Last active
July 5, 2017 06:29
-
-
Save saraswatmks/6c8821a8763cd7755c72bcd9c00950e3 to your computer and use it in GitHub Desktop.
Address File
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(data.table) | |
sdata <- fread("address_data.csv") | |
head(sdata) | |
setnames(sdata,"x","address") | |
# some cleaning | |
sdata$pincodes := unlist(regmatches(address, gregexpr("(\\d+){6}",sdata$address)))] | |
sdata$address := gsub(pattern = "(\\d+){6}",replacement = "", x = sdata$address)] | |
sdata$address := unlist(lapply(sdata$address, function(x) gsub("[[:cntrl:]]", "", x)))] | |
sdata$address := lapply(strsplit(sdata$address, split = " "), function(x) x[nchar(x) > 2])]) | |
# as required | |
new_frame <- data.frame(address = unlist(sdata$address), pincodes = rep(unlist(sdata$pincodes), lapply(sdata$address, length))) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment