library(tidyverse)paygap <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-06-28/paygap.csv')paygap%>%headpaygap%>%namesdf <- paygap%>% # count(employer_id,sort=T)
arrange(employer_id) %>%
group_by(employer_id)%>%
summarize(employer_size,across(.cols = is.numeric,median)) %>%
ungroup()
dfdf_bonus
df_bonus <- df%>% #DataExplorer::profile_missing()
select(employer_id,employer_size,contains("bonus")) %>%
filter(!employer_size=="Not Provided") %>%
mutate(id=case_when(employer_size=="Less than 250"~1,
employer_size=="250 to 499"~2,
employer_size=="500 to 999"~3,
employer_size=="1000 to 4999"~4,
employer_size=="5000 to 19,999"~5,
employer_size=="20,000 or more"~6)) %>%
relocate(id) %>%
arrange(id)
df_bonus %>% DataExplorer::profile_missing()df_bonus %>%
#group_by(employer_size) %>%
#summarize(across(is.numeric,.fns = median)) %>%
#ungroup() %>%
ggplot(aes(x=male_bonus_percent,y=female_bonus_percent))+
geom_boxplot(aes(group=employer_size),size=0.2)+
geom_point(size=0.1,aes(color=employer_id))+
geom_abline(intercept = max(df_bonus$male_bonus_percent),slope=-1,size=0.1,linetype="dashed")+
geom_abline(intercept = 0,slope=1,size=0.5,linetype="dashed",color="red")+
geom_smooth(method="lm")df_bonus%>%
filter(male_bonus_percent>50,female_bonus_percent<50) %>%
ggplot(aes(x=male_bonus_percent,y=female_bonus_percent))+
# geom_boxplot(aes(group=employer_size),size=0.2)+
geom_point(size=0.1,aes(color=employer_id))+
geom_abline(intercept = max(df_bonus$male_bonus_percent),slope=-1,size=0.5,linetype="dashed")+
geom_abline(intercept = 0,slope=1,size=0.5,linetype="dashed",color="red")+
geom_text(aes(label=employer_id),check_overlap = T,size=2)+
geom_smooth(method="lm")library(tidymodels)pay_bonus_pca<- df_bonus %>%
select(-employer_size) %>%
drop_na() %>%
prcomp(scale = TRUE)
tidy(pay_bonus_pca, matrix = "scores") %>%
filter(PC%in%c(1,2)) %>%
pivot_wider(names_from=PC,values_from=value)%>%
janitor::clean_names() %>%
ggplot(aes(x=x1,y=x2))+
geom_point()df%>%count(employer_size)df %>%
mutate(id=case_when(employer_size=="Less than 250"~1,
employer_size=="250 to 499"~2,
employer_size=="500 to 999"~3,
employer_size=="1000 to 4999"~4,
employer_size=="5000 to 19,999"~5,
employer_size=="20,000 or more"~6)) %>%
relocate(id) %>%
arrange(id)
#DataExplorer::profile_missing()Sampling
df1<-df %>%
mutate(id=case_when(employer_size=="Less than 250"~1,
employer_size=="250 to 499"~2,
employer_size=="500 to 999"~3,
employer_size=="1000 to 4999"~4,
employer_size=="5000 to 19,999"~5,
employer_size=="20,000 or more"~6)) %>%
relocate(id) %>%
arrange(id)
df1
# library(sampling)
# strata(df1,size=300)df2<-df %>% #DataExplorer::profile_missing()
filter(!is.na(female_lower_quartile),!employer_size=="Not Provided") %>%
select(!contains("bonus")) %>%
mutate(id=case_when(employer_size=="Less than 250"~1,
employer_size=="250 to 499"~2,
employer_size=="500 to 999"~3,
employer_size=="1000 to 4999"~4,
employer_size=="5000 to 19,999"~5,
employer_size=="20,000 or more"~6)) %>%
relocate(id) %>%
arrange(id) %>%
group_by(id,employer_size)%>%
mutate(n=n()) %>%
ungroup() %>%
mutate(pct=round(n/sqrt(sum(n))*100,5))%>%#count(pct,n) %>%
relocate(n,pct)%>%
group_by(id,employer_size)%>%
summarise(across(.cols = everything(),.fns = mean)) %>%
ungroup() %>%
# select(-diff_mean_bonus_percent) %>%
#mutate(diff_mean_bonus=round(male_bonus_percent-female_bonus_percent,2)) %>%
mutate_if(is.numeric, round, 2)
df2df2 %>%
arrange(id)%>%namesdf2 %>%
arrange(id)%>%
ggplot(aes(x=25,y=fct_reorder(employer_size,id),label=employer_size))+
geom_point(color="grey80",shape=".")+
geom_text(hjust=1)+
