mapsf\nThe free R software spatial ecosystem is rich, dynamic and mature and several packages allow to import, process and represent spatial data. The package mapsf (Giraud 2022) relies on this ecosystem to integrate the creation of quality thematic maps into processing chains with R.\nOther packages can be used to make thematic maps. The package ggplot2 (Wickham 2016), in association with the package ggspatial (Dunnington 2021), allows for example to display spatial objects and to make simple thematic maps. The package tmap (Tennekes 2018) is dedicated to the creation of thematic maps, it uses a syntax close to that of ggplot2 (sequence of instructions combined with the ‘+’ sign). Documentation and tutorials for using these two packages are readily available on the web.\nHere, we will mainly use the package mapsf whose functionalities are quite complete and the handling rather simple. In addition, the package is relatively light.\n\nmapsf allows you to create most of the types of map usually used in statistical cartography (choropleth maps, typologies, proportional or graduated symbols, etc.). For each type of map, several parameters are used to customize the cartographic representation. These parameters are the same as those found in the usual GIS or cartography software (for example, the choice of discretizations and color palettes, the modification of the size of the symbols or the customization of the legends). Associated with the data representation functions, other functions are dedicated to cartographic dressing (themes or graphic charters, legends, scales, orientation arrows, title, credits, annotations, etc.), the creation of boxes or the exporting maps.\nmapsf is the successor of cartography (Giraud and Lambert 2016), it offers the same main functionalities while being lighter and more ergonomic.\nTo use this package several sources can be consulted:\n\nThe package documentation accessible on the internet or directly in R (?mapsf),\nA cheat sheet,\n\n\n\n\n\n\n\nThe vignettes associated with the package show sample scripts,\nThe R Geomatics blog which provides resources and examples related to the package and more generally to the R spatial ecosystem."
- },
- {
- "objectID": "01-introduction.html#the-package-terra",
- "href": "01-introduction.html#the-package-terra",
- "title": "1Â Introduction",
- "section": "1.4 The package terra",
- "text": "1.4 The package terra\n The package terra was release in early 2020 by Robert J. Hijmans (also author of raster). Its objective is to propose methods of treatment and analysis of raster data. This package is very similar to the package raster; but it has more features, it’s easier to use, and it’s faster.\n\n\n\n\n\n\nWebsite of package terra : Spatial Data Science with R and “terraâ€\n\n\n\n\n\n\n\n\n\nTip\n\n\n\nA benchmark of raster processing libraries is available here.\n\n\n\n\n\n\nBivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. “Rgdal: Bindings for the ’Geospatial’ Data Abstraction Library.†https://CRAN.R-project.org/package=rgdal.\n\n\nBivand, Roger, and Colin Rundel. 2021. “Rgeos: Interface to Geometry Engine - Open Source (’GEOS’).†https://CRAN.R-project.org/package=rgeos.\n\n\nDunnington, Dewey. 2021. “Ggspatial: Spatial Data Framework for Ggplot2.†https://CRAN.R-project.org/package=ggspatial.\n\n\nGDAL/OGR contributors. n.d. GDAL/OGR Geospatial Data Abstraction Software Library. Open Source Geospatial Foundation. https://gdal.org.\n\n\nGiraud, Timothée. 2022. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\nGiraud, Timothée, and Nicolas Lambert. 2016. “Cartography: Create and Integrate Maps in Your r Workflow†1. https://doi.org/10.21105/joss.00054.\n\n\nHijmans, Robert J. 2022a. “Raster: Geographic Data Analysis and Modeling.†https://CRAN.R-project.org/package=raster.\n\n\n———. 2022b. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nPebesma, Edzer. 2018a. “Simple Features for r: Standardized Support for Spatial Vector Data†10. https://doi.org/10.32614/RJ-2018-009.\n\n\n———. 2018b. “Simple Features for R: Standardized Support for Spatial Vector Data.†The R Journal 10 (1): 439. https://doi.org/10.32614/rj-2018-009.\n\n\n———. 2021. “Stars: Spatiotemporal Arrays, Raster and Vector Data Cubes.†https://CRAN.R-project.org/package=stars.\n\n\nPebesma, Edzer J., and Roger S. Bivand. 2005. “Classes and Methods for Spatial Data in r†5. https://CRAN.R-project.org/doc/Rnews/.\n\n\nPROJ contributors. 2021. PROJ Coordinate Transformation Software Library. Open Source Geospatial Foundation. https://proj.org/.\n\n\nTennekes, Martijn. 2018. “Tmap: Thematic Maps in r†84. https://doi.org/10.18637/jss.v084.i06.\n\n\nWickham, Hadley. 2016. “Ggplot2: Elegant Graphics for Data Analysis.†https://ggplot2.tidyverse.org."
- },
- {
- "objectID": "02-data_acquisition.html",
- "href": "02-data_acquisition.html",
- "title": "2Â Data Acquisition",
- "section": "",
- "text": "The function st_as_sf() makes it possible to transform a data.frame container of geographic coordinates into an object sf. Here we use the data.frame places2 created in the previous point.\n\nlibrary(sf)\nplace_sf <- st_as_sf(read.csv(\"data_cambodia/adress.csv\"), coords = c(\"long\", \"lat\"), crs = 4326)\nplace_sf\n\nSimple feature collection with 2 features and 1 field\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 104.8443 ymin: 11.54366 xmax: 104.9047 ymax: 11.55349\nGeodetic CRS: WGS 84\n address\n1 Phnom Penh International Airport, Phnom Penh, Cambodia\n2 Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia\n geometry\n1 POINT (104.8443 11.55349)\n2 POINT (104.9047 11.54366)\n\n\n\n\nSpherical geometry (s2) switched off\n\n\nTo create a sf POINT type object with only one pair of coordinate (WGS84, longitude=0.5, latitude = 45.5) :\n\nlibrary(sf)\ntest_point <- st_as_sf(data.frame(x = 0.5, y = 45.5), coords = c(\"x\", \"y\"), crs = 4326)\ntest_point\n\nSimple feature collection with 1 feature and 0 fields\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 0.5 ymin: 45.5 xmax: 0.5 ymax: 45.5\nGeodetic CRS: WGS 84\n geometry\n1 POINT (0.5 45.5)\n\n\nWe can display this object sf on an OpenStreetMap basesmap with the package maptiles maptiles (Giraud 2021).\n\nlibrary(maptiles)\nosm <- get_tiles(x = place_sf, zoom = 12)\nplot_tiles(osm)\nplot(st_geometry(place_sf), pch = 2, cex = 2, col = \"red\", add = TRUE)"
- },
- {
- "objectID": "02-data_acquisition.html#online-databases",
- "href": "02-data_acquisition.html#online-databases",
- "title": "2Â Data Acquisition",
- "section": "2.2 Online databases",
- "text": "2.2 Online databases"
- },
- {
- "objectID": "02-data_acquisition.html#openstreetmap",
- "href": "02-data_acquisition.html#openstreetmap",
- "title": "2Â Data Acquisition",
- "section": "2.3 OpenStreetMap",
- "text": "2.3 OpenStreetMap\n\n\n\nOpenStreetMap (OSM) is a participatory mapping project that aims to built a free geographic database on a global scale. OpenStreetMap lets you view, edit and use geographic data around the world.\nTerms of use\n\nOpenStreetMap is open data : you are free to use it for ant purpose as long as you credit OpenStreetMap and its contributers. If you modify or rely data in any way, you may distribute the result only under the same license. (…)\n\nContributors\n\n(…) Our contributors incloude enthusiastic mapmakers, GIS professional, engineers running OSM servers, humanitarians mapping disaster-stricken areas and many mmore.(…)\n\n\n2.3.1 Display and interactive map\nThe two main packages that allow to display as interactive map based on OSM are leaflet (Cheng, Karambelkar, and Xie 2022) and mapview (Appelhans et al. 2022).\n\n2.3.1.1 leaflet\n leaflet uses the javascript library Leaflet (Agafonkin 2015) to create interactive maps.\n\nlibrary(sf)\nlibrary(leaflet)\n\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\nhospital <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE)\n\n\nbanan <- district[district$ADM2_PCODE == \"KH0201\", ] #Select one district (Banan district: KH0201)\nhealth_banan <- hospital[hospital$DCODE == \"201\", ] #Select Health centers in Banan\n\nbanan <- st_transform(banan, 4326) #Transform coordinate system to WGS84\nhealth_banan <- st_transform(health_banan, 4326)\n\nbanan_map <- leaflet(banan) %>% #Create interactive map\n addTiles() %>%\n addPolygons() %>%\n addMarkers(data = health_banan)\nbanan_map\n\n\n\n\n\n\n\n\n\n\n\nWebsite of leaflet\nLeaflet for R\n\n\n\n\n\n2.3.1.2 mapview\n mapview relies on leaflet to create interactive maps, its use is easier and its documentation is a bit dense.\n\nlibrary(mapview)\nmapview(banan) + mapview(health_banan)\n\n\n\n\n\n\n\n\n\n\n\n\nWebsite of mapview\nmapview\n\n\n\n\n\n\n2.3.2 Import basemaps\nThe package maptiles (Giraud 2021) allows downlaoding and displaying raster basemaps.\nThe function get_tiles() allow you to download OSM background maps and the function plot_tiles() allows to display them.\nRenders are better if the input data used the same coordinate system as the tiles (EPSG:3857).\n\nlibrary(sf)\nlibrary(maptiles)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\ndistrict <- st_transform(district, 3857)\nosm_tiles <- get_tiles(x = district, zoom = 10, crop = TRUE)\nplot_tiles(osm_tiles)\nplot(st_geometry(district), border = \"grey20\", lwd = .7, add = TRUE)\nmtext(side = 1, line = -2, text = get_credit(\"OpenStreetMap\"), col=\"tomato\")\n\n\n\n\n\n\n2.3.3 Import OSM data\n\n2.3.3.1 osmdata\n The package osmdata (Padgham et al. 2017) allows extracting vector data from OSM using the Overpass turbo API.\n\nlibrary(sf)\nlibrary(osmdata)\nlibrary(sf)\n\ncountry <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\next <- opq(bbox = st_bbox(st_transform(country, 4326))) #Define the bounding box\nquery <- add_osm_feature(opq = ext, key = 'amenity', value = \"hospital\") #Health Center Extraction\nhospital <- osmdata_sf(query)\nhospital <- unique_osmdata(hospital) #Result reduction (points composing polygon are detected)\n\nThe result contains a point layer and a polygon layer. The polygon layer contains polygons that represent fast food-food place. To obtain a coherent point layer we can use the centroids of the polygons.\n\nhospital_point <- hospital$osm_points\nhospital_poly <- hospital$osm_polygons #Extracting centroids of polygons\nhospital_poly_centroid <- st_centroid(hospital_poly)\n\ncambodia_point <- intersect(names(hospital_point), names(hospital_poly_centroid)) #Identify fields in Cambodia boundary\nhospitals <- rbind(hospital_point[, cambodia_point], hospital_poly_centroid[, cambodia_point]) #Gather the 2 objects\n\nResult display\n\nlibrary(mapview)\nmapview(country) + mapview(hospitals)\n\n\n\n\n\n\n\n\n\n\n\n\nWebsite of osmdata\nosmdata\n\n\n\n\n\n2.3.3.2 osmextract\n The package osmextract (Gilardi and Lovelace 2021) allows to extract data from an OSM database directly. This package make it possible to work on very large volumes of data.\n\n\n\n\n\n\nWebsite of osmextract\nosmextract\n\n\n\nFor administrative boundaries, check here the administrative levels by country:\n\nlibrary(osmextract)\nlibrary(mapsf)\nprovince <- oe_get(\n place = \"Cambodia\",\n download_directory = \"data_cambodia/\",\n layer = \"multipolygons\",\n extra_tags = c(\"wikidata\", \"ISO3166-2\", \"wikipedia\", \"name:en\"),\n vectortranslate_options = c(\n \"-t_srs\", \"EPSG:32648\",\n \"-nlt\", \"PROMOTE_TO_MULTI\",\n \"-where\", \"type = 'boundary' AND boundary = 'administrative' AND admin_level = '4'\"\n ))\n\n0...10...20...30...40...50...60...70...80...90...100 - done.\nReading layer `multipolygons' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/geofabrik_cambodia-latest.gpkg' \n using driver `GPKG'\nSimple feature collection with 25 features and 29 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211418.1 ymin: 1047956 xmax: 784614.9 ymax: 1625621\nProjected CRS: WGS 84 / UTM zone 48N\n\nmf_map(x = province)\n\n\n\n\n\nroads <- oe_get(\n place = \"Cambodia\",\n download_directory = \"data_cambodia/\",\n layer = \"lines\",\n extra_tags = c(\"access\", \"service\", \"maxspeed\"),\n vectortranslate_options = c(\n \"-t_srs\", \"EPSG:32648\",\n \"-nlt\", \"PROMOTE_TO_MULTI\",\n \"-where\", \"\n highway IS NOT NULL\n AND\n highway NOT IN (\n 'abandonded', 'bus_guideway', 'byway', 'construction', 'corridor', 'elevator',\n 'fixme', 'escalator', 'gallop', 'historic', 'no', 'planned', 'platform',\n 'proposed', 'cycleway', 'pedestrian', 'bridleway', 'footway',\n 'steps', 'path', 'raceway', 'road', 'service', 'track'\n )\n \"\n),\n boundary = subset(province, name_en == \"Phnom Penh\"),\n boundary_type = \"clipsrc\"\n)\n\n0...10...20...30...40...50...60...70...80...90...100 - done.\nReading layer `lines' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/geofabrik_cambodia-latest.gpkg' \n using driver `GPKG'\nSimple feature collection with 18794 features and 12 fields\nGeometry type: MULTILINESTRING\nDimension: XY\nBounding box: xmin: 469524.2 ymin: 1263268 xmax: 503494.3 ymax: 1296780\nProjected CRS: WGS 84 / UTM zone 48N\n\nmf_map(x = roads)"
- },
- {
- "objectID": "02-data_acquisition.html#geocoding",
- "href": "02-data_acquisition.html#geocoding",
- "title": "2Â Data Acquisition",
- "section": "2.4 Geocoding",
- "text": "2.4 Geocoding\nServeral pakages alow you to geocode addresses. The package tidygeocoder (Cambon et al. 2021) allow the use of a large number of online geocoding sevices. The package banR (Gombin and Chevalier 2022), which is based on the National Address Base, is the particularly suitable for geocoding addresses in France.\n\n2.4.1 tidygeocoder\n\nlibrary(tidygeocoder)\ntest_adresses <- data.frame(\n address = c(\"Phnom Penh International Airport, Phnom Penh, Cambodia\",\n \"Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia\"))\nplaces1 <- geocode(test_adresses, address)\nplaces1\n\n# A tibble: 2 × 3\n address lat long\n <chr> <dbl> <dbl>\n1 Phnom Penh International Airport, Phnom Penh, Cambodia 11.6 105.\n2 Khmer Soviet Friendship Hospital, Phnom Penh, Cambodia 11.5 105.\n\n\n\n\n\n\n\n\nWebsite by tidygeocoder :\ntidygeocoder\n\n\n\n\n\n2.4.2 banR (Base Adresse Nationale)\n\n# remotes::install_github(\"joelgombin/banR\")\nlibrary(banR)\nmes_adresses <- data.frame(\n address = c(\"19 rue Michel Bakounine, 29600 Morlaix, France\",\n \"2 Allee Emile Pouget, 920128 Boulogne-Billancourt\")\n)\nplaces2 <- geocode_tbl(tbl = mes_adresses, adresse = address)\nplaces2\n\n# A tibble: 2 × 18\n address latit…¹ longi…² resul…³ resul…ⴠresul…ⵠresul…ⶠresul…ⷠresul…â¸\n <chr> <dbl> <dbl> <chr> <dbl> <chr> <chr> <chr> <chr> \n1 19 rue Michel… 48.6 -3.82 19 Rue… 0.81 housen… 29151_… 19 Rue Mi…\n2 2 Allee Emile… 48.8 2.24 2 Allé… 0.83 housen… 92012_… 2 Allée …\n# … with 9 more variables: result_street <chr>, result_postcode <chr>,\n# result_city <chr>, result_context <chr>, result_citycode <chr>,\n# result_oldcitycode <chr>, result_oldcity <chr>, result_district <chr>,\n# result_status <chr>, and abbreviated variable names ¹​latitude, ²​longitude,\n# ³​result_label, â´â€‹result_score, âµâ€‹result_type, â¶â€‹result_id,\n# â·â€‹result_housenumber, â¸â€‹result_name\n\n\n\n\n\n\n\n\nWebsite of banR :\nAn R client for the BAN API"
- },
- {
- "objectID": "02-data_acquisition.html#digitization",
- "href": "02-data_acquisition.html#digitization",
- "title": "2Â Data Acquisition",
- "section": "2.5 Digitization",
- "text": "2.5 Digitization\nThe package mapedit (Appelhans, Russell, and Busetto 2020) allows you to digitize base map directly in R. Although it can be practical in some cases, in package cannot replace the functionalities of a GIS for important digitization tasks.\n\n\n\nGif taken from mapedit website\n\n\n\n\n\n\nAgafonkin, Vladimir. 2015. “Leaflet Javascript Libary.â€\n\n\nAppelhans, Tim, Florian Detsch, Christoph Reudenbach, and Stefan Woellauer. 2022. “Mapview: Interactive Viewing of Spatial Data in r.†https://CRAN.R-project.org/package=mapview.\n\n\nAppelhans, Tim, Kenton Russell, and Lorenzo Busetto. 2020. “Mapedit: Interactive Editing of Spatial Data in r.†https://CRAN.R-project.org/package=mapedit.\n\n\nCambon, Jesse, Diego Hernangómez, Christopher Belanger, and Daniel Possenriede. 2021. “Tidygeocoder: An r Package for Geocoding†6: 3544. https://doi.org/10.21105/joss.03544.\n\n\nCheng, Joe, Bhaskar Karambelkar, and Yihui Xie. 2022. “Leaflet: Create Interactive Web Maps with the JavaScript ’Leaflet’ Library.†https://CRAN.R-project.org/package=leaflet.\n\n\nGilardi, Andrea, and Robin Lovelace. 2021. “Osmextract: Download and Import Open Street Map Data Extracts.†https://CRAN.R-project.org/package=osmextract.\n\n\nGiraud, Timothée. 2021. “Maptiles: Download and Display Map Tiles.†https://CRAN.R-project.org/package=maptiles.\n\n\nGombin, Joel, and Paul-Antoine Chevalier. 2022. “banR: R Client for the BAN API.â€\n\n\nPadgham, Mark, Bob Rudis, Robin Lovelace, and Maëlle Salmon. 2017. “Osmdata†2. https://doi.org/10.21105/joss.00305."
