INFO H-510 Week 2

The basic structure of the New York City Airbnb market, including pricing, availability, and location-based patterns, are analyzed and understood using this dataset.

Rows as Observations: Each row represents a unique Airbnb listing in New York City.

Columns as Variables

• Continuous Variables: price, latitude and longitude ,minimum_night.

• Time-based Column: last_review.

• Categorical Variables: neighbourhood_group, room_type.

library(tidyverse) 

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

data <- read_delim("./AB_NYC_2019.csv", delim = ",")

## Rows: 48895 Columns: 16
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (5): name, host_name, neighbourhood_group, neighbourhood, room_type
## dbl  (10): id, host_id, latitude, longitude, price, minimum_nights, number_o...
## date  (1): last_review
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(data)

view(data)

str(data)

## spc_tbl_ [48,895 × 16] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ id                            : num [1:48895] 2539 2595 3647 3831 5022 ...
##  $ name                          : chr [1:48895] "Clean & quiet apt home by the park" "Skylit Midtown Castle" "THE VILLAGE OF HARLEM....NEW YORK !" "Cozy Entire Floor of Brownstone" ...
##  $ host_id                       : num [1:48895] 2787 2845 4632 4869 7192 ...
##  $ host_name                     : chr [1:48895] "John" "Jennifer" "Elisabeth" "LisaRoxanne" ...
##  $ neighbourhood_group           : chr [1:48895] "Brooklyn" "Manhattan" "Manhattan" "Brooklyn" ...
##  $ neighbourhood                 : chr [1:48895] "Kensington" "Midtown" "Harlem" "Clinton Hill" ...
##  $ latitude                      : num [1:48895] 40.6 40.8 40.8 40.7 40.8 ...
##  $ longitude                     : num [1:48895] -74 -74 -73.9 -74 -73.9 ...
##  $ room_type                     : chr [1:48895] "Private room" "Entire home/apt" "Private room" "Entire home/apt" ...
##  $ price                         : num [1:48895] 149 225 150 89 80 200 60 79 79 150 ...
##  $ minimum_nights                : num [1:48895] 1 1 3 1 10 3 45 2 2 1 ...
##  $ number_of_reviews             : num [1:48895] 9 45 0 270 9 74 49 430 118 160 ...
##  $ last_review                   : Date[1:48895], format: "2018-10-19" "2019-05-21" ...
##  $ reviews_per_month             : num [1:48895] 0.21 0.38 NA 4.64 0.1 0.59 0.4 3.47 0.99 1.33 ...
##  $ calculated_host_listings_count: num [1:48895] 6 2 1 1 1 1 1 1 1 4 ...
##  $ availability_365              : num [1:48895] 365 355 365 194 0 129 0 220 0 188 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   id = col_double(),
##   ..   name = col_character(),
##   ..   host_id = col_double(),
##   ..   host_name = col_character(),
##   ..   neighbourhood_group = col_character(),
##   ..   neighbourhood = col_character(),
##   ..   latitude = col_double(),
##   ..   longitude = col_double(),
##   ..   room_type = col_character(),
##   ..   price = col_double(),
##   ..   minimum_nights = col_double(),
##   ..   number_of_reviews = col_double(),
##   ..   last_review = col_date(format = ""),
##   ..   reviews_per_month = col_double(),
##   ..   calculated_host_listings_count = col_double(),
##   ..   availability_365 = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>

# Summary of Price column
summary(data$price)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     0.0    69.0   106.0   152.7   175.0 10000.0

#Summary of Reviews per month Column
 summary(data$reviews_per_month)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.010   0.190   0.720   1.373   2.020  58.500   10052

# Summary of Room type

table(data$room_type)

## 
## Entire home/apt    Private room     Shared room 
##           25409           22326            1160

# Summary of neighbourhood
table(data$neighbourhood_group)

## 
##         Bronx      Brooklyn     Manhattan        Queens Staten Island 
##          1091         20104         21661          5666           373

# Combined summary of price (numeric) and room_type (categorical)
summary(data[, c("price", "room_type")])

##      price          room_type        
##  Min.   :    0.0   Length:48895      
##  1st Qu.:   69.0   Class :character  
##  Median :  106.0   Mode  :character  
##  Mean   :  152.7                     
##  3rd Qu.:  175.0                     
##  Max.   :10000.0

mean_price_roomtype <-data|>
  group_by(room_type) |>
  summarize(mean_price =mean(price))

mean_price_roomtype

# Calculate average price by room type and neighborhood group
avg_price <- data %>%
  group_by(neighbourhood_group, room_type) %>%
  summarize(mean_price = mean(price, na.rm = TRUE))

## `summarise()` has grouped output by 'neighbourhood_group'. You can override
## using the `.groups` argument.

print(avg_price)

## # A tibble: 15 × 3
## # Groups:   neighbourhood_group [5]
##    neighbourhood_group room_type       mean_price
##    <chr>               <chr>                <dbl>
##  1 Bronx               Entire home/apt      128. 
##  2 Bronx               Private room          66.8
##  3 Bronx               Shared room           59.8
##  4 Brooklyn            Entire home/apt      178. 
##  5 Brooklyn            Private room          76.5
##  6 Brooklyn            Shared room           50.5
##  7 Manhattan           Entire home/apt      249. 
##  8 Manhattan           Private room         117. 
##  9 Manhattan           Shared room           89.0
## 10 Queens              Entire home/apt      147. 
## 11 Queens              Private room          71.8
## 12 Queens              Shared room           69.0
## 13 Staten Island       Entire home/apt      174. 
## 14 Staten Island       Private room          62.3
## 15 Staten Island       Shared room           57.4

ggplot(avg_price, aes(x = neighbourhood_group, y = mean_price, fill = room_type)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(title = "Average Listing Price by Room Type and Neighborhood Group",
       x = "Neighborhood Group",
       y = "Average Price",
       ) +
  theme_minimal()

# Scatter plot of price vs. number of reviews
ggplot(data, aes(x = number_of_reviews, y = price)) +
  geom_point(alpha = 0.5, color = "blue") +
  geom_smooth(method = "lm", color = "red") +
  labs(title = "Price vs. Number of Reviews", x = "Number of Reviews", y = "Price")

## `geom_smooth()` using formula = 'y ~ x'