Data Exploratory and Explanatory

Before we do the exploratory and explanatory data analysis, we will install all the library needed to support the data analysis.

library(lubridate)
library(scales)
library(readr)
library(dplyr)
library(ggplot2)
library(plotly)
library(tidyr)
library(glue)
library(viridis)
library(leaflet)
library(treemapify)
library(skimr)

After we install the libraries, we call the data and check all the detail of the data.

air <- read_csv("airbnb/listings.csv")

glimpse(air)

## Rows: 7,907
## Columns: 16
## $ id                             <dbl> 49091, 50646, 56334, 71609, 71896, 7190~
## $ name                           <chr> "COZICOMFORT LONG TERM STAY ROOM 2", "P~
## $ host_id                        <dbl> 266763, 227796, 266763, 367042, 367042,~
## $ host_name                      <chr> "Francesca", "Sujatha", "Francesca", "B~
## $ neighbourhood_group            <chr> "North Region", "Central Region", "Nort~
## $ neighbourhood                  <chr> "Woodlands", "Bukit Timah", "Woodlands"~
## $ latitude                       <dbl> 1.44255, 1.33235, 1.44246, 1.34541, 1.3~
## $ longitude                      <dbl> 103.7958, 103.7852, 103.7967, 103.9571,~
## $ room_type                      <chr> "Private room", "Private room", "Privat~
## $ price                          <dbl> 83, 81, 69, 206, 94, 104, 208, 50, 54, ~
## $ minimum_nights                 <dbl> 180, 90, 6, 1, 1, 1, 1, 90, 90, 90, 15,~
## $ number_of_reviews              <dbl> 1, 18, 20, 14, 22, 39, 25, 174, 198, 23~
## $ last_review                    <date> 2013-10-21, 2014-12-26, 2015-10-01, 20~
## $ reviews_per_month              <dbl> 0.01, 0.28, 0.20, 0.15, 0.22, 0.38, 0.2~
## $ calculated_host_listings_count <dbl> 2, 1, 2, 9, 9, 9, 9, 4, 4, 4, 32, 32, 9~
## $ availability_365               <dbl> 365, 365, 365, 353, 355, 346, 172, 59, ~

After we check, the dimension of the data is 7,907 rows and 16 columns. We also check the data types for every column. There are 5 columns that we have to change the data types:

• name
• host_name
• neighbourhood_group
• neighbourhood
• room_type

airsg <- air %>% 
  mutate(name = as.factor(name),
         host_name = as.factor(host_name),
         neighbourhood_group = as.factor(neighbourhood_group),
         neighbourhood = as.factor(neighbourhood),
         room_type = as.factor(room_type))

head(airsg)

Now let us check once more the data and skim the details to check if there is some cleanings necessary

skim(airsg)

Variable type: Date

Variable type: factor

Variable type: numeric

We found large missing value data on “reviews_per_month” column and “last_review” column. We probably will not use this column for analysis. So at the moment we keep the column and will do the transformation of the column in the future if necessary

Now let us look at the summary of the data to check the descriptive statistic for each columns

summary(airsg)

