Dubois Challenge

Data Visualization Exercise

This notebook uses TidyTuesday’s 2021 Week 8 Dubois Challenge, data from Anthony Starks, Allen Hillery and Sekou Tyler.

# load libraries
library(tidyverse)
library(janitor)
library(cowplot)
library(showtext)
library(grid)

# font
font_add_google("Teko","teko")
showtext_auto()

# load data
georgia_pop <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/georgia_pop.csv')
census <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/census.csv')
furniture <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/furniture.csv')
city_rural <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/city_rural.csv')
income <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/income.csv')
freed_slaves <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/freed_slaves.csv')
occupation <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/occupation.csv')
conjugal <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/conjugal.csv')

challenge01: Comparative Increase of White and Colored Population in Georgia

• shared on twitter (https://twitter.com/leeolney3/status/1361575377777352704/photo/1)

c1 = georgia_pop %>% 
  pivot_longer(!Year) %>%
  ggplot(aes(y=value, x=as.factor(Year))) +
  geom_line(aes(group=name, linetype=name)) + 
  scale_y_reverse(limits=c(100,0), expand=c(0,0), breaks=seq(0,100,5)) +
  coord_flip() + 
  theme_light() + 
  theme(legend.position="bottom",
        axis.ticks=element_blank(),
        panel.grid.minor=element_blank(),
        panel.grid = element_line(size=0.2, color="red"),
        plot.title = element_text(hjust=0.5, size=13.5, face="bold"),
        plot.background=element_rect(fill="#ead4bc"),
        panel.background = element_rect(fill="#ead4bc"),
        legend.background = element_rect(fill="#ead4bc"),
        legend.key =element_rect(fill="#ead4bc"),
        legend.key.width=unit(2.2, "cm"),
        legend.spacing=unit(1.5, "cm"),
        axis.title = element_text(size=8.5),
        legend.text =element_text(margin=margin(r=2, unit="cm")),
        plot.margin = margin(20, 70, 20, 50)
        ) + 
  labs(x="",linetype="", y="PERCENTS",
       title="COMPARATIVE INCREASE OF WHITE AND COLORED\nPOPULATION OF GEORGIA")
c1

challenge02: Conjugal Condition

• shared on twitter (https://twitter.com/leeolney3/status/1361635828599029760/photo/1)

# capitalize col names
names(conjugal) = toupper(names(conjugal))
# filter data for labeling 
labeldata = conjugal %>% pivot_longer(cols=3:5, values_to="Count", names_to="Status") %>%
  mutate(POPULATION= str_to_upper(POPULATION)) %>% arrange(Count) %>% filter(Count>1)

conjugal%>% pivot_longer(cols=3:5, values_to="Count", names_to="Status") %>%
  mutate(POPULATION= str_to_upper(POPULATION)) %>%
  ggplot(aes(y=fct_rev(POPULATION), 
             x=Count, 
             fill=factor(Status, level=c("DIVORCED AND WIDOWED","MARRIED","SINGLE")),
             color=factor(Status, level=c("DIVORCED AND WIDOWED","MARRIED","SINGLE")),
             label = paste0((Count),"%"))) + 
  geom_bar(position = "fill", stat = "identity", color = "#4a4e69", width=0.5, size=0.25) +
  geom_text(data=labeldata, position = position_fill(vjust = 0.5), size =2.7, color = "white") +
  facet_grid(AGE~., labeller = label_both) + 
  theme_minimal() +
  theme(legend.position="top",
        plot.margin = margin(10, 40, 0, 20),
        axis.text.x=element_blank(),
        strip.background = element_rect(fill="#ead4bc",color="#4a4e69"),
        strip.text=element_text(color="black",size=12),
        panel.grid=element_blank(),
        plot.background=element_rect(fill="#ead4bc", color=NA),
        panel.background = element_rect(fill="#ead4bc", color=NA),
        legend.background = element_rect(fill="#ead4bc", color=NA),
        legend.key =element_rect(fill="#ead4bc", color=NA),
        legend.text= element_text(size=10),
        axis.text.y=element_text(size=12),
        #plot.title.position = "plot",
        text= element_text(family="teko"),
        plot.title=element_text(hjust=0.5, size=22, face="bold")
        ) + 
  scale_fill_manual(values=c("#426351","#f9b42a","#de2d48"),
                    guide=guide_legend(reverse=TRUE)
                    ) +
  labs(color="",x="", fill="", y="",
       title="CONJUGAL CONDITION") 

