```{r message=FALSE}
setwd("C:/Users/Alain/Documents")
options(repos = c(CRAN = "https://cloud.r-project.org/"))
requiredPackages <- c("sf","RColorBrewer", "spatstat.geom", "spatstat.utils", "ggplot2",
"spatstat", "maptools", "httr","ggspatial", "viridis", "dplyr", "readxl",
"forcats","tidyr", "stringr")
for(i in requiredPackages)
{if(!require(i,character.only = TRUE)) install.packages(i)}
```This geospatial analysis aims to map the distribution of affected adolescents in the Democratic Republic of Congo (DRC) across three key dimensions:
The primary objective is to identify priority zones for targeted interventions by answering:
- Where are the most critical needs?
- Are there significant gender disparities?
- How do provinces compare after population standardization?
Data sources:
- Geographic layers:
- Provincial boundaries (IGF)
- Natural Earth base map
- Demographic data:
- Affected adolescent census (2023)
- INS population projections
Technical approach:
- Bivariate mapping (intensity + gender)
- Standardized ratios per 1,000 inhabitants
- Interactive visualizations with ggplot2 and sf
Three main visualizations will be presented:
```{r}
banderies <- st_read("C:/Users/Alain/Downloads/province26/provinces26/Province26.shp")
banderies_nad83 <- st_transform(banderies, crs = "+proj=longlat +datum=NAD83")
banderies_nad83$CODE_INS
library(rnaturalearth)
rdc <- ne_states(country = "Democratic Republic of the Congo", returnclass = "sf")
rdc_83<- st_transform(rdc, crs = 3857)
rdc_83$adm1_code
ggplot() +
geom_sf(rdc_83, mapping = aes(geometry=geometry))
```Reading layer `Province26' from data source
`C:\Users\Alain\Downloads\province26\provinces26\Province26.shp'
using driver `ESRI Shapefile'
Simple feature collection with 26 features and 8 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 1358728 ymin: -1501941 xmax: 3481773 ymax: 596454.8
Projected CRS: World_Mercator
[1] 10 20 302 303 305 402 403 405 406 407 502 503 504 505 61 62 63 704 705
[20] 706 707 802 803 804 902 903
[1] "COD-1461" "COD-1871" "COD-1884" "COD-1883" "COD-1559" "COD-1894"
[7] "COD-1897" "COD-1898" "COD-1872" "COD-1896" "COD-1895"
```{r}
provinces <- st_read("C:/Users/Alain/Downloads/geoBoundaries-COD-ADM2-all/geoBoundaries-COD-ADM2.shp")
provinces_nad83 <- st_transform(provinces, crs = "+proj=longlat +datum=NAD83")
ggplot() +
geom_sf(provinces_nad83, mapping = aes(geometry=geometry))
crds <- st_centroid(st_make_valid(provinces_nad83))
head(crds)
plot(st_geometry(provinces_nad83)) # rysuje kontur / plotting the contour
plot(st_geometry(crds), pch=21, bg='red', add=TRUE)
```Reading layer `geoBoundaries-COD-ADM2' from data source
`C:\Users\Alain\Downloads\geoBoundaries-COD-ADM2-all\geoBoundaries-COD-ADM2.shp'
using driver `ESRI Shapefile'
Simple feature collection with 189 features and 5 fields
Geometry type: POLYGON
Dimension: XY
Bounding box: xmin: 12.20566 ymin: -13.456 xmax: 31.30522 ymax: 5.386098
Geodetic CRS: WGS 84
Simple feature collection with 6 features and 5 fields
Geometry type: POINT
Dimension: XY
Bounding box: xmin: 23.7547 ymin: 0.7354574 xmax: 30.70698 ymax: 4.471862
Geodetic CRS: +proj=longlat +datum=NAD83
shapeName shapeISO shapeID shapeGroup shapeType
1 Aba <NA> 63176286B20411552692002 COD ADM2
2 Aketi <NA> 63176286B77771623677962 COD ADM2
3 Ango <NA> 63176286B24678106401017 COD ADM2
4 Ariwara <NA> 63176286B55306571020797 COD ADM2
5 Aru <NA> 63176286B14719092717616 COD ADM2
6 Bafwasende <NA> 63176286B50174012793828 COD ADM2
geometry
1 POINT (30.23818 3.858422)
2 POINT (23.7547 2.98004)
3 POINT (26.07273 4.471862)
4 POINT (30.70698 3.136862)
5 POINT (30.53241 3.065347)
6 POINT (26.99695 0.7354574)
```{r}
library(rnaturalearth)
rdc <- ne_states(country = "Democratic Republic of the Congo", returnclass = "sf")
rdc_83<- st_transform(rdc, crs = 3857)
rdc_83$adm1_code
``` [1] "COD-1461" "COD-1871" "COD-1884" "COD-1883" "COD-1559" "COD-1894"
[7] "COD-1897" "COD-1898" "COD-1872" "COD-1896" "COD-1895"```{r}
unique(rdc$name)
Kasai_Oriental <- rdc[rdc$name == "Kasaï-Oriental", ]
Kasai_Oriental <- rdc[grepl("Kasaï-Oriental", rdc$name, ignore.case = TRUE), ]
nrow(Kasai_Oriental)
Kasai_Oriental_proj <- st_transform(Kasai_Oriental, crs = 32733)
