in class data cleaning

gistfile1.txt

library(maptools)

get_second_element <- function(item) {
  return (item[2])
}

get_first_element <- function(item) {
  return (item[1])
}

# load the data
data <- read.delim("http://shancarter.github.io/ucb-dataviz-fall-2013/classes/data-practice/county-data.txt", header=F, stringsAsFactors=F)

# rename it like a human
names(data) <- c("county_orig", "guns_orig")

# split it up based on parenthesis
split <- strsplit(data$county_orig, split="\\(")

#make a new field for state
data$state_clean <- sapply(split, get_second_element)

#clean guns
data$state_clean <- gsub("\\)", "", data$state_clean)

#make a new county
data$county_clean <- sapply(split, get_first_element)

#clean guns
data$guns_clean <- as.numeric(gsub(",", "", data$guns_orig))