- },
- {
- "objectID": "03-vector_data.html",
- "href": "03-vector_data.html",
- "title": "3Â Vector Data",
- "section": "",
- "text": "The st_read() and st_write() function are used to import and export many types of files. The following lines import the administrative data in district level layer located in the cambodia.gpkg geopackage file.\n\nlibrary(sf)\n\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\") #import district data\n\nReading layer `district' from data source \n `/home/lucas/Documents/Framagit/rspatial-for-onehealth/data_cambodia/cambodia.gpkg' \n using driver `GPKG'\nSimple feature collection with 197 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211534.7 ymin: 1149105 xmax: 784612.1 ymax: 1625495\nProjected CRS: WGS 84 / UTM zone 48N\n\n\nThe following lines export the district object to a data folder in geopackage and shapefile format.\n\nst_write(obj = district, dsn = \"data_cambodia/district.gpkg\", delete_layer = TRUE)\n\nDeleting layer `district' using driver `GPKG'\nWriting layer `district' to data source \n `data_cambodia/district.gpkg' using driver `GPKG'\nWriting 197 features with 10 fields and geometry type Multi Polygon.\n\nst_write(obj = district, \"data_cambodia/district.shp\", layer_options = \"ENCODING=UTF-8\", delete_layer = TRUE)\n\nDeleting layer `district' using driver `ESRI Shapefile'\nWriting layer `district' to data source \n `data_cambodia/district.shp' using driver `ESRI Shapefile'\noptions: ENCODING=UTF-8 \nWriting 197 features with 10 fields and geometry type Multi Polygon."
- },
- {
- "objectID": "03-vector_data.html#display",
- "href": "03-vector_data.html#display",
- "title": "3Â Vector Data",
- "section": "3.2 Display",
- "text": "3.2 Display\nPreview of the variables via the function head() and plot().\n\nhead(district)\n\nSimple feature collection with 6 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 300266.9 ymin: 1180566 xmax: 767313.9 ymax: 1563861\nProjected CRS: WGS 84 / UTM zone 48N\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP Area.Km2.\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416 1067.8638\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708 837.7064\n3 Angk Snuol KH0808 Kandal KH08 45436 47141 92577 183.9050\n4 Angkor Borei KH2101 Takeo KH21 26306 27168 53474 301.0502\n5 Angkor Chey KH0701 Kampot KH07 42448 44865 87313 316.7576\n6 Angkor Chum KH1701 Siemreap KH17 34269 34576 68845 478.6988\n Status DENs geom\n1 <4500km2 79.98773 MULTIPOLYGON (((306568.1 14...\n2 <4500km2 17.55747 MULTIPOLYGON (((751459.2 15...\n3 <4500km2 503.39580 MULTIPOLYGON (((471954.3 12...\n4 <4500km2 177.62485 MULTIPOLYGON (((490048.2 12...\n5 <4500km2 275.64610 MULTIPOLYGON (((462702.2 12...\n6 <4500km2 143.81696 MULTIPOLYGON (((363642.5 15...\n\nplot(district)\n\n\n\n\nfor Geometry display only.\n\nplot(st_geometry(district))"
- },
- {
- "objectID": "03-vector_data.html#coordinate-systems",
- "href": "03-vector_data.html#coordinate-systems",
- "title": "3Â Vector Data",
- "section": "3.3 Coordinate systems",
- "text": "3.3 Coordinate systems\n\n3.3.1 Look up the coordinate system of an object\nThe function st_crs() makes it possible to consult the system of coordinates used and object sf.\n\nst_crs(district)\n\nCoordinate Reference System:\n User input: WGS 84 / UTM zone 48N \n wkt:\nPROJCRS[\"WGS 84 / UTM zone 48N\",\n BASEGEOGCRS[\"WGS 84\",\n ENSEMBLE[\"World Geodetic System 1984 ensemble\",\n MEMBER[\"World Geodetic System 1984 (Transit)\"],\n MEMBER[\"World Geodetic System 1984 (G730)\"],\n MEMBER[\"World Geodetic System 1984 (G873)\"],\n MEMBER[\"World Geodetic System 1984 (G1150)\"],\n MEMBER[\"World Geodetic System 1984 (G1674)\"],\n MEMBER[\"World Geodetic System 1984 (G1762)\"],\n MEMBER[\"World Geodetic System 1984 (G2139)\"],\n ELLIPSOID[\"WGS 84\",6378137,298.257223563,\n LENGTHUNIT[\"metre\",1]],\n ENSEMBLEACCURACY[2.0]],\n PRIMEM[\"Greenwich\",0,\n ANGLEUNIT[\"degree\",0.0174532925199433]],\n ID[\"EPSG\",4326]],\n CONVERSION[\"UTM zone 48N\",\n METHOD[\"Transverse Mercator\",\n ID[\"EPSG\",9807]],\n PARAMETER[\"Latitude of natural origin\",0,\n ANGLEUNIT[\"degree\",0.0174532925199433],\n ID[\"EPSG\",8801]],\n PARAMETER[\"Longitude of natural origin\",105,\n ANGLEUNIT[\"degree\",0.0174532925199433],\n ID[\"EPSG\",8802]],\n PARAMETER[\"Scale factor at natural origin\",0.9996,\n SCALEUNIT[\"unity\",1],\n ID[\"EPSG\",8805]],\n PARAMETER[\"False easting\",500000,\n LENGTHUNIT[\"metre\",1],\n ID[\"EPSG\",8806]],\n PARAMETER[\"False northing\",0,\n LENGTHUNIT[\"metre\",1],\n ID[\"EPSG\",8807]]],\n CS[Cartesian,2],\n AXIS[\"(E)\",east,\n ORDER[1],\n LENGTHUNIT[\"metre\",1]],\n AXIS[\"(N)\",north,\n ORDER[2],\n LENGTHUNIT[\"metre\",1]],\n USAGE[\n SCOPE[\"Engineering survey, topographic mapping.\"],\n AREA[\"Between 102°E and 108°E, northern hemisphere between equator and 84°N, onshore and offshore. Cambodia. China. Indonesia. Laos. Malaysia - West Malaysia. Mongolia. Russian Federation. Singapore. Thailand. Vietnam.\"],\n BBOX[0,102,84,108]],\n ID[\"EPSG\",32648]]\n\n\n\n\n3.3.2 Changing the coordinate system of an object\nThe function st_transform() allows to change the coordinate system of an sf object, to re-project it.\n\nplot(st_geometry(district))\ntitle(\"WGS 84 / UTM zone 48N\")\n\n\n\ndist_reproj <- st_transform(district, \"epsg:4326\")\nplot(st_geometry(dist_reproj))\ntitle(\"WGS84\")\n\n\n\n\nThe Spatial Reference site provides reference for a large number of coordinate systems."
- },
- {
- "objectID": "03-vector_data.html#selection-by-attributes",
- "href": "03-vector_data.html#selection-by-attributes",
- "title": "3Â Vector Data",
- "section": "3.4 Selection by attributes",
- "text": "3.4 Selection by attributes\nThe object sf are data.frame, so you can select their rows and columns in the same way as data.frame.\n\n# row Selection\ndistrict[1:2, ]\n\nSimple feature collection with 2 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 300266.9 ymin: 1449408 xmax: 767313.9 ymax: 1563861\nProjected CRS: WGS 84 / UTM zone 48N\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP Area.Km2.\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416 1067.8638\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708 837.7064\n Status DENs geom\n1 <4500km2 79.98773 MULTIPOLYGON (((306568.1 14...\n2 <4500km2 17.55747 MULTIPOLYGON (((751459.2 15...\n\ndistrict[district$ADM1_EN == \"Phnom Penh\", ]\n\nSimple feature collection with 12 features and 10 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 468677.5 ymin: 1262590 xmax: 505351.9 ymax: 1297419\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n29 Chamkar Mon KH1201 Phnom Penh KH12 52278 54478 106756\n31 Chbar Ampov KH1212 Phnom Penh KH12 64816 68243 133059\n43 Chraoy Chongvar KH1210 Phnom Penh KH12 30920 31087 62007\n48 Dangkao KH1205 Phnom Penh KH12 46999 48525 95524\n50 Doun Penh KH1202 Phnom Penh KH12 33844 36471 70315\n93 Mean Chey KH1206 Phnom Penh KH12 68381 70366 138747\n117 Praek Pnov KH1211 Phnom Penh KH12 27566 27698 55264\n118 Prampir Meakkakra KH1203 Phnom Penh KH12 31091 33687 64778\n133 Pur SenChey KH1209 Phnom Penh KH12 95050 109297 204347\n141 Russey Keo KH1207 Phnom Penh KH12 67357 68419 135776\n Area.Km2. Status DENs geom\n29 11.049600 <4500km2 9661.5265 MULTIPOLYGON (((494709.4 12...\n31 86.780498 <4500km2 1533.2823 MULTIPOLYGON (((498855.3 12...\n43 85.609156 <4500km2 724.3034 MULTIPOLYGON (((491161.3 12...\n48 113.774833 <4500km2 839.5881 MULTIPOLYGON (((489191.1 12...\n50 7.734808 <4500km2 9090.7234 MULTIPOLYGON (((492447.1 12...\n93 28.998026 <4500km2 4784.7051 MULTIPOLYGON (((491068.2 12...\n117 115.384300 <4500km2 478.9560 MULTIPOLYGON (((481483.3 12...\n118 2.224892 <4500km2 29115.1253 MULTIPOLYGON (((491067.6 12...\n133 148.357984 <4500km2 1377.3913 MULTIPOLYGON (((479078.8 12...\n141 23.381517 <4500km2 5806.9800 MULTIPOLYGON (((490264.8 12...\n\n# column selection\ndistrict[district$ADM1_EN == \"Phnom Penh\", 1:4] \n\nSimple feature collection with 12 features and 4 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 468677.5 ymin: 1262590 xmax: 505351.9 ymax: 1297419\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE\n29 Chamkar Mon KH1201 Phnom Penh KH12\n31 Chbar Ampov KH1212 Phnom Penh KH12\n43 Chraoy Chongvar KH1210 Phnom Penh KH12\n48 Dangkao KH1205 Phnom Penh KH12\n50 Doun Penh KH1202 Phnom Penh KH12\n93 Mean Chey KH1206 Phnom Penh KH12\n117 Praek Pnov KH1211 Phnom Penh KH12\n118 Prampir Meakkakra KH1203 Phnom Penh KH12\n133 Pur SenChey KH1209 Phnom Penh KH12\n141 Russey Keo KH1207 Phnom Penh KH12\n geom\n29 MULTIPOLYGON (((494709.4 12...\n31 MULTIPOLYGON (((498855.3 12...\n43 MULTIPOLYGON (((491161.3 12...\n48 MULTIPOLYGON (((489191.1 12...\n50 MULTIPOLYGON (((492447.1 12...\n93 MULTIPOLYGON (((491068.2 12...\n117 MULTIPOLYGON (((481483.3 12...\n118 MULTIPOLYGON (((491067.6 12...\n133 MULTIPOLYGON (((479078.8 12...\n141 MULTIPOLYGON (((490264.8 12..."
