Problem Set 1
Task 1: Visualization
packages <- c("tidyverse", "gapminder", "fst", "viridis", "ggridges", "modelsummary", "RColorBrewer", "effects")
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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
## Loading required package: viridisLite
##
## Loading required package: carData
##
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "gapminder" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "gapminder" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "viridis" "viridisLite" "fst" "gapminder" "lubridate"
## [6] "forcats" "stringr" "dplyr" "purrr" "readr"
## [11] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[5]]
## [1] "ggridges" "viridis" "viridisLite" "fst" "gapminder"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "modelsummary" "ggridges" "viridis" "viridisLite" "fst"
## [6] "gapminder" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "RColorBrewer" "modelsummary" "ggridges" "viridis" "viridisLite"
## [6] "fst" "gapminder" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[8]]
## [1] "effects" "carData" "RColorBrewer" "modelsummary" "ggridges"
## [6] "viridis" "viridisLite" "fst" "gapminder" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"data(gapminder)gapminder_subset <- gapminder %>% dplyr::select(country, year, lifeExp, gdpPercap)
head(gapminder_subset)## # A tibble: 6 × 4
## country year lifeExp gdpPercap
## <fct> <int> <dbl> <dbl>
## 1 Afghanistan 1952 28.8 779.
## 2 Afghanistan 1957 30.3 821.
## 3 Afghanistan 1962 32.0 853.
## 4 Afghanistan 1967 34.0 836.
## 5 Afghanistan 1972 36.1 740.
## 6 Afghanistan 1977 38.4 786.gapminder <- gapminder %>% mutate(total_gdp = pop * gdpPercap)
head(gapminder)## # A tibble: 6 × 7
## country continent year lifeExp pop gdpPercap total_gdp
## <fct> <fct> <int> <dbl> <int> <dbl> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779. 6567086330.
## 2 Afghanistan Asia 1957 30.3 9240934 821. 7585448670.
## 3 Afghanistan Asia 1962 32.0 10267083 853. 8758855797.
## 4 Afghanistan Asia 1967 34.0 11537966 836. 9648014150.
## 5 Afghanistan Asia 1972 36.1 13079460 740. 9678553274.
## 6 Afghanistan Asia 1977 38.4 14880372 786. 11697659231.gapminder %>% group_by(continent) %>% summarize(mean_lifeExp = mean(lifeExp, na.rm = TRUE))## # A tibble: 5 × 2
## continent mean_lifeExp
## <fct> <dbl>
## 1 Africa 48.9
## 2 Americas 64.7
## 3 Asia 60.1
## 4 Europe 71.9
## 5 Oceania 74.3ggplot(gapminder, aes(x = gdpPercap, y = lifeExp)) +
geom_point(aes(color = continent), alpha = 0.9) +
labs(title = "Life Expectancy Based on GDP per Capita",
x = "GDP per Capita", y = "Life Expectancy", color = "Continent") +
theme_minimal() 
Task 2: Descriptive Statistic Interpretation
summary_mean <- gapminder %>%
group_by(continent) %>%
summarize(
mean_lifeExp = mean(lifeExp, na.rm = TRUE),
mean_gdpPercap = mean(gdpPercap, na.rm = TRUE)
)
print(summary_mean)## # A tibble: 5 × 3
## continent mean_lifeExp mean_gdpPercap
## <fct> <dbl> <dbl>
## 1 Africa 48.9 2194.
## 2 Americas 64.7 7136.
## 3 Asia 60.1 7902.
## 4 Europe 71.9 14469.
## 5 Oceania 74.3 18622.The table shows a strong positive correlation: as the GDP per capita mean increases, the life expectancy mean tends to increase as well
Task 3: Printing
print('I did it!')## [1] "I did it!"