Week 6 Assignment

library(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

library(dslabs)
library(treemap)

head(gapminder)

              country year infant_mortality life_expectancy fertility
1             Albania 1960           115.40           62.87      6.19
2             Algeria 1960           148.20           47.50      7.65
3              Angola 1960           208.00           35.98      7.32
4 Antigua and Barbuda 1960               NA           62.97      4.43
5           Argentina 1960            59.87           65.39      3.11
6             Armenia 1960               NA           66.86      4.55
  population          gdp continent          region
1    1636054           NA    Europe Southern Europe
2   11124892  13828152297    Africa Northern Africa
3    5270844           NA    Africa   Middle Africa
4      54681           NA  Americas       Caribbean
5   20619075 108322326649  Americas   South America
6    1867396           NA      Asia    Western Asia

dim(gapminder)

[1] 10545     9

gap_2007 <- filter(gapminder , year == 2007)
dim(gap_2007)

[1] 185   9

head(gap_2007)

              country year infant_mortality life_expectancy fertility
1             Albania 2007             16.7            76.6      1.80
2             Algeria 2007             26.4            75.3      2.66
3              Angola 2007            117.1            56.2      6.52
4 Antigua and Barbuda 2007              9.2            75.3      2.18
5           Argentina 2007             14.1            75.2      2.25
6             Armenia 2007             18.8            72.3      1.40
  population          gdp continent          region
1    3010849   5330152753    Europe Southern Europe
2   34261971  73085186314    Africa Northern Africa
3   19183907  21674668197    Africa   Middle Africa
4      84397   1009354032  Americas       Caribbean
5   39969903 369614509411  Americas   South America
6    2988117   4378219566      Asia    Western Asia

gap_cont_2007 <- gap_2007 %>% group_by(continent)
head(gap_cont_2007)

# A tibble: 6 × 9
# Groups:   continent [4]
  country     year infant_mortality life_expectancy fertility population     gdp
  <fct>      <int>            <dbl>           <dbl>     <dbl>      <dbl>   <dbl>
1 Albania     2007             16.7            76.6      1.8     3010849 5.33e 9
2 Algeria     2007             26.4            75.3      2.66   34261971 7.31e10
3 Angola      2007            117.             56.2      6.52   19183907 2.17e10
4 Antigua a…  2007              9.2            75.3      2.18      84397 1.01e 9
5 Argentina   2007             14.1            75.2      2.25   39969903 3.70e11
6 Armenia     2007             18.8            72.3      1.4     2988117 4.38e 9
# ℹ 2 more variables: continent <fct>, region <fct>

colnames(gap_cont_2007)

[1] "country"          "year"             "infant_mortality" "life_expectancy" 
[5] "fertility"        "population"       "gdp"              "continent"       
[9] "region"          

continent_totals <- gap_cont_2007 %>%
  summarise(
    population = sum(population, na.rm = TRUE), 
    total_count = n()                                
  )
print(continent_totals)

# A tibble: 5 × 3
  continent population total_count
  <fct>          <dbl>       <int>
1 Africa     948156290          51
2 Americas   911419886          36
3 Asia      3911346015          47
4 Europe     730984863          39
5 Oceania     34130212          12

treemap(
  continent_totals,
  index = c("continent"),
  vSize = "population",
  type = "index",
  title = "Population of each continent"
  
)