Life_expectancy_pj.Rmd

---
title: "Tuan Linh Dao"
output: html_notebook
---
####
# Project 2: Data visualization with life expectancy 
# 10/08/2021
####
# A. Load library :
####
### To install a package from R, type the command install.packages("name of the package") or click "Packages" then "Install", type the name of package that we want to install. 
####
```{r}
library(ggplot2)
library(gganimate)
library(dplyr)
library(ggthemes)
library(RColorBrewer)
```

####
# B. Import dataset :
####
```{r}
data <- read.csv(file.choose(), header = T)
data
```

####
# C. Line chart with ggplot :
####
```{r}
data %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy every 50 years of 9 countries",
       y = "Life expectancy",
       x = "Year",
       color = "Country") +
  theme_fivethirtyeight()
```
####
# D. Countries :
####
## 1) Australia :
####
### a) Dataframe :
```{r}
aus <- data[data$Entity == "Australia", ]
aus
```
####
### b) Summarize data :
####
```{r}
summary(aus)
# Average life expectancy of Australia :
m_aus <- mean(aus$Life.expectancy)
m_aus
```
####
### c) Plot :
```{r}
aus %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Australia",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```



####
## 2) Canada :
####
### a) Dataframe :
```{r}
can <- data[data$Entity == "Canada", ]
can
```

####
### b) Summarize data :
```{r}
summary(can)
# Average life expectancy of Canada :
m_can <- mean(can$Life.expectancy)
m_can
```
####
### c) Plot :
```{r}
can %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Canada",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```
####
## 3) France :
####
### a) Dataframe :
```{r}
fra <- data[data$Entity == "France", ]
fra
```

####
### b) Summarize data :
```{r}
summary(fra)
# Average life expectancy of France :
m_fra <- mean(fra$Life.expectancy)
m_fra
```
####
### c) Plot :
```{r}
fra %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of France",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
## 3) Germany :
####
### a) Dataframe :
```{r}
ger <- data[data$Entity == "Germany", ]
ger
```

####
### b) Summarize data :
```{r}
summary(ger)
# Average life expectancy of Germany :
m_ger <- mean(ger$Life.expectancy)
m_ger
```
####
### c) Plot :
```{r}
ger %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Germany",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
## 5) Italy :
####
### a) Dataframe :
```{r}
ita <- data[data$Entity == "Italy", ]
ita
```

####
### b) Summarize data :
```{r}
summary(ita)
# Average life expectancy of Italy :
m_ita <- mean(ita$Life.expectancy)
m_ita
```
####
### c) Plot :
```{r}
ita %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Italy",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
## 6) Japan :
####
### a) Dataframe :
```{r}
jpn <- data[data$Entity == "Japan", ]
jpn
```

####
### b) Summarize data :
```{r}
summary(jpn)
# Average life expectancy of Japan :
m_jpn <- mean(jpn$Life.expectancy)
m_jpn
```
####
### c) Plot :
```{r}
jpn %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Japan",
       y = "Life expectancy",
       x = "Year",
       color = "Country") +
  transition_time(Year)
```

####
## 7) Switzerland :
####
### a) Dataframe :
```{r}
swi <- data[data$Entity == "Switzerland", ]
swi
```

####
### b) Summarize data :
```{r}
summary(swi)
# Average life expectancy of Switzerland :
m_swi <- mean(swi$Life.expectancy)
m_swi
```
####
### c) Plot :
```{r}
swi %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of Switzerland",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
## 8) United Kingdom :
####
### a) Dataframe :
```{r}
uk <- data[data$Entity == "United Kingdom", ]
uk
```

####
### b) Summarize data :
```{r}
summary(uk)
# Average life expectancy of UK :
m_uk <- mean(uk$Life.expectancy)
m_uk
```
####
### c) Plot :
```{r}
uk %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of United Kingdom",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
## 9) United States :
####
### a) Dataframe :
```{r}
usa <- data[data$Entity == "United States", ]
usa
```

####
### b) Summarize data :
```{r}
summary(usa)
# Average life expectancy of USA :
m_usa <- mean(usa$Life.expectancy)
m_usa
```
####
### c) Plot :
```{r}
usa %>%
  ggplot(aes(y=Life.expectancy,x=Year, col=Entity)) + 
  geom_line() +
  labs(title = "Life expectancy of United States",
       y = "Life expectancy",
       x = "Year",
       color = "Country") 
```

####
# E. Summary :
####
## a) Dataframe with all countries :
```{r}
# Column of countries :
Country <- c("Australia","Canada","France","Germany","Italy","Japan","Swiss","UK","USA")
n
df1 <- rbind(m_aus,m_can,m_fra,m_ger,m_ita,m_jpn,m_swi,m_uk,m_usa)
df1

```
####
```{r}
df2 <- data.frame(Country,df1)
df2
```
####
## b) Plot :
####
### b.1) Bar plot by defautlt :
####
```{r}
df2 %>%
  ggplot(aes(Country,df1,fill=Country)) +
  geom_bar(stat = "identity") +
  labs(title = "Average life expectency of 9 countries",
       y="Life expectancy",
       x="Countries") 
  # Customize the color of the bar :
  #+ scale_fill_manual(values = c("Australia" = "salmon",
                               #"Canada" = "firebrick",
                               #"France" = "blue",
                               #"Germany" = "yellow",
                               #"Italy" = "green",
                               #"Japan" = "white",
                               #"Swiss" = "brown",
                               #"UK" = "red",
                               #"USA" = "orange"))
```
####
### b.2) Bar plot in ascending order :
####
```{r}
df2 %>%
  ggplot(aes(reorder(Country,df1),df1,fill=Country)) +
  geom_bar(stat = "identity") +
  labs(title = "Average life expectency of 9 countries in ascending order",
       y="Life expectancy",
       x="Countries") 
```
####
### b.3) Bar plot in descending order :
####
```{r}
df2 %>%
  ggplot(aes(reorder(Country,-df1),df1,fill=Country)) +
  geom_bar(stat = "identity") +
  labs(title = "Average life expectency of 9 countries in descending order",
       y="Life expectancy",
       x="Countries")
```
####
### b.4) We can type geom_col() instead of geom_bar(stat="identity) to reduce the amount of code, they are the same function.
####
```{r}
df2 %>%
  ggplot(aes(reorder(Country,-df1),df1,fill=Country)) +
  geom_col() +
  labs(title = "Average life expectency of 9 countries in descending order",
       y="Life expectancy",
       x="Countries")
```