Sanitize U.S. States Names

# load data

StateData = read.csv('65States.pip', sep="|", col.names = c("FullName", "Abbr"))

StateFullName = toupper(StateData$FullName)

StateAbbr = as.vector(StateData$Abbr)

# define a function

sanitizeState = function(inputcol, StateFullName, StateAbbr){

  match = amatch(inputcol, StateFullName, maxDist=1)

  inputcol[!is.na(match)] = StateAbbr[na.omit(match)]

  return (inputcol)

}

# use the function

df$State = sanitizeState(gls$State,StateFullName, StateAbbr )