FC Week 4 Nations HW 2.0

Call up the needed packages: dplyr, ggplot2, tidyverse, RColorBrewer.

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ tibble  3.0.1     ✓ purrr   0.3.4
## ✓ tidyr   1.1.0     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

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

library(RColorBrewer)

Load in the dataset and create a new variable in the data, using mutate from dplyr, giving the GDP of each country in trillions of dollars, by multiplying gdp_percap by population and dividing by a trillion.

nations <- read_csv("nations.csv") %>%
  mutate(gdp_tn = gdp_percap*population/1000000000000)

## Parsed with column specification:
## 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()
## )

Plot 1

Filter the data with dplyr for the four desired countries.

big4 <- nations %>%
  filter(iso3c == "CHN" | iso3c == "DEU" | iso3c == "JPN" | iso3c == "USA") %>%
  arrange(year)

Create chart using ggplot2. Add both geom_point and geom_line layers, and use the Set1 ColorBrewer palette using: scale_color_brewer(palette = “Set1”).

plot1 <- big4 %>% 
  ggplot(aes(year, gdp_tn, color = country)) +
  geom_point(size = 2) +
  xlab("Year") +
  ylab("GDP ($ Trillion)") +
  geom_line() +
  scale_color_brewer(palette = "Set1") +
  labs(fill= "Country") +
  ggtitle("China's Rise to Become the Largest Economy")
plot1

Plot 2

Use the group_by command for region and year, and then summarize on the mutated value for gdp_percap using summarise(sum = sum(gdp_percap, na.rm = TRUE)). We use na.rm = TRUE because there are NAs in this data.

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

## `summarise()` regrouping output by 'year' (override with `.groups` argument)

Use ggplot2 and geom_area to create an area graph based on region. Use the Set2 ColorBrewer palette using scale_fill_brewer(palette = “Set2”) and put a thin white line around each area using geom_area(size = .5, color = “white”).

plot2 <- regions %>% 
  ggplot(aes(year, gdp_tn, fill = region)) +
  geom_area(size = .5, color = "white") +
  xlab("Year") +
  ylab("GDP ($ Trillion)") +
  scale_fill_brewer(palette = "Set2") +
  labs(fill= "Region") +
  ggtitle("GDP by World Bank Region")
plot2