HappinessVisualization.Rmd

---
title: 'WHO GETS TO BE HAPPY?'
output:
  html_document:
    code_folding: hide
  pdf_document: default
---
<style type="text/css">
h1.title {
  font-size: 30px;
  text-align: center;
}
h4.author { 
    font-size: 20px;
  font-family: "Times New Roman", Times, serif;
  text-align: center;
}
h4.date { 
  font-size: 20px;
  font-family: "Times New Roman", Times, serif;
  text-align: center;
}

</style>

<style type="text/css">
  body {
    background-color: #F6F6F4;
  }
</style>
```{r include=FALSE}
library(ggplot2)
library(ggthemes)
library(nlme)
library(gganimate)
library(gapminder)
library(ggExtra)
library(psych)
library(reshape2)
library(dplyr)
library(nycflights13)
library(ggcorrplot)
library(waffle)
library(tidyr)
library(scales)
library(ggalt)
library(data.table)
library(extrafont)
library(lubridate)
library(DT)
library(grid)
library(gridExtra)
library(prettydoc)
library(devtools)
library(tidyverse)
library(ggdark)
library(here)
library(png)
library(gifski)
library(forcats)
library(tufte)
library(colorspace)
library(viridisLite)
library(Zelig)
library(formatR)
library(DiagrammeR)
library(xaringan)
library(ggridges)
library(GGally)
library(RColorBrewer)

```

```{r include=FALSE}
#### General Colors ####
Axis_color = '#888888'
Background_color= '#f6f6f4'
General_color1 = '#9b2d6e'
General_color2= '#2f9480'
General_color3 = '#779ECB'
Africa_color = '#404040'
Europe_color= '#00c8de'
Asia_color = '#ffca50'
America_color = '#ff552d'
Oceania_color = '#088A08'
Trend_color = '#FFFFFF'

#### Theme ####
GroupC_theme<- theme_bw()+theme(
  #Panel
    panel.background = element_rect(fill=Background_color),
    panel.border = element_blank(),
    panel.grid = element_blank(),
    panel.grid.major = element_blank(), 
    panel.grid.minor = element_blank(),
  #Plot
    
    plot.background = element_rect(fill=Background_color),
    plot.title = element_text(size = 10, hjust = 0.5, color = Axis_color),
  #Axis
    axis.title = element_text(size =9, hjust = 0.5, color = Axis_color),
    axis.text = element_text(colour = Axis_color, size = 7),
    axis.ticks = element_blank(),
    axis.line = element_line(colour = Axis_color, size=0.2), 
  #Legend
    legend.background = element_rect(fill = Background_color),
    legend.text	= element_text(size = 9, hjust = 0.5, color = Axis_color), 
    legend.position = c(0.9, 0.15),
    legend.key = element_blank(),
    legend.title = element_blank(),
  #Strip
    strip.background =element_rect(fill = Background_color), 
    strip.text = element_text(size = 9, color = Axis_color)
  #Labs
)
theme_set(GroupC_theme)
```
```{r include=FALSE}
folder_path <- "C:/Users/Katlego/OneDrive - IE Students/IE BUSINESS SCHOOL/II/Data Visualization/Assignments/First"
happiness <- fread(file.path(folder_path, "Dataset 2005-2018.csv"), sep = ",", header = TRUE)

```
# Who is the happiest?

```{r include=FALSE}
names(happiness)
head(happiness, n=20)
str(happiness)
summary(happiness)
```

```{r collapse = TRUE,echo=FALSE,fig.show='hold',fig.align="center",tidy=TRUE}
# Happiness by Country over Time 
ggplot(happiness) +
  geom_line(aes (Year, Score, group = Country), alpha = 0.7,lwd = 0.2, show.legend = F, color= General_color1)+
  coord_cartesian(xlim=c(2008,2018))+
  scale_x_continuous(breaks = c(2008, 2018), label = c("2008", "2018"))+ 
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  xlab("Year") + ylab("Happiness Index")
```

```{r include=FALSE,fig.align="center",tidy=TRUE}
# Happiness by Continent over Time 
ggplot(happiness) +
  geom_line(aes (Year, Score, group = Country, color=Continent), alpha = 0.9,lwd = 0.2, show.legend = T)+
  coord_cartesian(xlim=c(2008,2018))+
  scale_color_manual(values=c(Africa_color, America_color, Asia_color, Europe_color, Oceania_color))+
  scale_x_continuous(breaks = c(2008, 2018), label = c("2008", "2018"))+ 
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  xlab("Year") + ylab("Happiness Index")
```


```{r fig.align="center",tidy=TRUE}
# Happiness - Continent Trendline
Trend<- happiness %>% group_by(Continent,Year) %>% summarise(Score=mean(Score))
ggplot() +
  geom_line(data = transform(happiness, Continent = NULL), aes (Year, Score, group=Country), alpha = 0.5, lwd = 0.05)+
  coord_cartesian(xlim=c(2008,2018))+
  geom_line(data=Trend,aes(Year,Score, group= Continent, color=Continent),lwd = 0.8, show.legend=F)+
  scale_color_manual(values=c(Africa_color, America_color, Asia_color, Europe_color, Oceania_color))+
  scale_x_continuous(breaks = c(2008, 2018), label = c("2008", "2018"))+ 
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  theme(axis.title.x = element_blank()) + ylab("Happiness Index")


```

```{r message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
# Happiness by Continent  over Time - Splited #
ggplot() +
  geom_line(data = transform(happiness, Continent = NULL), aes (Year, Score, group=Country), alpha = 0.25, lwd = 0.05)+
  geom_line(data=happiness, aes (Year, Score, group = Country, color=Continent), lwd = 0.20, show.legend = FALSE)+
  scale_color_manual(values=c(Africa_color, America_color, Asia_color, Europe_color, Oceania_color))+
  facet_wrap(~ Continent, ncol=3, strip.position = "bottom")+ 
  theme(strip.background = element_blank(), strip.placement = "outside") +
  theme(axis.text.x = element_blank(), axis.line.x =  element_blank() )+
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  coord_cartesian(xlim=c(2008,2018))+
  geom_smooth(data=happiness,aes(Year, Score, group = 1), lwd = 1, method = 'loess', span = 0.1, se = TRUE, color = Trend_color)+
  ylab("Happiness Index")+theme(axis.title.x = element_blank())
```

# Can money buy happiness?
```{r messages=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
Recent <- happiness[happiness$Year==2018,]

# Can money buy happiness? 
ggplot(Recent, aes(x=exp(GDP), y=Score, color=Continent)) + 
  geom_point(size=1.5,show.legend = F)+ 
  scale_color_manual(values=c(Africa_color, America_color, Asia_color, Europe_color, Oceania_color))+
  geom_vline(xintercept=30000, color= Axis_color, linetype = "dashed")+
  scale_x_continuous(breaks = c(0,30000,75000), label = c("low", "30.000","high"))+ 
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  xlab("GDP per Capita") + ylab("Happiness Index")
```
\
There is a positive relationship between happiness and GDP per Capita. But why is this not true for the Americas? 

```{r message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
# Zoom to Low GDP(Treshold=30K) Countries # (Add X Label)

ggplot()+
  geom_point(data = transform(Recent, Continent = NULL), aes (x=exp(GDP), y=Score), alpha = 0.08, lwd = 2)+
  geom_point(data=Recent, aes (x=exp(GDP), y=Score, color=Continent), lwd = 2, show.legend = FALSE)+
  scale_color_manual(values=c(Africa_color, America_color, Asia_color, Europe_color, Oceania_color))+
  facet_wrap(~ Continent, ncol=3, strip.position = "bottom")+ 
  theme(strip.background = element_blank(), strip.placement = "outside") +
  theme(axis.text.x = element_blank(), axis.line.x =  element_blank())+
  ylab("Happiness Index")+theme(axis.title.x = element_blank())+
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+
  xlim(0,30000)
```
\
When compared to countries within the same GDP range, the americas have a higher average ranking in the Happiness Index.