Kasai_Oriental_geom <- st_geometry(Kasai_Oriental_proj)[[1]]
Kasai_Oriental_win <- as.owin(Kasai_Oriental_geom)
``` [1] "Équateur" "Bandundu" "Kinshasa City" "Bas-Congo"
[5] "Orientale" "Sud-Kivu" "Katanga" "Nord-Kivu"
[9] "Kasaï-Occidental" "Kasaï-Oriental" "Maniema"
[1] 1```{r}
plot(Kasai_Oriental_win, main = "Observation window - Kasaï-Oriental")
ggplot() +
geom_sf(Kasai_Oriental_proj, mapping = aes(geometry=geometry))
Kasai_Oriental_proj <- st_transform(Kasai_Oriental, crs = 32733)
st_bbox(Kasai_Oriental_proj)
``` xmin ymin xmax ymax
1268838 9113480 1757329 9804526 
#st_bbox(banderies_nad83)
```{r}
crds <- st_centroid(st_make_valid(Kasai_Oriental_proj))
head(crds)
plot(st_geometry(Kasai_Oriental_proj))
plot(st_geometry(crds), pch=21, bg='red', add=TRUE)
```Simple feature collection with 1 feature and 121 fields
Geometry type: POINT
Dimension: XY
Bounding box: xmin: 1496407 ymin: 9491290 xmax: 1496407 ymax: 9491290
Projected CRS: WGS 84 / UTM zone 33S
featurecla scalerank adm1_code diss_me iso_3166_2
3789 Admin-1 states provinces lakes 5 COD-1896 1896 CD-KE
wikipedia iso_a2 adm0_sr name name_alt name_local
3789 <NA> CD 1 Kasaï-Oriental East Kasai|Kasai East <NA>
type type_en code_local code_hasc note hasc_maybe region region_cod
3789 Province Province <NA> CD.KR <NA> <NA> <NA> <NA>
provnum_ne gadm_level check_me datarank abbrev postal area_sqkm sameascity
3789 9 1 0 3 <NA> KR 0 -99
labelrank name_len mapcolor9 mapcolor13 fips fips_alt woe_id
3789 6 14 4 7 CG04 <NA> 2344980
woe_label woe_name latitude
3789 Kasai-Oriental, CD, Democratic Republic of Congo Kasaï-Oriental -4.40511
longitude sov_a3 adm0_a3 adm0_label admin
3789 24.0842 COD COD 2 Democratic Republic of the Congo
geonunit gu_a3 gn_id gn_name
3789 Democratic Republic of the Congo COD 214138 Province du Kasai-Oriental
gns_id gns_name gn_level gn_region gn_a1_code region_sub sub_code
3789 -2046899 Kasai-Oriental 1 <NA> CD.04 <NA> <NA>
gns_level gns_lang gns_adm1 gns_region min_label max_label min_zoom
3789 1 fra CG04 <NA> 6 11 6
wikidataid name_ar name_bn name_de name_en
3789 Q80953 كاساي الشرقية কাসাই-ওরিয়েন্টাল Kasaï-Oriental Kasaï-Oriental
name_es name_fr name_el name_hi name_hu
3789 Kasai Oriental Kasaï-Oriental Κασάι-Οριεντάλ कासाइ-पूर्वी प्रान्त Kelet-Kasai
name_id name_it name_ja name_ko name_nl
3789 Kasai-Oriental Kasai Orientale 東カサイ州 카사이오리앙탈 Oost-Kasaï
name_pl name_pt name_ru name_sv name_tr
3789 Kasai Wschodnie Kasaï-Oriental Восточное Касаи Kasaï-Oriental Doğu Kasai
name_vi name_zh ne_id name_he name_uk
3789 Kasai-Oriental 东开赛省 1159311343 קאסאי-אוריינטל Східне Касаї
name_ur name_fa name_zht FCLASS_ISO FCLASS_US FCLASS_FR
3789 کاسائی-مشرقی کاسای- اورینتال 东开赛省 <NA> <NA> <NA>
FCLASS_RU FCLASS_ES FCLASS_CN FCLASS_TW FCLASS_IN FCLASS_NP FCLASS_PK
3789 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
FCLASS_DE FCLASS_GB FCLASS_BR FCLASS_IL FCLASS_PS FCLASS_SA FCLASS_EG
3789 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
FCLASS_MA FCLASS_PT FCLASS_AR FCLASS_JP FCLASS_KO FCLASS_VN FCLASS_TR
3789 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
FCLASS_ID FCLASS_PL FCLASS_GR FCLASS_IT FCLASS_NL FCLASS_SE FCLASS_BD
3789 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
FCLASS_UA FCLASS_TLC geometry
3789 <NA> <NA> POINT (1496407 9491290)
```{r}
railways <- st_read("C:/Users/Alain/Downloads/congo-democratic-republic-latest-free.shp/gis_osm_railways_free_1.shp")
railways_nad83 <- st_transform(railways, crs = "+proj=longlat +datum=NAD83")
str(railways)
table(railways$fclass)
plot(railways$geometry)
district <- st_read("C:/Users/Alain/Downloads/district/District.shp")
district_nad83 <- st_transform(district, crs = "+proj=longlat +datum=NAD83")
table(district$NOM)
plot(district$geometry)
```Reading layer `gis_osm_railways_free_1' from data source
`C:\Users\Alain\Downloads\congo-democratic-republic-latest-free.shp\gis_osm_railways_free_1.shp'
using driver `ESRI Shapefile'
Simple feature collection with 1900 features and 7 fields
Geometry type: LINESTRING
Dimension: XY
Bounding box: xmin: 13.43202 ymin: -13.49397 xmax: 30.71915 ymax: 3.36139
Geodetic CRS: WGS 84
Classes 'sf' and 'data.frame': 1900 obs. of 8 variables:
$ osm_id : chr "4402431" "4402432" "4402433" "4402434" ...