geom_text(aes(x=30,label=paste0(diff_mean_hourly_percent,"%"))) +
# lower
geomtextpath::geom_textsegment(label="Lower",size=4,
aes(x=female_lower_quartile,xend=male_lower_quartile,yend=employer_size),
position = position_nudge(y = 0.25),
color="grey50",size=0.5)+
geom_point(aes(x=female_lower_quartile,y=employer_size),
position = position_nudge(y = 0.25),
color="violet",size=5)+
geom_point(aes(x=male_lower_quartile,y=employer_size),
position = position_nudge(y = 0.25),
color="navy",size=5)+
# upper
geomtextpath::geom_textsegment(label="Upper",size=4,
aes(x=female_top_quartile,xend=male_top_quartile,yend=employer_size),
color="grey50",size=0.5)+
geom_point(aes(x=female_top_quartile,y=employer_size),color="violet",size=5)+
geom_point(aes(x=male_top_quartile,y=employer_size),color="navy",size=5)+
geom_vline(xintercept = 50,size=0.3,linetype="dashed")+
#scale_x_continuous(limits = c(0,65),breaks = c(40,50,60))+
labs(y="")+
ggthemes::theme_fivethirtyeight()+
theme(axis.text.y = element_blank(),
panel.grid.major.y = element_blank(),
panel.grid.major.x = element_blank())df2 %>%
arrange(id)%>%
ggplot(aes(x=25,y=fct_reorder(employer_size,id),label=employer_size))+
geom_text(hjust=1,fontface="bold",color="#003d59",size=6)+
geom_text(aes(x=30,label=paste0(diff_median_hourly_percent,"%")),
fontface="bold",size=4,
color="#003d59") +
# lower
geom_segment(size=3.5,
aes(x=female_lower_quartile,xend=female_top_quartile,yend=employer_size),
position = position_nudge(y = 0.2),
color="#a8bd3a",size=0.5)+
geom_point(aes(x=female_lower_quartile,y=employer_size),
position = position_nudge(y = 0.2),
shape=21,stroke=1,fill="violet",
color="#a8bd3a",size=5)+
geom_point(aes(x=female_top_quartile,y=employer_size),
position = position_nudge(y = 0.2),
shape=21,stroke=1,fill="violet",
color="#a8bd3a",size=5)+
# upper
geom_segment(size=3.5,
aes(x=male_lower_quartile,xend=male_top_quartile,yend=employer_size),
position = position_nudge(y = -0.2),
color="#a8bd3a",size=0.5)+
geom_point(aes(x=male_lower_quartile,y=employer_size),
position = position_nudge(y = -0.2),
shape=21,stroke=1,fill="navy",
color="#a8bd3a",size=5)+
geom_point(aes(x=male_top_quartile,y=employer_size),
position = position_nudge(y = -0.2),
shape=21,stroke=1,fill="navy",
color="#a8bd3a",size=5)+
# vertical line
geom_vline(xintercept = c(40,50,60),size=(c(40,100,40)/100),linetype="dashed",color="grey40")+
scale_x_continuous(limits = c(10,65),breaks = c(40,50,60),labels = paste0(c(40,50,60),"K"))+
coord_cartesian(clip = "off",ylim = c(1,6))+
labs(title="Difference in gender PayGap by size of Employers\n\n",
caption="\nDataSource: #TidyTuesday 2022 week26 ons.gov.uk | DataViz: Federica Gazzelloni (@fgazzelloni)")+
annotate("text",
x= c(18,30,50),
y = c(6.8,6.8,6.8),
label = c("Employer size", "PayGap", "Gender upper/lower values "),
family = "", fontface = 3, size=5,color="#a8bd3a") +
ggthemes::theme_fivethirtyeight()+
theme(text = element_text(color="#a8bd3a"),
plot.title = element_text(size=18),
plot.caption = element_text(size=8.5,family="",face=3),
axis.text.y = element_blank(),
axis.text.x = element_text(size=12,face="bold"),
panel.grid.major.y = element_line(size=14),
panel.grid.major.x = element_blank(),
plot.background = element_rect(color="#003d59",fill="#003d59"),
panel.background = element_rect(color="#003d59",fill="#003d59"))+
annotate("text",
x= 20.8,
y = 0.2,
label = "PayGap are median values calculated on unique employer id\nfrom hourly pay(%) mean difference\nPink = Female | Blue = Male",
family = "", fontface = 3, size=2.8,color="white") ggsave("w26_paygap.png",dpi=320)