##        id                                                          name     
##  Min.   :   49091   Luxury hostel with in-cabin locker - Single mixed:  13  
##  1st Qu.:15821800   Inviting & Cozy 1BR APT 3 mins from Tg Pagar MRT :   9  
##  Median :24706270   Studio Apartment - Oakwood Premier               :   9  
##  Mean   :23388625   City-located 1BR loft apartment *BRAND NEW*      :   8  
##  3rd Qu.:32348500   Stylish 1BR Located 7 mins from Tg Pagar MRT     :   8  
##  Max.   :38112762   (Other)                                          :7858  
##                     NA's                                             :   2  
##     host_id             host_name           neighbourhood_group
##  Min.   :    23666   Jay     : 290   Central Region   :6309    
##  1st Qu.: 23058075   Alvin   : 249   East Region      : 508    
##  Median : 63448912   Richards: 157   North-East Region: 346    
##  Mean   : 91144807   Aaron   : 145   North Region     : 204    
##  3rd Qu.:155381142   Rain    : 115   West Region      : 540    
##  Max.   :288567551   Darcy   : 114                             
##                      (Other) :6837                             
##      neighbourhood     latitude       longitude               room_type   
##  Kallang    :1043   Min.   :1.244   Min.   :103.6   Entire home/apt:4132  
##  Geylang    : 994   1st Qu.:1.296   1st Qu.:103.8   Private room   :3381  
##  Novena     : 537   Median :1.311   Median :103.8   Shared room    : 394  
##  Rochor     : 536   Mean   :1.314   Mean   :103.8                         
##  Outram     : 477   3rd Qu.:1.322   3rd Qu.:103.9                         
##  Bukit Merah: 470   Max.   :1.455   Max.   :104.0                         
##  (Other)    :3850                                                         
##      price         minimum_nights    number_of_reviews  last_review        
##  Min.   :    0.0   Min.   :   1.00   Min.   :  0.00    Min.   :2013-10-21  
##  1st Qu.:   65.0   1st Qu.:   1.00   1st Qu.:  0.00    1st Qu.:2018-11-21  
##  Median :  124.0   Median :   3.00   Median :  2.00    Median :2019-06-27  
##  Mean   :  169.3   Mean   :  17.51   Mean   : 12.81    Mean   :2019-01-11  
##  3rd Qu.:  199.0   3rd Qu.:  10.00   3rd Qu.: 10.00    3rd Qu.:2019-08-07  
##  Max.   :10000.0   Max.   :1000.00   Max.   :323.00    Max.   :2019-08-27  
##                                                        NA's   :2758        
##  reviews_per_month calculated_host_listings_count availability_365
##  Min.   : 0.010    Min.   :  1.00                 Min.   :  0.0   
##  1st Qu.: 0.180    1st Qu.:  2.00                 1st Qu.: 54.0   
##  Median : 0.550    Median :  9.00                 Median :260.0   
##  Mean   : 1.044    Mean   : 40.61                 Mean   :208.7   
##  3rd Qu.: 1.370    3rd Qu.: 48.00                 3rd Qu.:355.0   
##  Max.   :13.000    Max.   :274.00                 Max.   :365.0   
##  NA's   :2758

If we look at above the data summary descriptive statistic, we can conclude:

• The most booked host in Singapore listing is Jay
• Central Region is the most favourite area for airbnb booking in Singapore and North Region is the least favourite.
• In terms of Neighbourhood, Kallang is the most desirable area in Singapore for Airbnb booking
• There are 3 type of listing : ‘Entire home/apt’, ‘Private room’ and ‘Shared room’ type
• Price median is around SGD 124.0
• Average staying nights is 17 days

Visualization and Analyis

plot1 <- airsg %>% 
  select(room_type,price,name) %>%
  mutate(label=glue(
    "{name}
    Price in SGD: {price}
    Room Type: {room_type}"
  )) %>% 
  ggplot(aes(x=room_type,y=price,text=label)) +
  geom_jitter(aes(col=room_type),cex=1.8,shape=8,alpha=0.3,show.legend = F) + 
  scale_y_continuous(limits=c(0,500),breaks=seq(0,500,100))+
  geom_hline(aes(yintercept=median(price, na.rm=T)),   
               color="red", linetype="dashed", size=1)+
  labs(title = "Price Distribution to Room Type",
       subtitle = "AirBnb Singapore",
       caption= "Data Source: Kaggle.com",
       x="Room Type",
       y="Price in SGD"
       )+
  theme_bw()
  
ggplotly(plot1,tooltip = "text")  %>% layout(showlegend = FALSE)

plot2 <- airsg %>% 
  select(neighbourhood_group,neighbourhood,price,name) %>%
  mutate(label=glue(
    "{name}
    Price in SGD: {price}
    Region: {neighbourhood_group}
    Area: {neighbourhood}"
  )) %>% 
  ggplot(aes(y=price,x=neighbourhood_group,text=label)) +
  geom_jitter(aes(col=neighbourhood_group)
              ,alpha=0.3,show.legend = F,cex=1.8,shape=8) + 
    scale_fill_viridis(discrete = TRUE)+
  scale_color_viridis(discrete = TRUE)+
  scale_y_continuous(limits=c(0,500),breaks=seq(0,500,100))+
  geom_hline(aes(yintercept=median(price, na.rm=T)),   
               color="red", linetype="dashed", size=1) +
  labs(title = "Price Distribution to Neighbourhood Group Region",
       subtitle = "AirBnb Singapore",
       caption= "Data Source: Kaggle.com",
       x="",
       y="Price in SGD",
       fill="",
       col="")+
  theme_bw()
  
ggplotly(plot2,tooltip = "text")  %>% layout(showlegend = FALSE)

plot3 <- airsg %>% 
  filter(neighbourhood_group=="Central Region") %>% 
  select(neighbourhood,price,name) %>% 
  mutate(label=glue(
    "{name}
    Price avg in SGD: {price}
    {neighbourhood}"
  )) %>% 
  ggplot(aes(y=reorder(neighbourhood,price),x=price,text=label)) +
  geom_point(aes(col=neighbourhood),alpha=0.4,show.legend = F) + 
  scale_x_continuous(limits=c(0,3000),breaks=seq(0,3000,500))+
  geom_vline(aes(xintercept=median(price, na.rm=T)),   
               color="dodgerblue4", linetype="dashed", size=1) +
  labs(title = "Price Distribution in Central Region",
       subtitle = "AirBnb Singapore",
       caption= "Data Source: Kaggle.com",
       x="Price in SGD",
       y="",
       col="")+
  theme_bw()
  
