pacman::p_load(sf, tidyverse, funModeling)In-class_Ex02
Installing packages
GeoBoundaries data set
geoNGA <- st_read("data/geospatial/", layer = "geoBoundaries-NGA-ADM2") |>
st_transform(crs = 26392)Reading layer `geoBoundaries-NGA-ADM2' from data source
`/Users/pengyouyun/youyunpeng/IS415/In-class_Ex/In-class_Ex02/Data/geospatial'
using driver `ESRI Shapefile'
Simple feature collection with 774 features and 6 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 2.668534 ymin: 4.273007 xmax: 14.67882 ymax: 13.89442
Geodetic CRS: WGS 84The NGA data set
NGA <- st_read("Data/geospatial/",
layer = "nga_admbnda_adm2_osgof_20190417") %>%
st_transform(crs = 26392)Reading layer `nga_admbnda_adm2_osgof_20190417' from data source
`/Users/pengyouyun/youyunpeng/IS415/In-class_Ex/In-class_Ex02/Data/geospatial'
using driver `ESRI Shapefile'
Simple feature collection with 774 features and 16 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 2.668534 ymin: 4.273007 xmax: 14.67882 ymax: 13.89442
Geodetic CRS: WGS 84Importing Aspatial data
pacman::p_load(sf, tidyverse, funModeling)
wp_nga <- read_csv("data/aspatial/WPdx.csv") %>%
filter(`#clean_country_name` == "Nigeria")Warning: One or more parsing issues, call `problems()` on your data frame for details,
e.g.:
dat <- vroom(...)
problems(dat)Rows: 406566 Columns: 70
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (43): #source, #report_date, #status_id, #water_source_clean, #water_sou...
dbl (23): row_id, #lat_deg, #lon_deg, #install_year, #fecal_coliform_value, ...
lgl (4): #rehab_year, #rehabilitator, is_urban, latest_record
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Converting water point data into sf point features
if the dataframe has long and latt, use st_as_sf, and put coords = c(“long”, “latt”) to convert to sf object
wp_nga$Geometry = st_as_sfc(wp_nga$`New Georeferenced Column`)
wp_nga# A tibble: 95,008 × 71
row_id `#source` #lat_…¹ #lon_…² #repo…³ #stat…⁴ #wate…⁵ #wate…⁶ #wate…⁷
<dbl> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr>
1 429068 GRID3 7.98 5.12 08/29/… Unknown <NA> <NA> Tapsta…
2 222071 Federal Minis… 6.96 3.60 08/16/… Yes Boreho… Well Mechan…
3 160612 WaterAid 6.49 7.93 12/04/… Yes Boreho… Well Hand P…
4 160669 WaterAid 6.73 7.65 12/04/… Yes Boreho… Well <NA>
5 160642 WaterAid 6.78 7.66 12/04/… Yes Boreho… Well Hand P…
6 160628 WaterAid 6.96 7.78 12/04/… Yes Boreho… Well Hand P…
7 160632 WaterAid 7.02 7.84 12/04/… Yes Boreho… Well Hand P…
8 642747 Living Water … 7.33 8.98 10/03/… Yes Boreho… Well Mechan…
9 642456 Living Water … 7.17 9.11 10/03/… Yes Boreho… Well Hand P…
10 641347 Living Water … 7.20 9.22 03/28/… Yes Boreho… Well Hand P…
# … with 94,998 more rows, 62 more variables: `#water_tech_category` <chr>,
# `#facility_type` <chr>, `#clean_country_name` <chr>, `#clean_adm1` <chr>,
# `#clean_adm2` <chr>, `#clean_adm3` <chr>, `#clean_adm4` <chr>,
# `#install_year` <dbl>, `#installer` <chr>, `#rehab_year` <lgl>,
# `#rehabilitator` <lgl>, `#management_clean` <chr>, `#status_clean` <chr>,
# `#pay` <chr>, `#fecal_coliform_presence` <chr>,
# `#fecal_coliform_value` <dbl>, `#subjective_quality` <chr>, …wp_sf <- st_sf(wp_nga, crs=4326) #convert to sf, tell R what crs used for projection
wp_sfSimple feature collection with 95008 features and 70 fields