$ code : int 6101 6101 6101 6101 6101 6101 6101 6101 6101 6101 ...
$ fclass : chr "rail" "rail" "rail" "rail" ...
$ name : chr NA NA NA NA ...
$ layer : num 0 0 0 0 0 0 0 0 0 0 ...
$ bridge : chr "F" "F" "F" "F" ...
$ tunnel : chr "F" "F" "F" "F" ...
$ geometry:sfc_LINESTRING of length 1900; first list element: 'XY' num [1:3, 1:2] 15.3 15.3 15.3 -4.3 -4.3 ...
- attr(*, "sf_column")= chr "geometry"
- attr(*, "agr")= Factor w/ 3 levels "constant","aggregate",..: NA NA NA NA NA NA NA
..- attr(*, "names")= chr [1:7] "osm_id" "code" "fclass" "name" ...
funicular light_rail rail
1 12 1887
Reading layer `District' from data source
`C:\Users\Alain\Downloads\district\District.shp' using driver `ESRI Shapefile'
Simple feature collection with 48 features and 8 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 1358728 ymin: -1501941 xmax: 3481773 ymax: 596454.8
Projected CRS: World_Mercator
Bandundu Bas-Fleuve Bas-Uele Beni Boma Bukavu
1 1 1 1 1 1
Butembo Cataractes Equateur Gbadolite Goma Haut-Katanga
1 1 1 1 1 1
Haut-Lomami Haut-Uele Ituri Kabinda Kananga Kasai
1 1 1 1 1 1
Kikwit Kindu Kinshasa Kisangani Kolwezi Kwango
1 1 1 1 1 1
Kwilu Likasi Lualaba Lubumbashi Lukaya Lulua
1 1 1 1 1 1
Maï-Ndombe Maniema Matadi Mbandaka Mbuji-Mayi Mongala
1 1 1 1 1 1
Mwene-Ditu Nord-Kivu Nord-Ubangi Plateaux Sankuru Sud-Kivu
1 1 1 1 1 1
Sud-Ubangi Tanganyka Tshilenge Tshopo Tshuapa Zongo
1 1 1 1 1 1 
```{r}
parc <- st_read("C:/Users/Alain/Downloads/parc/Parc.shp")
parc_nad83 <- st_transform(parc, crs = "+proj=longlat +datum=NAD83")
table(parc$NOM)
plot(parc$geometry)
```Reading layer `Parc' from data source `C:\Users\Alain\Downloads\parc\Parc.shp' using driver `ESRI Shapefile'
Simple feature collection with 44 features and 6 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 12.35354 ymin: -11.19897 xmax: 30.20467 ymax: 5.388336
Geodetic CRS: WGS 84
Domaine de chasse de Bili-Uere Domaine de Chasse de Bombo Lumene
1 1
Domaine de Chasse de Bomu Domaine de Chasse de Bushimaie
1 1
Domaine de Chasse de Gangala-na Bodio Domaine de Chasse de Luama-Katanga
1 1
Domaine de chasse de Luama-Kivu Domaine de chasse de Lubudi Sampwe
1 1
Domaine de chasse de Maika-Penge Domaine de chasse de Mangai
1 1
Domaine de chasse de Rubi-Tele Domaine de chasse de Rutshuru
1 1
Domaine de Chasse de Swa-Kibula Domaine de chasse de Tshangalele
1 1
Massif d'Itombwe Parc de la N'Sele
1 1
Parc Marin des Mangroves Parc National de Kahuzi-Biega
1 1
Parc National de Kundelungu Parc National de l'Upemba
1 1
Parc National de la Garamba Parc National de la Maiko
1 1
Parc National de la Salonga Parc National des Virunga
2 1
Réserve de Abumonbazi Réserve de biosphère de la Lufira
1 1
Réserve de biosphere de la Luki Réserve de biosphère de Yangambi
1 1
Réserve de Bomu Réserve de Epi
1 1
Réserve de faune à okapis Réserve de Lomami-Lualaba
1 1
Réserve de Mai Mpili Réserve de Maniema
1 1
Réserve de Shaba Elephant Réserve du Lac Tumba-Lediima
1 1
Réserve du Mont Kabobo Réserve du Sud Masisi
1 1
Réserve du triangle de la Ngiri Réserve forestière de Lomako-Yokokala
1 1
Reserve Naturelle de Kisimba Ikobo Reserve Naturelle de Tayna
1 1
Réserve Scientifique de Luo
1 
```{r}
plot(st_geometry(st_transform(district, crs = st_crs(provinces_nad83))))
plot(st_geometry(provinces_nad83[provinces$shapeName == "Kinshasa", ]),
add = TRUE,
col = "red")
```
```{r}
b0 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon.gpkg")
b2 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon-lvl2.gpkg")
b4 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon-lvl4.gpkg")
b7 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon-lvl7.gpkg")
b8 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon-lvl8.gpkg")
b9 <- st_read("C:/Users/Alain/Downloads/CD-KN-b7bd0eae-20250601-fr-gpkg/data/boundary-polygon-lvl9.gpkg")
target_crs <- 3857
