Solving Real World Issues With RCzechia

Jindra Lacko

2019-01-03

Czech Republic population

Population of the Czech Republic as per the latest census in 2011, per district (okres).

library(RCzechia)
library(dplyr)
library(readxl)
library(httr)
library(tmap)
library(sf)

GET("https://raw.githubusercontent.com/jlacko/RCzechia/master/data-raw/zvcr034.xls", 
    write_disk(tf <- tempfile(fileext = ".xls")))
## Response [https://raw.githubusercontent.com/jlacko/RCzechia/master/data-raw/zvcr034.xls]
##   Date: 2019-01-03 21:14
##   Status: 200
##   Content-Type: application/octet-stream
##   Size: 44.5 kB
## <ON DISK>  /tmp/Rtmp7QWxv8/file322b22dec355.xls

src <- read_excel(tf, range = "Data!B5:C97") # read in with original column names

colnames(src) <- c('NAZ_LAU1', 'obyvatel') # meaningful names instead of the original ones

src <- src %>%
  mutate(obyvatel = as.double(obyvatel)) %>% 
    # convert from text to number
  mutate(NAZ_LAU1 = ifelse(NAZ_LAU1 == "Hlavní město Praha", "Praha", NAZ_LAU1)) 
    # rename Prague (from The Capital to a regular city)
  
okresni_data <- okresy("low") %>% # data shapefile
  inner_join(src, by = "NAZ_LAU1") 
    # key for data connection - note the use of inner (i.e. filtering) join

vystup <- tm_shape(okresni_data) + tm_fill(col = "obyvatel", title = "Population", 
                                           palette = "Blues", style = "quantile", n = 5) +
  tm_shape(okresni_data) + tm_borders("grey40", lwd = 0.5) + # thin edges of districts
  tm_shape(republika("low")) + tm_borders("grey30", lwd = 1.5) + # thick national borders
  tm_layout(frame = F) # clean does it

print(vystup)

Geocoding locations & drawing them on a map

Drawing a map: three semi-random landmarks on map, with rivers shown for better orientation.

To get the geocoded data frame you may consider using geocode() function from ggmap package, which implies consent with Google terms of use.

library(RCzechia)
library(dplyr)
library(tmap)
library(sf)

rivers <- reky()

rivers <- rivers %>%
  filter(Major == T)

mista <- data.frame(misto = c('kramarova vila', 'arcibiskupske zahrady v kromerizi', 'becov nad teplou'),
                    lon = c(14.41030, 17.39353, 12.83833),
                    lat = c(50.09380, 49.30048, 50.08346))

# to geocode a list of locations consider ggmap::geocode()

POI <- mista %>% # or geocode using ggmap
  st_as_sf(coords = c("lon", "lat"), crs = 4326) # convert plain data to spatial CRS = WGS84, used by Google

tm_plot <- tm_shape(republika("low")) + tm_borders("grey30", lwd = 1) +
  tm_shape(POI) + tm_symbols(col = "firebrick3", shape = 20, size = 0.5) +
  tm_shape(rivers) + tm_lines(col = 'steelblue', lwd = 1.5, alpha = 0.5) +
  tm_legend(title = "Very Special Places") + # ... or whatever :)
  tm_layout(frame = F)
  

print(tm_plot)

Unemployment in Czech Republic - a chloropleth

A visualization problem: unemployment in the Czech Republic is in general low, but not uniformly low.
What are the hotspots?

library(dplyr)
library(RCzechia)
library(tmap)
library(sf)

src <- read.csv(url("https://raw.githubusercontent.com/jlacko/RCzechia/master/data-raw/unempl.csv"), stringsAsFactors = F) 
# open data on unemployment from Czech Statistical Office - https://www.czso.cz/csu/czso/otevrena_data
# lightly edited for size (rows filtered)

src <- src %>%
  mutate(KOD_OBEC = as.character(uzemi_kod))  # keys in RCzechia are of type character

podklad <- obce_polygony() %>% # obce_polygony = municipalities in RCzechia package
  inner_join(src, by = "KOD_OBEC") # linking by key


vystup <- tm_shape(republika()) + tm_borders(col = "grey40") +
  tm_shape(podklad) + tm_fill(col = "hodnota", title = "Unemployment", palette = "YlOrRd") +
  tm_legend(legend.format = list(fun = function(x) paste0(formatC(x, digits = 0, format = "f"), " %"))) +
  tm_layout(frame = F)

print(vystup)

Distnance between Prague to Brno

Calculate distance between two spatial objects; the sf package supports (via gdal) point to point, point to polygon and polygon to polygon distances.

Calculating distance from Prague (#1 Czech city) to Brno (#2 Czech city).

library(dplyr)
library(RCzechia)
library(sf)
library(units)

obce <- obce_polygony()

praha <- obce[obce$NAZ_OBEC == "Praha", ]
brno <- obce[obce$NAZ_OBEC == "Brno", ]

vzdalenost <- st_distance(praha, brno) %>%
  set_units("kilometers") # easier to interpret than meters, miles or decimal degrees..

print(vzdalenost)
## Units: [kilometers]
##          [,1]
## [1,] 152.8073

Interactive Map

Interactive maps are powerful tools for data vizualization. They are easy to produce with the tmap package.

I found the stamen toner basemap a good company for interactive chloropleths - it gives enough context without distracting from the story of your data.

A map of the whole Czech Republic in original resolution (the accuracy is about 1 meter) would be rather sizeable, and I found it better policy to either:

library(dplyr)
library(RCzechia)
library(tmap)
library(sf)

src <- read.csv(url("https://raw.githubusercontent.com/jlacko/RCzechia/master/data-raw/unempl.csv"), stringsAsFactors = F) 
# open data on unemployment from Czech Statistical Office - https://www.czso.cz/csu/czso/otevrena_data
# lightly edited for size (rows filtered)


src <- src %>%
  mutate(KOD_OBEC = as.character(uzemi_kod))  # keys in RCzechia are of type character

podklad <- obce_polygony() %>% # obce_polygony = municipalities in RCzechia package
  inner_join(src, by = "KOD_OBEC") %>% # linking by key
  filter(KOD_CZNUTS3 == "CZ071") # Olomoucký kraj

tmap_mode("view")

vystup <- tm_shape(podklad) + tm_fill(col = "hodnota", title = "Unemployment", palette = "YlOrRd", id = "NAZ_OBEC") +
  tm_legend(legend.format = list(fun = function(x) paste0(formatC(x, digits = 0, format = "f"), " %"))) +
  tm_view(basemaps = "Stamen.Toner")

print(vystup)

sigma

Dissolving sf Polygons

Creating custom polygons by aggregating administrative units is a common use case in sales reporting and analysis. Function union_sf() makes this task easier by dissolving polygons accoring to a value of a data column.

In this demonstration the Czech LAU1 units are grouped into two categories: those with odd lettered names, and those with even letters. They are then dissolved into two multipolygons.

library(RCzechia)
library(dplyr)
library(sf)


poly <- okresy("low") %>% # Czech LAU1 regions as sf data frame
  mutate(oddeven = ifelse(nchar(NAZ_LAU1) %% 2 == 1, "odd", "even" )) %>% # odd or even?
  union_sf("oddeven") # ... et facta est lux

plot(poly, key.pos = 1)