library(dplyr)Warning: package 'dplyr' was built under R version 4.5.2
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(ggplot2)Warning: package 'ggplot2' was built under R version 4.5.2nations <- 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 incomenations1 <- nations |>
mutate(gdp = gdp_percap * population / 1000000000000)
head(nations1) 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
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 NAFiltering the 4 countries
chart1 <- nations1 |>
filter(country %in% c("Germany", "Japan", "China", "United States"))
head(chart1) 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
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 3.319429Plotting
ggplot(chart1, aes(x = year, y = gdp, color = country)) +
geom_line() + geom_point() +
scale_color_brewer(palette = "Set1") +
labs( title = "China's Rise to Become the Largest Economy",
x = "year", y = "GDP ($ trillions)")
Peparing the Data
chart2 <- nations1 |>
group_by(region, year) |>
summarise(GDP = sum(gdp, 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.head(chart2)# A tibble: 6 × 3
# Groups: region [1]
region year GDP
<chr> <int> <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 8.29Plotting
ggplot(chart2, aes( x = year, y = GDP, fill = region)) +
geom_area(color = "white", size = 0.2) +
scale_fill_brewer(palette = "Set2") +
labs(title = "GDP by World Bank Region", x = "year",
Y = "GDP (3 trillion)")Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.Ignoring unknown labels:
• Y : "GDP (3 trillion)"