Load required libraries
library(conflicted)
library(dplyr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.4
## ✔ ggplot2 3.4.4 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.0
Read data
airbnb <- read.csv("challenge_datasets/AB_NYC_2019.csv")
head(airbnb)
## id name host_id host_name
## 1 2539 Clean & quiet apt home by the park 2787 John
## 2 2595 Skylit Midtown Castle 2845 Jennifer
## 3 3647 THE VILLAGE OF HARLEM....NEW YORK ! 4632 Elisabeth
## 4 3831 Cozy Entire Floor of Brownstone 4869 LisaRoxanne
## 5 5022 Entire Apt: Spacious Studio/Loft by central park 7192 Laura
## 6 5099 Large Cozy 1 BR Apartment In Midtown East 7322 Chris
## neighbourhood_group neighbourhood latitude longitude room_type price
## 1 Brooklyn Kensington 40.64749 -73.97237 Private room 149
## 2 Manhattan Midtown 40.75362 -73.98377 Entire home/apt 225
## 3 Manhattan Harlem 40.80902 -73.94190 Private room 150
## 4 Brooklyn Clinton Hill 40.68514 -73.95976 Entire home/apt 89
## 5 Manhattan East Harlem 40.79851 -73.94399 Entire home/apt 80
## 6 Manhattan Murray Hill 40.74767 -73.97500 Entire home/apt 200
## minimum_nights number_of_reviews last_review reviews_per_month
## 1 1 9 2018-10-19 0.21
## 2 1 45 2019-05-21 0.38
## 3 3 0 NA
## 4 1 270 2019-07-05 4.64
## 5 10 9 2018-11-19 0.10
## 6 3 74 2019-06-22 0.59
## calculated_host_listings_count availability_365
## 1 6 365
## 2 2 355
## 3 1 365
## 4 1 194
## 5 1 0
## 6 1 129
str(airbnb)
## 'data.frame': 48895 obs. of 16 variables:
## $ id : int 2539 2595 3647 3831 5022 5099 5121 5178 5203 5238 ...
## $ name : chr "Clean & quiet apt home by the park" "Skylit Midtown Castle" "THE VILLAGE OF HARLEM....NEW YORK !" "Cozy Entire Floor of Brownstone" ...
## $ host_id : int 2787 2845 4632 4869 7192 7322 7356 8967 7490 7549 ...
## $ host_name : chr "John" "Jennifer" "Elisabeth" "LisaRoxanne" ...
## $ neighbourhood_group : chr "Brooklyn" "Manhattan" "Manhattan" "Brooklyn" ...
## $ neighbourhood : chr "Kensington" "Midtown" "Harlem" "Clinton Hill" ...
## $ latitude : num 40.6 40.8 40.8 40.7 40.8 ...
## $ longitude : num -74 -74 -73.9 -74 -73.9 ...
## $ room_type : chr "Private room" "Entire home/apt" "Private room" "Entire home/apt" ...
## $ price : int 149 225 150 89 80 200 60 79 79 150 ...
## $ minimum_nights : int 1 1 3 1 10 3 45 2 2 1 ...
## $ number_of_reviews : int 9 45 0 270 9 74 49 430 118 160 ...
## $ last_review : chr "2018-10-19" "2019-05-21" "" "2019-07-05" ...
## $ reviews_per_month : num 0.21 0.38 NA 4.64 0.1 0.59 0.4 3.47 0.99 1.33 ...
## $ calculated_host_listings_count: int 6 2 1 1 1 1 1 1 1 4 ...
## $ availability_365 : int 365 355 365 194 0 129 0 220 0 188 ...
Function
compute_common_room_type <- function(data, neighbourhood=NULL, return_count=TRUE) {
# If a specific neighbourhood is provided, filter the data
if (!is.null(neighbourhood)) {
data <- data %>% dplyr::filter(neighbourhood_group == "Manhattan")
}
# Compute frequency of each room type
freqs <- table(data$room_type)
max_n <- max(freqs)
common_room_type <- names(freqs[which(freqs == max_n)])
# Return the result
if (return_count) {
return(data.frame(room_type = common_room_type, count = max_n))
} else {
return(data.frame(room_type = common_room_type))
}
}
# Find the most common room type in the entire dataset
compute_common_room_type(airbnb)
## room_type count
## 1 Entire home/apt 25409
# Find the most common room type in a specific neighbourhood, e.g., 'Manhattan'
compute_common_room_type(airbnb, neighbourhood = "Manhattan")
## room_type count
## 1 Entire home/apt 13199
# Find the most common room type in the entire dataset, but only return the room type
compute_common_room_type(airbnb, return_count = FALSE)
## room_type
## 1 Entire home/apt