Assignment 6 Part 2

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)

## Warning: package 'ggplot2' was built under R version 4.5.2

nations <- read.csv("nations.csv")
head(nations)

##   iso2c iso3c country year gdp_percap population birth_rate neonat_mortal_rate
## 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                2.0
## 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
##                  region      income
## 1 Europe & Central Asia High income
## 2 Europe & Central Asia High income
## 3 Europe & Central Asia High income
## 4 Europe & Central Asia High income
## 5 Europe & Central Asia High income
## 6 Europe & Central Asia High income

nations_change <- nations |>
  mutate(gdp_per_country = (gdp_percap*population)/1000000000000)
head(nations_change)

##   iso2c iso3c country year gdp_percap population birth_rate neonat_mortal_rate
## 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                2.0
## 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
##                  region      income gdp_per_country
## 1 Europe & Central Asia High income              NA
## 2 Europe & Central Asia High income              NA
## 3 Europe & Central Asia High income              NA
## 4 Europe & Central Asia High income              NA
## 5 Europe & Central Asia High income              NA
## 6 Europe & Central Asia High income              NA

graph1 <- nations_change |>
  filter(country %in% c("China","Germany","Japan","United States"))
head(graph1)

##   iso2c iso3c country year gdp_percap population birth_rate neonat_mortal_rate
## 1    CN   CHN   China 1992   1260.162 1164970000      18.27               29.4
## 2    CN   CHN   China 2005   5053.379 1303720000      12.40               14.0
## 3    CN   CHN   China 2000   2915.415 1262645000      14.03               21.2
## 4    CN   CHN   China 1991   1091.449 1150780000      19.68               29.7
## 5    CN   CHN   China 2013  12218.521 1357380000      12.08                6.3
## 6    CN   CHN   China 1999   2649.745 1252735000      14.64               22.2
##                region              income gdp_per_country
## 1 East Asia & Pacific Upper middle income        1.468052
## 2 East Asia & Pacific Upper middle income        6.588191
## 3 East Asia & Pacific Upper middle income        3.681134
## 4 East Asia & Pacific Upper middle income        1.256017
## 5 East Asia & Pacific Upper middle income       16.585176
## 6 East Asia & Pacific Upper middle income        3.319429

graph1 |>
  ggplot(aes(x = year, y = gdp_per_country, fill = country, colour = country)) + geom_point() +geom_line() + scale_color_brewer(palette = "Set1")

graph2 <- nations_change |>
  group_by(region, year) |>
  summarise(GDP = sum(gdp_per_country, na.rm = TRUE))

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

graph2 |>
  ggplot(aes(x= year, y = GDP, fill = region, colour = region)) + geom_area(colour= "white") + scale_fill_brewer(palette = "Set2")