NationsHW

Load the Libraries

library(RColorBrewer)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(highcharter)

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

library(ggplot2)

Nations Dataset

setwd("C:/Users/MCuser/Desktop/DATA110_CourseMaterials")
nations <- read_csv("nations.csv")

## Rows: 5275 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): iso2c, iso3c, country, region, income
## dbl (5): year, gdp_percap, population, birth_rate, neonat_mortal_rate
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Dataset Structure

str(nations)

## spec_tbl_df [5,275 × 10] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ iso2c             : chr [1:5275] "AD" "AD" "AD" "AD" ...
##  $ iso3c             : chr [1:5275] "AND" "AND" "AND" "AND" ...
##  $ country           : chr [1:5275] "Andorra" "Andorra" "Andorra" "Andorra" ...
##  $ year              : num [1:5275] 1996 1994 2003 1990 2009 ...
##  $ gdp_percap        : num [1:5275] NA NA NA NA NA NA NA NA NA NA ...
##  $ population        : num [1:5275] 64291 62707 74783 54511 85474 ...
##  $ birth_rate        : num [1:5275] 10.9 10.9 10.3 11.9 9.9 NA 10.9 9.8 11.8 11.2 ...
##  $ neonat_mortal_rate: num [1:5275] 2.8 3.2 2 4.3 1.7 1.6 2 1.7 2.1 2.1 ...
##  $ region            : chr [1:5275] "Europe & Central Asia" "Europe & Central Asia" "Europe & Central Asia" "Europe & Central Asia" ...
##  $ income            : chr [1:5275] "High income" "High income" "High income" "High income" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   iso2c = col_character(),
##   ..   iso3c = col_character(),
##   ..   country = col_character(),
##   ..   year = col_double(),
##   ..   gdp_percap = col_double(),
##   ..   population = col_double(),
##   ..   birth_rate = col_double(),
##   ..   neonat_mortal_rate = col_double(),
##   ..   region = col_character(),
##   ..   income = col_character()
##   .. )
##  - attr(*, "problems")=<externalptr>

Mutate GDP in Trillions of Dollars

nations2 = nations %>%
  mutate(gdp_tn = gdp_percap*population/1000000000000)

Filter - Four Desired Countries

top4 <- nations2 %>%
  filter(iso3c == "CHN" | iso3c == "DEU" | iso3c == "JPN" | iso3c == "USA") %>%
  arrange(year)

Plot 1 China’s Rise to Become the Largest Economy

p1<- ggplot(top4, aes(x=year,y = gdp_tn, color = country)) + 
  geom_point(aes(shape=country), size=1.5)+scale_color_brewer(palette = "Set1")+scale_shape_manual(values=c(16,16,16,16))+
  xlab("Year") +
  ylab("GDP ($ trillions)")+
  ggtitle("China's Rise to Become the Largest Economy")+
  theme_light()+
  theme(plot.title = element_text(hjust = 0.5))+geom_line(size = 0.5,alpha = 0.5)
p1

## Group By Region and Year

regions <- nations2 %>%
  group_by(year,region) %>%
  summarise(gdp_tn = sum(gdp_tn, na.rm = TRUE)) %>%
  arrange(year,region)

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

Plot 2 GDP by World Bank Region

p2<- ggplot(regions, aes(x=year,y = gdp_tn, fill=region), color="white", lwd=2) + 
  geom_area(alpha=1, size=0.5, colour="white")+
  scale_fill_brewer(palette = "Set2")+
  xlab("Year") +
  ylab("GDP ($ trillions)")+
  ggtitle("GDP by World Bank Region")+
  theme_light()+
  theme(plot.title = element_text(hjust = 0.5))

p2