Employment and Earnings

Data Visualization Exercise

TidyTuesday week9/2021 Employment and Earnings, data from BLS

# load libaries
library(tidyverse)
library(ggtext)

# import data
employed <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-23/employed.csv')

── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  industry = col_character(),
  major_occupation = col_character(),
  minor_occupation = col_character(),
  race_gender = col_character(),
  industry_total = col_double(),
  employ_n = col_double(),
  year = col_double()
)

earn <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-23/earn.csv')

── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  sex = col_character(),
  race = col_character(),
  ethnic_origin = col_character(),
  age = col_character(),
  year = col_double(),
  quarter = col_double(),
  n_persons = col_double(),
  median_weekly_earn = col_double()
)

# plot 1
p1 = earn %>%
    group_by(year, sex) %>%
    filter(sex!="Both Sexes") %>%
    summarise(med = median(median_weekly_earn)) %>%
    ggplot(aes(x=year, y=med)) +
    geom_line(aes(group=year), color="#3d405b", size=0.7) + 
    geom_point(aes(color=sex), size=8, show.legend=FALSE) + 
    geom_text(aes(label=paste0("$",round(med))), size=2.2, color="white") +
    scale_color_manual(values=c("#668586","#9E8FB2")) + 
  scale_x_continuous(breaks=(seq(2010,2020,1))) +
  theme_minimal() + 
  theme(plot.title = ggtext::element_markdown(size=17, face="bold"),
        axis.title.y=element_markdown(size=10),
        axis.title.x=element_markdown(size=10),
        plot.caption=element_markdown(),
        panel.grid.minor.x=element_blank()) +
  labs(x="__Year__",
       y="__Median Weekly Earn__ (current dollars)",
       title= "Median Weekly Earn of <span style = 'color:#668586'><b>Men</b></span> and <span style = 'color:#9E8FB2'><b>Women</b></span> in the U.S.",
       caption="TidyTuesday Week 9 | Data from _BLS_"
       )
p1

e1 = employed %>% 
  filter(year=="2020") %>% filter(race_gender=="Women"|race_gender=="Men") %>% 
  filter(!is.na(employ_n)) %>%
  group_by(industry, race_gender) %>% 
  summarise(industry_total=max(industry_total)) %>%
  pivot_wider(names_from=race_gender, values_from=industry_total) %>%
  mutate(pct = Women/(Men+Women)) %>% 
  arrange(desc(pct))

e1 %>% 
  ggplot(aes(y=reorder(industry,pct), x=pct)) +
  geom_point() + 
  #geom_segment(aes(x=0, xend=pct, y=industry, yend=industry)) + 
  geom_label(aes(label=paste(industry, round(pct*100,1),"%")), size=2) + 
  scale_y_discrete(labels=function(x) str_wrap(x,25)) +
  scale_x_continuous(labels=scales::percent, limits=c(0,1),breaks=seq(0,1,0.2),expand=c(0,0)) +
  theme_light() + 
  theme(axis.text.y = element_blank(),
        axis.ticks.y=element_blank(),
        plot.title=element_markdown(size=16,face="bold")) + 
  labs(x="Percent", y="Industry",
       title="Percentage of <span style = 'color:#0091ad'><b>Women</b></span> Employed in the U.S., by Industry in 2020",
       caption="TidyTuesday Week 9 | Data from BLS")

e2 = employed %>% 
  filter(year=="2020") %>% filter(race_gender=="Women"|race_gender=="Men") %>% 
  filter(!is.na(employ_n)) %>%
  group_by(industry, race_gender) %>% 
  summarise(industry_total=max(industry_total/1000)) 

`summarise()` has grouped output by 'industry'. You can override using the `.groups` argument.

e2

p3 = e2 %>% 
  ggplot(aes(y=reorder(industry, industry_total), x=industry_total)) + 
  geom_line(aes(group=industry), color="#778da9") +
  geom_point(aes(color = race_gender)) + 
  scale_y_discrete(labels=function(x) str_wrap(x,25)) +
  scale_color_manual(values=c("#A23E48","#FF8C42")) + 
  theme_light() + 
  theme(legend.position="none",
        plot.title = ggtext::element_markdown(size=16, face="bold"),
        axis.title.y=element_markdown(size=10),
        axis.title.x=element_markdown(size=10),
        plot.caption=element_markdown(),
        ) + 
  labs(x="__Employed Number__ (in thousands)", y="__Industry__", 
       caption="TidyTuesday Week 9 | Data from BLS",
       title="Employed <span style = 'color:#A23E48'><b>Men</b></span> and <span style = 'color:#FF8C42'><b>Women</b></span> in the U.S., by Industry in 2020")
p3  

# women in major occupation
p4_data = employed %>% 
  filter(year=="2020") %>% 
  filter(race_gender=="Women"|race_gender=="Men") %>% 
  filter(!is.na(employ_n))%>%
  group_by(major_occupation, race_gender) %>%
  summarise(employ_n = sum(employ_n))

p4 = ggplot(p4_data, aes(y=reorder(major_occupation,employ_n), x=employ_n, fill=fct_rev(race_gender))) +
  geom_col(position="dodge", show.legend = F) + 
  geom_text(aes(x=employ_n+2200000,label=scales::comma(employ_n)), color="black", size=3,position=position_dodge(0.9)) +
  scale_y_discrete(labels=function(x) str_wrap(x,20)) +
  scale_fill_manual(values=c("#6a6b83","#86bbbd")) + 
  scale_x_continuous(expand=c(0,0), labels=comma, limits=c(0,42000000)) + 
  theme_light() + 
  theme(plot.title=element_markdown()) + 
  labs(y="Major Occupation", x= "Employed number",
       title= "Major Occupation of <span style = 'color:#86bbbd'><b>Men</b></span> and <span style = 'color:#6a6b83'><b>Women</b></span> in 2020.",
       subtitle="U.S. Employed Numbers",
       caption= "TidyTuesday Week 9 | Data from BLS")

p4

# Minor occupations
p5_data = employed %>% 
  filter(year=="2020") %>% 
  filter(race_gender=="Women"|race_gender=="Men") %>% 
  filter(!is.na(employ_n))%>%
  group_by(minor_occupation, race_gender) %>%
  summarise(employ_n = sum(employ_n)) %>%
  mutate(pct= employ_n/sum(employ_n)) %>%
  filter(race_gender!="Men")

p5 = p5_data %>% 
  ggplot(aes(y=reorder(minor_occupation,pct), x=pct)) + 
  geom_col(aes(fill=I(ifelse(pct==max(pct),"#4281a4","#9cafb7"))), width=0.85) + 
  geom_text(aes(label=percent(round(pct,3)), color= I(ifelse(pct==max(pct),"white","black"))), size=2.9, hjust=1.1) + 
  scale_y_discrete(labels=function(x) str_wrap(x,28)) + 
  scale_x_continuous(labels=percent, limits=c(0,0.80), expand=c(0,0)) + 
  theme_light() + 
  theme(plot.margin=ggplot2::margin(0,10,0,0),
        plot.title=element_text(face="bold", size=15)) +
  theme(axis.ticks.y=element_blank()) + 
  labs(y="Minor Occupation", x="Percent", 
       title= "Percentage of Women in Minor Occupations",
       subtitle="U.S. Employed Numbers in 2020", 
       caption="TidyTuesday Week 9 | Data from BLS")

p5