Nations Dataset HW

Chart 1

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.1     ✔ purrr   1.0.1
## ✔ tibble  3.1.8     ✔ dplyr   1.1.0
## ✔ tidyr   1.3.0     ✔ stringr 1.5.0
## ✔ readr   2.1.3     ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

nd <- 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.

Preparing the Data

withGDP <- nd %>% mutate(GDP = gdp_percap * population / 1000000000000 ) %>% select(country, GDP, year) %>% filter(country == c("United States", "Mexico", "Panama", "France"))

## Warning: There was 1 warning in `filter()`.
## ℹ In argument: `country == c("United States", "Mexico", "Panama", "France")`.
## Caused by warning in `country == c("United States", "Mexico", "Panama", "France")`:
## ! longer object length is not a multiple of shorter object length

glimpse(withGDP)

## Rows: 24
## Columns: 3
## $ country <chr> "France", "France", "France", "France", "France", "France", "M…
## $ GDP     <dbl> 1.76167055, 2.26225547, 1.82020918, 1.27204185, 1.58203157, 1.…
## $ year    <dbl> 2002, 2008, 2004, 1996, 2000, 2003, 1994, 2000, 1992, 2007, 19…

Creating the Dot and Line Plot

GDPld <- ggplot(withGDP, aes(x = year, y= GDP, color = country)) +
  xlab("Year") +
  ylab("GDP ($trillion)") +
  scale_color_brewer(palette = "Set1") +
  geom_point() +
  geom_line() +
  ggtitle("GDP Comparison of Four Personal Countries")
GDPld

Chart 2

Preparing the Data

GDP2 <- nd %>% mutate(GDP = gdp_percap * population / 1000000000000) %>% 
  select(year, country, GDP, region) %>% group_by(region, year) %>%
  summarise(GDP = sum(GDP, na.rm = TRUE))

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

GDP2

## # A tibble: 175 × 3
## # Groups:   region [7]
##    region               year   GDP
##    <chr>               <dbl> <dbl>
##  1 East Asia & Pacific  1990  5.52
##  2 East Asia & Pacific  1991  6.03
##  3 East Asia & Pacific  1992  6.50
##  4 East Asia & Pacific  1993  7.04
##  5 East Asia & Pacific  1994  7.64
##  6 East Asia & Pacific  1995  8.29
##  7 East Asia & Pacific  1996  8.96
##  8 East Asia & Pacific  1997  9.55
##  9 East Asia & Pacific  1998  9.60
## 10 East Asia & Pacific  1999 10.1 
## # … with 165 more rows

Creating the Area Graph

GDParea <- ggplot(GDP2, aes(x = year, y = GDP, area = region, fill = region)) + 
  ggtitle("GDP by World Bank Region") +
  xlab("Year") +
  ylab("GDP($trillions)") + 
  scale_fill_brewer(palette = "Set2") +
  geom_area()
GDParea

Personal Comment

In the mood to read more about how to make beautiful graphs in R Studio? Check out R Graphics Cookbook by Winston Chang! https://r-graphics.org/