- },
- {
- "objectID": "03-vector_data.html#spatial-selection",
- "href": "03-vector_data.html#spatial-selection",
- "title": "3Â Vector Data",
- "section": "3.5 Spatial selection",
- "text": "3.5 Spatial selection\n\n3.5.1 Intersections\nSelection of roads that are intersecting dangkao district\n\nroad <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE) %>% st_cast(\"LINESTRING\")\ndangkao <- district[district$ADM2_EN == \"Dangkao\", ]\ninter <- st_intersects(x = road, y = dangkao, sparse = FALSE)\nhead(inter)\n\n [,1]\n[1,] FALSE\n[2,] FALSE\n[3,] FALSE\n[4,] FALSE\n[5,] FALSE\n[6,] FALSE\n\ndim(inter)\n\n[1] 108285 1\n\n\nThe inter object is a matrix which indicates for each of element of the road object (6 elements) whether it intersects each elements the dangkao object (1 element). The dimension of the matrix is therefore indeed 6 rows * 1 column. Note the use of the parameter sparse = FALSE here. It is then possible to create a column from this object:\n\nroad$intersect_dangkao <- inter\nplot(st_geometry(dangkao), col = \"lightblue\")\nplot(st_geometry(road), add = TRUE)\nplot(st_geometry(road[road$intersect_dangkao, ]),\n col = \"tomato\", lwd = 1.5, add = TRUE)\n\n\n\n\n\n3.5.1.1 Difference between sparse = TRUE and sparse = FALSE\n\n\n\n\n\n\nsparse = TRUE\n\n\ninter <- st_intersects(x = grid, y = pt, sparse = TRUE)\ninter\n\nSparse geometry binary predicate list of length 4, where the predicate\nwas `intersects'\n 1: (empty)\n 2: 6, 7\n 3: 1, 4\n 4: 2, 3, 5, 8\n\n\n\nsparse = FALSE\n\n\ninter <- st_intersects(x = grid, y = pt, sparse = FALSE)\nrownames(inter) <- grid$id\ncolnames(inter) <- pt$id\ninter\n\n a b c d e f g h\n1 FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE\n2 FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE\n3 TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE\n4 FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE\n\n\n\n\n\n3.5.2 Contains / Within\nSelection of roads contained in the municipality of Dangkao. The function st_within() works like the function st_intersects()\n\nroad$within_dangkao <- st_within(road, dangkao, sparse = FALSE)\nplot(st_geometry(dangkao), col = \"lightblue\")\nplot(st_geometry(road), add = TRUE)\nplot(st_geometry(road[road$within_dangkao, ]), col = \"tomato\",\n lwd = 2, add = TRUE)"
- },
- {
- "objectID": "03-vector_data.html#operation-of-geometries",
- "href": "03-vector_data.html#operation-of-geometries",
- "title": "3Â Vector Data",
- "section": "3.6 Operation of geometries",
- "text": "3.6 Operation of geometries\n\n3.6.1 Extract centroids\n\ndist_c <- st_centroid(district)\nplot(st_geometry(district))\nplot(st_geometry(dist_c), add = TRUE, cex = 1.2, col = \"red\", pch = 20)\n\n\n\n\n\n\n3.6.2 Aggregate polygons\n\ncambodia_dist <- st_union(district) \nplot(st_geometry(district), col = \"lightblue\")\nplot(st_geometry(cambodia_dist), add = TRUE, lwd = 2, border = \"red\")\n\n\n\n\n\n\n3.6.3 Aggregate polygons based on a variable\n\ndist_union <- aggregate(x = district[,c(\"T_POP\")],\n by = list(STATUT = district$Status),\n FUN = \"sum\")\nplot(dist_union)\n\n\n\n\n\n\n3.6.4 Create a buffer zone\n\ndangkao_buffer <- st_buffer(x = dangkao, dist = 1000)\nplot(st_geometry(dangkao_buffer), col = \"#E8DAEF\", lwd=2, border = \"#6C3483\")\nplot(st_geometry(dangkao), add = TRUE, lwd = 2)\n\n\n\n\n\n\n3.6.5 Making an intersection\nBy using the function st_intersection() we will cut one layer by another.\n\nlibrary(magrittr)\n# creation of a buffer zone around the centroid of the municipality of Dangkao district\n# using the pipe\nzone <- st_geometry(dangkao) %>%\n st_centroid() %>%\n st_buffer(30000)\nplot(st_geometry(district))\nplot(zone, border = \"#F06292\", lwd = 2, add = TRUE)\n\n\n\ndist_z <- st_intersection(x = district, y = zone)\nplot(st_geometry(district))\nplot(st_geometry(dist_z), col=\"#AF7AC5\", border=\"#F9E79F\", add=T)\n\n\n\nplot(st_geometry(dist_z))\n\n\n\n\n\n\n3.6.6 Create regular grid\nThe function st_make_grid() allows you to create regular grid. The function produce and object sfc, you must then use the function st_sf() to transform the object sfc into and object sf. During this transformation we add here a column of unique identifiers.\n\ngrid <- st_make_grid(x = district, cellsize = 10000)\ngrid <- st_sf(ID = 1:length(grid), geom = grid)\n\nplot(st_geometry(grid), col = \"grey\", border = \"white\")\nplot(st_geometry(district), border = \"grey50\", add = TRUE)\n\n\n\n\n\n\n3.6.7 Counting points in a polygon (in a grid tile)\n\n# selection of grid tiles that intersect the district\n\ninter <- st_intersects(grid, cambodia_dist, sparse = FALSE)\ngrid <- grid[inter, ]\n\ncase_cambodia <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\" , quiet = TRUE)\nplot(st_geometry(grid), col = \"grey\", border = \"white\")\nplot(st_geometry(case_cambodia), pch = 20, col = \"red\", add = TRUE, cex = 0.8)\n\n\n\ninter <- st_intersects(grid, case_cambodia, sparse = TRUE)\nlength(inter)\n\n[1] 1964\n\n\nHere we use the argument sparse = TRUE. The inter object is a list the length of the grid and each item in the list contain the index of the object items of cases and grid intersection.\nFor example grid tile 35th intersect with four cases 97, 138, 189, 522, 624, 696\n\ninter[35]\n\n[[1]]\n[1] 97 138 189 522 624 696\n\nplot(st_geometry(grid[35, ]))\nplot(st_geometry(case_cambodia), add = T)\nplot(st_geometry(case_cambodia[c(97, 138, 189, 522, 624, 696), ]), \n col = \"red\", pch = 19, add = TRUE)\n\n\n\n\nTo count number of case, simply go to the list and report length of the elements.\n\ngrid$nb_case <- sapply(X = inter, FUN = length) # create 'nb_case' column to store number of health centers in each grid tile \nplot(grid[\"nb_case\"])\n\n\n\n\n\n\n3.6.8 Aggregate point values into polygons\nIn this example we import a csv file that contain data from a population grid. Once import we transform it data.frame into an object sf.\nThe objective is to aggregate the values id these points (the population contained in the “DENs†field) in the municipalities of the district.\n\npp_pop_raw <- read.csv(\"data_cambodia/pp_pop_dens.csv\") # import file\npp_pop_raw$id <- 1:nrow(pp_pop_raw) # adding a unique identifier\npp_pop <- st_as_sf(pp_pop_raw, coords = c(\"X\", \"Y\"), crs = 32648) # Transform into object sf\npp_pop <- st_transform(pp_pop, st_crs(district)) # Transform projection\ninter <- st_intersection(pp_pop, district) # Intersection\ninter\n\nSimple feature collection with 1295 features and 12 fields\nGeometry type: POINT\nDimension: XY\nBounding box: xmin: 469177.5 ymin: 1263090 xmax: 505177.5 ymax: 1297090\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n DENs id ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n149 NA 149 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n150 NA 150 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n151 NA 151 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n186 NA 186 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n187 NA 187 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n188 NA 188 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n223 NA 223 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n224 NA 224 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n225 NA 225 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n226 3.400075 226 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n Area.Km2. Status DENs.1 geometry\n149 183.905 <4500km2 503.3958 POINT (469177.5 1267090)\n150 183.905 <4500km2 503.3958 POINT (470177.5 1267090)\n151 183.905 <4500km2 503.3958 POINT (471177.5 1267090)\n186 183.905 <4500km2 503.3958 POINT (469177.5 1268090)\n187 183.905 <4500km2 503.3958 POINT (470177.5 1268090)\n188 183.905 <4500km2 503.3958 POINT (471177.5 1268090)\n223 183.905 <4500km2 503.3958 POINT (469177.5 1269090)\n224 183.905 <4500km2 503.3958 POINT (470177.5 1269090)\n225 183.905 <4500km2 503.3958 POINT (471177.5 1269090)\n226 183.905 <4500km2 503.3958 POINT (472177.5 1269090)\n\n\nBy using the function st_intersection() we add to each point of the grid all the information on the municipality in which it is located.\nWe can then use the function aggregate() to aggregate the population by municipalities.\n\nresultat <- aggregate(x = list(pop_from_grid = inter$DENs), \n by = list(ADM2_EN = inter$ADM2_EN), \n FUN = \"sum\")\nhead(resultat)\n\n ADM2_EN pop_from_grid\n1 Angk Snuol NA\n2 Chamkar Mon 10492.7159\n3 Chbar Ampov 1593.9593\n4 Chraoy Chongvar 1434.1785\n5 Dangkao 942.3595\n6 Doun Penh 10781.8026\n\n\nWe can then create a new object with this result.\n\ndist_result <- merge(district, resultat, by = \"ADM2_EN\", all.x = TRUE)\ndist_result\n\nSimple feature collection with 197 features and 11 fields\nGeometry type: MULTIPOLYGON\nDimension: XY\nBounding box: xmin: 211534.7 ymin: 1149105 xmax: 784612.1 ymax: 1625495\nProjected CRS: WGS 84 / UTM zone 48N\nFirst 10 features:\n ADM2_EN ADM2_PCODE ADM1_EN ADM1_PCODE Male Female T_POP\n1 Aek Phnum KH0205 Battambang KH02 41500 43916 85416\n2 Andoung Meas KH1601 Ratanak Kiri KH16 7336 7372 14708\n3 Angk Snuol KH0808 Kandal KH08 45436 47141 92577\n4 Angkor Borei KH2101 Takeo KH21 26306 27168 53474\n5 Angkor Chey KH0701 Kampot KH07 42448 44865 87313\n6 Angkor Chum KH1701 Siemreap KH17 34269 34576 68845\n7 Angkor Thum KH1702 Siemreap KH17 13802 14392 28194\n8 Anlong Veaeng KH2201 Oddar Meanchey KH22 24122 23288 47410\n9 Aoral KH0504 Kampong Speu KH05 19874 19956 39830\n10 Ba Phnum KH1401 Prey Veng KH14 46562 49852 96414\n Area.Km2. Status DENs pop_from_grid geometry\n1 1067.8638 <4500km2 79.98773 NA MULTIPOLYGON (((306568.1 14...\n2 837.7064 <4500km2 17.55747 NA MULTIPOLYGON (((751459.2 15...\n3 183.9050 <4500km2 503.39580 NA MULTIPOLYGON (((471954.3 12...\n4 301.0502 <4500km2 177.62485 NA MULTIPOLYGON (((490048.2 12...\n5 316.7576 <4500km2 275.64610 NA MULTIPOLYGON (((462702.2 12...\n6 478.6988 <4500km2 143.81696 NA MULTIPOLYGON (((363642.5 15...\n7 357.8890 <4500km2 78.77862 NA MULTIPOLYGON (((376584.4 15...\n8 1533.5702 <4500km2 30.91479 NA MULTIPOLYGON (((404936.4 15...\n9 2381.7084 <4500km2 16.72329 NA MULTIPOLYGON (((414000.6 13...\n10 342.3439 <4500km2 281.62910 NA MULTIPOLYGON (((545045.4 12..."
- },
- {
- "objectID": "03-vector_data.html#measurements",
- "href": "03-vector_data.html#measurements",
- "title": "3Â Vector Data",
- "section": "3.7 Measurements",
- "text": "3.7 Measurements\n\n3.7.1 Create a distance matrix\nIf the dataset’s projection system is specified, the distance are expressed in the projection measurement unit (most often in meter)\n\nmat <- st_distance(x = dist_c, y = dist_c)\nmat[1:5,1:5]\n\nUnits: [m]\n [,1] [,2] [,3] [,4] [,5]\n[1,] 0.0 425993.7 232592.12 298254.12 299106.92\n[2,] 425993.7 0.0 386367.88 414428.82 452431.87\n[3,] 232592.1 386367.9 0.00 67060.05 82853.88\n[4,] 298254.1 414428.8 67060.05 0.00 40553.15\n[5,] 299106.9 452431.9 82853.88 40553.15 0.00\n\n\n\n\n3.7.2 Calculate routes\n The package osrm (R-osrm?) acts as an interface R and the OSRM (luxen-vetter-2011?). This package allows to calculate time and distance matrices, road routes, isochrones. The package uses the OSRM demo server by default. In case of intensive use it is strongly recommended to use your own instance of OSRM (with Docker).\n\n3.7.2.1 Calculate a route\nThe fonction osrmRoute() allows you to calculate routes.\n\nlibrary(sf)\nlibrary(osrm)\nlibrary(maptiles)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\",layer = \"district\", quiet = TRUE)\ndistrict <- st_transform(district, 32648)\n\nodongk <- district[district$ADM2_PCODE == \"KH0505\", ] # Itinerary between Odongk district and Toul Kouk\ntakmau <- district[district$ADM2_PCODE == \"KH0811\",]\nroute <- osrmRoute(src = odongk, \n dst = takmau, \n returnclass = \"sf\")\nosm <- get_tiles(route, crop = TRUE)\nplot_tiles(osm)\nplot(st_geometry(route), col = \"#b23a5f\", lwd = 6, add = T)\nplot(st_geometry(route), col = \"#eee0e5\", lwd = 1, add = T)\n\n\n\n\n\n\n3.7.2.2 Calculation of a time matrix\nThe function osrmTable() makes it possible to calculate matrices of distances or times by road.\nIn this example we calculate a time matrix between 2 addresses and health centers in Phnom Penh on foot.\n\nlibrary(sf)\nlibrary(tidygeocoder)\nhospital <- st_read(\"data_cambodia/cambodia.gpkg\",layer= \"hospital\", quiet = TRUE)\n\nhospital_pp <- hospital[hospital$PCODE == \"12\", ] # Selection of health centers in Phnom Penh\n\nadresses <- data.frame(adr = c(\"Royal Palace Park, Phnom Penh Phnom, Cambodia\",\n \"Wat Phnom Daun Penh, Phnom Penh, Cambodia\")) # Geocoding of 2 addresses in Phnom Penh\n\nplaces <- tidygeocoder::geocode(.tbl = adresses,address = adr)\nplaces\n\n# A tibble: 2 × 3\n adr lat long\n <chr> <dbl> <dbl>\n1 Royal Palace Park, Phnom Penh Phnom, Cambodia 11.6 105.\n2 Wat Phnom Daun Penh, Phnom Penh, Cambodia 11.6 105.\n\n# Calculation of the distance matrix between the 2 addresses and the health center in Phnom Penh\n\ncal_mat <- osrmTable(src = places[,c(1,3,2)], \n dst = hospital_pp, \n osrm.profile = \"foot\")\n\ncal_mat$durations[1:2, 1:5]\n\n 684 685 686 687 691\nRoyal Palace Park, Phnom Penh Phnom, Cambodia 55.9 71.6 64.4 40.2 76.7\nWat Phnom Daun Penh, Phnom Penh, Cambodia 60.1 80.4 40.1 32.8 53.1\n\n# Which address has better accessibility to health center in Phnom Penh?\n\nboxplot(t(cal_mat$durations[,]), cex.axis = 0.7)"
- },
- {
- "objectID": "04-raster_data.html",
- "href": "04-raster_data.html",
- "title": "4Â Work with Raster Data",
- "section": "",
- "text": "This chapter is largely inspired by two presentation; Madelin (2021) and Nowosad (2021); carried out as part of the SIGR2021 thematic school."
