R wold map

install.packages('tidyverse')
install.packages('ggthemes')
install.packages('plotly')
install.packages('dplyr')
library('tidyverse')
library('ggthemes')
library('plotly')
library('dplyr')
install.packages('factoextra')
install.packages('cluster')
library(factoextra)
library(cluster)
install.packages('maps', dependencies = TRUE)
library(ggplot2)
require(maps)

df<-read.csv('https://raw.githubusercontent.com/annstasi/R/main/world-happiness-report-2021.csv', stringsAsFactors = F)
df <- subset(df, select=c("п.їCountry.name", "Regional.indicator", "Ladder.score", "Logged.GDP.per.capita", "Social.support", "Healthy.life.expectancy", "Freedom.to.make.life.choices", "Generosity", "Perceptions.of.corruption", "Dystopia...residual"))
df <- df %>% rename( Country=п.їCountry.name, Region=Regional.indicator, Happiness_score=Ladder.score, GDP=Logged.GDP.per.capita, Social_support=Social.support, Life_expectancy=Healthy.life.expectancy, Freedom=Freedom.to.make.life.choices, Corruption=Perceptions.of.corruption, Dystopia_residual=Dystopia...residual)

str(df)
# Стандартизация данных
data_ST <- scale(df[,-(1:2)])
head(data_ST)

set.seed(1234)
countries <- kmeans(data_ST, 4)

countries1 <- df
countries1$cluster <- as.factor(countries$cluster) # Добавление колонки с кластерами

head(countries1,3)

# Уровень счастья по кластерам (1 самый большой, 3 меньший)
countries_avg <- countries1 %>%
  group_by(cluster) %>%
  summarize_if(is.numeric, mean, na.rm = TRUE)


countries_avg[,1:2]

countries_max <- countries1 %>%
  group_by(cluster) %>%
  summarize_if(is.numeric, max, na.rm = TRUE)
countries_max[,1:2]

countries_min <- countries1 %>%
  group_by(cluster) %>%
  summarize_if(is.numeric, min, na.rm = TRUE)
countries_min[,1:2]

world_map <- map_data("world") # Информация по странам
head(world_map,3)

countries1$Country[countries1$Country == "United Kingdom"] <- "UK"
countries1$Country[countries1$Country == "United States"] <- "USA"
countries1$Country[countries1$Country == "Taiwan Province of China"] <- "Taiwan"
countries1$Country[countries1$Country == "North Cyprus"] <- "Cyprus"
countries1$Country[countries1$Country == "Hong Kong S.A.R. of China"] <- "China"
countries1$Country[countries1$Country == "Congo (Brazzaville)"] <- "Republic of Congo"
countries1$Country[countries1$Country == "Palestinian Territories"] <- "Palestine"

countries_by_cluster <- countries1[,c("Country", "cluster")]
countries_by_cluster$cluster <- as.numeric(countries_by_cluster$cluster)
# Объединяем данные
clustering_map <- left_join(countries_by_cluster, world_map, by = c("Country"  = "region"), keep = TRUE)

clustering_map %>% filter (is.na(region))


all.layer <- geom_polygon(data = world_map, aes(long, lat, group = group))

ggplot(clustering_map, aes(long, lat, group = group))+
  all.layer +
  geom_polygon(aes(fill = cluster)) +
  scale_fill_viridis_c(option = "C", labels=c("5.48-7.84", "4.52-7.07", "3.14-5.38", "2.52-5.34")) # разбить на кластеры по цветам
options(repr.plot.width=15, repr.plot.height=8) # изменить размер карты



# Рисуем карту
thismap <- mutate(world_map, fill = ifelse(region %in% clustering_map$Country, clustering_map$cluster, "white"))
scale_fill_viridis_c(option = "C") # разбить на кластеры по цветам

# Use scale_fiil_identity to set correct colors
ggplot(thismap, aes(long, lat, fill = fill, group=group)) +
  geom_polygon(colour="black") + ggtitle("Map of World") #+
#scale_fill_identity()