Geometry type: POINT
Dimension: XY
Bounding box: xmin: 2.707441 ymin: 4.301812 xmax: 14.21828 ymax: 13.86568
Geodetic CRS: WGS 84
# A tibble: 95,008 × 71
row_id `#source` #lat_…¹ #lon_…² #repo…³ #stat…⁴ #wate…⁵ #wate…⁶ #wate…⁷
* <dbl> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr>
1 429068 GRID3 7.98 5.12 08/29/… Unknown <NA> <NA> Tapsta…
2 222071 Federal Minis… 6.96 3.60 08/16/… Yes Boreho… Well Mechan…
3 160612 WaterAid 6.49 7.93 12/04/… Yes Boreho… Well Hand P…
4 160669 WaterAid 6.73 7.65 12/04/… Yes Boreho… Well <NA>
5 160642 WaterAid 6.78 7.66 12/04/… Yes Boreho… Well Hand P…
6 160628 WaterAid 6.96 7.78 12/04/… Yes Boreho… Well Hand P…
7 160632 WaterAid 7.02 7.84 12/04/… Yes Boreho… Well Hand P…
8 642747 Living Water … 7.33 8.98 10/03/… Yes Boreho… Well Mechan…
9 642456 Living Water … 7.17 9.11 10/03/… Yes Boreho… Well Hand P…
10 641347 Living Water … 7.20 9.22 03/28/… Yes Boreho… Well Hand P…
# … with 94,998 more rows, 62 more variables: `#water_tech_category` <chr>,
# `#facility_type` <chr>, `#clean_country_name` <chr>, `#clean_adm1` <chr>,
# `#clean_adm2` <chr>, `#clean_adm3` <chr>, `#clean_adm4` <chr>,
# `#install_year` <dbl>, `#installer` <chr>, `#rehab_year` <lgl>,
# `#rehabilitator` <lgl>, `#management_clean` <chr>, `#status_clean` <chr>,
# `#pay` <chr>, `#fecal_coliform_presence` <chr>,
# `#fecal_coliform_value` <dbl>, `#subjective_quality` <chr>, …Projection Transformation
Converting Aspatial Data into Geospatial
wp_nga$Geometry = st_as_sfc(wp_nga$`New Georeferenced Column`)
wp_nga# A tibble: 95,008 × 71
row_id `#source` #lat_…¹ #lon_…² #repo…³ #stat…⁴ #wate…⁵ #wate…⁶ #wate…⁷
<dbl> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr>
1 429068 GRID3 7.98 5.12 08/29/… Unknown <NA> <NA> Tapsta…
2 222071 Federal Minis… 6.96 3.60 08/16/… Yes Boreho… Well Mechan…
3 160612 WaterAid 6.49 7.93 12/04/… Yes Boreho… Well Hand P…
4 160669 WaterAid 6.73 7.65 12/04/… Yes Boreho… Well <NA>
5 160642 WaterAid 6.78 7.66 12/04/… Yes Boreho… Well Hand P…
6 160628 WaterAid 6.96 7.78 12/04/… Yes Boreho… Well Hand P…
7 160632 WaterAid 7.02 7.84 12/04/… Yes Boreho… Well Hand P…
8 642747 Living Water … 7.33 8.98 10/03/… Yes Boreho… Well Mechan…
9 642456 Living Water … 7.17 9.11 10/03/… Yes Boreho… Well Hand P…
10 641347 Living Water … 7.20 9.22 03/28/… Yes Boreho… Well Hand P…
# … with 94,998 more rows, 62 more variables: `#water_tech_category` <chr>,
# `#facility_type` <chr>, `#clean_country_name` <chr>, `#clean_adm1` <chr>,
# `#clean_adm2` <chr>, `#clean_adm3` <chr>, `#clean_adm4` <chr>,
# `#install_year` <dbl>, `#installer` <chr>, `#rehab_year` <lgl>,
# `#rehabilitator` <lgl>, `#management_clean` <chr>, `#status_clean` <chr>,
# `#pay` <chr>, `#fecal_coliform_presence` <chr>,
# `#fecal_coliform_value` <dbl>, `#subjective_quality` <chr>, …wp_sf<-st_sf(wp_nga, crs=4326)
wp_sfSimple feature collection with 95008 features and 70 fields
Geometry type: POINT
