This template follows lecture 6.1 slides. Please be sure to cross-reference the slides, which contain important information and additional context!
System fonts
# import packages ---- library(palmerpenguins)library(tidyverse)# create ggplot to demonstrate use of system fonts ----ggplot(penguins, aes(x = bill_length_mm, y = bill_depth_mm)) +geom_point() +labs(title ="This title is serif font",subtitle ="This subtitle is mono font",x ="This axis label is sans font\n(default)",y ="This axis is also sans font\n(default)") +theme(plot.title =element_text(family ="serif", size =30),plot.subtitle =element_text(family ="mono", size =25),axis.title =element_text(family ="sans", size =22),axis.text.x =element_text(family ="serif", face ="bold", size =18),axis.text.y =element_text(family ="mono", face ="italic", size =18) )
Our “first draft” of this plot began in week 4 during our rankings lecture. We’ll focus on improving colors and fonts today.
##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~## setup ----##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#..........................load packages.........................library(tidyverse)library(showtext)#......................import Google fonts.......................# `name` is the name of the font as it appears in Google Fonts# `family` is the user-specified id that you'll use to apply a font in your ggpplotfont_add_google(name ="Josefin Sans", family ="josefin")font_add_google(name ="Sen", family ="sen")#....................import Font Awesome fonts...................font_add(family ="fa-brands",regular = here::here("fonts", "Font Awesome 6 Brands-Regular-400.otf"))font_add(family ="fa-regular",regular = here::here("fonts", "Font Awesome 6 Free-Regular-400.otf")) font_add(family ="fa-solid",regular = here::here("fonts", "Font Awesome 6 Free-Solid-900.otf"))#......enable {showtext} rendering for all newly opened GDs......showtext_auto()#..........................import data...........................# find import code at: https://github.com/rfordatascience/tidytuesday/tree/master/data/2019/2019-03-05#grab-the-clean-data-herejobs <-read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-03-05/jobs_gender.csv")
Wrangle data
See lecture 4.1 slides #4, #5, & #17 as reminders of where we left off.
##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~## wrangle data ----##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~jobs_clean <- jobs |># add col with % men in a given occupation (% females in a given occupation was already included) ----mutate(percent_male =100- percent_female) |># rearrange columns ----relocate(year, major_category, minor_category, occupation, total_workers, workers_male, workers_female, percent_male, percent_female, total_earnings, total_earnings_male, total_earnings_female, wage_percent_of_male) |># drop rows with missing earnings data ----drop_na(total_earnings_male, total_earnings_female) |># make occupation a factor (necessary for reordering groups in our plot) ----mutate(occupation =as.factor(occupation)) |># classify jobs by percentage male or female (these will become facet labels in our plot) ----mutate(group_label =case_when( percent_female >=75~"Occupations that are 75%+ female", percent_female >=45& percent_female <=55~"Occupations that are 45-55% female", percent_male >=75~"Occupations that are 75%+ male" )) ##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~## create subset df ----##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#....guarantee the same random samples each time we run code.....set.seed(0)#...............get random samples from each group...............# 10 random jobs that are 75%+ female (2016) ----f75 <- jobs_clean |>filter(year ==2016, group_label =="Occupations that are 75%+ female") |>slice_sample(n =10)# 10 random jobs that are 75%+ male (2016) ----m75 <- jobs_clean |>filter(year ==2016, group_label =="Occupations that are 75%+ male") |>slice_sample(n =10)# 10 random jobs that are 45-55%+ female (2016) ----f50 <- jobs_clean |>filter(year ==2016, group_label =="Occupations that are 45-55% female") |>slice_sample(n =10)#.......combine dfs & relevel factors (for plotting order).......subset_jobs <-rbind(f75, m75, f50) |>mutate(group_label =fct_relevel(group_label, "Occupations that are 75%+ female", "Occupations that are 45-55% female", "Occupations that are 75%+ male"))
# create a named color palette ----earnings_pal <-c("males"="#2D7787","females"="#FC6B4B","dark_text"="#0C1509","light_text"="#4E514D") # preview it -----monochromeR::view_palette(earnings_pal)