b0 <- st_transform(b0, crs = target_crs)
b2 <- st_transform(b2, crs = target_crs)
b4 <- st_transform(b4, crs = target_crs)
b7 <- st_transform(b7, crs = target_crs)
b8 <- st_transform(b8, crs = target_crs)
b9 <- st_transform(b9, crs = target_crs)
boundaries <- rbind(b0, b2, b4, b7, b8, b9)
nb_col <- length(unique(boundaries$NAME))
palette <- colorRampPalette(brewer.pal(9, "Set3"))(nb_col)
```Reading layer `boundary-polygon' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon.gpkg'
using driver `GPKG'
Simple feature collection with 234 features and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.12706 ymin: -5.032536 xmax: 16.53412 ymax: -3.927611
Geodetic CRS: WGS 84
Reading layer `boundary-polygon-lvl2' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon-lvl2.gpkg'
using driver `GPKG'
Simple feature collection with 1 feature and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.12706 ymin: -5.032536 xmax: 16.53412 ymax: -3.927611
Geodetic CRS: WGS 84
Reading layer `boundary-polygon-lvl4' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon-lvl4.gpkg'
using driver `GPKG'
Simple feature collection with 1 feature and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.12706 ymin: -5.032536 xmax: 16.53412 ymax: -3.927611
Geodetic CRS: WGS 84
Reading layer `boundary-polygon-lvl7' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon-lvl7.gpkg'
using driver `GPKG'
Simple feature collection with 24 features and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.12982 ymin: -5.032536 xmax: 16.53412 ymax: -3.927611
Geodetic CRS: WGS 84
Reading layer `boundary-polygon-lvl8' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon-lvl8.gpkg'
using driver `GPKG'
Simple feature collection with 197 features and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.20606 ymin: -4.440094 xmax: 15.42763 ymax: -4.296267
Geodetic CRS: WGS 84
Reading layer `boundary-polygon-lvl9' from data source
`C:\Users\Alain\Downloads\CD-KN-b7bd0eae-20250601-fr-gpkg\data\boundary-polygon-lvl9.gpkg'
using driver `GPKG'
Simple feature collection with 11 features and 25 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 15.21345 ymin: -4.398089 xmax: 15.37933 ymax: -4.320823
Geodetic CRS: WGS 84```{r}
ggplot(boundaries) +
geom_sf(aes(fill = NAME), color = "black", size = 0.2, show.legend = FALSE) +
scale_fill_manual(values = palette) +
labs(title = "Communes, quartiers et districts de Kinshasa",
subtitle = "Chaque entité est représentée par une couleur distincte") +
annotation_scale(location = "bl") +
annotation_north_arrow(location = "tl", which_north = "true",
style = north_arrow_fancy_orienteering()) +
theme_minimal() +
# 🏷️ Affichage des noms des entités
geom_sf_text(aes(label = NAME), size = 2.5, color = "black", check_overlap = TRUE)
```
```{r}
commune_zoom <- boundaries %>%
filter(NAME %in% c("Gombe", "Limete", "Kintambo", "Bandalungwa"))
# Create a manual color palette for the 4 targeted communes
palette_zoom <- setNames(c("red", "blue", "green", "orange"),
c("Gombe", "Limete", "Kintambo", "Bandalungwa"))
ggplot(commune_zoom) +
geom_sf(aes(fill = NAME), color = "black", size = 0.2, show.legend = FALSE) +
scale_fill_manual(values = palette_zoom) +
labs(
title = "Zoom on Selected Communes of Kinshasa",
subtitle = "Communes: Gombe, Limete, Kintambo, Bandalungwa"
) +
annotation_scale(location = "bl") +
annotation_north_arrow(location = "tl", which_north = "true",
style = north_arrow_fancy_orienteering()) +
theme_minimal() +
geom_sf_text(aes(label = NAME), size = 2.5, color = "black", check_overlap = TRUE)
```
```{r}
# 📥 Charger les données adolescents affectes par les Infections carabines
ado <- read_excel("C:/Users/Alain/Downloads/ADO&JEUNES 2023.xlsx")
str(ado)
```tibble [28 × 4] (S3: tbl_df/tbl/data.frame)
$ Indicateur: chr [1:28] NA "Somme de Valeur" "Étiquettes de lignes" "Bas-Uele" ...
