Nations Charts

library(ggplot2)
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(RColorBrewer)
library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ lubridate 1.9.2     ✔ tibble    3.2.1
✔ purrr     1.0.2     ✔ tidyr     1.3.0
✔ readr     2.1.4     

── 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

library(readr)

getwd()

[1] "/Users/zwang30/Desktop/DATA110"

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.

head(nations)

# A tibble: 6 × 10
  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 2 more variables: region <chr>, income <chr>

nations <- nations %>%
  mutate(gdp_trillions = (gdp_percap * population) / 10^12)

countries_to_plot <- c('China', 'Germany', 'Japan','United States')

filtered_data <- nations %>%
  filter(country %in% countries_to_plot)

ggplot(filtered_data, aes(x = year, y = gdp_trillions, group = country, color = country)) +
  geom_point() +
  geom_line() +
  scale_color_brewer(palette = "Set1") +
  labs(title = "China's Rise to Become the Largest Economy", x = "Year", y = "GDP (in Trillions)")

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

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

ggplot(region_data, aes(x = year, y = GDP, fill = region)) +
  geom_area(aes(color = region), size = 0.1, position = "stack") +
  scale_fill_brewer(palette = "Set2") +
  scale_color_manual(values = rep("white", length(unique(region_data$region)))) +
  labs(title = "GDP by World Bank Region", y = "GDP in Trillions", x = "Year")

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.