- },
- {
- "objectID": "04-raster_data.html#format-of-objects-spatraster",
- "href": "04-raster_data.html#format-of-objects-spatraster",
- "title": "4Â Work with Raster Data",
- "section": "4.1 Format of objects SpatRaster",
- "text": "4.1 Format of objects SpatRaster\nThe package terra (Hijmans 2022) allows to handle vector and raster data. To manipulate this spatial data, terra store it in object of type SpatVector and SpatRaster. In this chapter, we focus on the manipulation of raster data (SpatRaster) from functions offered by this package.\nAn object SpatRaster allows to handle vector and raster data, in one or more layers (variables). This object also stores a number of fundamental parameters that describe it (number of columns, rows, spatial extent, coordinate reference system, etc.).\n\n\n\nSource : (Racine 2016)"
- },
- {
- "objectID": "04-raster_data.html#importing-and-exporting-data",
- "href": "04-raster_data.html#importing-and-exporting-data",
- "title": "4Â Work with Raster Data",
- "section": "4.2 Importing and exporting data",
- "text": "4.2 Importing and exporting data\nThe package terra allows importing and exporting raster files. It is based on the GDAL library which makes it possible to read and process a very large number of geographic image formats.\n\nlibrary(terra)\n\nThe function rast() allows you to create and/or import raster data. The following lines import the raster file elevation.tif (Tagged Image File Format) into an object of type SpatRaster (default).\n\nelevation <- rast(\"data_cambodia/elevation.tif\") \nelevation\n\nclass : SpatRaster \ndimensions : 5235, 6458, 1 (nrow, ncol, nlyr)\nresolution : 0.0008333394, 0.0008332568 (x, y)\nextent : 102.2935, 107.6752, 10.33984, 14.70194 (xmin, xmax, ymin, ymax)\ncoord. ref. : lon/lat WGS 84 (EPSG:4326) \nsource : elevation.tif \nname : elevation \n\n\nModifying the name of the stored variable (altitude).\n\nnames(elevation) <- \"Altitude\" \n\nThe function writeRaster() allow you to save an object SpatRaster on your machine, in the format of your choice.\n\nwriteRaster(x = elevation, filename = \"data_cambodia/new_elevation.tif\")"
- },
- {
- "objectID": "04-raster_data.html#displaying-a-spatraster-object",
- "href": "04-raster_data.html#displaying-a-spatraster-object",
- "title": "4Â Work with Raster Data",
- "section": "4.3 Displaying a SpatRaster object",
- "text": "4.3 Displaying a SpatRaster object\nThe function plot() is use to display an object SpatRaster.\n\nplot(elevation)\n\n\n\n\n\n\n\n\nA raster always contains numerical data, but it can be both quantitative data and numerically coded qualitative (categorical) data (ex: type of land cover).\nSpecify the type of data stored with the augment type (type = \"continuous\" default), to display them correctly.\nImport and display of raster containing categorical data: Phnom Penh Land Cover 2019 (land cover types) with a resolution of 1.5 meters:\n\nlulc_2019 <- rast(\"data_cambodia/lulc_2019.tif\") #Import Phnom Penh landcover 2019, landcover types\n\nThe landcover data was produced from SPOT7 satellite image with 1.5 meter spatial resolution. An extraction centered on the municipality of Phnom Penh was then carried out.\n\nplot(lulc_2019, type = \"classes\")\n\n\n\n\n\n\n\n\nTo display the actual tiles of landcover types, as well as the official colors of Phnom Penh Landcover nomenclature (available here), you can proceed as follows.\n\nclass_name <- c(\n \"Roads\",\n \"Built-up areas\",\n \"Water Bodies and rivers\",\n \"Wetlands\",\n \"Dry bare area\",\n \"Bare crop fields\",\n \"Low vegetation areas\",\n \"High vegetation areas\",\n \"Forested areas\")\n\nclass_color <- c(\"#070401\", \"#c84639\", \"#1398eb\",\"#8bc2c2\",\n \"#dc7b34\", \"#a6bd5f\",\"#e8e8e8\", \"#4fb040\", \"#35741f\")\nplot(lulc_2019,\n type = \"classes\",\n levels = class_name,\n col = class_color,\n plg = list(cex = 0.7),\n mar = c(3.1, 3.1, 2.1, 10) #The margin are (bottom, left, top, right) respectively\n )"
- },
- {
- "objectID": "04-raster_data.html#change-to-the-study-area",
- "href": "04-raster_data.html#change-to-the-study-area",
- "title": "4Â Work with Raster Data",
- "section": "4.4 Change to the study area",
- "text": "4.4 Change to the study area\n\n4.4.1 (Re)projections\nTo modify the projection system of a raster, use the function project(). It is then necessary to indicate the method for estimating the new cell values.\n\n\n\nSource : Centre Canadien de Télédétection\n\n\nFour interpolation methods are available:\n\nnear : nearest neighbor, fast and default method for qualitative data;\n\nbilinear : bilinear interpolation. Default method for quantitative data;\n\ncubic : cubic interpolation;\n\ncubicspline : cubic spline interpolation.\n\n\n# Re-project data \n\nelevation_utm = project(x = elevation, y = \"EPSG:32648\", method = \"bilinear\") #from WGS84(EPSG:4326) to UTM zone48N(EPSG:32648) \nlulc_2019_utm = project(x = lulc_2019, y = \"EPSG:32648\", method = \"near\") #keep original projection: UTM zone48N(EPSG:32648)\n\n\n\n\n\n\n\n\n\n\n\n\n4.4.2 Crop\nClipping a raster to the extent of another object SpatVector or SpatRaster is achievable with the crop().\n\n\n\n\n\n\n\n\n\n\n\nSource : (Racine 2016)\n\n\n\nImport vector data of (municipal divisions) using function vect. This data will be stored in an SpatVector object.\n\ndistrict <- vect(\"data_cambodia/cambodia.gpkg\", layer=\"district\")\n\nExtraction of district boundaries of Thma Bang district (ADM2_PCODE : KH0907).\n\nthma_bang <- subset(district, district$ADM2_PCODE == \"KH0907\") \n\nUsing the function crop(), Both data layers must be in the same projection.\n\ncrop_thma_bang <- crop(elevation_utm, thma_bang)\n\nplot(crop_thma_bang)\nplot(thma_bang, add=TRUE)\n\n\n\n\n\n\n\n\n\n\n4.4.3 Mask\nTo display only the values of a raster contained in a polygon, use the function mask().\n\n\n\nSource : (Racine 2016)\n\n\nCreation of a mask on the crop_thma_bang raster to the municipal limits (polygon) of Thma Bang district.\n\nmask_thma_bang <- mask(crop_thma_bang, thma_bang)\n\nplot(mask_thma_bang)\nplot(thma_bang, add = TRUE)\n\n\n\n\n\n\n\n\n\n\n4.4.4 Aggregation and disaggregation\nResampling a raster to a different resolution is done in two steps.\n\n\n\n\n\n\n1\n\n\n\n\n\n\n\n2\n\n\n\n\n\n\n\n3\n\n\n\n\n\n\nSource : (Racine 2016)\n\n\n\nDisplay the resolution of a raster with the function res().\n\nres(elevation_utm) #check cell size\n\n[1] 91.19475 91.19475\n\n\nCreate a grid with the same extent, then decrease the spatial resolution (larger cells).\n\nelevation_LowerGrid <- elevation_utm\n# elevation_HigherGrid <- elevation_utm\n\nres(elevation_LowerGrid) <- 1000 #cells size = 1000 meter\n# res(elevation_HigherGrid) <- 10 #cells size = 10 meter\n\nelevation_LowerGrid\n\nclass : SpatRaster \ndimensions : 484, 589, 1 (nrow, ncol, nlyr)\nresolution : 1000, 1000 (x, y)\nextent : 203586.3, 792586.3, 1142954, 1626954 (xmin, xmax, ymin, ymax)\ncoord. ref. : WGS 84 / UTM zone 48N (EPSG:32648) \n\n\nThe function resample() allows to resample the atarting values in the new spatial resolution. Several resampling methods are available (cf. partie 5.4.1).\n\nelevation_LowerGrid <- resample(elevation_utm, \n elevation_LowerGrid, \n method = \"bilinear\") \n\nplot(elevation_LowerGrid, \n main=\"Cell size = 1000m\\nBilinear resampling method\")\n\n\n\n\n\n\n\n\n\n\n4.4.5 Raster fusion\nMerge multiple objects SpatRaster into one with merge() or mosaic().\n\n\n\nSource : https://desktop.arcgis.com/fr/arcmap/10.3/manage-data/raster-and-images/what-is-a-mosaic.htm\n\n\nAfter cutting the elevation raster by the municipal boundary of Thma Bang district (cf partie 5.4.2), we do the same thing for the neighboring municipality of Phnum Kravanh district.\n\nphnum_kravanh <- subset(district, district$ADM2_PCODE == \"KH1504\") # Extraction of the municipal boundaries of Phnum Kravanh district\n\ncrop_phnum_kravanh <- crop(elevation_utm, phnum_kravanh) #clipping the elevation raster according to district boundaries\n\nThe crop_thma_bang and crop_phnum_kravanh elevation raster overlap spatially:\n\n\n\n\n\n\n\n\n\nThe difference between the functions merge() and mosiac() relates to values of the overlapping cells. The function mosaic() calculate the average value while merge() holding the value of the object SpaRaster called n the function.\n\n#in this example, merge() and mosaic() give the same result\nmerge_raster <- merge(crop_thma_bang, crop_phnum_kravanh) \nmosaic_raster <- mosaic(crop_thma_bang, crop_phnum_kravanh)\n\nplot(merge_raster)\n\n\n\n\n\n\n\n# plot(mosaic_raster)\n\n\n\n4.4.6 Segregate\nDecompose a raster by value (or modality) into different rasterlayers with the function segregate.\n\nlulc_2019_class <- segregate(lulc_2019, keep=TRUE, other=NA) #creating a raster layer by modality\nplot(lulc_2019_class)"
- },
- {
- "objectID": "04-raster_data.html#map-algebra",
- "href": "04-raster_data.html#map-algebra",
- "title": "4Â Work with Raster Data",
- "section": "4.5 Map Algebra",
- "text": "4.5 Map Algebra\nMap algebra is classified into four groups of operation (Tomlin 1990):\n\nLocal : operation by cell, on one or more layers;\n\nFocal : neighborhood operation (surrounding cells);\n\nZonal : to summarize the matrix values for certain zones, usually irregular;\nGlobal : to summarize the matrix values of one or more matrices.\n\n\n\n\nSource : (Li 2009)\n\n\n\n4.5.1 Local operations\n\n\n\nSource : (Mennis 2015)\n\n\n\n4.5.1.1 Value replacement\n\nelevation_utm[elevation_utm[[1]]== -9999] <- NA #replaces -9999 values with NA\n\nelevation_utm[elevation_utm < 1500] <- NA #Replace values < 1500 with NA\n\n\nelevation_utm[is.na(elevation_utm)] <- 0 #replace NA values with 0\n\n\n\n4.5.1.2 Operation on each cell\n\nelevation_1000 <- elevation_utm + 1000 # Adding 1000 to the value of each cell\n\nelevation_median <- elevation_utm - global(elevation_utm, median)[[1]] # Removed median elevation to each cell's value\n\n\n\n\n\n\n\n\n\n\n\n\n4.5.1.3 Reclassification\nReclassifying raster values can be used to discretize quantitative data as well as to categorize qualitative categories.\n\nreclassif <- matrix(c(1, 2, 1, \n 2, 4, 2,\n 4, 6, 3,\n 6, 9, 4), \n ncol = 3, byrow = TRUE)\n\nValues between 1 and 2 will be replaced by the value 1.\nValues between 3 and 4 will be replaced by the value 2.\nValues between 5 and 6 will be replaced by the value 3. Values between 7 and 9 will be replaced by the value 4.\n…\n\nreclassif\n\n [,1] [,2] [,3]\n[1,] 1 2 1\n[2,] 2 4 2\n[3,] 4 6 3\n[4,] 6 9 4\n\n\nThe function classify() allows you to perform the reclassification.\n\nlulc_2019_reclass <- classify(lulc_2019, rcl = reclassif)\nplot(lulc_2019_reclass, type =\"classes\")\n\n\n\n\nDisplay with the official titles and colors of the different categories.\n\nplot(lulc_2019_reclass, \n type =\"classes\", \n levels=c(\"Urban areas\",\n \"Water body\",\n \"Bare areas\",\n \"Vegetation areas\"),\n col=c(\"#E6004D\",\n \"#00BFFF\",\n \"#D3D3D3\", \n \"#32CD32\"),\n mar=c(3, 1.5, 1, 11))\n\n\n\n\n\n\n\n\n\n\n4.5.1.4 Operation on several layers (ex: NDVI)\nIt is possible to calculate the value of a cell from its values stored in different layers of an object SpatRaster.\nPerhaps the most common example is the calculation of the Normalized Vegetation Index (NDVI). For each cell, a value is calculated from two layers of raster from a multispectral satellite image.\n\n# Import d'une image satellite multispectrale\nsentinel2a <- rast(\"data_cambodia/Sentinel2A.tif\")\n\nThis multispectral satellite image (10m resolution) dated 25/02/2020, was produced by Sentinel-2 satellite and was retrieved from plateforme Copernicus Open Access Hub. An extraction of Red and near infrared spectral bands, centered on the Phnom Penh city, was then carried out.\n\nplot(sentinel2a)\n\n\n\n\n\n\n\n\nTo lighten the code, we assign the two matrix layers in different SpatRaster objects.\n\nB04_Red <- sentinel2a[[1]] #spectral band Red\n\nB08_NIR <-sentinel2a[[2]] #spectral band near infrared\n\nFrom these two raster objects , we can calculate the normalized vegetation index:\n\\[{NDVI}=\\frac{\\mathrm{NIR} - \\mathrm{Red}} {\\mathrm{NIR} + \\mathrm{Red}}\\]\n\nraster_NDVI <- (B08_NIR - B04_Red ) / (B08_NIR + B04_Red )\n\nplot(raster_NDVI)\n\n\n\n\n\n\n\n\nThe higher the values (close to 1), the denser the vegetation.\n\n\n\n4.5.2 Focal operations\n\n\n\nSource : (Mennis 2015)\n\n\nFocal analysis conisders a cell plus its direct neighbors in contiguous and symmetrical (neighborhood operations). Most often, the value of the output cell is the result of a block of 3 x 3 (odd number) input cells.\nThe first step is to build a matrix that determines the block of cells that will be considered around each cell.\n\n# 5 x 5 matrix, where each cell has the same weight\nmon_focal <- matrix(1, nrow = 5, ncol = 5)\nmon_focal\n\n [,1] [,2] [,3] [,4] [,5]\n[1,] 1 1 1 1 1\n[2,] 1 1 1 1 1\n[3,] 1 1 1 1 1\n[4,] 1 1 1 1 1\n[5,] 1 1 1 1 1\n\n\nThe function focal() Then allows you to perform the desired analysis. For example: calculating the average of the values of all contiguous cells, for each cell in the raster.