#install.packages("readxl")
library(readxl)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, uniondf <- read_excel("Airbnb_DC_25.csv")#look at the data
summary(df) id name host_id host_name
Min. :3.686e+03 Length :6257 Min. : 4617 Length :6257
1st Qu.:3.792e+07 N.unique :5996 1st Qu.: 22024017 N.unique :1860
Median :7.501e+17 N.blank : 0 Median : 81005284 N.blank : 0
Mean :6.159e+17 Min.nchar: 4 Mean :176451046 Min.nchar: 1
3rd Qu.:1.143e+18 Max.nchar: 107 3rd Qu.:304261532 Max.nchar: 34
Max. :1.375e+18 Max. :681391481 NAs : 2
neighbourhood_group neighbourhood latitude longitude
Mode:logical Length :6257 Min. :38.82 Min. :-77.11
NAs :6257 N.unique : 39 1st Qu.:38.90 1st Qu.:-77.03
N.blank : 0 Median :38.91 Median :-77.01
Min.nchar: 18 Mean :38.91 Mean :-77.01
Max.nchar: 97 3rd Qu.:38.92 3rd Qu.:-76.99
Max. :38.99 Max. :-76.91
room_type price minimum_nights number_of_reviews
Length :6257 Min. : 10.0 Min. : 1.00 Min. : 0.00
N.unique : 4 1st Qu.: 88.0 1st Qu.: 1.00 1st Qu.: 1.00
N.blank : 0 Median : 131.0 Median : 2.00 Median : 19.00
Min.nchar: 10 Mean : 168.7 Mean : 13.23 Mean : 66.38
Max.nchar: 15 3rd Qu.: 193.0 3rd Qu.: 31.00 3rd Qu.: 86.00
Max. :7000.0 Max. :701.00 Max. :1205.00
NAs :1488
last_review reviews_per_month calculated_host_listings_count
Min. :2013-06-15 00:00:00 Min. : 0.010 Min. : 1.00
1st Qu.:2024-10-17 00:00:00 1st Qu.: 0.470 1st Qu.: 1.00
Median :2025-01-23 00:00:00 Median : 1.460 Median : 3.00
Mean :2024-09-12 12:48:19 Mean : 1.974 Mean : 33.15
3rd Qu.:2025-02-27 00:00:00 3rd Qu.: 2.940 3rd Qu.: 14.00
Max. :2025-03-14 00:00:00 Max. :28.200 Max. :289.00
NAs :1236 NAs :1236
availability_365 number_of_reviews_ltm license
Min. : 0.0 Min. : 0.0 Length :6257
1st Qu.: 43.0 1st Qu.: 0.0 N.unique :2459
Median :175.0 Median : 5.0 N.blank : 0
Mean :175.8 Mean : 15.8 Min.nchar: 6
3rd Qu.:303.0 3rd Qu.: 25.0 Max.nchar: 72
Max. :365.0 Max. :290.0 NAs :1560
#view(df)by_neighborhood <- df |>
group_by(neighbourhood)|> #grouping all neighborhoods
summarise(count=n(),#totals for each neighborhood
avg_cost = mean(price, na.rm =TRUE),
avg_min_night = mean(minimum_nights, na.rm=TRUE),
.groups = "drop"
) |>
arrange(neighbourhood)by_neighborhood_matrix <- data.matrix(by_neighborhood[, -1])
row.names(by_neighborhood_matrix) <- by_neighborhood$neighbourhood
#str(by_neighborhood)#heatmap by neighborhood
library(viridis)Loading required package: viridisLiteby_neighborhood_heatmap <- heatmap(by_neighborhood_matrix,
Rowv=NA,
Colv=NA,
col =viridis(25),
cexCol=.5,
cexRow =.4,
scale="column",
xlab="",
ylab="Neighborhoods",
margins=c(10,15),
main ="Heatmap of Airbnb Neighborhoods in Washington, DC")