$ (Tous) : chr [1:28] NA "Étiquettes de colonnes" "Féminin" "13993" ...
$ ...3 : chr [1:28] NA NA "Masculin" "10896" ...
$ ...4 : chr [1:28] NA NA "Total général" "24889" ...```{r}
ado_large <- ado %>%
rename(
Province = Indicateur,
Femme = `(Tous)`,
Homme = `...3`,
Total_general = `...4`
) %>%
filter(!is.na(Province)) %>%
mutate(
Femme = as.numeric(Femme),
Homme = as.numeric(Homme),
Total_general = as.numeric(Total_general)
) %>%
drop_na(Femme, Homme, Total_general) %>% # ✅ Supprimer les lignes avec au moins un NA
distinct() %>%
arrange(Province)
# Affichage final
print(ado_large)
glimpse(ado_large)
# Transformation en format long avec gestion des doublons
ado_long <- ado_large %>%
distinct() %>% # Élimine les doublons complets
pivot_longer(
cols = c(Femme, Homme),
names_to = "Gender",
values_to = "valeur"
) %>%
mutate(
Gender = as_factor(Gender) %>% # Convertir en facteur
fct_relevel("Femme", "Homme") %>% # Ordonner les niveaux
fct_recode("Female" = "Femme", "Male" = "Homme"), # Renommer en anglais
.after = Province # Placer la colonne Gender après Province
) %>%
distinct(Province, Gender, .keep_all = TRUE) %>% # Éviter les doublons par combinaison Province-Gender
select(Province, Gender, valeur, Total_general) # Sélection des colonnes
# 👀 Afficher le résultat
glimpse(ado_long)
View(ado_long)
ado_clean <- ado_long[complete.cases(ado_long), ]
```# A tibble: 25 × 4
Province Femme Homme Total_general
<chr> <dbl> <dbl> <dbl>
1 Bas-Uele 13993 10896 24889
2 Haut-Katanga 2435551 2124191 4559742
3 Haut-Lomami 111958 35086 147044
4 Haut-Uele 80677 54107 134784
5 Ituri 40843 36467 77310
6 Kasaï 139262 112649 251911
7 Kasaï-Central 78996 66261 145257
8 Kasaï-Oriental 520251 315834 836085
9 Kinshasa 207106 233067 440173
10 Kongo-Central 86683 77415 164098
# ℹ 15 more rows
Rows: 25
Columns: 4
$ Province <chr> "Bas-Uele", "Haut-Katanga", "Haut-Lomami", "Haut-Uele", …
$ Femme <dbl> 13993, 2435551, 111958, 80677, 40843, 139262, 78996, 520…
$ Homme <dbl> 10896, 2124191, 35086, 54107, 36467, 112649, 66261, 3158…
$ Total_general <dbl> 24889, 4559742, 147044, 134784, 77310, 251911, 145257, 8…
Rows: 50
Columns: 4
$ Province <chr> "Bas-Uele", "Bas-Uele", "Haut-Katanga", "Haut-Katanga", …
$ Gender <fct> Female, Male, Female, Male, Female, Male, Female, Male, …
$ valeur <dbl> 13993, 10896, 2435551, 2124191, 111958, 35086, 80677, 54…
$ Total_general <dbl> 24889, 24889, 4559742, 4559742, 147044, 147044, 134784, …```{r}
pop_total_Rdc <- c(
"Bas-Uele" = 1419000,
"Équateur" = 1856000,
"Haut-Katanga" = 5378000,
"Haut-Lomami" = 2842000,
"Haut-Uele" = 2614000,
"Ituri" = 4392000,
"Kasaï" = 3199000,
"Kasaï-Central" = 3743000,
"Kasaï-Oriental" = 3145000,
"Kinshasa" = 17071000,
"Kongo-Central" = 6365000,
"Kwango" = 2416000,
"Kwilu" = 6149000,
"Lomami" = 2842000,
"Lualaba" = 3138000,
"Mai-Ndombe" = 2482000,
"Mongala" = 2358000,
"Nord-Kivu" = 8103000,
"Nord-Ubangi" = 1482000,
"Sankuru" = 2478000,
"Sud-Kivu" = 6565000,
"Sud-Ubangi" = 2614000,
"Tanganyika" = 3561000,
"Tshopo" = 3113000,
"Tshuapa" = 1887000
)
# 1. Convertir le vecteur en dataframe
pop_data <- data.frame(
Province = names(pop_total_Rdc),
pop_total_Rdc = pop_total_Rdc,
row.names = NULL
)
View(pop_data)
# 2. Jointure avec ado_clean
# Ajouter la colonne des adolescents par 1000 habitant
``````{r}
pop_data <- pop_data %>%
mutate(Province = str_trim(str_to_title(Province))) # Normalisation des noms
ado_clean <- ado_clean %>%
mutate(Province = str_trim(str_to_title(Province))) # Harmonisation des noms
# Fusion des deux data.frames sur la colonne "Province"
merged_data <- full_join(pop_data, ado_clean, by = "Province") %>%
distinct() # Supprimer les doublons
# Vérifier la structure des données après fusion
glimpse(merged_data)
