knitr::opts_chunk$set(echo = TRUE)

Distill is a publication format for scientific and technical writing, native to the web.

Learn more about using Distill for R Markdown at https://rstudio.github.io/distill.

My Hw2 code lines

1.Read the dataset hotel_bookings.csv locally

library(readr)
hotels <- read_csv("C:\\Umass\\hotel_bookings.csv")

#hotels

2.Explain the variables in the dataset

head(hotels)

# A tibble: 6 × 32
  hotel        is_canceled lead_time arrival_date_ye… arrival_date_mo…
  <chr>              <dbl>     <dbl>            <dbl> <chr>           
1 Resort Hotel           0       342             2015 July            
2 Resort Hotel           0       737             2015 July            
3 Resort Hotel           0         7             2015 July            
4 Resort Hotel           0        13             2015 July            
5 Resort Hotel           0        14             2015 July            
6 Resort Hotel           0        14             2015 July            
# … with 27 more variables: arrival_date_week_number <dbl>,
#   arrival_date_day_of_month <dbl>, stays_in_weekend_nights <dbl>,
#   stays_in_week_nights <dbl>, adults <dbl>, children <dbl>,
#   babies <dbl>, meal <chr>, country <chr>, market_segment <chr>,
#   distribution_channel <chr>, is_repeated_guest <dbl>,
#   previous_cancellations <dbl>,
#   previous_bookings_not_canceled <dbl>, reserved_room_type <chr>, …

colnames(hotels)

 [1] "hotel"                          "is_canceled"                   
 [3] "lead_time"                      "arrival_date_year"             
 [5] "arrival_date_month"             "arrival_date_week_number"      
 [7] "arrival_date_day_of_month"      "stays_in_weekend_nights"       
 [9] "stays_in_week_nights"           "adults"                        
[11] "children"                       "babies"                        
[13] "meal"                           "country"                       
[15] "market_segment"                 "distribution_channel"          
[17] "is_repeated_guest"              "previous_cancellations"        
[19] "previous_bookings_not_canceled" "reserved_room_type"            
[21] "assigned_room_type"             "booking_changes"               
[23] "deposit_type"                   "agent"                         
[25] "company"                        "days_in_waiting_list"          
[27] "customer_type"                  "adr"                           
[29] "required_car_parking_spaces"    "total_of_special_requests"     
[31] "reservation_status"             "reservation_status_date"

#As you may see with colnames(), we have list all variables
#Varible type classification:
#String/char type
#<chr>: hotel, arrival_date_month, meal, country, market_segment, distribution_channel, reserved_room_type, assigned_room_type, deposit_type, agent, company, customer_type, reservation_status
#Numeric type
#<dbl>: is_canceled, lead_time, arrival_date_year, arrival_date_week_number, arrival_date_day_of_month, stays_in_weekend_nights, stays_in_week_nights, adults, children, babies, is_repeated_guest, previous_cancellations, previous_bookings_not_canceled, booking_changes, days_in_waiting_list, adr, required_car_parking_spaces, total_of_special_requests, 
#Date type
#<date>: reservation_status_date

3.Perform at least 2 basic data-wrangling operations.

#Here we would like to figure out/slice out the customer who has been in the waiting list for more than 1 day and using descending order to rank them so that we know who needs to be serviced at priority
library(dplyr)
#Use filter() to list all the customers
waitingList <- filter(hotels, `days_in_waiting_list` > 0) 
head(select(waitingList, `days_in_waiting_list`))

# A tibble: 6 × 1
  days_in_waiting_list
                 <dbl>
1                   50
2                   47
3                   47
4                   47
5                   47
6                   47

#descend to find the most urgent ones
waitingListDec <- arrange(waitingList, desc(`days_in_waiting_list`))
head(select(waitingListDec, `days_in_waiting_list`))

# A tibble: 6 × 1
  days_in_waiting_list
                 <dbl>
1                  391
2                  391
3                  391
4                  391
5                  391
6                  391

head(waitingListDec)

# A tibble: 6 × 32
  hotel      is_canceled lead_time arrival_date_year arrival_date_mon…
  <chr>            <dbl>     <dbl>             <dbl> <chr>            
1 City Hotel           1       443              2016 October          
2 City Hotel           1       443              2016 October          
3 City Hotel           1       443              2016 October          
4 City Hotel           1       443              2016 October          
5 City Hotel           1       443              2016 October          
6 City Hotel           1       443              2016 October          
# … with 27 more variables: arrival_date_week_number <dbl>,
#   arrival_date_day_of_month <dbl>, stays_in_weekend_nights <dbl>,
#   stays_in_week_nights <dbl>, adults <dbl>, children <dbl>,
#   babies <dbl>, meal <chr>, country <chr>, market_segment <chr>,
#   distribution_channel <chr>, is_repeated_guest <dbl>,
#   previous_cancellations <dbl>,
#   previous_bookings_not_canceled <dbl>, reserved_room_type <chr>, …

#Hence we know that some customers have been waiting for 391 days

HuidiDingHW2

My Hw2 code lines

1.Read the dataset hotel_bookings.csv locally

2.Explain the variables in the dataset

3.Perform at least 2 basic data-wrangling operations.