Load liabraries
library(ggplot2)
library(tidyverse)
library(dplyr)
library(plotly)
library(corrplot)
library(highcharter)
library(plot3D)
library(countrycode)
library(maps)
library(caret)
library(caTools)
library(randomForest)
library(e1071)Data Preprocessing
data15 <- read.csv("C:/Users/power/BST260/Project/world-happiness/world-happiness-new/2015.csv", stringsAsFactors = F)
data16 <- read.csv("C:/Users/power/BST260/Project/world-happiness/world-happiness-new/2019.csv", stringsAsFactors = F)
data17 <- read.csv("C:/Users/power/BST260/Project/world-happiness/world-happiness-new/2017.csv", stringsAsFactors = F)Adding continents
data15$continent <- NA
data15$continent[which(data15$Region %in% c("Eastern Asia", "Southeastern Asia", "Southern Asia"))] <- "Asia"
data15$continent[which(data15$Region %in% c("Central and Eastern Europe", "Western Europe"))] <- "Europe"
data15$continent[which(data15$Region == "North America")] <- "North America"
data15$continent[which(data15$Country %in% c("Canada", "Jamaica", "Honduras", "Trinidad and Tobago",
"Panama", "El Salvador","Haiti", "Peru",
"Costa Rica", "Dominican Republic", "Mexico", "United States",
"Guatemala", "Nicaragua"))] <- "North America"
data15$continent[which(data15$Country %in% c("Brazil", "Chile", "Argentina", "Uruguay",
"Colombia", "Ecuador","Paraguay", "Peru",
"Bolivia", "Venezuela", "Suriname"))] <- "South America"
data15$continent[which(data15$Country %in% c("United Arab Emirates", "Oman", "Qatar", "Saudi Arabia",
"Kuwait", "Bahrain","Libya", "Jordan",
"Lebanon", "Iraq", "Iran", "Yemen", "Syria",
"Turkey", "Israel", "Egypt", "Palestinian Territories"))] <- "Middle East"
data15$continent[which(data15$Country %in% c("Mauritius", "Nigeria", "Zambia", "Somaliland region",
"Mozambique", "Lesotho","Swaziland", "South Africa",
"Ghana", "Zimbabwe", "Tunisia", "Morocco", "Algeria",
"Sudan", "Congo (Kinshasa)", "Liberia",
"Ethiopia", "Sierra Leone", "Mauritania", "Kenya", "Djibouti",
"Botswana", "Malawi", "Cameroon", "Angola",
"Mali", "Congo (Brazzaville)", "Comoros", "Uganda",
"Senegal", "Gabon", "Niger", "Tanzania", "Madagascar",
"Central African Republic", "Chad", "Guinea",
"Ivory Coast", "Burkina Faso", "Rwanda",
"Benin", "Burundi", "Togo", "Namibia"))] <- "Africa"
data15$continent[which(data15$Country %in% c("Australia", "New Zealand"))] <- "Oceania"
data16$continent <- NA
data16$continent[which(data16$Region %in% c("Eastern Asia", "Southeastern Asia", "Southern Asia"))] <- "Asia"
data16$continent[which(data16$Region %in% c("Central and Eastern Europe", "Western Europe"))] <- "Europe"
data16$continent[which(data16$Region == "North America")] <- "North America"
data16$continent[which(data16$Country %in% c("Canada", "Jamaica", "Honduras", "Trinidad and Tobago",
"Panama", "El Salvador","Haiti", "Peru",
"Costa Rica", "Dominican Republic", "Mexico", "United States",
"Guatemala", "Nicaragua", "Puerto Rico", "Belize"))] <- "North America"
data16$continent[which(data16$Country %in% c("Brazil", "Chile", "Argentina", "Uruguay",
"Colombia", "Ecuador","Paraguay", "Peru",
"Bolivia", "Venezuela", "Suriname"))] <- "South America"
data16$continent[which(data16$Country %in% c("United Arab Emirates", "Oman", "Qatar", "Saudi Arabia",
"Kuwait", "Bahrain","Libya", "Jordan",
"Lebanon", "Iraq", "Iran", "Yemen", "Syria",
"Turkey", "Israel", "Egypt", "Palestinian Territories"))] <- "Middle East"
data16$continent[which(data16$Country %in% c("Mauritius", "Nigeria", "Zambia", "Somaliland region",
"Mozambique", "Lesotho","Swaziland", "South Africa",
"Ghana", "Zimbabwe", "Tunisia", "Morocco", "Algeria",
"Sudan", "Congo (Kinshasa)", "Liberia",
"Ethiopia", "Sierra Leone", "Mauritania", "Kenya", "Djibouti",
