01-preparation.r

require(dplyr)
require(data.table)

questions <- tbl_df(fread(input = "questions.csv", header = TRUE, sep = ",")) %>%
  mutate(Score = as.integer(Score)) %>%
  mutate(ViewCount = as.integer(ViewCount)) %>%
  mutate(CreationDate = as.Date(CreationDate)) %>%
  mutate(Tags = Tags %>%
           gsub("<", "", .) %>%
           gsub(">", ",", .) %>%
           gsub(".{1}$", "", .)
         )