But is this true for all countries in the Americas?

```{r message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
#### Understanding the Americas ####

America <- filter(happiness, Continent == "America" & Year %in% c(2010, 2018)) %>% select(Country, Year, GDP)
America$GDP<- exp(America$GDP)
America2 <- spread(America, Year, GDP)
names(America2) <- c("Country", "y2010", "y2018")
America2 <- arrange(America2, desc(y2010))
America2$Country <- factor(America2$Country, levels=rev(America2$Country))

# Does North America have low GDP (Treshold=30K)? #
ggplot(America2, aes(Country, x = y2010, xend = y2018)) +
  geom_vline(xintercept=30000, color= Axis_color, linetype = "dashed")+
  geom_dumbbell(color=America_color)+
  scale_x_continuous(breaks = c(0,30000,55000), label = c("low", "30.000","high"))+
  xlab("GDP per Capita")+theme(axis.title.y = element_blank())
```
\
Latin American and Carribean countries are below the threshold. Begging the question, what are the other factors that affect happiness? 

```{r message=FALSE,warning=FALSE,fig.align='center',tidy=TRUE}
# Focus on Latin America & Caribbean  
# What factors are truly impacting their happiness index? #
Latin<- happiness %>% filter(Region=="Latin America and Caribbean"& Year>=2010 ) %>%
        select(Region,Year, GDP,Social_Support, Life_Expectancy,Freedom_Choices) %>%
        group_by(Year)%>%
        summarise( Social_Support=mean(Social_Support),Freedom_Choices=mean(Freedom_Choices),
                   Life_Expectancy=mean(Life_Expectancy),GDP=mean(exp(GDP)))
World <- happiness %>% filter(Year>=2010) %>%
          select(Continent,Year, GDP,Social_Support, Life_Expectancy,Freedom_Choices) %>%
          group_by(Year)%>%
          summarise( Social_Support=mean(Social_Support, na.rm = T), Freedom_Choices=mean(Freedom_Choices,na.rm = T),
                     Life_Expectancy=mean(Life_Expectancy, na.rm = T),GDP=mean(exp(GDP),na.rm = T))
Latin$Continent<-"Latin America"
World$Continent<-"Rest of the World"
df <- rbind(World,Latin)

ggparcoord(df, columns = 2:5, groupColumn = 6, alphaLines = 0.3, showPoints = TRUE)+
  scale_color_manual(values=c(America_color, General_color1))+
  theme(legend.text	= element_text(size = 6, hjust = 0.5), legend.position = c(0.9, 0.9))+
  theme(axis.title.x = element_blank(),axis.title.y = element_blank())+
  scale_y_continuous(breaks = c(-0.8, 1.8), label = c("low", "high"))+
  scale_x_discrete(labels=c("Social_Support" = "Social Support", "Freedom_Choices" = "Freedom of Choices", "Life_Expectancy" = "Life Expectancy","GDP"="GDP per Capita"))

```
\
We can observe that the support of family and friends, the level of freedom they enjoy and their longevity affect the happiness of Latin Americans than GDP per Capita.

Are all Latin American countries happy all the time? 
```{r include=FALSE, message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
# Identifying the Venezuela
Latin2 <- happiness %>% filter(Region=="Latin America and Caribbean");
ggplot(Latin2, aes(Year, Score)) +
  geom_line(color="#cccccc") +
  facet_wrap(~Country,  ncol=3) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) 
```
```{r message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
Venezuela <- Latin2 %>% filter(Country=="Venezuela")
ggplot() +
  geom_line(data=Latin2,aes(Year, Score, group = Country), alpha = 0.7,lwd = 0.1, show.legend = F, color= America_color)+
  geom_line(data=Venezuela, aes (Year,Score,color=Country), lwd = 0.8, show.legend = T)+
  coord_cartesian(xlim=c(2008,2018))+
  theme(legend.text	= element_text(size = 6, hjust = 0.5), legend.position = c(0.88, 0.95))+
  scale_y_continuous(breaks = c(4, 7), label = c("low", "high"))+ ylab("Happiness Index")+
  scale_x_continuous(breaks = c(2008,2018), label = c("2008","2018"))+
  theme(axis.title.x = element_blank())
```