"Botswana", "Malawi", "Cameroon", "Angola",
"Mali", "Congo (Brazzaville)", "Comoros", "Uganda",
"Senegal", "Gabon", "Niger", "Tanzania", "Madagascar",
"Central African Republic", "Chad", "Guinea",
"Ivory Coast", "Burkina Faso", "Rwanda",
"Benin", "Burundi", "Togo", "Namibia", "Somaliland Region",
"South Sudan", "Somalia"))] <- "Africa"
data16$continent[which(data16$Country %in% c("Australia", "New Zealand"))] <- "Oceania"newdata15 <- data15[,c("Country","Happiness.Score")]
newdata15$Country <- as.character(data15$Country)
colnames(newdata15)<-c("country","value")
Countryname15 <-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands")
for(i in names(Countryname15)){
newdata15[newdata15$country==i,"country"] <- Countryname15[i]
}
hc14 <- highchart() %>%
hc_add_series_map(worldgeojson, newdata15, value = "value", joinBy = c('name','country')) %>%
hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
#hc_colorAxis(minColor = "#FFFFFF", maxColor = "#434348")%>%
hc_title(text = "Happiness Score") %>%
hc_subtitle(text = "2014") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value")
newdata16 <- data16[,c("Country","Happiness.Score")]
newdata16$Country <- as.character(newdata16$Country)
colnames(newdata16)<-c("country","value")
Countryname16<-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo","Somaliland region"="Somaliland",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands",
"Somaliland Region"="Somaliland")
for(i in names(Countryname16)){
newdata16[newdata16$country==i,"country"]<-Countryname16[i]
}
hc18 <- highchart() %>%
hc_add_series_map(worldgeojson, newdata16, value = "value", joinBy = c('name','country')) %>%
hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
#hc_colorAxis(minColor = "#e6ebf5", maxColor = "#003399")%>%
hc_title(text = "Happiness Score") %>%
hc_subtitle(text = "2018") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value") hc14hc18Compared scores between 2014 and 2018, the GDP per capita distribution did not change very much. Scandinavian Peninsula, West Europe, North America, middle east, and Oceania had the high value. Afghanistan and some Aferican countries had the low scores.
newdata15 <- data15[,c("Country","Economy")]
newdata15$Country <- as.character(data15$Country)
colnames(newdata15)<-c("country","value")
Countryname15 <-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands")
for(i in names(Countryname15)){
newdata15[newdata15$country==i,"country"] <- Countryname15[i]
}
hc14e <- highchart() %>%
hc_add_series_map(worldgeojson, newdata15, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "red", maxColor = "blue")%>%
hc_title(text = "GDP per Capita") %>%
hc_subtitle(text = "2014") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value")
newdata16 <- data16[,c("Country","Economy")]
newdata16$Country <- as.character(newdata16$Country)
colnames(newdata16)<-c("country","value")
Countryname16<-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo","Somaliland region"="Somaliland",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands",
"Somaliland Region"="Somaliland")
for(i in names(Countryname16)){
newdata16[newdata16$country==i,"country"]<-Countryname16[i]
}
hc18e <- highchart() %>%
hc_add_series_map(worldgeojson, newdata16, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "red", maxColor = "blue")%>%
hc_title(text = "GDP per Capita") %>%
hc_subtitle(text = "2018") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value") 2014 GDP per capita
hc14ehc18eScandinavian region, Canada, Oceania, and East Asian had high life expectancy. Most African countries and Afganistan had the low life expectancy.
