# Sample Reading Data -- ACS 
# This is an example for only illustrate to use the ACS without considering the weights on the individual personal record
# Heavy modifications are necessary to use as an actual research
# Ideas from Tom Bales (2021 Winter Class)

rm(list = ls())

acs2018_pop_il <- read_csv("http://bigblue.depaul.edu/jlee141/econdata/acs_data/acs2018_pop_il.csv")
str(acs2018_pop_il)
library(dplyr)

# Select only variables you need here to be used for the project.
# Find the variables you are interested in from see PUMS_DATA_Dictionary_2018.pdf after page 30
# Here is an example to include 8 variables and only BA or higher education attainment:

acs2018_pop_il2 <- acs2018_pop_il %>%  select(ST,SCHL,AGEP,CIT,FOD1P,WAGP,SEX,OCCP)
acs2018_pop_il2$SEX <- as.factor(acs2018_pop_il2$SEX)
acs2018_pop_il2$CIT <- as.factor(acs2018_pop_il2$CIT)
acs2018_pop_il2$SCHL <- as.factor(acs2018_pop_il2$SCHL)

# Filter out the Non-college / Graduate school degrees attained #
# Select only people has Associate and Bachelor Degree - see PUMS_DATA_Dictionary_2018.pdf Page 42
acs2018_pop_il2 <- filter(acs2018_pop_il2,SCHL %in% c("21","22","23","24")) 

# Degrees from FOD1P. Check the full list in the dictionary. Dummy for Business Major

acs2018_pop_il2 <- acs2018_pop_il2 %>%  mutate(Degree= case_when(
  FOD1P %in% c(6200,6201,6202,6203,6204,6205,6206,6207,6209,6210,6211,6212,6299) ~ "BUSINESS" ,
  FOD1P %in% c(2100,2101,2102,2105,2106,2107,3700,3701,3702,4005) ~ "COMP_MATH",
  TRUE ~ "A.OTHERS"   
  ))
acs2018_pop_il2$Degree <- as.factor(acs2018_pop_il2$Degree)
acs2018_pop_il2$OLDER <- ifelse(acs2018_pop_il2$AGEP >55,1,0)  # A Dummy for Older than 55 years old
  

# Let's find if the degree matter to the wage income
lm1 <- lm(WAGP~SEX+SCHL+AGEP+OLDER+CIT+Degree, data=acs2018_pop_il2)
summary(lm1)