Lab 3

#Lab3
#Morgan Waterman
#Column graphs

library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

data <- read_csv('./data/Lab3Newest.csv') %>% 
  filter(AGE>15 & AGE<65 & !(STATEFIP %in% c(2,15)))

table(data$RACE)
#Recode race

datab <-data %>% mutate(Race = factor(ifelse(RACE %in% c(1), 1,
                                      ifelse(RACE %in% c(2), 2,
                                      ifelse(RACE %in% c(3), 3, 4))),
                                  labels=c('white', 'black', 'Native American', 'Asian')))
#Recode sex
datac <- datab %>% mutate(Sex = ifelse(SEX==1, 'male', 'female'))

table(datac$Occupation)
#Create Occupation
                           
datad <- datac %>% mutate(Occupation = factor(ifelse(OCC1950<100, 6,
                                              ifelse(OCC1950>970, 1,
                                              ifelse(OCC1950>900 | (OCC1950>500 & OCC1950<700), 3,
                                              ifelse(OCC1950==100 | OCC1950==123 | OCC1950 > 800, 2,
                                              ifelse(OCC1950<500, 4, 5))))), 
labels = c("none", "farmers and farm laborers", "craftsmen/operatives/laborers", "managerial/clerical/sales", "service", "professional")))


#Select for only the variables I want in Fig 2
#YEAR, Race, Sex, PERWT

datae <- datad %>% select(YEAR, PERWT, Race, Occupation, Sex)

#Making 2 graphs

f2 <- datae %>% group_by(YEAR, Sex, Race) %>% summarise(Number = sum(PERWT))

f4 <- datae %>% group_by(YEAR, Sex, Race, Occupation) %>% summarise(Number = sum(PERWT))

#graphing fig 2

ggplot(data = f2, aes(x = YEAR, y = Number, fill = Sex)) +
    geom_bar(stat = 'identity') +
    labs(x = 'Year', y = 'Population', fill = 'Sex', title = '2. Population Aged 15-65 by Race, Year, and Sex, 1870-1920') +
    scale_y_continuous(labels=scales::comma) +
  scale_x_continuous(breaks=c(1870, 1900, 1920)) +
  scale_fill_brewer(palette='Set2',guide=guide_legend (reverse = TRUE)) +
  facet_wrap(~Race, ncol=2, scales = 'free_y') +
  theme_bw()
  
#graphing fig 3

ggplot(data = f4, aes(x = YEAR, y = Number, fill = Occupation)) +
  geom_bar(stat = 'identity', position = 'fill') +
  labs(x = 'Year', y = 'Percent of Population', fill = 'Occupation', title = '4. Occupation of Persons Aged 15-65 by Sex, Race, and Year 1870-1920') +
  scale_y_continuous(labels=scales::percent) +
  scale_x_continuous(breaks=c(1870, 1900, 1920)) +
  scale_fill_brewer(palette='Set1') +
  facet_grid(Sex~.~Race) +
  theme_bw() + theme(legend.position = 'bottom')