Homework Three

#Google FONTS
library(showtext)
#Lato for numbers, Assistant for text
font_add_google("Lato")
font_add_google("Assistant")
showtext_auto()

# Read in all three datasets.

life_expectancy_years <- read_csv("C:/Users/Adam Moffitt/OneDrive - West Chester University of PA/STA553/Week 5/life_expectancy_years.csv")

income_per_person <- read_csv("C:/Users/Adam Moffitt/OneDrive - West Chester University of PA/STA553/Week 5/income_per_person.csv")

countries_total <- read_csv("C:/Users/Adam Moffitt/OneDrive - West Chester University of PA/STA553/Week 5/countries_total.csv")

population <- read_csv("C:/Users/Adam Moffitt/OneDrive - West Chester University of PA/STA553/Week 5/population_total.csv")

# Manipulated the data to write a final data set

lifeexpectancylong <- life_expectancy_years %>%
  gather(key = "Year",       # the column names of the wide table
         value = "LifeExp",  # the numerical values of the table
         - geo,          # drop geo variable: its value will not be gathered (stacked)!
         na.rm = TRUE
         )   
incomeperpersonlong <- income_per_person %>%
  gather(key = "Year",       # the column names of the wide table
         value = "Income",  # the numerical values of the table
         - geo,          # drop geo variable: its value will not be gathered (stacked)!
         na.rm = TRUE
         )       # removing records with missing values ?
# combine the two tables together

populationlong <- population %>%
  gather(key = "Year",       # the column names of the wide table
         value = "Population",  # the numerical values of the table
         - geo,          # drop geo variable: its value will not be gathered (stacked)!
         na.rm = TRUE
         )       

LifeExpIncom <-left_join(incomeperpersonlong , lifeexpectancylong, by = c("geo" , "Year")) 
LifeExpIncom2 <- left_join(LifeExpIncom , populationlong , by = c("geo","Year"))



## Subregions data set
subregions <- countries_total %>% 
    select(name , region)

# Add sub regions to create final data set.
LifeExpIncomFinal <- LifeExpIncom2 %>% left_join(subregions, by = c("geo" = "name"))

#Location of Final dataset on Github
LifeExpIncomFinal <- "https://raw.githubusercontent.com/APM3030/STA553/main/homework3/LifeExpIncomFinal.csv"
LifeExpIncomFinal <- read_csv(LifeExpIncomFinal)
#convert year to integer
LifeExpIncomFinal <- mutate(LifeExpIncomFinal, Year = as.integer(LifeExpIncomFinal$Year))

    ggplot(LifeExpIncomFinal, aes(Income, LifeExp, 
                  size = Population, colour = region)) +
    geom_point(alpha = 0.5) +
        guides(size = FALSE)+
    scale_size(range = c(2, 12)) +
           scale_x_log10(labels = scales::dollar) +
    labs(title = 'Relationship Between Life Expectancy and GDP' ,
    subtitle = 'Year: {frame_time}', 
                    x = 'GDP Per Capita',
                    y = 'Life Expectancy in Years',
                    colour = 'Region:')+
    theme_minimal() +
    theme( 
        axis.line = element_line(size = .7, linetype = "solid") ,
        text=element_text(size = 18 , family="Assistant"),
        axis.title.y = element_text(vjust = -2),
        axis.title.x = element_text(vjust = 3),
        plot.title = element_text(face = "bold" , size = 26 , vjust = -3.5),
        plot.subtitle = element_text(vjust = -1),
        axis.text.x = element_text(family = "Lato" , size = 16),
        axis.text.y = element_text(family = "Lato" , size = 16),
        legend.title = element_text(face = "bold")
        ) +
    transition_time(Year)

leifinal2015 <- LifeExpIncomFinal %>% filter(Year == 2015)
#Rename Variables for Hover Text
leifinal2015 <- leifinal2015 %>% rename("Country" = geo) 
w <-     ggplot(leifinal2015, aes(Income, LifeExp, 
                  size = Population, colour = Country )) +
    geom_point(alpha = 0.5) +
        
    scale_size(range = c(2, 12)) +
           scale_x_log10(labels = scales::dollar) +
    labs(title = 'Relationship Between Life Expectancy and GDP 2015' ,
                    x = 'GDP Per Capita',
                    y = 'Life Expectancy in Years',
                    colour = 'Region:')+
    theme_minimal() +
  theme(legend.position = "none",
        axis.line = element_line(size = .7, linetype = "solid"),
        plot.title = element_text(face = "bold" , vjust = -3.5)
        )

ggplotly(w)