data_management

#START BY LOADING LIBRARIES AND OPTIONS
library(aws.s3)
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
options(scipen = 999)

#LOAD DATA FROM THE LEHMAN SERVER
Sys.setenv("AWS_ACCESS_KEY_ID" = "AKIAXIJLI7UET3TVMHRW",
           "AWS_SECRET_ACCESS_KEY" = "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",
           "AWS_DEFAULT_REGION" = "us-west-2")
s3load('addhealthW5.rdata', bucket = 'lehmansociologydata')


####FREQUENCY TABLES####
#change variable names and titles

#CATEGORICAL VARIABLE
frequency(wave5addhealth$H5HR2, title= "Frequency Distribution of Living Arrangements, Wave 5 Add Health")
#The two lines below here RECODE the homeless and other categories to combine them to make the dummy codes consecutive.
wave5addhealth$H5HR2[wave5addhealth$H5HR2==5]<-4
wave5addhealth$H5HR2[wave5addhealth$H5HR2==6]<-4

#The 3 lines below here LABEL the dummy codes as the categories that they represent after I RECODED
wave5addhealth$H5HR2 <- factor(wave5addhealth$H5HR2, levels = c(1,2,3,4), 
                                  labels = c("Own Place", "Parents' Home", "Another Person's Home","Other"))