# Afficher un aperçu
head(merged_data)
View(merged_data)
```Rows: 53
Columns: 5
$ Province <chr> "Bas-Uele", "Bas-Uele", "Équateur", "Équateur", "Haut-Ka…
$ pop_total_Rdc <dbl> 1419000, 1419000, 1856000, 1856000, 5378000, 5378000, 28…
$ Gender <fct> Female, Male, Female, Male, Female, Male, Female, Male, …
$ valeur <dbl> 13993, 10896, 12622, 16048, 2435551, 2124191, 111958, 35…
$ Total_general <dbl> 24889, 24889, 28670, 28670, 4559742, 4559742, 147044, 14…
Province pop_total_Rdc Gender valeur Total_general
1 Bas-Uele 1419000 Female 13993 24889
2 Bas-Uele 1419000 Male 10896 24889
3 Équateur 1856000 Female 12622 28670
4 Équateur 1856000 Male 16048 28670
5 Haut-Katanga 5378000 Female 2435551 4559742
6 Haut-Katanga 5378000 Male 2124191 4559742```{r}
province_code <- c(
"Kinshasa" = 10, "Kongo-Central" = 20, "Kwango" = 302, "Kwilu" = 303, "Mai-Ndombe" = 305,
"Tshuapa" = 402, "Mongala" = 403, "Nord-Ubangi" = 405, "Sud-Ubangi" = 406, "Équateur" = 407,
"Tshopo" = 502, "Haut-Uele" = 503, "Bas-Uele" = 504, "Ituri" = 505, "Haut-Lomami" = 61,
"Lomami" = 62, "Kasaï" = 63, "Kasaï-Central" = 704, "Kasaï-Oriental" = 705, "Sankuru" = 706,
"Maniema" = 707, "Tanganyika" = 802, "Haut-Katanga" = 803, "Lualaba" = 804, "Sud-Kivu" = 904, # Code approximatif ajouté
"Nord-Kivu" = 903
)
# Mise à jour de merged_data avec ce code
# Ajouter la colonne code avec cbind()
merged_data <- cbind(merged_data, code = province_code[merged_data$Province])
# Supprimer les lignes avec NA pour éviter les erreurs
merged_data <- merged_data[complete.cases(merged_data), ]
# Vérification
print(merged_data)
View(merged_data)
``` Province pop_total_Rdc Gender valeur Total_general code
1 Bas-Uele 1419000 Female 13993 24889 504
2 Bas-Uele 1419000 Male 10896 24889 504
3 Équateur 1856000 Female 12622 28670 407
4 Équateur 1856000 Male 16048 28670 407
5 Haut-Katanga 5378000 Female 2435551 4559742 803
6 Haut-Katanga 5378000 Male 2124191 4559742 803
7 Haut-Lomami 2842000 Female 111958 147044 61
8 Haut-Lomami 2842000 Male 35086 147044 61
9 Haut-Uele 2614000 Female 80677 134784 503
10 Haut-Uele 2614000 Male 54107 134784 503
11 Ituri 4392000 Female 40843 77310 505
12 Ituri 4392000 Male 36467 77310 505
13 Kasaï 3199000 Female 139262 251911 63
14 Kasaï 3199000 Male 112649 251911 63
15 Kasaï-Central 3743000 Female 78996 145257 704
16 Kasaï-Central 3743000 Male 66261 145257 704
17 Kasaï-Oriental 3145000 Female 520251 836085 705
18 Kasaï-Oriental 3145000 Male 315834 836085 705
19 Kinshasa 17071000 Female 207106 440173 10
20 Kinshasa 17071000 Male 233067 440173 10
21 Kongo-Central 6365000 Female 86683 164098 20
22 Kongo-Central 6365000 Male 77415 164098 20
23 Kwango 2416000 Female 106223 228126 302
24 Kwango 2416000 Male 121903 228126 302
25 Kwilu 6149000 Female 66973 124196 303
26 Kwilu 6149000 Male 57223 124196 303
27 Lomami 2842000 Female 560237 848427 62
28 Lomami 2842000 Male 288190 848427 62
30 Mai-Ndombe 2482000 Female 90209 127284 305
31 Mai-Ndombe 2482000 Male 37075 127284 305
32 Mongala 2358000 Female 451806 697983 403
33 Mongala 2358000 Male 246177 697983 403
34 Nord-Kivu 8103000 Female 1852584 2459446 903
35 Nord-Kivu 8103000 Male 606862 2459446 903
36 Nord-Ubangi 1482000 Female 110080 211618 405
37 Nord-Ubangi 1482000 Male 101538 211618 405
38 Sankuru 2478000 Female 69549 138639 706
39 Sankuru 2478000 Male 69090 138639 706
41 Sud-Ubangi 2614000 Female 150424 229227 406
42 Sud-Ubangi 2614000 Male 78803 229227 406
43 Tanganyika 3561000 Female 816465 1635918 802
44 Tanganyika 3561000 Male 819453 1635918 802
45 Tshopo 3113000 Female 60979 95752 502
46 Tshopo 3113000 Male 34773 95752 502```{r}
ado_ratios <- merged_data %>%
# Étape 1: Garder uniquement les combinaisons uniques Province-Gender
group_by(Province, Gender) %>%