\n\nelevation_LowerGrid_mean <- focal(elevation_LowerGrid, \n w = mon_focal, \n fun = mean)\n\n\n\n\n\n\n\n\n\n\n\n4.5.2.1 Focal operations for elevation rasters\nThe function terrain() allows to perform focal analyzes specific to elevation rasters. Six operations are available:\n\nslope = calculation of the slope or degree of inclination of the surface;\n\naspect = calculate slope orientation;\n\nroughness = calculate of the variability or irregularity of the elevation;\n\nTPI = calculation of the index of topgraphic positions;\n\nTRI = elevation variability index calculation;\n\nflowdir = calculation of the water flow direction.\n\nExample with calculation of slopes(slope).\n\n#slope calculation\nslope <- terrain(elevation_utm, \"slope\", \n neighbors = 8, #8 (or 4) cells around taken into account\n unit = \"degrees\") #Output unit\n\nplot(slope) #Inclination of the slopes, in degrees\n\n\n\n\n\n\n\n\n\n\n\n4.5.3 Global operations\n\n\n\nSource : https://gisgeography.com/map-algebra-global-zonal-focal-local\n\n\nGlobal operation are used to summarize the matrix values of one or more matrices.\n\nglobal(elevation_utm, fun = \"mean\") #average values\n\n mean\nAltitude 80.01082\n\n\n\nglobal(elevation_utm, fun = \"sd\") #standard deviation\n\n sd\nAltitude 155.885\n\n\n\nfreq(lulc_2019_reclass) #frequency\n\n layer value count\n1 1 1 47485325\n2 1 2 13656289\n3 1 3 14880961\n4 1 4 37194979\n\ntable(lulc_2019_reclass[]) #contingency table\n\n\n 1 2 3 4 \n47485325 13656289 14880961 37194979 \n\n\nStatistical representations that summarize matrix information.\n\nhist(elevation_utm) #histogram\n\nWarning: [hist] a sample of3% of the cells was used\n\n\n\n\n\n\n\n\ndensity(elevation_utm) #density\n\n\n\n\n\n\n\n\n\n\n4.5.4 Zonal operation\n\n\n\nSource : (Mennis 2015)\n\n\nThe zonal operation make it possible to summarize the matrix values of certain zones (group of contiguous cells in space or in value).\n\n4.5.4.1 Zonal operation on an extraction\nAll global operations can be performed on an extraction of cells resulting from the functions crop(), mask(), segregate()…\nExample: average elevation for the city of Thma Bang district (cf partie 5.4.3).\n\n# Average value of the \"mask\" raster over Thma Bang district\nglobal(mask_thma_bang, fun = \"mean\", na.rm=TRUE)\n\n mean\nAltitude 584.7703\n\n\n\n\n4.5.4.2 Zonal operation from a vector layer\nThe function extract() allows you to extract and manipulate the values of cells that intersect vector data.\nExample from polygons:\n\n# Average elevation for each polygon (district)?\nelevation_by_dist <- extract(elevation_LowerGrid, district, fun=mean)\nhead(elevation_by_dist, 10)\n\n ID Altitude\n1 1 8.953352\n2 2 196.422240\n3 3 23.453937\n4 4 3.973118\n5 5 29.545801\n6 6 41.579593\n7 7 50.162749\n8 8 85.128777\n9 9 269.068091\n10 10 8.439041\n\n\n\n\n4.5.4.3 Zonal operation from raster\nZonal operation can be performed by area bounded by the categorical values of a second raster. For this, the two raster must have exaclty the same extent and the same resolution.\n\n#create a second raster with same resolution and extent as \"elevation_clip\"\nelevation_clip <- rast(\"data_cambodia/elevation_clip.tif\")\nelevation_clip_utm <- project(x = elevation_clip, y = \"EPSG:32648\", method = \"bilinear\")\nsecond_raster_CLC <- rast(elevation_clip_utm)\n\n#resampling of lulc_2019_reclass \nsecond_raster_CLC <- resample(lulc_2019_reclass, second_raster_CLC, method = \"near\") \n \n#added a variable name for the second raster\nnames(second_raster_CLC) <- \"lulc_2019_reclass_resample\"\n\n\n\n\n\n\n\n\n\n\nCalculation of the average elevation for the different areas of the second raster.\n\n#average elevation for each area of the \"second_raster\"\nzonal(elevation_clip_utm, second_raster_CLC , \"mean\", na.rm=TRUE)\n\n lulc_2019_reclass_resample elevation_clip\n1 1 12.83846\n2 2 8.31809\n3 3 11.41178\n4 4 11.93546"
- },
- {
- "objectID": "04-raster_data.html#transformation-and-conversion",
- "href": "04-raster_data.html#transformation-and-conversion",
- "title": "4Â Work with Raster Data",
- "section": "4.6 Transformation and conversion",
- "text": "4.6 Transformation and conversion\n\n4.6.1 Rasterization\nConvert polygons to raster format.\n\nchamkarmon = subset(district, district$ADM2_PCODE ==\"KH1201\") \nraster_district <- rasterize(x = chamkarmon, y = elevation_clip_utm)\n\n\nplot(raster_district)\n\n\n\n\n\n\n\n\nConvert points to raster format\n\n#rasterization of the centroids of the municipalities\nraster_dist_centroid <- rasterize(x = centroids(district), \n y = elevation_clip_utm, fun=sum)\nplot(raster_dist_centroid, col = \"red\")\nplot(district, add =TRUE)\n\n\n\n\nConvert lines in raster format\n\n#rasterization of municipal boundaries\nraster_dist_line <- rasterize(x = as.lines(district), y = elevation_clip_utm, fun=sum)\n\n\nplot(raster_dist_line)\n\n\n\n\n\n\n4.6.2 Vectorisation\nTransform a raster to vector polygons.\n\npolygon_elevation <- as.polygons(elevation_clip_utm)\n\n\nplot(polygon_elevation, y = 1, border=\"white\")\n\n\n\n\nTransform a raster to vector points.\n\npoints_elevation <- as.points(elevation_clip_utm)\n\n\nplot(points_elevation, y = 1, cex = 0.3)\n\n\n\n\nTransform a raster into vector lines.\n\nlines_elevation <- as.lines(elevation_clip_utm)\n\n\nplot(lines_elevation)\n\n\n\n\n\n\n4.6.3 terra, raster, sf, stars…\nReference packages for manipulating spatial data all rely o their own object class. It is sometimes necessary to convert these objects from one class to another class to take advance of all the features offered by these different packages.\nConversion functions for raster data:\n\n\n\nFROM/TO\nraster\nterra\nstars\n\n\n\n\nraster\n\nrast()\nst_as_stars()\n\n\nterra\nraster()\n\nst_as_stars()\n\n\nstars\nraster()\nas(x, ‘Raster’) + rast()\n\n\n\n\nConversion functions for vector data:\n\n\n\nFROM/TO\nsf\nsp\nterra\n\n\n\n\nsf\n\nas(x, ‘Spatial’)\nvect()\n\n\nsp\nst_as_sf()\n\nvect()\n\n\nterra\nst_as_sf()\nas(x, ‘Spatial’)\n\n\n\n\n\n\n\n\nHijmans, Robert J. 2022. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nLi, Xingong. 2009. “Map Algebra and Beyond : 1. Map Algebra for Scalar Fields.†https://slideplayer.com/slide/5822638/.\n\n\nMadelin, Malika. 2021. “Analyse d’images Raster (Et Télédétection).†https://mmadelin.github.io/sigr2021/SIGR2021_raster_MM.html.\n\n\nMennis, Jeremy. 2015. “Fundamentals of GIS : Raster Operations.†https://cupdf.com/document/gus-0262-fundamentals-of-gis-lecture-presentation-7-raster-operations-jeremy.html.\n\n\nNowosad, Jakub. 2021. “Image Processing and All Things Raster.†https://nowosad.github.io/SIGR2021/workshop2/workshop2.html.\n\n\nRacine, Etienne B. 2016. “The Visual Raster Cheat Sheet.†https://rpubs.com/etiennebr/visualraster.\n\n\nTomlin, C. Dana. 1990. Geographic Information Systems and Cartographic Modeling. Prentice Hall."
- },
- {
- "objectID": "05-mapping_with_r.html",
- "href": "05-mapping_with_r.html",
- "title": "5Â Mapping With R",
- "section": "",
- "text": "The fonction mf_map() is the central function of the package mapsf (Giraud 2022a). It makes it possible to carry out most of the usual representations in cartography. These main arguments are:\n\nx, an sf object ;\nvar, the name of variable to present ;\ntype, the type of presentation.\n\n\n\nThe following lines import the spatial information layers located in the geopackage cambodia.gpkg file.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n#Import roads data in Cambodia\nroad = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE)\n#Import health center data in Cambodia\nhospital = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE)\n\n\n\n\nWithout using types specification, the function mf_map() simply display the background map.\n\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = road, lwd = .5, col = \"ivory4\", add = TRUE)\nmf_map(x = hospital, pch = 20, cex = 1, col = \"#FE9A2E\", add = TRUE) \n\n\n\n\n\n\n\nProportional symbol maps are used to represent inventory variables (absolute quantitative variables, sum and average make sense). The function mf_map(..., type = \"prop\") proposes this representation.\n\n#District\nmf_map(x = district) \n\n# Proportional symbol \nmf_map(\n x = district, \n var = \"T_POP\",\n val_max = 700000,\n type = \"prop\",\n col = \"#148F77\", \n leg_title = \"Population 2019\"\n)\n\n# Title\nmf_title(\"Distribution of population in provincial level\")\n\n\n\n\n\n\nIt is possible to fix the dimensions of the largest symbol corresponding to a certain value with the arguments inches and val_max. We can use construct maps with comparable proportional symbols.\n\npar(mfrow = c(1,2)) #Displaying two maps facing each other\n\n#district\nmf_map(x = district, border = \"grey90\", lwd = .5) \n# Add male Population\nmf_map(\n x = district, \n var = \"Male\", \n type = \"prop\",\n col = \"#1F618D\",\n inches = 0.2, \n val_max = 300000, \n leg_title = \"Male\", \n leg_val_cex = 0.5,\n)\nmf_title(\"Male Population by Distict\") #Adding map title\n\n#district\nmf_map(x = district, border = \"grey90\", lwd = .5) \n# Add female Population\nmf_map(\n x = district, \n var = \"Female\", \n type = \"prop\",\n col = \"#E74C3C\",\n inches = 0.2, \n val_max = 300000, \n leg_title =\"Female\", \n leg_val_cex = 0.5\n)\nmf_title(\"Female Population by Distict\") #Adding map title\n\n\n\n\nHere we have displayed two maps facing each other, see the point Displaying several maps on the same figure for more details.\n\n\n\n\nChoropleth maps are used to represent ratio variables (relative quantitative variables, mean has meaning, sum has no meaning).\nFor this type of representation, you must first:\n\nchoose a discretization method to transform a continuous statistical series into classes defined by intervals,\nchoose a number of classes,\nchoose a color palette.\n\nThe function mf_map(…, type = “choroâ€)makes it possible to create choroplete maps. The arguments nbreaks and breaks are used to parameterize the discretizations, and the function mf_get_breaks() makes it possible to work on the discretizations outside the function mf_map(). Similarly, the argument palis used to fill in a color palette, but several functions can be used to set the palettes apart from the (mf_get_pal…) function.\n\n# Population density (inhabitants/km2) using the sf::st_area() function\ndistrict$DENS <- 1e6 * district$T_POP / as.numeric(st_area(district)) #Calculate population density \nmf_map(\n x = district,\n var = \"DENS\",\n type = \"choro\",\n breaks = \"quantile\",\n pal = \"BuGn\",\n lwd = 1,\n leg_title = \"Distribution of population\\n(inhabitants per km2)\", \n leg_val_rnd = 0\n)\nmf_title(\"Distribution of the population in (2019)\")\n\n\n\n\n\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\npopulation <- read.csv(\"data_cambodia/khm_admpop_adm2_2016_v2.csv\")\npopulation <- population[, c(\"ADM2_PCODE\", \"T_TL\")]\n# Remove commas\npopulation$T_TL <- as.numeric(gsub(\",\",\"\",population$T_TL))\ndistrict$cases <- lengths(st_intersects(district, cases))\ndistrict <- merge(district,\n population,\n by = \"ADM2_PCODE\")\ndistrict$incidence <- district$cases / district$T_TL * 100000\n\nmf_map(x = district,\n var = \"incidence\",\n type = \"choro\",\n leg_title = \"Incidence (per 100 000)\")\nmf_layout(title = \"Incidence of W Fever in Cambodia\")\n\n\n\n\n\n\nThe fonction mf_get_breaks() provides the methods of discretization of classic variables: quantiles, average/standard deviation, equal amplitudes, nested averages, Fisher-Jenks, geometric, etc.\n\neducation$enrol_g_pct = 100 * education$enrol_girl/education$t_enrol #Calculate percentage of enrolled girl student\n\nd1 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"equal\", freq = TRUE)\nd2 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"quantile\")\nd3 = mf_get_breaks(education$enrol_g_pct, nbreaks = 6, breaks = \"geom\")\nd4 = mf_get_breaks(education$enrol_g_pct, breaks = \"msd\", central = FALSE)\n\n\n\n\n\n\n\n\n\nThe argument pal de mf_map() is dedicated to choosing a color palette. The palettes provided by the function hcl.colors() can be used directly.\n\nmf_map(x = education, var = \"enrol_g_pct\", type = \"choro\",\n breaks = d3, pal = \"Reds 3\")\n\n\n\n\n\n\n\n\n\nThe fonction mf_get_pal() allows you to build a color palette. This function is especially useful for creating balanced asymmetrical diverging palettes.\n\nmypal <- mf_get_pal(n = c(4,6), palette = c(\"Burg\", \"Teal\"))\nimage(1:10, 1, as.matrix(1:10), col=mypal, xlab = \"\", ylab = \"\", xaxt = \"n\",\n yaxt = \"n\",bty = \"n\")\n\n\n\n\n\n\n\nIt is possible to use this mode of presentation in specific implementation also.\n\ndist_c <- st_centroid(district)\nmf_map(district)\nmf_map(\n x = dist_c,\n var = \"DENS\",\n type = \"choro\",\n breaks = \"quantile\",\n nbreaks = 5,\n pal = \"PuRd\",\n pch = 23,\n cex = 1.5,\n border = \"white\",\n lwd = .7,\n leg_pos = \"topleft\",\n leg_title = \"Distribution of population\\n(inhabitants per km2)\", \n leg_val_rnd = 0, \n add = TRUE\n)\nmf_title(\"Distribution of population in (2019)\")\n\n\n\n\n\n\n\n\nTypology maps are used to represent qualitative variables. The function mf_map(..., type = \"typo\") proposes this representation.