Original Image
The image below was published in New York Times. https://archive.nytimes.com/www.nytimes.com/interactive/2013/03/22/us/politics/women-in-the-senate.html
Data Preparation
Below is the accompanying code to reproduce the chart above. The data was manually created by studying the chart.
library(dplyr)
library(ggplot2)
library(readr)
us_sen <- read_csv("./data/final_data_us_sen.csv")
female_sen_list <- c("Rebecca Latimer Felton","Hattie Caraway","Rose McConnell Long","Dixie Bibb Graves","Gladys Pyle","Vera C. Bushfield","Margaret Chase Smith","Eva Bowring","Hazel Abel","Maurine Brown Neuberger","Elaine S. Edwards","Nancy Landon Kassebaum","Maryon Pittman Allen","Muriel Humphrey","Paula Hawkins","Mikulski, BarbaraBarbara Mikulski","Feinstein, DianneDianne Feinstein","Jocelyn Birch Burdick","Murray, PattyPatty Murray","Carol Moseley-Braun","Kay Bailey Hutchison","Boxer, BarbaraBarbara Boxer","Olympia Snowe","Sheila Frahm","Mary Landrieu","Collins, SusanSusan Collins","Blanche Lincoln","Cantwell, MariaMaria Cantwell","Stabenow, DebbieDebbie Stabenow","Hillary Clinton","Jean Carnahan","Murkowski, LisaLisa Murkowski","Elizabeth Dole","Klobuchar, AmyAmy Klobuchar","McCaskill, ClaireClaire McCaskill","Gillibrand, KirstenKirsten Gillibrand","Kay Hagan","Shaheen, JeanneJeanne Shaheen","Ayotte, KellyKelly Ayotte","Heitkamp, HeidiHeidi Heitkamp","Fischer, DebDeb Fischer","Warren, ElizabethElizabeth Warren","Baldwin, TammyTammy Baldwin","Hirono, MazieMazie Hirono")
us_sen_femal <- dplyr::filter(us_sen, tolower(Senator) %in% tolower(female_sen_list))
# it seems that the table with current us senators have name duplicated while scraping
us_sen_femal$Senator <- ifelse(grepl(",",us_sen_femal$Senator),sub('.*,\\s*', '', us_sen_femal$Senator) %>% substr(.,nchar(gsub("([A-Za-z]+).*", "\\1",.))/2+1,nchar(us_sen_femal$Senator)),us_sen_femal$Senator)
us_sen_femal$Senator <- ifelse(us_sen_femal$Senator %in% c("Rebecca Latimer Felton","Rose McConnell Long","Dixie Bibb Graves","Vera C. Bushfield","Eva Bowring","Elaine S. Edwards","Maryon Pittman Allen","Muriel Humphrey","Jocelyn Birch Burdick","Sheila Frahm","Jean Carnahan"),paste0("* ",us_sen_femal$Senator),us_sen_femal$Senator)
us_sen_femal$Years <- ifelse(nchar(us_sen_femal$Years)<9,paste0(us_sen_femal$Years,"-",us_sen_femal$Years),ifelse(nchar(us_sen_femal$Years)>9,paste0(stringr::str_sub(us_sen_femal$Years,-4),"-","2013"),us_sen_femal$Years))
us_sen_femal <- us_sen_femal %>% mutate(start_year = as.numeric(as.character(substr(Years,1,4))),end_year = as.numeric(as.character(stringr::str_sub(Years,-4))),end_year = ifelse(end_year>=2013,2013,end_year), duration = ifelse(start_year==end_year,end_year - start_year + 1,end_year - start_year)) %>% select(-Years)
us_sen_femal$duration <- ifelse(us_sen_femal$Senator %in% c("* Rebecca Latimer Felton","* Vera C. Bushfield","* Eva Bowring","Hazel Abel","* Elaine S. Edwards","* Maryon Pittman Allen","* Muriel Humphrey","* Jocelyn Birch Burdick","* Sheila Frahm","Heidi Heitkamp","Deb Fischer","Elizabeth Warren","Tammy Baldwin","Mazie Hirono"),0.2,us_sen_femal$duration)
