Created
March 22, 2020 01:18
-
-
Save duttashi/add76c9d92132c9d9bfb073a0c275ae9 to your computer and use it in GitHub Desktop.
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
# load required libraries | |
library(tidyverse) | |
# READ DATA IN MEMORY | |
df_train<- read.csv("kaggle_fake_job_prediction/data/fake_job_postings.csv", | |
header=T, na.strings=c(" ","NA"), stringsAsFactors = FALSE, strip.white = TRUE) | |
# create copy | |
df<- df_train | |
# coerce character vars to factor for data cleanup | |
df<- df %>% | |
mutate_if(is.character, funs(factor(.))) | |
find_empty_level<- which(levels(df$employment_type)=="") | |
levels(df$employment_type)[find_empty_level]<-"NA" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment