Women_Emp

Women_Emp.r

#load packages
library(ggplot2)
library(RColorBrewer)
library(readr)
library(dplyr)
library(ggplot2)
library(scales)
#Import data
raw_data <- read.csv("usa_00016.csv")
#Remove data from Alaska and Hawaii before 1960, Only people over 18, Only Women, Only people in the workforce
a <- filter(raw_data,STATEFIP < 60 & (YEAR >= 1960 | !(STATEFIP %in% c(2,15)))) %>%
  filter(AGE>=18) %>%
  filter(SEX==2) %>%
  filter(EMPSTAT %in% c(1,2))
#Narrow data set down to identified columns of variables
b <- select(a, YEAR,PERWT,RACE,BPL,EMPSTAT)
#Create new column "Identity" based on the qualities of RACE and BPL indicated
c <- mutate(b, Identity = ifelse(RACE==1 & BPL<=99, "White Native Born",
                           ifelse(RACE==1 & BPL>99, "White Foreign Born",
                                  ifelse(RACE!=1 & BPL<=99, "Nonwhite Naitive Born","Nonwhite Foreign Born"))))
#Create new columns for individual Employment and Unemployment
d <- mutate(c,EMP=ifelse(EMPSTAT==1,PERWT,0), UNEMP= ifelse(EMPSTAT==2,PERWT,0))
#Sum EMP and UNEMP to get population in those categories for unique YEAR and Identity
e <- summarise(group_by(d,YEAR,Identity),EMP=sum(EMP),UNEMP=sum(UNEMP))
#Create new column for total by adding together Employment and unemployment
f <- mutate(e, TOTAL =EMP+UNEMP )
#Create new column for employment rate by dividing employment pop by total pop
g <- mutate(f, EMPR=EMP/TOTAL)
#Create a line graph showing employment rate over time for identiy groups
ggplot(g,aes(x=YEAR, y=EMPR, color=Identity)) + geom_line() +geom_point() +
  scale_y_continuous(labels= scales::percent, limits=c(0,1))+
  labs(title='US Employment Rate by Race and Nativity', x="Year", y='Employment Rate')
#Create a focussed line graph showing employment rate over time for identiy groups
ggplot(g,aes(x=YEAR, y=EMPR, color=Identity)) + geom_line() +geom_point() +
  scale_y_continuous(labels= scales::percent)+
  labs(title='US Employment Rate by Race and Nativity', x="Year", y='Employment Rate')

#Narrow data set down to identified columns of variables
h <- select(a,REGION,YEAR,PERWT,RACE,BPL,EMPSTAT)
#Create new column "Identity" based on the qualities of RACE and BPL indicated
i <- mutate(h, Identity = ifelse(RACE==1 & BPL<=99, "White Native Born",
                                 ifelse(RACE==1 & BPL>99, "White Foreign Born",
                                        ifelse(RACE!=1 & BPL<=99, "Nonwhite Naitive Born","Nonwhite Foreign Born"))))
#Create new columns for individual Employment and Unemployment
j <- mutate(i,EMP=ifelse(EMPSTAT==1,PERWT,0), UNEMP= ifelse(EMPSTAT==2,PERWT,0))
#Assign these titles to the specified numbers
Northeast <- c(11:13)
Midwest <-c(21:23)
South <- c(31:34)
West <- c(41:43)
#create a new variable Region, it's value is the previously assigned titles according to the REGION variable
k <-mutate(j,Region=ifelse(REGION %in% Northeast,"Northeast",
                           ifelse(REGION %in% Midwest,"Midwest",
                                  ifelse(REGION %in% South, "South",
                                         ifelse(REGION %in% West, "West", "Other")))))
#Narrow the data set to the identified columns
kk <- select(k,YEAR,Identity,Region,EMP,UNEMP)
#Sum EMP and UNEMP to get population in those categories for unique YEAR, Region and Identity
l <- summarise(group_by(kk,YEAR,Identity,Region),EMP=sum(EMP),UNEMP=sum(UNEMP))
#Create new column for total by adding together Employment and unemployment
m <- mutate(l, TOTAL =EMP+UNEMP)
#Create new column for employment rate by dividing employment pop by total pop
n <- mutate(m,EMPR=EMP/TOTAL)
#Create a line graph showing employment rate over time for identiy groups in each region
ggplot(n,aes(x=YEAR, y=EMPR, color=Identity)) + geom_line() +geom_point() +
  scale_y_continuous(labels= scales::percent, limits=c(0,1))+
  labs(title='US Employment Rate by Race and Nativity', x="Year", y='Employment Rate')+
  facet_grid(.~Region)