Nations

Nations Dataset Charts Assignment

Load tidyverse

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Set working directory

setwd("/Users/ashleyramirez/Desktop/data110")

Load data

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.

Create new GDP variable variable divided by trillions

nations <- nations %>%
  mutate(gdp_trillions = (gdp_percap*population)/ 1000000000000)

head(nations)

# A tibble: 6 × 11
  iso2c iso3c country  year gdp_percap population birth_rate neonat_mortal_rate
  <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>      <dbl>              <dbl>
1 AD    AND   Andorra  1996         NA      64291       10.9                2.8
2 AD    AND   Andorra  1994         NA      62707       10.9                3.2
3 AD    AND   Andorra  2003         NA      74783       10.3                2  
4 AD    AND   Andorra  1990         NA      54511       11.9                4.3
5 AD    AND   Andorra  2009         NA      85474        9.9                1.7
6 AD    AND   Andorra  2011         NA      82326       NA                  1.6
# ℹ 3 more variables: region <chr>, income <chr>, gdp_trillions <dbl>

Plot 1

Filter data for four countries

desired_countries <- c("Guinea-Bissau", "Liberia", "Mauritius", "Rwanda")

filtered_nations <- nations %>%
  filter(country %in% desired_countries) %>%
  filter(!is.na(gdp_trillions), !is.na(year))

Plot

ggplot(filtered_nations, aes(x = year, y = gdp_trillions, color = country)) +
  geom_point() +
  geom_line() +
  scale_color_brewer(palette = "Set1") +
  labs(title = "GDP in Trillions for Selected Countries",
       x = "Year",
       y = "GDP in Trillions of Dollars") +
  theme_minimal()

Plot 2

Group region and year then summarize GDP

gdp_by_region_year <- nations %>%
  group_by(region, year) %>%
  summarise(GDP = sum(gdp_trillions, na.rm = TRUE), .groups = 'drop')

Plot

ggplot(gdp_by_region_year, aes(x = year, y = GDP, fill = region)) +
  geom_area(alpha = 0.5, color = "white") + 
  scale_fill_brewer(palette = "Set2") + 
  labs(title = "Total GDP by Region Over Years",
       x = "Year",
       y = "Total GDP in Trillions of Dollars") +
  theme_minimal()