lesson1

#R operates using working directories. Basically, it lets R know what folder you're working in
setwd("~/Documents/Data Projects/Lessons")

#now we need to read in the files that we downloaded. the read.csv function should do very well here

VINTON <- read.csv("VINTON.csv")
VINTON2 <- read.csv("VINTON2.csv")
View(VINTON)
#so many variables that are uselsss to what we're doing

#explain libraries in R, open source nature
library(data.table)


#the data.table library makes it really easy to select whatever columns you want to use
VINTON <- fread("VINTON.csv", select = c("SOS_VOTERID", "DATE_OF_BIRTH", "FIRST_NAME", "LAST_NAME", "RESIDENTIAL_CITY", "GENERAL_11_06_2012"))
VINTON2 <- fread("VINTON2.csv", select = c("SOS_VOTERID", "DATE_OF_BIRTH", "FIRST_NAME", "LAST_NAME", "RESIDENTIAL_CITY", "GENERAL_11_06_2012"))

#the merge function allows you to make two dataframes into one
#all handles inner and outer joins
combo <- merge(VINTON, VINTON2, by = "SOS_VOTERID", all = TRUE)

#
purged <- combo[is.na(combo$LAST_NAME.y)]

library(ggplot2)
qplot(purged$RESIDENTIAL_CITY.x)
qplot(purged$GENERAL_11_06_2012.x)