library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.6.3
adult <- read.csv("adultincome.csv")
income.pct <- adult %>%
  group_by(occupation, income) %>%
  summarize(count = n()) %>%
  mutate(pct = count/sum(count)) %>%
  arrange(desc(income), pct)

income.pct$occupation <- factor(income.pct$occupation,levels=income.pct$occupation[1:(nrow(income.pct)/2)])

ggplot(income.pct, aes(reorder(occupation,-count), pct, fill = income)) + 
  geom_bar(stat="identity", position = "fill") + 
  geom_hline(yintercept = 0.2489, col = "blue") +
  ggtitle("Income by occupation") + 
  xlab("Occupation") + 
  ylab("Percentage") + 
  scale_y_continuous(labels=scales::percent) + 
  scale_fill_manual(values=c("#E3CD81FF", "#B1B3B3FF")) + 
  theme(plot.title = element_text(hjust = 0.5), 
        axis.title = element_text(size = 12), 
        axis.text.x = element_text(size = 12), 
        axis.text.y = element_text(size = 12),
        legend.position = "bottom", 
        legend.title = element_text(size = 12, face = "bold"),
        legend.text = element_text(colour="black", size = 12)) + 
  coord_flip()

```