Dimension: XY
Bounding box: xmin: 2.707441 ymin: 4.301812 xmax: 14.21828 ymax: 13.86568
Geodetic CRS: WGS 84
# A tibble: 95,008 × 71
row_id `#source` #lat_…¹ #lon_…² #repo…³ #stat…⁴ #wate…⁵ #wate…⁶ #wate…⁷
* <dbl> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr>
1 429068 GRID3 7.98 5.12 08/29/… Unknown <NA> <NA> Tapsta…
2 222071 Federal Minis… 6.96 3.60 08/16/… Yes Boreho… Well Mechan…
3 160612 WaterAid 6.49 7.93 12/04/… Yes Boreho… Well Hand P…
4 160669 WaterAid 6.73 7.65 12/04/… Yes Boreho… Well <NA>
5 160642 WaterAid 6.78 7.66 12/04/… Yes Boreho… Well Hand P…
6 160628 WaterAid 6.96 7.78 12/04/… Yes Boreho… Well Hand P…
7 160632 WaterAid 7.02 7.84 12/04/… Yes Boreho… Well Hand P…
8 642747 Living Water … 7.33 8.98 10/03/… Yes Boreho… Well Mechan…
9 642456 Living Water … 7.17 9.11 10/03/… Yes Boreho… Well Hand P…
10 641347 Living Water … 7.20 9.22 03/28/… Yes Boreho… Well Hand P…
# … with 94,998 more rows, 62 more variables: `#water_tech_category` <chr>,
# `#facility_type` <chr>, `#clean_country_name` <chr>, `#clean_adm1` <chr>,
# `#clean_adm2` <chr>, `#clean_adm3` <chr>, `#clean_adm4` <chr>,
# `#install_year` <dbl>, `#installer` <chr>, `#rehab_year` <lgl>,
# `#rehabilitator` <lgl>, `#management_clean` <chr>, `#status_clean` <chr>,
# `#pay` <chr>, `#fecal_coliform_presence` <chr>,
# `#fecal_coliform_value` <dbl>, `#subjective_quality` <chr>, …Projection transformation
wp_sf <- wp_sf %>%
st_transform(crs = 26392)Excluding redundant fields
NGA<- NGA |>
select(c(3:4, 8:9))Checking for duplicate name
NGA$ADM2_EN[duplicated(NGA$ADM2_EN)==TRUE][1] "Bassa" "Ifelodun" "Irepodun" "Nasarawa" "Obi" "Surulere"# Get all the duplicated LGA names
duplicated_LGA <- NGA$ADM2_EN[duplicated(NGA$ADM2_EN)==TRUE]
# Get all the indices with names that are included in the duplicated LGA names
duplicated_indices <- which(NGA$ADM2_EN %in% duplicated_LGA)
# For every index in the duplicated_indices, concatenate the two columns with a comma
for (ind in duplicated_indices) {
NGA$ADM2_EN[ind] <- paste(NGA$ADM2_EN[ind], NGA$ADM1_EN[ind], sep=", ")
}Data wrangling
wp_sf_nga <- wp_sf |>
rename(status_clean = '#status_clean') |>
select(status_clean) |>
mutate(status_clean = replace_na(
status_clean, "unknown"
))Extracting water point data
wp_functional <- wp_sf_nga |>
filter(status_clean %in%
c("Functional",
"Functional but not in use",
"Functional but needs repair"))The code chunk below is used to extract nonfunctional waterpoint
wp_nonfunctional <- wp_sf_nga |>
filter(status_clean %in%
c("Abandoned/Decommissioned",
"Abandoned",
"Non-Functional due to dry season",
"Non-Functional",
"Non functional due to dry season"))wp_unknown <- wp_sf_nga |>
filter(status_clean %in%
c("unknown"))NGA_wp <- NGA %>%
mutate(`total_wp` = lengths(
st_intersects(NGA, wp_sf_nga))) %>%
mutate(`wp_functional` = lengths(
st_intersects(NGA, wp_functional))) %>%
mutate(`wp_nonfunctional` = lengths(
st_intersects(NGA, wp_nonfunctional))) %>%
mutate(`wp_unknown` = lengths(
st_intersects(NGA, wp_unknown)))Saving the analytical data in rds format
write_rds(NGA_wp, "data/rds/NGA_wp.rds")