library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.5.2
## Warning: package 'ggplot2' was built under R version 4.5.2
## ── 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   4.0.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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
library(readxl)
library(dplyr)
 
setwd("C:/Users/rjzavaleta/Downloads/Data 110")
 
airbnb <- read_csv("airbnb_DC_25.csv")
## Multiple files in zip: reading '[Content_Types].xml'
## Rows: 1 Columns: 1
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
## 
## 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.
df <- read_excel("airbnb_DC_25.csv")
df
## # A tibble: 6,257 × 18
##       id name       host_id host_name neighbourhood_group neighbourhood latitude
##    <dbl> <chr>        <dbl> <chr>     <lgl>               <chr>            <dbl>
##  1  3686 Vita's Hi…    4645 Vita      NA                  Historic Ana…     38.9
##  2  3943 Historic …    5059 Vasa      NA                  Edgewood, Bl…     38.9
##  3  4197 Capitol H…    5061 Sandra    NA                  Capitol Hill…     38.9
##  4  4529 Bertina's…    5803 Bertina   NA                  Eastland Gar…     38.9
##  5  5589 Cozy apt …    6527 Ami       NA                  Kalorama Hei…     38.9
##  6  7103 Lovely gu…   17633 Charlotte NA                  Spring Valle…     38.9
##  7 11785 Sanctuary…   32015 Teresa    NA                  Cathedral He…     38.9
##  8 12442 Peaches &…   32015 Teresa    NA                  Cathedral He…     38.9
##  9 13744 Heart of …   53927 Victoria  NA                  Columbia Hei…     38.9
## 10 14218 Quiet Com…   32015 Teresa    NA                  Cathedral He…     38.9
## # ℹ 6,247 more rows
## # ℹ 11 more variables: longitude <dbl>, room_type <chr>, price <dbl>,
## #   minimum_nights <dbl>, number_of_reviews <dbl>, last_review <dttm>,
## #   reviews_per_month <dbl>, calculated_host_listings_count <dbl>,
## #   availability_365 <dbl>, number_of_reviews_ltm <dbl>, license <chr>
head(df)
## # A tibble: 6 × 18
##      id name        host_id host_name neighbourhood_group neighbourhood latitude
##   <dbl> <chr>         <dbl> <chr>     <lgl>               <chr>            <dbl>
## 1  3686 Vita's Hid…    4645 Vita      NA                  Historic Ana…     38.9
## 2  3943 Historic R…    5059 Vasa      NA                  Edgewood, Bl…     38.9
## 3  4197 Capitol Hi…    5061 Sandra    NA                  Capitol Hill…     38.9
## 4  4529 Bertina's …    5803 Bertina   NA                  Eastland Gar…     38.9
## 5  5589 Cozy apt i…    6527 Ami       NA                  Kalorama Hei…     38.9
## 6  7103 Lovely gue…   17633 Charlotte NA                  Spring Valle…     38.9
## # ℹ 11 more variables: longitude <dbl>, room_type <chr>, price <dbl>,
## #   minimum_nights <dbl>, number_of_reviews <dbl>, last_review <dttm>,
## #   reviews_per_month <dbl>, calculated_host_listings_count <dbl>,
## #   availability_365 <dbl>, number_of_reviews_ltm <dbl>, license <chr>
airbnb2 <- df |>
  filter(availability_365 == "365")|>
  group_by(room_type)
airbnb2
## # A tibble: 224 × 18
## # Groups:   room_type [3]
##        id name      host_id host_name neighbourhood_group neighbourhood latitude
##     <dbl> <chr>       <dbl> <chr>     <lgl>               <chr>            <dbl>
##  1 161913 X-tra la…  767543 Dana      NA                  Dupont Circl…     38.9
##  2 178395 Spare Ro…  852801 Allison   NA                  Takoma, Brig…     39.0
##  3 223203 ROOM FOR… 1159505 Elizabeth NA                  Colonial Vil…     39.0
##  4 251611 LUXURY L… 1159505 Elizabeth NA                  Colonial Vil…     39.0
##  5 251615 NICE HOU… 1159505 Elizabeth NA                  Colonial Vil…     39.0
##  6 251619 LUXURY L… 1159505 Elizabeth NA                  Colonial Vil…     39.0
##  7 501809 Upstair …  481929 Chris     NA                  Howard Unive…     38.9
##  8 654835 Georgeto… 1671809 Mary Beth NA                  Georgetown, …     38.9
##  9 688914 Master B… 3517743 Kanita    NA                  Douglas, Shi…     38.9
## 10 792578 Lovely C… 4027780 Leonard   NA                  River Terrac…     38.9
## # ℹ 214 more rows
## # ℹ 11 more variables: longitude <dbl>, room_type <chr>, price <dbl>,
## #   minimum_nights <dbl>, number_of_reviews <dbl>, last_review <dttm>,
## #   reviews_per_month <dbl>, calculated_host_listings_count <dbl>,
## #   availability_365 <dbl>, number_of_reviews_ltm <dbl>, license <chr>
ggplot(data = airbnb2, aes(x=room_type, fill = room_type)) + 
  geom_bar(alpha = 0.5)+  # try replacing alpha = 0.5 with 0.8 to see how it changes
  labs(x = "Room Type", y = "Count", 
       title = "Counts of Rooms Available All Year Round Based on Room Type")

This barplot shows the counts of rooms that are available all year round to rent for an airbnb. The different room types are entire homes or apartments, private room, and shared room. With entire rooms/apt being the most common. I was able to use the filter command to filter all of the places that were available all 365 days of the year. In comparison to the original dataset there were only 224 airbnbs, compared to the 6257 in the original. Something that I notice is about this graph is that the amount of shared rooms are little to none, showing that more people would rather have an airbnb by themselves.