hotel_subset.R

library(tidyverse)
library(lubridate)

# ------------------------------------------------------------------------------

set.seed(2427)
hotels <- 
  readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-02-11/hotels.csv') %>%
  filter(is_canceled == 0) %>%
  mutate(
    children = case_when(children + babies > 0 ~ "children", TRUE ~ "none"),
    required_car_parking_spaces = 
      case_when(required_car_parking_spaces > 0 ~ "parking", TRUE ~ "none"),
    arrival_date = paste(arrival_date_year, arrival_date_month, arrival_date_day_of_month, sep = "-"),
    arrival_date = ymd(arrival_date)
  ) %>%
  rename(average_daily_rate = adr) %>% 
  select(-is_canceled, -reservation_status, -babies, -starts_with("arrival_date_"),
         -reservation_status_date, -agent, -company) %>% 
  mutate_if(is.character, ~ str_replace_all(.x, " ", "_")) %>% 
  mutate_if(is.character, as.factor) %>% 
  sample_n(50000)

# ------------------------------------------------------------------------------

write_csv(hotels, path = "hotels.csv")