Challenge 6

challenge_6

hotel_bookings

air_bnb

fed_rate

debt

usa_households

abc_poll

Visualizing Time and Relationships

Author

Janani Natarajan

Published

May 12, 2023

library(tidyverse)
library(ggplot2)
library(lubridate)
knitr::opts_chunk$set(echo = TRUE, warning=FALSE, message=FALSE)

Read in data

Read in one (or more) of the following datasets, using the correct R package and command.

debt ⭐
fed_rate ⭐⭐
abc_poll ⭐⭐⭐
usa_hh ⭐⭐⭐
hotel_bookings ⭐⭐⭐⭐
AB_NYC ⭐⭐⭐⭐⭐

data <- read.csv("_data/AB_NYC_2019.csv")
glimpse(mydata)

Error in glimpse(mydata): object 'mydata' not found

View(data)

Error in check_for_XQuartz(file.path(R.home("modules"), "R_de.so")): X11 library is missing: install XQuartz from www.xquartz.org

colnames(data)

 [1] "id"                             "name"                          
 [3] "host_id"                        "host_name"                     
 [5] "neighbourhood_group"            "neighbourhood"                 
 [7] "latitude"                       "longitude"                     
 [9] "room_type"                      "price"                         
[11] "minimum_nights"                 "number_of_reviews"             
[13] "last_review"                    "reviews_per_month"             
[15] "calculated_host_listings_count" "availability_365"

Briefly describe the data

The dataset contains information about 48,895 AirBnB listings in New York City in the year 2019. Each listing is represented by 17 columns, providing details such as the neighborhood and neighborhood group, rental type (entire home, private room, shared room), prices, minimum stay requirements, and the number of guest reviews. The dataset also includes the number of listings each host has on AirBnB, the number of days a listing was available throughout 2019, and the date of the last guest review.

Tidy Data (as needed)

I want to show how the date of review and other variables relate to one another.There are blank values in the last_review variable. I thus save the observations that were reviewed initially. I then extract the date variable’s month and year columns.

mydata2 <- mydata %>% 
  mutate(Date = ymd(last_review))%>% 
  drop_na(Date)%>% 
  mutate(day = day(Date), month = month(Date, label=TRUE), year = year(Date))

Error in mutate(., Date = ymd(last_review)): object 'mydata' not found

#select the required variables.
select_df<-mydata2 %>%
  select(id, neighbourhood_group:year)

Error in select(., id, neighbourhood_group:year): object 'mydata2' not found

obtaining the average number of reviews

#Mean 
summary_numberofreviews <-select_df  %>% 
summarise (Mean_availability=mean(number_of_reviews, na.rm = TRUE))

Error in summarise(., Mean_availability = mean(number_of_reviews, na.rm = TRUE)): object 'select_df' not found

#Grouping by month
summary_month2 <-select_df  %>% 
filter (availability_365>0)  %>% 
  filter(price > quantile(price)[2] - 1.5 * IQR(price) & price < quantile(price)[4] + 1.5 * IQR(price))  %>% 
 group_by(year)  %>%
  summarise(
    Mean=mean(price, na.rm = TRUE),
    Quantile1 = quantile(price, c(0.25), q1 = c(0.25), na.rm = TRUE),
    Median=median(price, na.rm = TRUE),
    Quantile3 = quantile(price, c(0.75), q3 = c(0.75), na.rm = TRUE),
    SD=sd(price, na.rm = TRUE),
    min=min(price, na.rm = TRUE),
    max=max(price, na.rm = TRUE),
    )

Error in filter(., availability_365 > 0): object 'select_df' not found

summary_month3 <- select_df  %>% 
  filter(availability_365 > 0)  %>% 
  filter(price > quantile(price)[2] - 1.5 * IQR(price) & price < quantile(price)[4] + 1.5 * IQR(price))  %>% 
  group_by(year, room_type) %>%
  summarise(
    Mean=mean(price, na.rm = TRUE),
    Quantile1=quantile(price, c(0.25), q1 = c(0.25), na.rm = TRUE),
    Median=median(price, na.rm = TRUE),
    Quantile3=quantile(price, c(0.75), q3 = c(0.75), na.rm = TRUE),
    SD=sd(price, na.rm = TRUE),
    min=min(price, na.rm = TRUE),
    max=max(price, na.rm = TRUE),
    .groups = 'drop'
  )

Error in filter(., availability_365 > 0): object 'select_df' not found

Time Dependent Visualization

ggplot(summary_month2, aes(x = as.integer(year), y = Mean, group=1)) +
  geom_line(color = "red") +
  geom_point(size = 3, color = "blue") +
  labs(title = "Price",
       x = "Last Review", y = "Mean") +
  scale_x_continuous(breaks = seq(min(as.integer(summary_month2$year)), max(as.integer(summary_month2$year)), by = 1),
                     labels = seq(min(as.integer(summary_month2$year)), max(as.integer(summary_month2$year)), by = 1)) +
  theme_minimal()

Error in ggplot(summary_month2, aes(x = as.integer(year), y = Mean, group = 1)): object 'summary_month2' not found

Visualizing Part-Whole Relationships

People who had their entire apartment for rent and had last reviews in 2012-2014 probably sold their homes. These may have been some of those early starters who were buying up real estate and saw this as a great source of income before they were able to sell and move on to other ventures.

ggplot(mydata, aes(x=`last_review`, y=`room_type`)) + geom_point() +
    labs(title = "Last Review by Room Type", x = "Last Review", y = "Room Type")

Error in ggplot(mydata, aes(x = last_review, y = room_type)): object 'mydata' not found

ggplot(summary_month3, aes(x = factor(year), y = Mean, fill = room_type)) +
  geom_bar(stat = "identity", position = position_dodge(width = 0.9)) +
  labs(x = "Year", y = "Mean", fill = "Room Type") +
  ggtitle("Year and Room Type") +
  theme(plot.title = element_text(hjust = 1.0)) +
  scale_fill_brewer(palette = "Set2")

Error in ggplot(summary_month3, aes(x = factor(year), y = Mean, fill = room_type)): object 'summary_month3' not found

select_df_type <- select_df %>% filter(year>=2019)%>% group_by(month, room_type) %>% summarise(count=n(), mean_availability=mean(availability_365)) %>%  ungroup()

Error in filter(., year >= 2019): object 'select_df' not found

ggplot(select_df_type, aes(x = month, y = mean_availability, color = room_type, group = room_type)) +
  geom_line() +
  geom_point() +
  labs(title = "Average Availability(Room Type)",
       x = "Month",
       y = "Average Availability (in days)",
       color = "Room Type") +
  scale_color_manual(values = c("pink", "green", "violet")) +
  theme_minimal()

Error in ggplot(select_df_type, aes(x = month, y = mean_availability, : object 'select_df_type' not found

data_type2 <- select_df %>% filter(year>=2019)%>% group_by(month, neighbourhood_group ) %>% summarise(count=n(), mean_availability=mean(availability_365)) %>%  ungroup()

Error in filter(., year >= 2019): object 'select_df' not found

ggplot(select_df_type2, aes(x = month, y = count, fill = neighbourhood_group)) +
  geom_bar(stat = "identity", position = "stack") +
  labs(title = "Monthly count",
       x = "Month",
       y = "Count",
       fill = "Room Type") +
  scale_fill_manual(values = c("red", "purple", "yellow", "orange", "#FF69B4")) +
  theme_minimal()

Error in ggplot(select_df_type2, aes(x = month, y = count, fill = neighbourhood_group)): object 'select_df_type2' not found