Read someone else’s code

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── 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

billionaires_df <- read_tsv("../datasets_ATRIUM/billionaires_combined.tsv")

Rows: 28986 Columns: 21
── Column specification ────────────────────────────────────────────────────────
Delimiter: "\t"
chr (17): person, name.x, state, headquarters, source, industry, gender, las...
dbl  (4): time, daily_income, age, birth_comb

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.

billionaires_2020 <- billionaires_df %>% 
  filter(time == 2020) %>% select(daily_income, person, world_6region)

0.1 The task performed by the code

The data set compiles charts of world’s billionaires between 2002 and 2020. This means that the same person can occur more than one time, but their details may differ. Plot billionaires in each world region (column world_6region). Use boxplots to plot the distribution of daily_income among all billionaires in the given world region and text labels with values from the column person for outliers. You may have to plot each region separately, that is, not break one plot into facets but run the/a plotting script individually for each world region.

1 Solution

library(ggrepel)
billionaires_outliers <- billionaires_2020 %>% 
  group_by(world_6region) %>%
  mutate(Q3 = quantile(daily_income, 0.75), 
         IQR_col = IQR(daily_income), 
         outliers_above = Q3 + 1.5 * IQR_col) %>%
  mutate(is_outlier = if_else(condition = daily_income > outliers_above,
                              true = TRUE, 
                              false = FALSE)) %>% 
  arrange(desc(daily_income), world_6region)
world_6region_vec <- distinct(billionaires_outliers, world_6region) %>% 
  arrange(world_6region) %>% 
  pull()  
outliers_above <- distinct(billionaires_outliers, world_6region, outliers_above) %>% 
  arrange(world_6region) %>% 
  pull() 

for (i in seq_along(world_6region_vec)) {
  all_oneregion <- billionaires_outliers %>% 
    filter(world_6region == world_6region_vec[i])
  outliers_oneregion <- all_oneregion %>% 
    filter(is_outlier == TRUE)
  y_axis_offset_for_outlier_label <- range(all_oneregion$daily_income) %>% 
    diff()
  y_axis_offset_for_outlier_label <- y_axis_offset_for_outlier_label * 0.05
  if (nrow(outliers_oneregion) == 0){
    cat(world_6region_vec[i], "has no outliers. I will plot all names.\n")
  p <- ggplot() + 
    geom_boxplot(data = all_oneregion,
                 mapping = aes(y = daily_income, x = 1),
                 color = "purple")   +
    geom_text_repel(mapping = aes(y = daily_income, 
                                  x = 1,
                                  label = person,
                            size = daily_income), 
                    data = all_oneregion,
                    max.overlaps = 100,  
                    force = 7,
                    alpha = 0.7,
                    segment.alpha = 0.2,
                    segment.size = 0.1) + 
    scale_x_continuous(breaks = NULL, 
                       name = world_6region_vec[i]) +
    scale_y_continuous(breaks = seq(from = 10^6, 
                                    to = ceiling(round(
                                    max(all_oneregion$daily_income) * 10^(-6)) * 10^6), 
                                    by = 10^7),
                       labels = as.character(
                                             seq(from = 10^6, 
                                                 to = ceiling(round(max(all_oneregion$daily_income) * 10^(-6)) * 10^6), 
                                                 by = 10^7)
                                   )
                       ) 
  ggsave(plot = p, filename = paste0("../my_output_files/outliers_billionaires_", world_6region_vec[i], ".pdf"),
         width = 7 * 2)
    
  } else {
  set.seed(155)
  p <- ggplot() + 
    geom_boxplot(data = all_oneregion,
                          mapping = aes(y = daily_income, x = 1),
                          color = "purple", outlier.size = 3)  +
    geom_text_repel(mapping = aes(y = daily_income, 
                                  x = 1,
                                  label = person,
                                  size = daily_income), 
                    data = outliers_oneregion,
                    max.overlaps = 100,  force = 7,
                    alpha = 0.7,
                    segment.alpha = 0.3,
                    segment.size = 0.2) + 
    scale_x_continuous(breaks = NULL, 
                       name = world_6region_vec[i]) +
    scale_size_continuous(range = c(6,10), 
                          breaks = seq(from = round(min(outliers_oneregion$daily_income)),
                                       to = round(max(outliers_oneregion$daily_income)),
                                       by = round(max(outliers_oneregion$daily_income) * 0.4))) +
    scale_y_continuous(breaks = seq(from = 10^6, 
                                    to = ceiling(round(
                                      max(all_oneregion$daily_income) * 10^(-6)) * 10^6), 
                                    by = 10^7),
                        labels = as.character(seq(from = 10^6, 
                                                  to = ceiling(round(
                                                    max(all_oneregion$daily_income) * 10^(-6)) * 10^6), 
                                                  by = 10^7))) +
    geom_hline(yintercept = outliers_above[i], 
               color = "seagreen", 
               linewidth = 1, 
               linetype=3, 
               alpha = 0.4) + 
    annotate(geom = "text", 
             x = 0.6, 
             y = outliers_above[i] + y_axis_offset_for_outlier_label, 
             label = outliers_above[i], 
             color = "seagreen", 
             size = 6) +
    theme(axis.text = element_text(size = 12), 
          axis.title = element_text(size = 14))
  cat(world_6region_vec[i], "\n") 
  print(p)
  ggsave(plot = p, filename = paste0(
    "../my_output_files/outliers_billionaires_", 
    world_6region_vec[i], ".pdf"),
         width = 7 * 2.2)
    
  }
}

america 

Saving 15.4 x 20 in image

east_asia_pacific 

Saving 15.4 x 20 in image

europe_central_asia 

Saving 15.4 x 20 in image

middle_east_north_africa 

Saving 15.4 x 20 in image

south_asia 

Saving 15.4 x 20 in image

sub_saharan_africa has no outliers. I will plot all names.

Saving 14 x 20 in image