newdata15 <- data15[,c("Country","Life.expectancy")]
newdata15$Country <- as.character(data15$Country)
colnames(newdata15)<-c("country","value")
Countryname15 <-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands")
for(i in names(Countryname15)){
newdata15[newdata15$country==i,"country"] <- Countryname15[i]
}
hc14life <- highchart() %>%
hc_add_series_map(worldgeojson, newdata15, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "yellow", maxColor = "blue")%>%
hc_title(text = "Life Expectancy") %>%
hc_subtitle(text = "2014") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value")
newdata16 <- data16[,c("Country","Life.expectancy")]
newdata16$Country <- as.character(newdata16$Country)
colnames(newdata16)<-c("country","value")
Countryname16<-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo","Somaliland region"="Somaliland",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands",
"Somaliland Region"="Somaliland")
for(i in names(Countryname16)){
newdata16[newdata16$country==i,"country"]<-Countryname16[i]
}
hc18life <- highchart() %>%
hc_add_series_map(worldgeojson, newdata16, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "yellow", maxColor = "blue")%>%
hc_title(text = "Life Expectancy") %>%
hc_subtitle(text = "2018") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value") 2014 Life Expectancy
hc14lifehc18lifeMyanmar had the highest value of generosity in 2014 and 2018. North America, UK, and Oceania had the high values. Russia had the lowest value of 0.00199 in 2014 and increased to 0.082 in 2018.
newdata15 <- data15[,c("Country","Generosity")]
newdata15$Country <- as.character(data15$Country)
colnames(newdata15)<-c("country","value")
Countryname15 <-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands")
for(i in names(Countryname15)){
newdata15[newdata15$country==i,"country"] <- Countryname15[i]
}
hc14generosity <- highchart() %>%
hc_add_series_map(worldgeojson, newdata15, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "pink", maxColor = "blue")%>%
hc_title(text = "Generosity") %>%
hc_subtitle(text = "2014") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value")
newdata16 <- data16[,c("Country","Generosity")]
newdata16$Country <- as.character(newdata16$Country)
colnames(newdata16)<-c("country","value")
Countryname16<-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo","Somaliland region"="Somaliland",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands",
"Somaliland Region"="Somaliland")
for(i in names(Countryname16)){
newdata16[newdata16$country==i,"country"]<-Countryname16[i]
}
hc18generosity <- highchart() %>%
hc_add_series_map(worldgeojson, newdata16, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "pink", maxColor = "blue")%>%
hc_title(text = "Generosity") %>%
hc_subtitle(text = "2018") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value") 2014 Generosity
hc14generosityhc18generosityMost countries did not trust their governments except scandinavian region, Oceania, and United States.
newdata15 <- data15[,c("Country","Trust")]
newdata15$Country <- as.character(data15$Country)
colnames(newdata15)<-c("country","value")
Countryname15 <-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands")
for(i in names(Countryname15)){
newdata15[newdata15$country==i,"country"] <- Countryname15[i]
}
hc14trust <- highchart() %>%
hc_add_series_map(worldgeojson, newdata15, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "purple", maxColor = "blue")%>%
hc_title(text = "Trust") %>%
hc_subtitle(text = "2014") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value")
newdata16 <- data16[,c("Country","Trust")]
newdata16$Country <- as.character(newdata16$Country)
colnames(newdata16)<-c("country","value")
Countryname16<-c("Congo (Brazzaville)"="Democratic Republic of the Congo","Guinea"="Equatorial Guinea",
"North Cyprus"="Northern Cyprus","Serbia"="Republic of Serbia",
"Congo (Brazzaville)"="Republic of Congo","Somaliland region"="Somaliland",
"Tanzania"="United Republic of Tanzania","United States Minor Outlying Islands"="United States",
"United States"="United States of America","United States"="United States Virgin Islands",
"Somaliland Region"="Somaliland")
for(i in names(Countryname16)){
newdata16[newdata16$country==i,"country"]<-Countryname16[i]
}
hc18trust <- highchart() %>%
hc_add_series_map(worldgeojson, newdata16, value = "value", joinBy = c('name','country')) %>%
#hc_colorAxis(stops = color_stops()) %>%
####hc_colorAxis(dataClasses = color_classes(c(seq(0, 10, by = 2), 50)))%>%
hc_colorAxis(minColor = "purple", maxColor = "blue")%>%
hc_title(text = "Trust") %>%
hc_subtitle(text = "2018") %>%
hc_tooltip(borderWidth = 1.5, headerFormat = "", valueSuffix = "value") 2014 Trust
hc14trusthc18trust
Social Support
Most countries had fair social support. South Asian region had the low social support.
2014 Social Support
2018 Social Support