filter(row_number() == 1) %>% # Équivalent à unique() pour chaque groupe
ungroup() %>%
# Étape 2: Calcul des ratios (votre code original)
group_by(Province, Gender) %>%
mutate(
ratio_per_1000 = (valeur / first(Total_general)) * 1000
) %>%
ungroup()
# Vérification
stopifnot(
"There are still duplicates" = !any(duplicated(ado_ratios[, c("Province", "Gender")]))
)
``````{r}
glimpse(ado_ratios)
View(ado_ratios)
sum(is.na(ado_ratios))
banderies_nad83 <- banderies_nad83 %>% mutate(code = as.numeric(CODE_INS)*1000)
View(banderies_nad83)
View(ado_ratios)
```Rows: 44
Columns: 7
$ Province <chr> "Bas-Uele", "Bas-Uele", "Équateur", "Équateur", "Haut-K…
$ pop_total_Rdc <dbl> 1419000, 1419000, 1856000, 1856000, 5378000, 5378000, 2…
$ Gender <fct> Female, Male, Female, Male, Female, Male, Female, Male,…
$ valeur <dbl> 13993, 10896, 12622, 16048, 2435551, 2124191, 111958, 3…
$ Total_general <dbl> 24889, 24889, 28670, 28670, 4559742, 4559742, 147044, 1…
$ code <dbl> 504, 504, 407, 407, 803, 803, 61, 61, 503, 503, 505, 50…
$ ratio_per_1000 <dbl> 562.2162, 437.7838, 440.2511, 559.7489, 534.1423, 465.8…
[1] 0```{r}
# 1. Data Preparation
# Join the geographic data with the values
carte_data <- banderies_nad83 %>%
left_join(ado_ratios, by = c("CODE_INS" = "code")) %>%
group_by(NOM) %>% # Aggregation by province
summarise(
valeur_totale = sum(valeur, na.rm = TRUE),
geometry = first(geometry)
) %>%
st_as_sf()
``````{r}
# 2. Visualization
ggplot() +
# Base map with total intensity
geom_sf(data = carte_data,
aes(fill = valeur_totale),
color = "white", size = 0.2) +
# Points by gender (overlay)
geom_sf(data = ado_ratios %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf(),
aes(geometry = geometry,
color = Gender,
size = valeur),
alpha = 0.7) +
# Color scales
scale_fill_viridis_c(option = "D", name = "Total intensity") +
scale_color_manual(values = c("Male" = "#FF6B6B", "Female" = "#4ECDC4")) +
scale_size_continuous(range = c(2, 10), name = "Value by gender") +
# Theme
theme_minimal() +
labs(title = "Adolescents affected in DRC by province and gender",
caption = "Source: Your data")
```
```{r}
ggplot() +
geom_sf(data = banderies_nad83, fill = "grey90", color = "white") +
geom_sf(data = ado_ratios %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf(),
aes(fill = valeur, geometry = geometry),
color = "white", size = 0.2) +
facet_wrap(~Gender) +
scale_fill_viridis_c(option = "D", name = "Absolute value") +
theme_void() +
labs(title = "Distribution by gender and province")
```
```{r}
ggplot() +
geom_sf(data = banderies_nad83, fill = "grey90", color = "white") +
geom_sf(data = ado_ratios %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf(),
aes(fill = valeur, geometry = geometry),
color = "white", size = 0.2) +
# Province names in red
geom_sf_text(data = banderies_nad83,
aes(label = NOM, geometry = geometry),
color = "red", # Red color
size = 3,
check_overlap = TRUE) +
facet_wrap(~Gender) +
scale_fill_viridis_c(option = "D", name = "Absolute value") +
theme_void() +
labs(title = "Distribution by gender and province")
```
```{r}
carte_combi <- ado_ratios %>%
group_by(code) %>%
summarise(
prop_female = sum(valeur[Gender == "Female"])/sum(valeur),
valeur_tot = sum(valeur)
) %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf()
ggplot() +
geom_sf(data = carte_combi,
aes(fill = valeur_tot, color = prop_female),
size = 0.5) +
scale_fill_viridis_c(option = "D", name = "Intensité totale") +
scale_color_gradient2(low = "#FF6B6B", mid = "white", high = "#4ECDC4",
midpoint = 0.5, name = "% Femmes") +
theme_minimal()
```
```{r}
ggplot() +
# Basemap (empty provinces)
geom_sf(data = banderies_nad83, fill = "grey90", color = "white") +
# Fill by value and gender
geom_sf(