NA
NA

challenge02: Conjugal Condition v2

• reference: Judith Neve (https://twitter.com/JudithNeve/status/1361804705454837761/photo/1)
• reference: Georgios Karamanis (https://twitter.com/geokaramanis/status/1361733287564181507/photo/1)

conjugal <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/conjugal.csv')

conjugal %>%
  pivot_longer(cols = c("Single", "Married", "Divorced and Widowed"), 
               names_to = "Category", values_to = "Pct")  %>%
  mutate(Category= str_to_upper(Category)) %>%
ggplot(aes(x = Population, y = Pct, fill = Category)) +
  facet_wrap(~ Age, nrow = 3) +
  geom_bar(position = "fill", stat = "identity", key_glyph = draw_key_point, color="#4a4e69",size=0.25,width=0.6) +
  geom_text(aes(y = Pct, x = Population, label = paste0(Pct, "%")), 
            size = 4, position = position_fill(vjust = 0.5), family="mono") +
  geom_text(aes(x = Population, y = 0, label = toupper(Population)), 
            hjust = 1, nudge_y = -0.02, family="mono",size=4.2) +
  geom_text(aes(x = 1.5, y = 0.2, label = stringr::str_wrap(toupper(Age),5)), 
            hjust = 0.5, nudge_y = -0.4, stat = "unique", family="mono", size=4.2) +
  coord_flip() +
  scale_fill_manual(values=c("#426351","#f9b42a","#de2d48"),
                    breaks = c("SINGLE", "MARRIED", "DIVORCED AND WIDOWED")) +
  labs(fill = "") +
  theme_void() +
  theme(plot.margin = margin(20, 20, 90, 20),
        legend.position = "top",
        text=element_text(family="mono"),
        panel.spacing.y = unit(1.5, "lines"),
        plot.background = element_rect(fill = "#ead4bc", color = NA),
        strip.text = element_blank(),
        legend.text=element_text(size=12, margin=margin(r=0.4, unit="cm")),
        legend.margin=margin(10,30,10,0),
        plot.title=element_text(size=20,hjust=0.3)
        ) +
  guides(fill = guide_legend(override.aes = list(shape = 21, size = 15))) + 
  labs(title="CONJUGAL CONDITION")

challenge05: Income and Expenditure of 150 Negro Families in Atlanta, GA, USA

• reference: Amina (https://twitter.com/harratha_/status/1361541377885167619/photo/2)
• reference: Florence Galliers (https://twitter.com/florencelydia11/status/1361713384752832520/photo/1)

# plot
income_plot = 
income %>% 
  pivot_longer(3:7) %>%
  filter(!is.na(value)) %>%
  filter(value!=0) %>% 
  mutate(name=toupper(name)) %>%
  mutate(textcol= ifelse(name=="RENT","1","0")) %>%
  ggplot(aes(fill=factor(name,levels = c("OTHER", "TAX", "CLOTHES", "FOOD", "RENT")), 
                        x=value,
                        y=fct_rev(Class),
                        label = paste0(round(value),"%")), color = "black") +
  geom_bar(position = "fill", stat = "identity", color = "#495057", width=0.7, size=0.2) +
  geom_text(aes(color=textcol),position = position_fill(vjust = 0.5), size =3, show.legend = FALSE) +
  geom_text(aes(x = 1.07, y=Class, label = as.character(`Actual Average`)), vjust=0.5, color="#463f3a", family="mono",size=3) +
  theme(legend.position="top",
        plot.margin = margin(20, 40, 0, 20),
        plot.background=element_rect(fill="#ead4bc", color=NA),
        panel.background = element_rect(fill="#ead4bc", color=NA),
        legend.background = element_rect(fill="#ead4bc"),
        legend.key =element_rect(fill="#ead4bc"),
        axis.title=element_text(size=8),
        text=element_text(family="mono"),
        axis.ticks = element_blank(),
        axis.ticks.x = element_blank(),
        axis.text.x=element_blank(),
        axis.title.y.left=element_blank(),
        plot.title.position = "plot",
        plot.title=element_text(size=12.2),
        panel.grid=element_blank(),
        legend.text =element_text(margin=margin(r=0.82, unit="cm")),
        legend.margin=margin(0,24,0,0),
        legend.box.margin=margin(10,0,-5,0)
        )+ 
  scale_fill_manual(values = c("#cbdfbd","#8e9aaf","#d78879","#a08294","#161213"), guide=guide_legend(reverse=TRUE)) + 
  scale_color_manual(values=c("black","white")) +
  labs(fill="", x="", y="example",
       title="INCOME AND EXPENDITURE OF 150 NEGRO FAMILIES IN ATLANTA, GA.,U.S.A")

