library(tidyverse)STEM is science, technology, engineering, and mathematics.
sources: - https://ncses.nsf.gov/pubs/nsb20221/u-s-and-global-stem-education-and-labor-force - https://ncses.nsf.gov/pubs/nsb20212/data
extraresources: - https://www.bls.gov/oes/topics.htm#stem - https://www.aauw.org/resources/research/the-stem-gap/ - https://ngcproject.org/resources/state-girls-and-women-stem - https://blog.dol.gov/2022/02/10/women-and-girls-in-growing-stem-jobs - https://www.stemwomen.com/blog/2021/01/women-in-stem-percentages-of-women-in-stem-statistics
Employed scientists and engineers, by sex and occupation: 2019
scientists <- readxl::read_excel("~/Documents/R/WomenInSTEM/nsb20212-tabslbr-024_scientists.xlsx",
na = "0", skip = 3)
# View(scientists)scientists1 <- scientists[-1,]%>%
janitor::clean_names() %>%#names
rename(female_perc=x4,male_perc=x6) %>%
mutate(female=ifelse(female=="s",0,female),
female_perc=ifelse(female_perc=="s",0,female_perc),
male=ifelse(male=="s",0,male),
male_perc=ifelse(male_perc=="s",0,male_perc),
total=ifelse(total=="s",0,total)) %>%
mutate(across(-occupation,as.numeric)) %>%
filter(!occupation%in%c("All occupations"))
scientists1%>%
group_by(occupation)%>%
summarise_all(funs(mean)) %>%
ungroup() %>%
summary()scientists2 <- scientists1%>%
# mutate(occupation=case_when(occupation=="Accountants, auditors, and other financial specialists"~"Financial # specialists"),
# occupation=="Accounting clerks and bookkeepers"~"Accounting clerks",
# occupation=="Aerospace, aeronautical, or astronautical engineers"~"Aerospace engineers",
# occupation=="Atmospheric and space scientists"~"Space scientists",
# occupation=="Biochemists and biophysicists"~"Biochemists",
# occupation=="Biological and medical scientists"~"Medical scientists",
# occupation=="Bioengineers or biomedical engineers"~"Bioengineers",
# occupation=="Business, commerce, and marketing"~"Business",
# TRUE~occupation)
filter(occupation %in% c("Actuaries","Aerospace, aeronautical, or astronautical engineers",
"Chemical engineers","Biological and medical scientists",
"Computer and information scientists","Computer network architects",
"Earth, atmospheric, and ocean scientists","Economics",
"Earth, environmental, and marine sciences","Electrical and electronics engineers",
"Industrial engineers","Marine engineers and naval architects",
"Mathematics and statistics","Mechanical engineers",
"Nuclear engineers","Physical and related scientists",
"Physics","Statisticians","Transportation and material moving occupations")) %>%
arrange(occupation) scientists1 %>%
filter(female>0,female_perc>0.00001,total>0) %>%
ggplot(aes(x=total,y=female)) +
geom_smooth(method = "lm", se=FALSE, linetype="dashed",color="grey65")+
geom_jitter(aes(size=female_perc),
color="violet",
alpha=0.3,
shape=21,
fill="pink") +
geom_text(data=scientists2,
aes(label=occupation),
hjust="right",
vjust="top",
inherit.aes = TRUE,
check_overlap = T,
color="grey90",
family="Roboto Condensed",
fontface="bold")+
#xlim(0,15000)+
scale_x_log10(expand=expansion(add=c(0,-0.5)))+
scale_y_log10(expand=expansion(add=c(0,0))) +
labs(title="Women employed as Scientists in 2019",
subtitle="log scale by selected occupations",
caption="#30DayChartChallenge 2022 day13 - Correlation\nDataSource: NSF SCIENCE & ENGINEERING INDICATORS\nDataViz: Federica Gazzelloni",
size="Value(%)") +
hrbrthemes::theme_ft_rc()+
theme(legend.position = c(0.5,0.95),
legend.direction = "horizontal") ggsave("day13_correlation2.png",
dpi=320,
width = 9, height = 6)