Challenge 5

Introduction to Visualization

Author

Shuqi Hong

Published

June 15, 2023

library(tidyverse)
library(ggplot2)

knitr::opts_chunk$set(echo = TRUE, warning=FALSE, message=FALSE)

Read in data

AB_NYC_2019.csv

AB <- read_csv("_data/AB_NYC_2019.csv")
AB_clean <- AB %>% select(-c(1,3)) %>% mutate_at(c(1,2,3,4,7), as.factor)
AB_clean <- AB_clean %>% mutate_at(c(8,9,10,13,14), as.integer) %>% rename("dwelling_name" = name )
AB

ABCDEFGHIJ0123456789

id <dbl>	name <chr>	host_id <dbl>	host_name <chr>	neighbourhood_group <chr>	neighbourhood <chr>
2539	Clean & quiet apt home by the park	2787	John	Brooklyn	Kensington
2595	Skylit Midtown Castle	2845	Jennifer	Manhattan	Midtown
3647	THE VILLAGE OF HARLEM....NEW YORK !	4632	Elisabeth	Manhattan	Harlem
3831	Cozy Entire Floor of Brownstone	4869	LisaRoxanne	Brooklyn	Clinton Hill
5022	Entire Apt: Spacious Studio/Loft by central park	7192	Laura	Manhattan	East Harlem
5099	Large Cozy 1 BR Apartment In Midtown East	7322	Chris	Manhattan	Murray Hill
5121	BlissArtsSpace!	7356	Garon	Brooklyn	Bedford-Stuyvesant
5178	Large Furnished Room Near B'way	8967	Shunichi	Manhattan	Hell's Kitchen
5203	Cozy Clean Guest Room - Family Apt	7490	MaryEllen	Manhattan	Upper West Side
5238	Cute & Cozy Lower East Side 1 bdrm	7549	Ben	Manhattan	Chinatown

AB_clean

ABCDEFGHIJ0123456789

dwelling_name <fct>	host_name <fct>	neighbourhood_group <fct>	neighbourhood <fct>	latitude <dbl>
Clean & quiet apt home by the park	John	Brooklyn	Kensington	40.64749
Skylit Midtown Castle	Jennifer	Manhattan	Midtown	40.75362
THE VILLAGE OF HARLEM....NEW YORK !	Elisabeth	Manhattan	Harlem	40.80902
Cozy Entire Floor of Brownstone	LisaRoxanne	Brooklyn	Clinton Hill	40.68514
Entire Apt: Spacious Studio/Loft by central park	Laura	Manhattan	East Harlem	40.79851
Large Cozy 1 BR Apartment In Midtown East	Chris	Manhattan	Murray Hill	40.74767
BlissArtsSpace!	Garon	Brooklyn	Bedford-Stuyvesant	40.68688
Large Furnished Room Near B'way	Shunichi	Manhattan	Hell's Kitchen	40.76489
Cozy Clean Guest Room - Family Apt	MaryEllen	Manhattan	Upper West Side	40.80178
Cute & Cozy Lower East Side 1 bdrm	Ben	Manhattan	Chinatown	40.71344

Tidy Data and briefly describe the data

For this dataset, I first remove the first and third column which are not useful for my analysis. From tibble above, we can simply see the variable are not very suitable. I assume that this dataset won’t be changed anymore, so as you can see, I mutate some variable types. Also, I rename “name” column as “dwelling_name” which is more specific.

Univariate Visualizations

AB_clean %>% ggplot(aes(x = `neighbourhood_group`)) + 
  geom_bar() + geom_text(stat='count', aes(label=..count..), vjust=-0.5) +
   labs(x = "Neighbourhood group", 
       y = "Number of dwelling", 
       title = "The number of dewlling in each neighbourhood group") +
  theme_minimal()

From this graph, we can see how many dwellings were in each neighborhood group. We can clearly get the number of dwellings in Manhattan and Brooklyn were much more than others.

AB_clean %>% ggplot(aes(x = `availability_365`)) + 
  geom_histogram() + 
  labs(x = "Available days in 2019", 
       title = "The count available days in 2019") +
  theme_minimal()

From this graph, we can see most of the dwellings were rented out all year round. Dwellings that didn’t rented out for 200 days were the fewest. There are about 2500 dwellings that were barely rented out all year.

AB_clean %>% ggplot(aes(x = `availability_365`)) + 
  geom_density(alpha = 0.2, fill = "red") + 
  labs(x = "Available days in 2019", 
       title = "The count available days in 2019") +
  theme_minimal()

From this graph, we can see more directly that most houses were rented out all year round. There are also small peaks between 40 and 365 days and the last peak which is about 360 days is a little bit higher than other peaks.

Bivariate Visualization(s)

ggplot(AB_clean, aes( availability_365, price)) +
  geom_point() +
  labs(x = "Available days in 2019", 
       y = "The price of dwelling", 
       title = "The relationship between available days and price") +
  theme_minimal()

From this graph, we can see no matter how many days are available in a year, most of the prices were concentrated below 1250 dollars and only several prices of dwellings were higher than 2500 dollars. So we can take a closer look at the relationship between price and available days in the low price region.

ggplot(AB_clean, aes( availability_365, price)) +
  geom_smooth()  +
  labs(x = "Available days in 2019", 
       y = "The price of dwelling", 
       title = "The relationship between available days and price") +
  theme_minimal()

From this graph, we can see the price fluctuation is mainly concentrated below 240 dollars. From 0 to about 265 available days, the overall price was gradually rising. Then from 265 to 325 available days, there was a considerable reduction in price. From 325 to 365 available days, the price increased sharply.