# annotate left and right labels
income_plot + 
  scale_y_discrete(expand = expansion(add=1)) +
  draw_text("ACTUAL\nAVERAGE($)", x = 1.07, y = 7.7, family = "mono", size = 6.8) + 
  scale_x_continuous(expand=expansion(mult=c(0.02,0.05))) + 
  labs(tag="CLASS") +
  theme(plot.tag.position = c(0.07, 0.8),
        plot.tag=element_text(family="mono",size=7))

challenge07: Assessed Value of Household and Kitchen Furniture Owned by Georgia Negroes.

• shared on twitter (https://twitter.com/leeolney3/status/1361686816462671874/photo/1)

# create labels
data = furniture %>% 
  rename(Value= "Houshold Value (Dollars)") %>% 
  mutate(lab=paste(Year,"—","$",Value))

data$Year = as.factor(data$Year)

# add a blank row
blank_rows <- 
  data.frame(
    Year="",
   Value = 0,
   lab="")

# bind rows
graph_data = bind_rows(data, blank_rows)
  

graph_data %>% 
  ggplot(aes(x=lab, y=Value)) + 
  geom_bar(aes(fill=lab),stat="identity", width=0.5,alpha=0.9) + 
  geom_text(hjust = 1, size = 3.7,
            color = "#343a40", family="mono",
            aes( y = 0,
                 label = paste(lab," "))) +
  theme_minimal() +
  coord_polar(theta = "y") +
  ylim(0, 1700000) + 
  scale_fill_manual(values=c("green","#ff5c8a","#9ba2bf","#9c6644","#f9b42a","#fff1e6","#de2d48")) +
  theme(legend.position="none",
        plot.background=element_rect(fill="#ead4bc", color=NA),
        panel.background = element_rect(fill="#ead4bc", color=NA),
        plot.title=element_text(hjust=0.5, size=18, family="mono"),
        plot.title.position="plot",
        axis.text=element_blank(),
        panel.grid=element_blank(),
        plot.margin = margin(10, 40, 10, 40)
        ) + 
  labs(title="ASSESSED VALUE OF HOUSEHOLD AND KITCHEN FURNITURE\nOWNED BY GEORGIA NEGROES", x="",y="",subtitle="")

Relative Negro Population Of The States Of The United States

• reference: Rebecca Stevick (https://twitter.com/rjstevick/status/1361773685560999944/photo/1)

rel_pop <- read_csv('https://raw.githubusercontent.com/ajstarks/dubois-data-portraits/master/plate02/data.csv')

pal = c("black","#797d62","#9b9b7a","#84a98c","#95d5b2","#d8f3dc","#f1dca7","#ffcb69","#ffb4a2")

rel_pop %>%
  left_join(data.frame(state.abb, state.name), by = c("State" = "state.abb")) %>%
  mutate(region = tolower(state.name),
         Population = factor(Population,levels = c("750,000 AND OVER", 
                                        "600,000 - 750,000", 
                                        "500,000 - 600,000", 
                                        "300,000 - 500,000", 
                                        "200,000 - 300,000",
                                        "100,000 - 200,000", 
                                        "50,000 - 100,000", 
                                        "25,000 - 50,000", 
                                        "10,000 - 25,000", 
                                        "UNDER - 10,000"))) %>%
  left_join(map_data("state")) %>%
  ggplot(aes(x = long, y = lat, group = group, fill = Population)) +
  geom_polygon(color = "grey20", lwd = 0.2, key_glyph = "polygon3") + 
  coord_fixed(1.3) + 
  scale_fill_manual(values = pal) +
  theme_void() + 
  theme(text=element_text(family="mono"),
        plot.title.position = "plot",
        plot.title=element_text(hjust=0.5, size=16,face="bold", margin=margin(0,0,40,0)),
        plot.margin=margin(20,20,20,20)) +
  labs(fill="",
       title="RELATIVE NEGRO POPULATION OF THE STATES OF THE\nUNITED STATES.") 

NA