\n\nmf_map(\n x = district,\n var=\"Status\",\n type = \"typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n lwd = .7,\n leg_title = \"\"\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\nThe argument val_order is used to order the categories in the\n\nmf_map(\n x = district,\n var=\"Status\",\n type = \"typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n val_order = c(\"1st largest district\", \"2nd largest district\", \"3rd largest district\",\"<4500km2\"),\n lwd = .7,\n leg_title = \"\"\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\n\nWhen the implantation of the layer is punctual, symbols are used to carry the colors of the typology.\n\n#extract centroid point of the district\ndist_ctr <- st_centroid(district[district$Status != \"<4500km2\", ])\nmf_map(district)\nmf_map(\n x = dist_ctr,\n var = \"Status\",\n type = \"typo\",\n cex = 2,\n pch = 22,\n pal = c('#FF7396','#E4BAD4','#FFE3FE'),\n leg_title = \"\",\n leg_pos = \"bottomright\",\n add = TRUE\n)\nmf_title(\"Administrative status by size of area\")\n\n\n\n\n\n\n\n\n#Selection of roads that intersect the city of Siem Reap\npp <- district[district$ADM1_EN == \"Phnom Penh\", ]\nroad_pp <- road[st_intersects(x = road, y = pp, sparse = FALSE), ]\nmf_map(pp)\nmf_map(\n x = road_pp,\n var = \"fclass\",\n type = \"typo\",\n lwd = 1.2,\n pal = mf_get_pal(n = 6, \"Tropic\"),\n leg_title = \"Types of road\",\n leg_pos = \"topright\",\n leg_frame = T,\n add = TRUE\n)\nmf_title(\"Administrative status\")\n\n\n\n\n\n\n\n\nThe function mf_map(..., var = c(\"var1\", \"var2\"), type = \"prop_choro\") represents proportional symbols whose areas are proportional to the values of one variable and whose color is based on the discretization of a second variable. The function uses the arguments of the functions mf_map(..., type = \"prop\") and mf_map(..., type = \"choro\").\n\nmf_map(x = district)\nmf_map(\n x = district,\n var = c(\"T_POP\", \"DENS\"),\n val_max = 500000,\n type = \"prop_choro\",\n border = \"grey60\",\n lwd = 0.5,\n leg_pos = c(\"bottomright\", \"bottomleft\"),\n leg_title = c(\"Population\", \"Density of\\n population\\n(inhabitants per km2)\"),\n breaks = \"q6\",\n pal = \"Blues 3\",\n leg_val_rnd = c(0,1))\nmf_title(\"Population\")\n\n\n\n\n\n\n\nThe function mf_map(..., var = c(\"var1\", \"var2\"), type = \"prop_typo\") represents proportional symbols whose areas are proportional to the values of one variable and whose color is based on the discretization of a second variable. The function uses the arguments of the mf_map(..., type = \"prop\") and function mf_map(..., type = \"typo\").\n\nmf_map(x = district)\nmf_map(\n x = district,\n var = c(\"Area.Km2.\", \"Status\"),\n type = \"prop_typo\",\n pal = c('#E8F9FD','#FF7396','#E4BAD4','#FFE3FE'),\n val_order = c(\"<4500km2\",\"1st largest district\", \"2nd largest district\", \"3rd largest district\"),\n leg_pos = c(\"bottomleft\",\"topleft\"),\n leg_title = c(\"Population\\n(2019)\",\n \"Statut administratif\"),\n)\nmf_title(\"Population\")"
- },
- {
- "objectID": "05-mapping_with_r.html#layout",
- "href": "05-mapping_with_r.html#layout",
- "title": "5Â Mapping With R",
- "section": "5.2 Layout",
- "text": "5.2 Layout\nTo be finalized, a thematic map must contain certain additional elements such as: title, author, source, scale, orientation…\n\n5.2.1 Example data\nThe following lines import the spatial information layers located in the geopackage lot46.gpkg file.\n\nlibrary(sf)\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE) #Import Cambodia country border\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE) #Import provincial administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE) #Import district administrative border of Cambodia\nroad = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"road\", quiet = TRUE) #Import roads data in Cambodia\nhospital = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"hospital\", quiet = TRUE) #Import hospital data in Cambodia\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE) #Import example data of fever_cases in Cambodia\n\n\n\n5.2.2 Themes\nThe function mf_theme() defines a cartographic theme. Using a theme allows you to define several graphic parameters which are then applied to the maps created with mapsf. These parameters are: the map margins, the main color, the background color, the position and the aspect of the title. A theme can also be defined with the mf_init() and function mf_export().\n\n5.2.2.1 Use a predefined theme\nA series of predefined themes are available by default (see ?mf_theme).\n\nlibrary(mapsf)\n# use of a background color for the figure, to see the use of margin\nopar <- par(mfrow = c(2,2))\n# Using a predefined theme\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"Theme : 'default'\")\n\nmf_theme(\"darkula\")\nmf_map(district)\nmf_title(\"Theme : 'darkula'\")\n\nmf_theme(\"candy\")\nmf_map(district)\nmf_title(\"Theme : 'candy'\")\n\nmf_theme(\"nevermind\")\nmf_map(district)\nmf_title(\"Theme : 'nevermind'\")\npar(opar)\n\n\n\n\n\n\n5.2.2.2 Modify an existing theme\nIt is possible to modify an existing theme. In this example, we are using the “default†theme and modifying a few settings.\n\nlibrary(mapsf)\nopar <- par(mfrow = c(1,2))\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"default\")\n\nmf_theme(\"default\", tab = FALSE, font = 4, bg = \"grey60\", pos = \"center\")\nmf_map(district)\nmf_title(\"modified default\")\npar(opar)\n\n\n\n\n\n\n5.2.2.3 Create a theme\nIt is also possible to create a theme.\n\nmf_theme(\n bg = \"lightblue\", # background color\n fg = \"tomato1\", # main color\n mar = c(1,0,1.5,0), # margin\n tab = FALSE, # \"tab\" style for the title\n inner = FALSE, # title inside or outside of map area\n line = 1.5, # space dedicated to title\n pos = \"center\", # heading position\n cex = 1.5, # title size\n font = 2 # font types for title\n)\nmf_map(district)\nmf_title(\"New theme\")\n\n\n\n\n\n\n\n5.2.3 Titles\nThe function mf_title() adds a title to a map.\n\nmf_theme(\"default\")\nmf_map(district)\nmf_title(\"Map title\")\n\n\n\n\nIt is possible to customize the appearance of the title\n\nmf_map(district)\nmf_title(\n txt = \"Map title\", \n pos = \"center\", \n tab = FALSE, \n bg = \"tomato3\", \n fg = \"lightblue\", \n cex = 1.5, \n line = 1.7, \n font = 1, \n inner = FALSE\n)\n\n\n\n\n\n\n5.2.4 Arrow orientation\nThe function mf_arrow() allows you to choose the position and aspect of orientation arrow.\n\nmf_map(district)\nmf_arrow()\n\n\n\n\n\n\n5.2.5 Scale\nThe function mf_scale() allows you to choose the position and the aspect of the scale.\n\nmf_map(district)\nmf_scale(\n size = 60,\n lwd = 1,\n cex = 0.7\n)\n\n\n\n\n\n\n5.2.6 Credits\nThe function mf_credits() displays a line of credits (sources, author, etc.).\n\nmf_map(district)\nmf_credits(\"IRD\\nInstitut Pasteur du Cambodge, 2022\")\n\n\n\n\n\n\n5.2.7 Complete dressing\nThe function mf_layout() displays all these elements.\n\nmf_map(district)\nmf_layout(\n title = \"Cambodia\",\n credits = \"IRD\\nInstitut Pasteur du Cambodge, 2022\",\n arrow = TRUE\n)\n\n\n\n\n\n\n5.2.8 Annotations\n\nmf_map(district)\nmf_annotation(district[district$ADM2_EN == \"Bakan\",], txt = \"Bakan\", col_txt = \"darkred\", halo = TRUE, cex = 1.5)\n\n\n\n\n\n\n5.2.9 Legends\n\nmf_map(district)\nmf_legend(\n type = \"prop\", \n val = c(1000,500,200,10), \n inches = .2, \n title = \"Population\", \n pos = \"topleft\"\n)\nmf_legend(\n type = \"choro\", \n val = c(0,10,20,30,40),\n pal = \"Greens\", \n pos = \"bottomright\", \n val_rnd = 0\n)\n\n\n\n\n\n\n5.2.10 Labels\nThe function mf_label() is dedicated to displaying labels.\n\ndist_selected <- district[st_intersects(district, district[district$ADM2_EN == \"Bakan\", ], sparse = F), ]\n\nmf_map(dist_selected)\nmf_label(\n x = dist_selected,\n var = \"ADM2_EN\",\n col= \"darkgreen\",\n halo = TRUE,\n overlap = FALSE, \n lines = FALSE\n)\nmf_scale()\n\n\n\n\nThe argument halo = TRUE allows to display a slight halo around the labels and the argument overlap = FALSE allows to create non-overlapping labels.\n\n\n5.2.11 Center the map on a region\nThe function mf_init() allows you to initialize a map by centering it on a spatial object.\n\nmf_init(x = dist_selected)\nmf_map(district, add = TRUE)\nmf_map(dist_selected, col = NA, border = \"#29a3a3\", lwd = 2, add = TRUE)\n\n\n\n\n\n\n5.2.12 Displaying several maps on the sam figure\nHere you have to use mfrow of the function par(). The first digit represents the number of of rows and second the number of columns.\n\n# define the figure layout (1 row, 2 columns)\npar(mfrow = c(1, 2))\n\n# first map\nmf_map(district)\nmf_map(district, \"Male\", \"prop\", val_max = 300000)\nmf_title(\"Population, male\")\n\n# second map\nmf_map(district)\nmf_map(district, \"Female\", \"prop\", val_max = 300000)\nmf_title(\"Population, female\")\n\n\n\n\n\n\n5.2.13 Exporting maps\nIt is quite difficult to export figures (maps or others) whose height/width ratio is satisfactory. The default ratio of figures in png format is 1 (480x480 pixels):\n\ndist_filter <- district[district$ADM2_PCODE == \"KH0808\", ]\npng(\"img/dist_filter_1.png\")\nmf_map(dist_filter)\nmf_title(\"Filtered district\")\ndev.off()\n\n\n\n\n\n\nOn this map a lot of space is lost to the left and right of the district.\nThe function mf_export() allows exports of maps whose height/width ratio is controlled and corresponds to that of a spatial object.\n\nmf_export(dist_filter, \"img/dist_filter_2.png\", width = 480)\nmf_map(dist_filter)\nmf_title(\"Filtered district\")\ndev.off()\n\n\n\n\n\n\nThe extent of this map is exactly that of the displayed region.\n\n\n5.2.14 Adding an image to a map\nThis can be useful for adding a logo, a pictograph. The function readPNG() of package png allows the additional images on the figure.\n\nmf_theme(\"default\", mar = c(0,0,0,0))\nlibrary(png)\n\nlogo <- readPNG(\"img/ird_logo.png\") #Import image\npp <- dim(logo)[2:1]*200 #Image dimension in map unit (width and height of the original image)\n\n#The upper left corner of the department's bounding box\nxy <- st_bbox(district)[c(1,4)]\nmf_map(district, col = \"#D1914D\", border = \"white\")\nrasterImage(\n image = logo,\n xleft = xy[1] ,\n ybottom = xy[2] - pp[2],\n xright = xy[1] + pp[1],\n ytop = xy[2]\n)\n\n\n\n\n\n\n5.2.15 Place an item precisely on the map\nThe function locator() allows clicking on the figure and obtaining the coordinate of a point in the coordinate system of the figure (of the map).\n\n# locator(1) # click to get coordinate on map\n# points(locator(1)) # click to plot point on map\n# text(locator(1), # click to place the item on map\n# labels =\"Located any texts on map\", \n# adj = c(0,0))\n\n\nVideo\nlocator()peut être utilisée sur la plupart des graphiques (pas ceux produits avec ggplot2).\n\n\n\n\n\n\nHow to interactively position legends and layout elements on a map with cartography\n\n\n\n\n\n5.2.16 Add shading to a layer\nThe function mf_shadow() allows to create a shadow to a layer of polygons.\n\nmf_shadow(district)\nmf_map(district, add=TRUE)\n\n\n\n\n\n\n5.2.17 Creating Boxes\nThe function mf_inset_on() allows to start creation a box. You must then “close†the box with mf_inset_off().\n\nmf_init(x = dist_selected, theme = \"agolalight\", expandBB = c(0,.1,0,.5)) \nmf_map(district, add = TRUE)\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = 2, add = TRUE)\n\n# Cambodia inset box\nmf_inset_on(x = country, pos = \"topright\", cex = .3)\nmf_map(country, lwd = .5, border= \"grey90\")\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = .5, add = TRUE)\nmf_scale(size = 100, pos = \"bottomleft\", cex = .6, lwd = .5)\nmf_inset_off()\n\n# District inset box\nmf_inset_on(x = district, pos = \"bottomright\", cex = .3)\nmf_map(district, lwd = 0.5, border= \"grey90\")\nmf_map(dist_selected, col = \"tomato4\", border = \"tomato1\", lwd = .5, add = TRUE)\nmf_scale(size = 100, pos = \"bottomright\", cex = .6, lwd = .5)\nmf_inset_off()\n\n# World inset box\nmf_inset_on(x = \"worldmap\", pos = \"topleft\")\nmf_worldmap(dist_selected, land_col = \"#cccccc\", border_col = NA, \n water_col = \"#e3e3e3\", col = \"tomato4\")\n\nmf_inset_off()\nmf_title(\"Bakan district and its surroundings\")\nmf_scale(10, pos = 'bottomleft')"
- },
- {
- "objectID": "05-mapping_with_r.html#d-maps",
- "href": "05-mapping_with_r.html#d-maps",
- "title": "5Â Mapping With R",
- "section": "5.3 3D maps",