us_sen_femal$Senator <- factor(us_sen_femal$Senator,levels = c("* Rebecca Latimer Felton","Hattie Caraway","* Rose McConnell Long","* Dixie Bibb Graves","Gladys Pyle","* Vera C. Bushfield","Margaret Chase Smith","* Eva Bowring","Hazel Abel","Maurine Brown Neuberger","* Elaine S. Edwards","Nancy Landon Kassebaum","* Maryon Pittman Allen","* Muriel Humphrey","Paula Hawkins","Barbara Mikulski","Dianne Feinstein","* Jocelyn Birch Burdick","Patty Murray","Carol Moseley-Braun","Kay Bailey Hutchison","Barbara Boxer","Olympia Snowe","* Sheila Frahm","Mary Landrieu","Susan Collins","Blanche Lincoln","Maria Cantwell","Debbie Stabenow","Hillary Clinton","* Jean Carnahan","Lisa Murkowski","Elizabeth Dole","Amy Klobuchar","Claire McCaskill","Kirsten Gillibrand","Kay Hagan","Jeanne Shaheen","Kelly Ayotte","Heidi Heitkamp","Deb Fischer","Elizabeth Warren","Tammy Baldwin","Mazie Hirono")) # in order of their being appointed/selected.GGPLOT2
ggplot(us_sen_femal) + # the data frame
geom_tile(aes(x=ifelse(start_year==2013,2013-0.1,start_year+duration/2),y=Senator,width=duration,fill=Party)) + # for floating bars of common height
scale_fill_manual(values=c("#91B5D2","#FF6868")) + # colors as per nyt chart
theme_bw() + # set theme to bw
theme(
panel.grid.minor.x = element_blank(),
panel.grid.major.x = element_blank(),
panel.grid.minor.y = element_blank(),
panel.grid.major.y= element_blank(),
panel.border = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank(),
plot.title = element_text(face="bold", size = 15),
plot.subtitle = element_text(size = 8, margin=margin(0,0,30,0)),
plot.margin=unit(c(1.5,5,1.5,1.5),"cm"),
legend.position="none"
) + # styling
geom_text(aes(x=start_year-6,y=Senator,label=Senator),size=2) + # senator name alongside bars
xlab("") + ylab("") + # no x and y labels
labs(title = "Women in the Senate", subtitle = "Only 44 women have served in the history of the Senate, and many of them had very brief terms.\nTwenty women are current senators.") +
scale_x_continuous(breaks = seq(1910,2010,20), sec.axis = dup_axis()) + # place years on top x axis as well
geom_vline(xintercept=seq(1910,2010,20),linetype="dotted",size=0.2,color="grey") + # vertical dotted lines
geom_hline(yintercept=seq(1.5,43.5,1),linetype="dotted",size=0.2,color="grey") + # horizontal dotted lines
annotate("text", label = "* Appointed\nAppointed refers to women\nwho were never elected,\nseveral appointed members were also\nelected to later terms.", x = 1932, y = 40, size = 2.5, colour = "black",hjust = 0) + # annotation 1
annotate("text", label = "Hillary Rodham Clinton\nhas a longer senate\ncareer than half of\nthe other female\nsenators.", x = 1965, y = 35, size = 2.5, colour = "black",hjust=0) +
geom_segment(aes(x = x1, y = y1, xend = x2, yend = y2), data = data.frame(x1=1977, x2=1993, y1=35, y2=30), color = "grey") + #annotation 2
annotate("text", label = "Senators Feinstein, Boxer\nand Murray were elected\nin 1992, and now lead\ncomittees.", x = 1978, y = 20, size = 2.5, colour = "black",hjust=1) + geom_segment(aes(x = x1, y = y1, xend = x2, yend = y2), data = data.frame(x1=rep(1980,5),x2=c(1985,1978,1985,1984,1980),y1=c(22,21,19,17,22),y2=c(22,21,19,17,17)),color = "grey") + #annotation 3
annotate("text", label = "The widow of a senator\nwho died in office was often\nappointed to serve\ntemporarily.", x = 1956, y = 16, size = 2.5, colour = "black",hjust=0) + geom_segment(aes(x = x1, y = y1, xend = x2, yend = y2), data = data.frame(x1=1963,x2=1970,y1=15.5,y2=14),color = "grey") #annotation 4