# Government policy influence on happiness
```{r message=FALSE,warning=FALSE,fig.align="center",tidy=TRUE}
# Does the government con
Venezuela <- Venezuela %>% mutate_each_(funs(scale(.) %>% as.vector), vars=c(5,11:13))  
df2<-Venezuela %>% filter(Year %in% c(2012,2013,2016))

Government <-ggplot()+
  geom_line(data=Venezuela, aes (Year,Score,color=America_color), lwd = 0.8,show.legend = T)+
  geom_line(data=Venezuela, aes (Year,Confidence_Government,color=General_color2), lwd = 0.8, show.legend = T)+
  scale_color_manual(values=c(America_color, General_color2),labels=c("Happiness","Government Trust"))+
  theme(legend.text	= element_text(size = 8, hjust = 0.5), legend.position = c(0.88, 0.90))+
  geom_point(data=df2, aes (x=Year, y=Score,color=America_color) ,lwd = 2)+
  geom_point(data=df2, aes (x=Year, y=Confidence_Government,color=General_color2), lwd = 2)+
  
  coord_cartesian(xlim=c(2010,2018))+
  annotate(geom = "curve", x = 2011.5, y = -0.2, xend = 2012, yend =0.6 , curvature = .3, arrow = arrow(length = unit(1.5, "mm")), color=Axis_color) +
  annotate(geom = "text", x = 2011.4, y = -0.3, label = "Chavez Died", hjust = "right",color=Axis_color,size=3)+
  annotate(geom = "curve", x = 2012.3, y = -1, xend = 2013, yend =-0.3 , curvature = .3, arrow = arrow(length = unit(1.5, "mm")),color=Axis_color) +
  annotate(geom = "text", x = 2012.2, y = -1, label = "New President", hjust = "right",color=Axis_color, size=3)+
  scale_x_continuous(breaks = c(2012,2013,2016), label = c("2012","2013","2016"))+
  scale_y_continuous(breaks = c(-2, 1), label = c("low", "high"))+
  theme(axis.title.y = element_blank(),axis.title.x = element_blank())

Corruption <- ggplot()+
  geom_line(data=Venezuela, aes (Year,Score), color=America_color,lwd = 0.8,show.legend = T)+
  geom_line(data=Venezuela, aes (Year,Corruption_Perception,color=General_color3), lwd = 0.8,show.legend = T)+
  scale_color_manual(values=c(General_color3),labels=c("Corruption"))+
  theme(legend.text	= element_text(size = 8, hjust = 0.5), legend.position = c(0.88, 0.94))+
  geom_point(data=df2, aes (x=Year, y=Score), color=America_color, lwd = 2)+
  geom_point(data=df2, aes (x=Year, y=Corruption_Perception, color=General_color3),lwd = 2)+
  
  coord_cartesian(xlim=c(2010,2018))+  
  annotate(geom = "curve", x = 2016.5, y = 0.5, xend = 2016.1, yend =1.3 , curvature = .3, arrow = arrow(length = unit(1.5, "mm")),color=Axis_color) +
  annotate(geom = "text", x = 2016.3, y = 0,5, label = "Highest Inflation \n 800%", hjust = "left", color=Axis_color, size=3)+
  annotate(geom = "curve", x = 2012, y = 1.7, xend = 2012.8, yend =1 , curvature = .3, arrow = arrow(length = unit(1.5, "mm")),color=Axis_color) +
  annotate(geom = "text", x = 2011.3, y = 2, label = "Electoral Fraud", hjust = "left",color=Axis_color, size=3)+
  scale_x_continuous(breaks = c(2012,2013,2016), label = c("2012","2013","2016"))+
  scale_y_continuous(breaks = c(-2, 1.65), label = c("low", "high"))+
  theme(axis.title.y = element_blank(),axis.title.x = element_blank())

grid.arrange(Government,Corruption,ncol=1)
```
\
In Venezuela there has been political unrest during the last decade. How the people perceive their leaders actions