- "text": "5.3 3D maps\n\n5.3.1 linemap\nThe package linemap (Giraud 2021) allows you to make maps made up of lines.\n\nlibrary(linemap)\nlibrary(mapsf)\nlibrary(sf)\nlibrary(dplyr)\n\npp = st_read(\"data_cambodia/PP.gpkg\", quiet = TRUE) # import Phnom Penh administrative border\npp_pop_dens <- getgrid(x = pp, cellsize =1000, var = \"DENs\") # create population density in grid format (pop density/1km)\n\nmf_init(pp)\n\nlinemap(\n x = pp_pop_dens, \n var = \"DENs\",\n k = 1,\n threshold = 5, \n lwd = 1,\n col = \"ivory1\",\n border = \"ivory4\",\n add = T)\n\nmf_title(\"Phnom Penh Population Density, 2019\")\nmf_credits(\"Humanitarian Data Exchange, 2022\\nunit data:km2\")\n\n\n\n# url = \"https://data.humdata.org/dataset/1803994d-6218-4b98-ac3a-30c7f85c6dbc/resource/f30b0f4b-1c40-45f3-986d-2820375ea8dd/download/health_facility.zip\"\n# health_facility.zip = \"health_facility.zip\"\n# download.file(url, destfile = health_facility.zip)\n# unzip(health_facility.zip) # Unzipped files are in a new folder named Health\n# list.files(path=\"Health\")\n\n\n\n5.3.2 Relief Tanaka\nWe use the tanaka package (Giraud 2022b) which provides a method (Tanaka 1950) used to improve the perception of relief.\n\nlibrary(tanaka)\nlibrary(terra)\n\nrpop <- rast(\"data_cambodia/khm_pd_2019_1km_utm.tif\") # Import population raster data (in UTM)\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE) # Import Cambodian districts layer\ndistrict <- st_transform(district, st_crs(rpop)) # Transform data into the same coordinate system\n\nmat <- focalMat(x = rpop, d = c(1500), type = \"Gauss\") # Raster smoothing\nrpopl <- focal(x = rpop, w = mat, fun = sum, na.rm = TRUE)\n\n# Mapping\ncols <- hcl.colors(8, \"Reds\", alpha = 1, rev = T)[-1]\nmf_theme(\"agolalight\")\nmf_init(district)\ntanaka(x = rpop, breaks = c(0,10,25,50,100,250,500,64265),\n col = cols, add = T, mask = district, legend.pos = \"n\")\nmf_legend(type = \"choro\", pos = \"bottomright\", \n val = c(0,10,25,50,100,250,500,64265), pal = cols,\n bg = \"#EDF4F5\", fg = NA, frame = T, val_rnd = 0,\n title = \"Population\\nper km2\")\nmf_title(\"Population density of Cambodia, 2019\")\nmf_credits(\"Humanitarian Data Exchange, 2022\",\n bg = \"#EDF4F5\")\n\n\n\n\n\n\n\n\n\n\nThe tanaka package"
- },
- {
- "objectID": "05-mapping_with_r.html#cartographic-transformation",
- "href": "05-mapping_with_r.html#cartographic-transformation",
- "title": "5Â Mapping With R",
- "section": "5.4 Cartographic Transformation",
- "text": "5.4 Cartographic Transformation\n\nclassical anamorphosis is a representation of States(or any cells) by rectangle or any polygons according to a quantities attached to them. (…) We strive to keep the general arrangement of meshes or the silhouette of the continent.â€\nBrunet, Ferras, and Théry (1993)\n\n3 types of anamorphoses or cartograms are presented here:\n\nDorling’s cartograms (Dorling 1996)\nNon-contiguous cartograms (Olson 1976)\nContiguous cartograms (Dougenik, Chrisman, and Niemeyer 1985)\n\n\n\n\n\n\n\nA comprehensive course on anamorphoses : Les anamorphoses cartographiques (Lambert 2015).\n\n\n\n\n\n\n\n\n\nMake cartograms with R\n\n\n\nTo make the cartograms we use the package cartogram (Jeworutzki 2020).\n\n5.4.1 Dorling’s cartograms\nThe territories are represented by figures (circles, squares or rectangles) which do not overlap, the surface of which are proportional to a variable. The proportion of the figures are defined according to the starting positions.\n\n\n\n\n\n\n\n\nSpace is quite poorly identified.\nYou can name the circles to get your bearings and/or use the color to make clusters appear and better identify the geographical blocks.\n\n\n\n\n\nThe perception of quantities is very good. The circle sizes are really comarable.\n\n\n\nlibrary(mapsf)\nlibrary(cartogram)\ndistrict <- st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\" , quiet = TRUE)\ndist_dorling <- cartogram_dorling(x = district, weight = \"T_POP\", k = 0.7)\nmf_map(dist_dorling, col = \"#40E0D0\", border= \"white\")\nmf_label(\n x = dist_dorling[order(dist_dorling$T_POP, decreasing = TRUE), ][1:10,], \n var = \"ADM2_EN\",\n overlap = FALSE, \n # show.lines = FALSE,\n halo = TRUE, \n r = 0.15\n)\nmf_title(\"Population of District - Dorling Cartogram\")\n\n\n\n\nThe parameter k allows to vary the expansion factor of the circles.\n\n\n5.4.2 Non-continuous cartograms\nThe size of the polygons is proportional to a variable. The arrangement of the polygons relative to each other is preserved. The shape of the polygons is similar.\n\n\n\n\n\n(Cauvin, Escobar, and Serradj 2013)\n\n\n\nThe topology of the regions is lost.\n\n\n\n\n\nThe converstion of the polygons shape is optimal.\n\n\n\ndist_ncont <- cartogram_ncont(x = district, weight = \"T_POP\", k = 1.2)\nmf_map(district, col = NA, border = \"#FDFEFE\", lwd = 1.5)\nmf_map(dist_ncont, col = \"#20B2AA\", border= \"white\", add = TRUE)\nmf_title(\"Population of District - Non-continuous cartograms\")\n\n\n\n\nThe parameter k allows to vary the expansion of the polygons.\n\n\n5.4.3 Continuous cartograms\nThe size of the polygons is proportional to variable. The arrangement of the polygons relative to each other is preserved. To maintain contiguity, the sape of the polygons is heavily transformed.\n\n\n\n\n\n(Paull and Hennig 2016)\n\n\n\nThe shape of the polygond is strongly distorted.\n\n\n\n\n\nIt is a “real geographical mapâ€: topology and contiguity are preserved.\n\n\n\ndist_ncont <- cartogram_cont(x = district, weight = \"DENs\", maxSizeError = 6)\n\nMean size error for iteration 1: 15.8686749410166\n\n\nMean size error for iteration 2: 12.1107731631101\n\n\nMean size error for iteration 3: 9.98940057337996\n\n\nMean size error for iteration 4: 8.62323208787643\n\n\nMean size error for iteration 5: 7.60706404894655\n\n\nMean size error for iteration 6: 6.83561617758241\n\n\nMean size error for iteration 7: 10.1399490743501\n\n\nMean size error for iteration 8: 5.79418495291592\n\nmf_map(dist_ncont, col = \"#66CDAA\", border= \"white\", add = FALSE)\nmf_title(\"Population of District - Continuous cartograms\")\nmf_inset_on(district, cex = .2, pos = \"bottomleft\")\nmf_map(district, lwd = .5)\nmf_inset_off()\n\n\n\n\n\n\n5.4.4 Stengths and weaknessses of cartograms\ncartograms are cartographic representations perceived as innovative (although the method is 40 years old). These very generalize images capture quantities and gradients well. These are real communication images that provoke, arouse interest, convey a strong message, challenge.\nBut cartograms induce a loss of visual cues (difficult to find one’s country or region on the map), require a reading effort which can be significant and do not make it possible to manage missing data.\n\n\n\n\nBrunet, Roger, Robert Ferras, and Hervé Théry. 1993. Les Mots de La géographie: Dictionnaire Critique. 03) 911 BRU.\n\n\nCauvin, Colette, Francisco Escobar, and Aziz Serradj. 2013. Thematic Cartography, Cartography and the Impact of the Quantitative Revolution. Vol. 2. John Wiley & Sons.\n\n\nDorling, Daniel. 1996. Area Cartograms: Their Use and Creation, Concepts and Techniques in Modern Geography. Vol. 59. CATMOG: Concepts and Techniques in Modern Geography. Institute of British Geographers.\n\n\nDougenik, James A, Nicholas R Chrisman, and Duane R Niemeyer. 1985. “An Algorithm to Construct Continuous Area Cartograms.†The Professional Geographer 37 (1): 75–81.\n\n\nGiraud, Timothée. 2021. “Linemap: Line Maps.†https://CRAN.R-project.org/package=linemap.\n\n\n———. 2022a. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\n———. 2022b. “Tanaka: Design Shaded Contour Lines (or Tanaka) Maps.†https://CRAN.R-project.org/package=tanaka.\n\n\nJeworutzki, Sebastian. 2020. “Cartogram: Create Cartograms with r.†https://CRAN.R-project.org/package=cartogram.\n\n\nLambert, Nicolas. 2015. “Les Anamorphoses Cartographiques.†Blog. Carnet Néocartographique. https://neocarto.hypotheses.org/366.\n\n\nOlson, Judy M. 1976. “Noncontiguous Area Cartograms.†The Professional Geographer 28 (4): 371–80.\n\n\nPaull, John, and Benjamin Hennig. 2016. “Atlas of Organics: Four Maps of the World of Organic Agriculture.†Journal of Organics 3 (1): 25–32.\n\n\nTanaka, Kitiro. 1950. “The Relief Contour Method of Representing Topography on Maps.†Geographical Review 40 (3): 444. https://doi.org/10.2307/211219."
- },
- {
- "objectID": "06-advanced_spatial_analysis.html",
- "href": "06-advanced_spatial_analysis.html",
- "title": "6Â Advanced Spatial Analysis",
- "section": "",
- "text": "RGeoHealth (Herbreteau, Révillion, and Trimaille 2018)\n\n# remotes::install_git(\"https://framagit.org/espace-dev/geohealth/RGeoHealth\")\n# library(geohealth)\n\n\n\n\n\nHerbreteau, Vincent, Christophe Révillion, and Etienne Trimaille. 2018. “GeoHealth and QuickOSM, two QGIS plugins for health applications.†In Earth Systems - Environmental Sciences : QGIS in Remote Sensing Set, edited by Nicolas Baghdadi, Clément Mallet, and Mehrez Zribi, 1:257–86. QGIS and Generic Tools. ISTE. https://hal.archives-ouvertes.fr/hal-01787435."
- },
- {
- "objectID": "07-basic_statistics.html",
- "href": "07-basic_statistics.html",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "",
- "text": "This section aims at providing some basic statistical tools to study the spatial distribution of the cases."
- },
- {
- "objectID": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "href": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.1 Import and visualize epidemiological data",
- "text": "7.1 Import and visualize epidemiological data\nIn this section, we load data that reference the cases of an imaginary disease throughout Cambodia.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n\n# Import locations of cases from an imaginary disease\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\n\n# Aggregate cases over districts\ndistrict$cases <- lengths(st_intersects(district, cases))\n\nThe first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.\n\n# View the cases object\nhead(cases)\n\nSimple feature collection with 6 features and 2 fields\nGeometry type: MULTIPOINT\nDimension: XY\nBounding box: xmin: 255891 ymin: 1179092 xmax: 506647.4 ymax: 1467441\nProjected CRS: WGS 84 / UTM zone 48N\n id Disease geom\n1 0 W fever MULTIPOINT ((280036.2 12841...\n2 1 W fever MULTIPOINT ((451859.5 11790...\n3 2 W fever MULTIPOINT ((255891 1467441))\n4 5 W fever MULTIPOINT ((506647.4 12322...\n5 6 W fever MULTIPOINT ((440668 1197958))\n6 7 W fever MULTIPOINT ((481594.5 12714...\n\n# Map the cases\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = cases, lwd = .5, col = \"#990000\", pch = 20, add = TRUE)"
- },
- {
- "objectID": "07-basic_statistics.html#basics-statistics",
- "href": "07-basic_statistics.html#basics-statistics",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.2 Basics statistics",
- "text": "7.2 Basics statistics\nThe problem is usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nThe statistical analysis performed relies on the type of data.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test.\nMoran’s I test tells us whether nearby units tend to exhibit similar rates. It ranges from -1 to +1, whith a value of -1 denoting that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nWe will compute the Moran’s statistics using spdep and Dcluster packages. This package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n# Compte incidence in each district (per 100 000 population)\ndistrict$incidence <- district$cases/district$T_POP * 100000\n\n# Plot the incidence histogramm\nhist(log(district$incidence))"
- },
- {
- "objectID": "07-basic_statistics.html#cluster-analysis",
- "href": "07-basic_statistics.html#cluster-analysis",
- "title": "7Â Basic statistics for spatial analysis",
-<<<<<<< HEAD
- "section": "7.2 Cluster analysis",
- "text": "7.2 Cluster analysis\nSince this W fever seems to have a heterogeneous distribution across Cambodia, it would be interesting to study where excess of cases appears, i.e. to identify clusters of the disease. The first question is to wonder if data are auto correlated or spatially independent, i.e. study if neighboring districts are likely to have similar incidence.\nIn statistics, problems are usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nHere the statistics hypothesis are :\n\nH0 :\nH1: , i.e. Moran’s I value is different than 0.\n\nWe will compute the Moran’s statistics using spdep and Dcluster packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\nlibrary(spdep) # Functions for creating spatial weight, spatial analysis\nlibrary(DCluster) # Package with functions for spatial cluster analysis)\n\nqnb <- poly2nb(district)\nq_listw <- nb2listw(qnb, style = 'W') # row-standardized weights\n\n# Moran's I test\nmoranI.test(cases ~ offset(log(expected)), \n data = district,\n model = 'poisson',\n R = 499,\n listw = q_listw,\n n = 159,\n S0 = Szero(q_listw))\n\nMoran's I test of spatial autocorrelation \n\n Type of boots.: parametric \n Model used when sampling: Poisson \n Number of simulations: 499 \n Statistic: 0.1264291 \n p-value : 0.016 \n\n\n\n\n7.2.2 Spatial scan statistics\nWhile Moran’s indice focuses on finding correlation between neighboring polygons, the spatial scan statistic compare the incidence level of a given windows of observation with the incidence level outside of this windows.\nThe package SpatialEpi\n\n\n7.2.3 Population-based clusters (kulldorf statistic)\nKulldorff ’s spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.\n\n\n7.2.4 Expectation-based cluster\nIn many case, population is not specific enough to\n\n\n7.2.5 To go further …"
-=======
- "section": "7.3 Cluster analysis",
- "text": "7.3 Cluster analysis\nIn epidemiology, the definition of a cluster\n\n7.3.1 Population-based clusters (kulldorf statistic)\nKulldorff ’s spatial scan statistic identifies the most likely disease clusters maximizing the likelihood that disease cases are located within a set of concentric circles that are moved across the study area.\n\n\n7.3.2 Expectation-based cluster\nIn many case, population is not specific enough to\n\n\n7.3.3 To go further …"
->>>>>>> refs/remotes/origin/main
- },
- {
- "objectID": "references.html",
- "href": "references.html",
- "title": "References",
- "section": "",
-<<<<<<< HEAD
- "text": "This section aims at providing some basic statistical tools to study the spatial distribution of epidemiological data."