ggplotly(plot3,tooltip = "text")  %>% layout(showlegend = FALSE)

ploth <- airsg %>% 
  group_by(host_name) %>% 
  summarise(avg_price=mean(price)) %>% 
  arrange(desc(avg_price)) %>% 
  head(10) %>% 
  mutate(label=glue(
    "Host Name: {host_name}
     avg price: {avg_price}"
  )) %>% 
  ggplot(aes(x=avg_price,y=reorder(host_name,avg_price),text=label))+
  geom_col(aes(fill=host_name),show.legend = F)+
  scale_fill_viridis(discrete = TRUE)+
  scale_color_viridis(discrete = TRUE)+
  labs(title="Top 10 Host with The Average Highest Price per Listing",
       x="Price in SG",
       y="")+
  theme_bw()

ggplotly(ploth,tooltip = "text") %>% layout(showlegend=F)

plotpop <- airsg %>% 
  select(neighbourhood_group) %>% 
  count(neighbourhood_group) %>% 
  mutate(label=glue(
    "number of listing: {n} rooms
     {neighbourhood_group}"
  )) %>% 
  ggplot(aes(y=reorder(neighbourhood_group,n),x=n,text=label))+
  geom_col(aes(fill=neighbourhood_group)) +
  labs(title= "Population of Listings per Region",
       x="Numbers of Listings", 
       y = NULL) +
    theme_bw()

ggplotly(plotpop,tooltip = "text") %>% layout(showlegend = FALSE)

plotr <- airsg %>%
  select(room_type) %>%
  count(room_type) %>%
  mutate(label = glue(
    "number of listing: {n} rooms
     {room_type}")) %>%
  ggplot(aes(
    x = reorder(room_type, n),
    y = n,
    text = label
  )) +
  geom_col(aes(fill = room_type)) +
  labs(title = "Population of Listings per Room Type",
       x = "Numbers of Listings",
       y = NULL) +
  theme_bw()

ggplotly(plotr, tooltip = "text") %>% layout(showlegend = FALSE)

plot4 <- airsg %>%
  group_by(neighbourhood_group, room_type) %>%
  summarise(average_avail = mean(availability_365)) %>%
  mutate(
    label = glue(
    "Avg availability {round(average_avail,0)} days
    Type: {room_type}
    {neighbourhood_group}"
    )
  ) %>%
  ggplot(aes(
    y = reorder(neighbourhood_group, average_avail),
    x = average_avail,
    text = label
  )) +
  geom_col(aes(fill = room_type), position = "dodge", alpha = 0.8) +
  scale_fill_viridis(discrete = TRUE) +
  scale_color_viridis(discrete = TRUE) +
  facet_wrap( ~ room_type, scales = "free_x") +
  labs(
    title = "Average Days Availibility in a Year",
    subtitle = "AirBnb Singapore",
    caption = "Data Source: Kaggle.com",
    x = "",
    y = "",
    fill = ""
  ) +
  theme_bw()

ggplotly(plot4, tooltip = "text") %>% layout(legend = list(
  orientation = "h",
  x = 0.2,
  y = -0.1
))

plothn <- airsg %>%
  group_by(host_name) %>%
  count(host_name) %>%
  arrange(desc(n)) %>%
  head(10) %>%
  mutate(label = glue(
    "Host Name: {host_name}
     Total Listing: {n} rooms")) %>%
  ggplot(aes(
    x = n,
    y = reorder(host_name, n),
    text = label
  )) +
  geom_col(aes(fill = host_name), show.legend = F) +
  scale_fill_viridis(discrete = TRUE) +
  scale_color_viridis(discrete = TRUE) +
  labs(title = "Top 10 Host with The Most Number of Listing",
       x = "Number of Listing",
       y = "") +
  theme_bw()

ggplotly(plothn, tooltip = "text") %>% layout(showlegend = F)

Pic <- makeIcon(
  iconUrl = "images (1).png",
  iconWidth = 100 * 0.35,
  iconHeight = 100 * 0.35
)

map <- leaflet()
map <- addTiles(map)

map <- addMarkers(
  map,
  lng = airsg$longitude,
  lat = airsg$latitude,
  popup = airsg$name,
  clusterOptions = markerClusterOptions(),
  icon = Pic
)

map