### Install and Load libraries--------------------------------------------------
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("rnaturalearthdata")) install.packages("rnaturalearthdata")
if (!require("mapview")) install.packages("mapview")
if (!require("sf")) install.packages("sf")
if (!require("leafsync")) install.packages("leafsync")
if (!require("leaflet.extras2")) install.packages("leaflet.extras2")
if (!require("countrycode")) install.packages("countrycode")
library(tidyverse) # data wrangling and viz ecosystem
library(rnaturalearth) # Access Natural Earth dataset
library(mapview) # Create Interactive Maps easily
library(sf) # mapping with Simple Feature
library(leaflet) # interactive maps
library(leafsync) # plugin for leaflet
### Cleaning Data---------------------------------------------------------------
df <- read.csv("D:/it proj/portfolio1/population-and-demography.csv")
print(lapply(df, class))
colnames(df) <- make.names(colnames(df))
hfa_sf <- ne_countries(scale = "medium", returnclass = "sf")
#(RENAMING)
df <- df %>% mutate(
Country.name = case_match(Country.name,
"United States" ~ "United States of America",
"Democratic Republic of Congo" ~
"Democratic Republic of the Congo",
"Tanzania" ~ "United Republic of Tanzania",
"Congo" ~ "Republic of Congo",
"Cote d'Ivoire" ~ "Ivory Coast",
"Czechia" ~ "Czech Republic",
.default = Country.name))
#(CLEANING AND SYNCING THE MAP)
hfa_map <- df %>%
filter(!Country.name %in% c("world",
"Less developed regions",
"Less developed regions, excluding China",
"Less developed regions,
excluding least developed countries",
"Lower-middle-income countries",
"Asia (UN)",
"Africa (UN)",
"Least developed countries",
"Upper-middle-income countries",
"Low-income countries",
"Land-locked developing countries (LLDC)",
"High-income countries",
"More developed regions",
"Latin America and the Caribbean (UN)",
"Europe (UN)",
"Small island developing states (SIDS)")) %>%
mutate(Country.name = str_trim(Country.name)) %>%
mutate(Percentage.Under.25 = Population.under.the.age.of.25/Population*100)%>%
left_join(hfa_sf, by = c("Country.name" = "sovereignt")) %>%
sf::st_as_sf()
#(MAKING 4 CATEGORIES)
hfa_map <- hfa_map %>%
mutate(Population.Above.60 = hfa_map$Population.aged.60.to.69.years+
hfa_map$Population.aged.70.to.79.years+
hfa_map$Population.aged.80.to.89.years+
hfa_map$Population.aged.90.to.99.years+
hfa_map$Population.older.than.100.years) %>%
mutate(Percentage.Above.60 = round(Population.Above.60/Population*100, 1)) %>%
mutate(Population.40.to.59 = hfa_map$Population.aged.40.to.49.years+
hfa_map$Population.aged.50.to.59.years) %>%
mutate(Percentage.40.to.59 = round(Population.40.to.59/Population*100, 1)) %>%
mutate(Population.20.to.39 = hfa_map$Population.aged.20.to.29.years+
hfa_map$Population.aged.30.to.39.years) %>%
mutate(Percentage.20.to.39 = round(Population.20.to.39/Population*100, 1)) %>%
mutate(Population.Below.20 = hfa_map$Population.at.age.1+
hfa_map$Population.aged.1.to.4.years+
hfa_map$Population.aged.5.to.9.years+
hfa_map$Population.aged.10.to.14.years+
hfa_map$Population.aged.15.to.19.years) %>%
mutate(Percentage.Below.20 = round(Population.Below.20/Population*100, 1))
### Customizing Data and Creating Maps------------------------------------------
cols<- c("#F0F9E8", "#CCEBC5", "#A8DDB5", "#7BCCC4", "#4EB3D3"
, "#2B8CBE", "#0868AC", "#084081")
breaks <- c(1e6, 5e6, 10e6, 50e6, 100e6, 500e6, 1000e6, 1500e6)
new.breaks <- c(1, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100)
## Youth Population in Different Countries______________________________________
numbers.of.youngs <- hfa_map %>%
filter(Year=="2021") %>%
select(Country.name,Population.under.the.age.of.25, Population, Year)
Youth.num <- mapview(numbers.of.youngs ,zcol = "Population.under.the.age.of.25",
layer.name = "Population under age 25 in 2021",
col.regions = cols, at = breaks, crs = "+proj=robin")
# Compare with The Past---
numbers.of.youngs.old <- hfa_map %>%
filter(Year=="1950") %>%
select(Country.name,Population.under.the.age.of.25, Population, Year)
Youth.num.old <-mapview(numbers.of.youngs.old,zcol =
"Population.under.the.age.of.25",
layer.name = "Population under age 25 in 1950",
col.regions = cols, at = breaks, crs = "+proj=robin")
Youth.num | Youth.num.old
## Youth Percentage in Different Countries______________________________________
percentage.of.youngs <- hfa_map %>%
filter(Year=="2021") %>%
select(Country.name,Percentage.Under.25, Population, Year)
Youth.perc <- mapview(percentage.of.youngs ,zcol = "Percentage.Under.25",
at = new.breaks,layer.name = "Age Under 25 in % (2021)",
crs = "+proj=robin")
# Compare with The Past---
percentage.of.youngs.old <- hfa_map %>%
filter(Year=="1950") %>%
select(Country.name,Percentage.Under.25, Population, Year)
Youth.perc.old <-mapview(percentage.of.youngs.old ,zcol = "Percentage.Under.25",
at =new.breaks,layer.name = "Age Under 25 in % (1950)",
crs = "+proj=robin")
Youth.perc | Youth.perc.old
## Elderly percentage and Population in Different countries_____________________
Eldery.new <- hfa_map %>%
filter(Year == "2021") %>%
select(Country.name,Population,Population.Above.60,Percentage.Above.60, Year)
Elderly.perc <- mapview(Eldery.new, zcol = "Percentage.Above.60",at =new.breaks,
layer.name = "Age Above 60 in % (2021)",
crs = "+proj=robin")
# Compare with The Past---
Eldery.old <- hfa_map %>%
filter(Year == "1950") %>%
select(Country.name,Population,Population.Above.60,Percentage.Above.60, Year)
Elderly.perc.old<-mapview(Eldery.old, zcol = "Percentage.Above.60",
at=new.breaks,layer.name = "Age Above 60 in % (1950)",
crs = "+proj=robin")
Elderly.perc | Youth.perc
## Compare of four different categories of ages_________________________________
four.categories <- hfa_map %>%
filter(Year == "2021") %>%
select(Country.name,Population, Population.Below.20, Population.20.to.39,
Population.40.to.59, Population.Above.60,
Percentage.Below.20, Percentage.20.to.39, Percentage.40.to.59,
Percentage.Above.60, Year)
leafsync::sync(
mapview(four.categories, zcol = "Percentage.Below.20", at = new.breaks,
layer.name = "Age under 20 in %(2021)", crs = "+proj=robin"),
mapview(four.categories, zcol = "Percentage.20.to.39", at = new.breaks,
layer.name = "Age 20.to.39 in %(2021)", crs = "+proj=robin"),
mapview(four.categories, zcol = "Percentage.40.to.59", at = new.breaks,
layer.name = "Age 40.to.59 in %(2021)", crs = "+proj=robin"),
mapview(four.categories, zcol = "Percentage.Above.60", at = new.breaks,
layer.name = "Age over 60 in %(2021)", crs = "+proj=robin")
)