- },
- {
- "objectID": "07-basic_statistics.html#basics-statistics",
- "href": "07-basic_statistics.html#basics-statistics",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.2 Basics statistics",
- "text": "7.2 Basics statistics\nThe problem is usually expressed by defining two hypothesis : the null hypothesis (H0), i.e. an a priori hypothesis of the studied phenomenon (e.g. the situation is a random) and the alternative hypothesis (HA), e.g. the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nThe statistical analysis performed relies on the type of data.\n\n7.2.1 Spatial autocorrelation (Moran’s I test)\nA popular test for spatial autocorrelation is the Moran’s test.\nMoran’s I test tells us whether nearby units tend to exhibit similar rates. It ranges from -1 to +1, whith a value of -1 denoting that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\nWe will compute the Moran’s statistics using spdep and Dcluster packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n# Plot the incidence histogramm\nhist(log(district$incidence))"
- },
- {
- "objectID": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "href": "07-basic_statistics.html#import-and-visualize-epidemiological-data",
- "title": "7Â Basic statistics for spatial analysis",
- "section": "7.1 Import and visualize epidemiological data",
- "text": "7.1 Import and visualize epidemiological data\nIn this section, we load data that reference the cases of an imaginary disease throughout Cambodia. Each point correspond to the geolocalisation of a case.\n\nlibrary(sf)\n\n#Import Cambodia country border\ncountry = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"country\", quiet = TRUE)\n#Import provincial administrative border of Cambodia\neducation = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"education\", quiet = TRUE)\n#Import district administrative border of Cambodia\ndistrict = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"district\", quiet = TRUE)\n\n# Import locations of cases from an imaginary disease\ncases = st_read(\"data_cambodia/cambodia.gpkg\", layer = \"cases\", quiet = TRUE)\ncases = subset(cases, Disease == \"W fever\")\n\nThe first step of any statistical analysis always consists on visualizing the data to check they were correctly loaded and to observe general pattern of the cases.\n\n# View the cases object\nhead(cases)\n\nSimple feature collection with 6 features and 2 fields\nGeometry type: MULTIPOINT\nDimension: XY\nBounding box: xmin: 255891 ymin: 1179092 xmax: 506647.4 ymax: 1467441\nProjected CRS: WGS 84 / UTM zone 48N\n id Disease geom\n1 0 W fever MULTIPOINT ((280036.2 12841...\n2 1 W fever MULTIPOINT ((451859.5 11790...\n3 2 W fever MULTIPOINT ((255891 1467441))\n4 5 W fever MULTIPOINT ((506647.4 12322...\n5 6 W fever MULTIPOINT ((440668 1197958))\n6 7 W fever MULTIPOINT ((481594.5 12714...\n\n# Map the cases\nlibrary(mapsf)\n\nmf_map(x = district, border = \"white\")\nmf_map(x = country,lwd = 2, col = NA, add = TRUE)\nmf_map(x = cases, lwd = .5, col = \"#990000\", pch = 20, add = TRUE)\n\n\n\n\nIn epidemiology, the true meaning of point is very questionable. If it usually gives the location of an observation, its not clear if this observation represents an event of interest (e.g. illness, death, …) or a person at risk (e.g. a participant that may or may not experience the disease). Considering a ratio of event compared to a population at risk is often more informative than just considering cases. Administrative divisions of countries appears as great areal units for cases aggregation since they make available data on population count and structures. In this study, we will use district as the areal unit of the study.\n\n# Aggregate cases over districts\ndistrict$cases <- lengths(st_intersects(district, cases))\n\nThe incidence (\\(\\frac{cases}{population}\\)) is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represents the deviation of observed and expected number of cases and is expressed as \\(SIR = \\frac{Y_i}{E_i}\\) with \\(Y_i\\), the observed number of cases and \\(E_i\\), the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e. the incidence is the same in each district.\n\n# Compute incidence in each district (per 100 000 population)\ndistrict$incidence = district$cases/district$T_POP * 100000\n\n# Compute the global risk\nrate = sum(district$cases)/sum(district$T_POP)\n\n# Compute expected number of cases \ndistrict$expected = district$T_POP * rate\n\n# Compute SIR\ndistrict$SIR = district$cases / district$expected\n\n\npar(mfrow = c(1, 3))\n# Plot number of cases using proportional symbol \nmf_map(x = district) \nmf_map(\n x = district, \n var = \"cases\",\n val_max = 50,\n type = \"prop\",\n col = \"#990000\", \n leg_title = \"Cases\")\nmf_layout(title = \"Number of cases of W Fever\")\n\n# Plot incidence \nmf_map(x = district,\n var = \"incidence\",\n type = \"choro\",\n pal = \"Reds 3\",\n leg_title = \"Incidence \\n(per 100 000)\")\nmf_layout(title = \"Incidence of W Fever\")\n\n# Plot SIRs\n# create breaks and associated color palette\nbreak_SIR = c(0, exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = \"pretty\")))\ncol_pal = c(\"#273871\", \"#3267AD\", \"#6496C8\", \"#9BBFDD\", \"#CDE3F0\", \"#FFCEBC\", \"#FF967E\", \"#F64D41\", \"#B90E36\")\n\nmf_map(x = district,\n var = \"SIR\",\n type = \"choro\",\n breaks = break_SIR, \n pal = col_pal, \n cex = 2,\n leg_title = \"SIR\")\nmf_layout(title = \"Standardized Incidence Ratio of W Fever\")\n\n\n\n\nThese maps illustrates the spatial heterogenity of the cases. The incidence shows how the disease vary from one district to another while the SIR highlight districts that have :\n\nhigher risk than average (SIR > 1) when standardized for population\nlower risk than average (SIR < 1) when standardized for population\naverage risk (SIR ~ 1) when standardized for population\n\nIn this example, we standardized the cases distribution for population count. This simple standardization assume that the risk of contracting the disease is similar for each person. However, assumption does not hold for all diseases and for all observed events since confounding effects can create nuisance into the interpretations (e.g. the number of childhood illness and death outcomes in a district are usually related to the age pyramid) and you should keep in mind that other standardization can be performed based on variables known to have an effect but that you don’t want to analyze (e.g. sex ratio, occupations, age pyramid)."
-=======
- "text": "Agafonkin, Vladimir. 2015. “Leaflet Javascript Libary.â€\n\n\nAppelhans, Tim, Florian Detsch, Christoph Reudenbach, and Stefan\nWoellauer. 2022. “Mapview: Interactive Viewing of Spatial Data in\nr.†https://CRAN.R-project.org/package=mapview.\n\n\nAppelhans, Tim, Kenton Russell, and Lorenzo Busetto. 2020.\n“Mapedit: Interactive Editing of Spatial Data in r.†https://CRAN.R-project.org/package=mapedit.\n\n\nBivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. “Rgdal:\nBindings for the ’Geospatial’ Data Abstraction Library.†https://CRAN.R-project.org/package=rgdal.\n\n\nBivand, Roger, and Colin Rundel. 2021. “Rgeos: Interface to\nGeometry Engine - Open Source (’GEOS’).†https://CRAN.R-project.org/package=rgeos.\n\n\nBrunet, Roger, Robert Ferras, and Hervé Théry. 1993. Les Mots de La\ngéographie: Dictionnaire Critique. 03) 911 BRU.\n\n\nCambon, Jesse, Diego Hernangómez, Christopher Belanger, and Daniel\nPossenriede. 2021. “Tidygeocoder: An r Package for\nGeocoding†6: 3544. https://doi.org/10.21105/joss.03544.\n\n\nCauvin, Colette, Francisco Escobar, and Aziz Serradj. 2013. Thematic\nCartography, Cartography and the Impact of the Quantitative\nRevolution. Vol. 2. John Wiley & Sons.\n\n\nCheng, Joe, Bhaskar Karambelkar, and Yihui Xie. 2022. “Leaflet:\nCreate Interactive Web Maps with the JavaScript ’Leaflet’\nLibrary.†https://CRAN.R-project.org/package=leaflet.\n\n\nDorling, Daniel. 1996. Area Cartograms: Their Use and Creation,\nConcepts and Techniques in Modern Geography. Vol. 59. CATMOG:\nConcepts and Techniques in Modern Geography. Institute of British\nGeographers.\n\n\nDougenik, James A, Nicholas R Chrisman, and Duane R Niemeyer. 1985.\n“An Algorithm to Construct Continuous Area Cartograms.â€\nThe Professional Geographer 37 (1): 75–81.\n\n\nDunnington, Dewey. 2021. “Ggspatial: Spatial Data Framework for\nGgplot2.†https://CRAN.R-project.org/package=ggspatial.\n\n\nGDAL/OGR contributors. n.d. GDAL/OGR Geospatial Data\nAbstraction Software Library. Open Source Geospatial Foundation. https://gdal.org.\n\n\nGilardi, Andrea, and Robin Lovelace. 2021. “Osmextract: Download\nand Import Open Street Map Data Extracts.†https://CRAN.R-project.org/package=osmextract.\n\n\nGiraud, Timothée. 2021a. “Linemap: Line Maps.†https://CRAN.R-project.org/package=linemap.\n\n\n———. 2021b. “Maptiles: Download and Display Map Tiles.†https://CRAN.R-project.org/package=maptiles.\n\n\n———. 2022a. “Mapsf: Thematic Cartography.†https://CRAN.R-project.org/package=mapsf.\n\n\n———. 2022b. “Tanaka: Design Shaded Contour Lines (or Tanaka)\nMaps.†https://CRAN.R-project.org/package=tanaka.\n\n\nGiraud, Timothée, and Nicolas Lambert. 2016. “Cartography: Create\nand Integrate Maps in Your r Workflow†1. https://doi.org/10.21105/joss.00054.\n\n\nGombin, Joel, and Paul-Antoine Chevalier. 2022. “banR: R Client\nfor the BAN API.â€\n\n\nHerbreteau, Vincent, Christophe Révillion, and Etienne Trimaille. 2018.\n“GeoHealth and QuickOSM, two QGIS plugins for\nhealth applications.†In Earth\nSystems - Environmental Sciences : QGIS in Remote Sensing\nSet, edited by Nicolas Baghdadi, Clément Mallet, and Mehrez\nZribi, 1:257–86. QGIS and Generic Tools. ISTE. https://hal.archives-ouvertes.fr/hal-01787435.\n\n\nHijmans, Robert J. 2022a. “Raster: Geographic Data Analysis and\nModeling.†https://CRAN.R-project.org/package=raster.\n\n\n———. 2022b. “Terra: Spatial Data Analysis.†https://CRAN.R-project.org/package=terra.\n\n\nJeworutzki, Sebastian. 2020. “Cartogram: Create Cartograms with\nr.†https://CRAN.R-project.org/package=cartogram.\n\n\nLambert, Nicolas. 2015. “Les Anamorphoses Cartographiques.â€\nBlog. Carnet Néocartographique. https://neocarto.hypotheses.org/366.\n\n\nLi, Xingong. 2009. “Map Algebra and Beyond : 1. Map Algebra for\nScalar Fields.†https://slideplayer.com/slide/5822638/.\n\n\nMadelin, Malika. 2021. “Analyse d’images Raster (Et\nTélédétection).†https://mmadelin.github.io/sigr2021/SIGR2021_raster_MM.html.\n\n\nMennis, Jeremy. 2015. “Fundamentals of GIS : Raster\nOperations.†https://cupdf.com/document/gus-0262-fundamentals-of-gis-lecture-presentation-7-raster-operations-jeremy.html.\n\n\nNowosad, Jakub. 2021. “Image Processing and All Things\nRaster.†https://nowosad.github.io/SIGR2021/workshop2/workshop2.html.\n\n\nOlson, Judy M. 1976. “Noncontiguous Area Cartograms.â€\nThe Professional Geographer 28 (4): 371–80.\n\n\nPadgham, Mark, Bob Rudis, Robin Lovelace, and Maëlle Salmon. 2017.\n“Osmdata†2. https://doi.org/10.21105/joss.00305.\n\n\nPaull, John, and Benjamin Hennig. 2016. “Atlas of Organics: Four\nMaps of the World of Organic Agriculture.†Journal of\nOrganics 3 (1): 25–32.\n\n\nPebesma, Edzer. 2018b. “Simple Features for r:\nStandardized Support for Spatial Vector Data†10. https://doi.org/10.32614/RJ-2018-009.\n\n\n———. 2018a. “Simple Features for R: Standardized Support for\nSpatial Vector Data.†The R Journal 10 (1): 439. https://doi.org/10.32614/rj-2018-009.\n\n\n———. 2021. “Stars: Spatiotemporal Arrays, Raster and Vector Data\nCubes.†https://CRAN.R-project.org/package=stars.\n\n\nPebesma, Edzer J., and Roger S. Bivand. 2005. “Classes and Methods\nfor Spatial Data in r†5. https://CRAN.R-project.org/doc/Rnews/.\n\n\nPROJ contributors. 2021. PROJ Coordinate Transformation\nSoftware Library. Open Source Geospatial Foundation. https://proj.org/.\n\n\nRacine, Etienne B. 2016. “The Visual Raster Cheat Sheet.â€\nhttps://rpubs.com/etiennebr/visualraster.\n\n\nTanaka, Kitiro. 1950. “The Relief Contour Method of Representing\nTopography on Maps.†Geographical Review 40 (3): 444. https://doi.org/10.2307/211219.\n\n\nTennekes, Martijn. 2018. “Tmap: Thematic\nMaps in r†84. https://doi.org/10.18637/jss.v084.i06.\n\n\nTomlin, C. Dana. 1990. Geographic Information Systems and\nCartographic Modeling. Prentice Hall.\n\n\nWickham, Hadley. 2016. “Ggplot2: Elegant Graphics for Data\nAnalysis.†https://ggplot2.tidyverse.org."
->>>>>>> refs/remotes/origin/main
- }
-]
\ No newline at end of file
--
GitLab