# Loading the tidyverse package first for data analysis and visualizationlibrary(tidyverse)
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.2.1 ✔ readr 2.2.0
✔ forcats 1.0.1 ✔ stringr 1.6.0
✔ ggplot2 4.0.3 ✔ tibble 3.3.1
✔ lubridate 1.9.5 ✔ tidyr 1.3.2
✔ purrr 1.2.2
── 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
# Now going to import the Nations datasetnations <- readr::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.
# We will preview the data so we can examine its structurehead(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>
spc_tbl_ [5,275 × 10] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
$ iso2c : chr [1:5275] "AD" "AD" "AD" "AD" ...
$ iso3c : chr [1:5275] "AND" "AND" "AND" "AND" ...
$ country : chr [1:5275] "Andorra" "Andorra" "Andorra" "Andorra" ...
$ year : num [1:5275] 1996 1994 2003 1990 2009 ...
$ gdp_percap : num [1:5275] NA NA NA NA NA NA NA NA NA NA ...
$ population : num [1:5275] 64291 62707 74783 54511 85474 ...
$ birth_rate : num [1:5275] 10.9 10.9 10.3 11.9 9.9 NA 10.9 9.8 11.8 11.2 ...
$ neonat_mortal_rate: num [1:5275] 2.8 3.2 2 4.3 1.7 1.6 2 1.7 2.1 2.1 ...
$ region : chr [1:5275] "Europe & Central Asia" "Europe & Central Asia" "Europe & Central Asia" "Europe & Central Asia" ...
$ income : chr [1:5275] "High income" "High income" "High income" "High income" ...
- attr(*, "spec")=
.. cols(
.. iso2c = col_character(),
.. iso3c = col_character(),
.. country = col_character(),
.. year = col_double(),
.. gdp_percap = col_double(),
.. population = col_double(),
.. birth_rate = col_double(),
.. neonat_mortal_rate = col_double(),
.. region = col_character(),
.. income = col_character()
.. )
- attr(*, "problems")=<pointer: 0x00000131adffff70>
Calculating the GDP in trillions
# Calculate each country's GDP in trillionsnations <- nations %>%mutate(gdp = (gdp_percap * population) /10^12)# Let's preview the new GDP variablehead(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 <dbl>
Filtering the dataset so that it’s four countries
# We are keeping only China, Germany, Japan, and the United Statesnations_four <- nations %>%filter(country %in%c("China", "Germany", "Japan", "United States"))# Checking the countries and also previewing their GDP valuesunique(nations_four$country)
[1] "China" "Germany" "Japan" "United States"
head(nations_four %>%select(country, year, gdp))
# A tibble: 6 × 3
country year gdp
<chr> <dbl> <dbl>
1 China 1992 1.47
2 China 2005 6.59
3 China 2000 3.68
4 China 1991 1.26
5 China 2013 16.6
6 China 1999 3.32
Comparing the GDP of the four countries
# Making a line chart to compare GDP across four countriesggplot(nations_four, aes(x = year, y = gdp, color = country)) +geom_point(size =2) +geom_line(linewidth =0.8) +scale_color_brewer(palette ="Set1") +theme_minimal() +labs(title ="China's Rise to Become the Largest Economy",x ="Year",y ="GDP ($ trillion)",color ="Country" )
Calculating the total GDP by World Bank region
# Grouping the countries by region and year, then calculating their combined GDPnations_regions <- nations %>%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.
# Previewing the regional GDP totalshead(nations_regions)
# A tibble: 6 × 3
# Groups: region [1]
region year GDP
<chr> <dbl> <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 8.29
unique(nations_regions$region)
[1] "East Asia & Pacific" "Europe & Central Asia"
[3] "Latin America & Caribbean" "Middle East & North Africa"
[5] "North America" "South Asia"
[7] "Sub-Saharan Africa"
Comparing GDP across the World Bank regions
# Creating a stacked area chart to show total GDP by world regionggplot(nations_regions, aes(x = year, y = GDP, fill = region)) +geom_area(color ="white", linewidth =0.15) +scale_fill_brewer(palette ="Set2") +theme_minimal() +labs(title ="GDP by World Bank Region",x ="Year",y ="GDP ($ trillion)",fill ="Region" )