data = ado_ratios %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf(),
aes(fill = valeur, geometry = geometry),
color = "white", size = 0.2
) +
# Facets
facet_wrap(~Gender, ncol = 2) +
# Single color scale
scale_fill_viridis_c(option = "D", name = "Valeur absolue") +
# Theme
theme_void() +
labs(title = "Répartition genrée des adolescents affectés")
```
```{r}
carte_bivariee <- ado_ratios %>%
group_by(code) %>%
summarise(
prop_female = sum(valeur[Gender == "Female"]) / sum(valeur),
valeur_tot = sum(valeur)
) %>%
left_join(banderies_nad83, by = c("code" = "CODE_INS")) %>%
st_as_sf()
# Visualization
ggplot() +
geom_sf(
data = carte_bivariee,
aes(fill = prop_female, alpha = valeur_tot),
color = "white", size = 0.3
) +
# Scales
scale_fill_gradient2(
low = "#E41A1C", mid = "#F7F7F7", high = "#377EB8",
midpoint = 0.5, name = "Percentage of Females"
) +
scale_alpha_continuous(range = c(0.3, 0.9), name = "Total Intensity") +
# Thème
theme_void() +
labs(title = "Intensity and Gender Distribution by Province")
```
```{r}
# 1. 📥 Load and clean the adolescent health data
ado <- read_excel("C:/Users/Alain/Downloads/ADO&JEUNES 2023.xlsx") %>%
rename(
Province = Indicateur,
Female = `(Tous)`,
Male = `...3`,
Total_general = `...4`
) %>%
filter(!is.na(Province)) %>%
mutate(
Female = as.numeric(Female),
Male = as.numeric(Male),
Total_general = as.numeric(Total_general)
) %>%
drop_na(Female, Male, Total_general)
# 2. 🌍 Add simulated coordinates for provinces (e.g., approximate centroids)
set.seed(123)
ado$lon <- runif(nrow(ado), min = 21, max = 31) # approximate longitude in DRC
ado$lat <- runif(nrow(ado), min = -13, max = 5) # approximate latitude in DRC
# 3. 🎯 Select a 20% random sample of provinces
set.seed(456)
ado$u <- runif(nrow(ado))
ado_small <- ado %>% filter(u <= 0.2)
# 4. 🔄 Convert to sf (projected geographic coordinate system)
ado_small.sf <- st_as_sf(ado_small, coords = c("lon", "lat"), crs = 4326)
ado_small.sf <- st_transform(ado_small.sf, crs = 3857) # Mercator projection
# 5. 🗺️ Define the spatial window (based on observed coordinates)
W <- as.owin(st_bbox(ado_small.sf))
rsc <- 1000 # rescaling factor (1 unit = 1 km)
# 6. 🔘 Create spatial patterns
# Unmarked pattern
pattern.um <- ppp(
x = st_coordinates(ado_small.sf)[,1],
y = st_coordinates(ado_small.sf)[,2],
window = W
)
pattern.um <- rescale(pattern.um, rsc, "km")
plot(pattern.um, main = "Affected adolescents (unmarked pattern)")
# Marked pattern: pivot_longer to split by gender
ado_long <- ado_small %>%
pivot_longer(cols = c(Female, Male), names_to = "Gender", values_to = "value")
ado_long.sf <- st_as_sf(ado_long, coords = c("lon", "lat"), crs = 4326) %>%
st_transform(crs = 3857)
pattern.m <- ppp(
x = st_coordinates(ado_long.sf)[,1],
y = st_coordinates(ado_long.sf)[,2],
window = W,
marks = as.factor(ado_long.sf$Gender)
)
pattern.m <- rescale(pattern.m, rsc, "km")
plot(pattern.m, main = "Affected adolescents by gender (marked pattern)")
# 7. 📏 Distance analysis
between_dist <- pairdist(pattern.um)
between_dist_df <- as.data.frame(between_dist)
between_dist_df$min_d <- apply(between_dist_df, 1, function(x) sort(x)[2])
first_neib <- nndist(pattern.um)
# 8. 🗺️ Display map of DRC with case intensity
rdc <- ne_states(country = "Democratic Republic of the Congo", returnclass = "sf")
rdc_83 <- st_transform(rdc, crs = 3857)
# Join total cases to map
carte_rdc <- left_join(rdc_83, ado, by = c("name" = "Province"))
# 9. 🖼️ Choropleth visualization
ggplot() +
geom_sf(data = carte_rdc, aes(fill = Total_general), color = "white") +
scale_fill_viridis_c(name = "Reported cases") +
labs(
title = "Distribution of affected adolescents in DRC",
subtitle = "Total number of cases per province",
caption = "Source: ADO & JEUNES 2023"
) +
theme_minimal()
```
