一些数据：
x <- structure(list(X. = c("4,084", "4,084", "4,084", "4,084", "4,084"
), ADR = c("1,099.69", "68.66", "232.72", "195.66", "98"), hotel_id = c("2,313,076",
"583,666", "1,251,372", "1,545,890", "298,160"), city_id = c("9,395",
"17,193", "5,085", "16,808", "8,584"), star_rating = c(5, 2,
3, 4, 4), accommodation_type_name = c("Hotel", "Bungalow", "Hotel",
"Hotel", "Hotel"), chain_hotel = c("chain", "non-chain", "non-chain",
"non-chain", "non-chain"), booking_date = c("10/5/2016", "12/4/2016",
"11/6/2016", "10/22/2016", "12/11/2016"), checkin_date = c("10/27/2016",
"12/9/2016", "11/18/2016", "11/3/2016", "12/11/2016"), checkout_date = c("10/30/2016",
"12/12/2016", "11/20/2016", "11/4/2016", "12/12/2016"), city = c("A",
"B", "C", "D", …