Assignment_6

Load Library & Data

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(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ readr     2.1.6
## ✔ ggplot2   4.0.2     ✔ stringr   1.6.0
## ✔ lubridate 1.9.5     ✔ tibble    3.3.1
## ✔ purrr     1.2.1     ✔ tidyr     1.3.2

## ── 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

library(ggplot2)

setwd("C:/Users/tonge/Desktop/Data 110")
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.

Removing NAs

colSums(is.na(nations))

##              iso2c              iso3c            country               year 
##                 25                  0                  0                  0 
##         gdp_percap         population         birth_rate neonat_mortal_rate 
##                766                 14                295                525 
##             region             income 
##                  0                  0

nations <- filter(nations,!is.na(gdp_percap))

nations <- filter(nations,!is.na(population))

Create a new variable where gdp of each country in trillions = (gdp_percap * population) / a trillion

nations1 <- nations |>
  mutate(gdp_trill = (gdp_percap * population) / 10^12 )

GDP by Country

nations_filtered <- filter(nations1, country %in% c("China", "Germany", "Japan", "United States")) 

ggplot(nations_filtered, aes(x=year, y=gdp_trill, color = country)) +
  geom_line() +
  geom_point() +
  labs(
    title = "GDP by World Bank",
    x = "Year",
    y = "GDP($trillion)"
       ) +
  scale_color_brewer(palette = "Set1")

GDP by Region

regions_filtered <- nations1 |>
group_by(region, year) |>
  summarise(GDP = sum(gdp_trill, na.rm = TRUE))

## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by region and year.
## ℹ Output is grouped by region.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(region, year))` for per-operation grouping
##   (`?dplyr::dplyr_by`) instead.

ggplot(regions_filtered, aes(x = year, y = GDP, fill = region)) +
  geom_area(
    color = "white"
  )+
  labs(
    title = "GDP by Region Over Time",
    x = "Year",
    y = "GDP ($ trillions)",
    fill = "Region"
  )+
  scale_fill_brewer(palette = "Set2")