Take_home_ex02.RMD
Vanessa Su
5/16/2020
Overview
In this take-home exercise, I will be analysing the distribution of Airbnb Airbnb listing by using appropriate spatial point patterns analysis techniques. The analysis will be conducted on a nation-wide level and subzone level.
Data
The listing data set of Inside Airbnb will be used. This data set is downloaded from Inside Airbnb (http://insideairbnb.com/get-the-data.html)
Singapore coastal outline boundary from Singapore Land Authorithy (SLA) (i.e. CostalOutline). It is in ESRI shapefile format.
URA Planning Subzone boundary data (i.e. MP14_SUBZONE_WEB_PL). It is in ESRI shapefile format.
Loading in required packages
packages <- c('rgdal', 'maptools', 'raster','spatstat', 'tmap', 'sf','tidyverse','tmaptools','cartography')
for (p in packages){
if(!require(p, character.only = T)){
install.packages(p)
}
library(p,character.only = T)
}## Loading required package: rgdal## Loading required package: sp## rgdal: version: 1.4-8, (SVN revision 845)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 2.2.3, released 2017/11/20
## Path to GDAL shared files: C:/Users/vanes/Documents/R/win-library/3.6/rgdal/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
## Path to PROJ.4 shared files: C:/Users/vanes/Documents/R/win-library/3.6/rgdal/proj
## Linking to sp version: 1.4-1## Loading required package: maptools## Checking rgeos availability: TRUE## Loading required package: raster## Loading required package: spatstat## Loading required package: spatstat.data## Loading required package: nlme##
## Attaching package: 'nlme'## The following object is masked from 'package:raster':
##
## getData## Loading required package: rpart##
## spatstat 1.64-1 (nickname: 'Help you I can, yes!')
## For an introduction to spatstat, type 'beginner'##
## Attaching package: 'spatstat'## The following objects are masked from 'package:raster':
##
## area, rotate, shift## Loading required package: tmap## Loading required package: sf## Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1## Loading required package: tidyverse## Registered S3 method overwritten by 'cli':
## method from
## print.boxx spatstat## -- Attaching packages ------- tidyverse 1.3.0 --## v ggplot2 3.3.0 v purrr 0.3.4
## v tibble 3.0.1 v dplyr 0.8.5
## v tidyr 1.0.3 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0## -- Conflicts ---------- tidyverse_conflicts() --
## x dplyr::collapse() masks nlme::collapse()
## x tidyr::extract() masks raster::extract()
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x dplyr::select() masks raster::select()## Loading required package: tmaptools## Loading required package: cartographyImporting Coastal data and performing projection and validity checks
sg <- readOGR(dsn = "data/geospatial", layer="CostalOutline")## OGR data source with driver: ESRI Shapefile
## Source: "C:\IS415\take home exercise\take home exercise 2\data\geospatial", layer: "CostalOutline"
## with 60 features
## It has 4 fieldssg_sp <- as(sg, "SpatialPolygons")
class(sg_sp)## [1] "SpatialPolygons"
## attr(,"package")
## [1] "sp"crs(sg)## CRS arguments:
## +proj=tmerc +lat_0=1.366666666666667 +lon_0=103.8333333333333 +k=1
## +x_0=28001.642 +y_0=38744.572 +datum=WGS84 +units=m +no_defs
## +ellps=WGS84 +towgs84=0,0,0Importing subzone data, performing projection and validity checks
subzone <- readOGR(dsn = "data/geospatial", layer="MP14_SUBZONE_WEB_PL")## OGR data source with driver: ESRI Shapefile
## Source: "C:\IS415\take home exercise\take home exercise 2\data\geospatial", layer: "MP14_SUBZONE_WEB_PL"
## with 323 features
## It has 15 fieldssubzone <- st_as_sf(subzone)any(is.na(subzone))## [1] FALSEtest <- st_is_valid(subzone)
length(which(test==FALSE))## [1] 9subzone <- st_transform(subzone, crs= 3414)
subzone <- st_make_valid(subzone)crs(subzone)## [1] "+proj=tmerc +lat_0=1.36666666666667 +lon_0=103.833333333333 +k=1 +x_0=28001.642 +y_0=38744.572 +ellps=WGS84 +towgs84=0,0,0,0,0,0,0 +units=m +no_defs"Selecting polygons to be removed
subzone <-subzone[!subzone$SUBZONE_N=="CENTRAL WATER CATCHMENT",]
subzone <-subzone[!subzone$SUBZONE_N=="WESTERN WATER CATCHMENT",]
subzone <-subzone[!subzone$SUBZONE_N=="TUAS VIEW EXTENSION",] # Not built yetsubzone <- as(subzone, "Spatial")
class(subzone)## [1] "SpatialPolygonsDataFrame"
## attr(,"package")
## [1] "sp"Importing listings data and performing validity checks
listings <- read_csv("data/aspatial/listings.csv")## Parsed with column specification:
## cols(
## id = col_double(),
## name = col_character(),
## host_id = col_double(),
## host_name = col_character(),
## neighbourhood_group = col_character(),
## neighbourhood = col_character(),
## latitude = col_double(),
## longitude = col_double(),
## room_type = col_character(),
## price = col_double(),
## minimum_nights = col_double(),
## number_of_reviews = col_double(),
## last_review = col_date(format = ""),
## reviews_per_month = col_double(),
## calculated_host_listings_count = col_double(),
## availability_365 = col_double()
## )listings[rowSums(is.na(listings))!=0,]## # A tibble: 2,826 x 16
## id name host_id host_name neighbourhood_g~ neighbourhood latitude
## <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 1.18e5 Priv~ 448620 Lynnity North-East Regi~ Sengkang 1.39
## 2 3.56e5 Doub~ 1759905 Aresha Central Region Geylang 1.31
## 3 4.82e5 Mast~ 2386154 Susan East Region Tampines 1.35
## 4 6.43e5 BEST~ 3212572 Roger Central Region Rochor 1.30
## 5 7.20e5 HDB ~ 3648224 Audrey Central Region Queenstown 1.31
## 6 7.34e5 Home~ 3824517 Shirlnet North-East Regi~ Serangoon 1.37
## 7 7.56e5 Bedr~ 3981177 Sharon East Region Pasir Ris 1.38
## 8 7.68e5 Comm~ 4053150 Immellym~ North-East Regi~ Punggol 1.40
## 9 8.24e5 Apar~ 4177147 Tania East Region Bedok 1.31
## 10 1.56e6 Delu~ 8270362 Domus Central Region Novena 1.32
## # ... with 2,816 more rows, and 9 more variables: longitude <dbl>,
## # room_type <chr>, price <dbl>, minimum_nights <dbl>,
## # number_of_reviews <dbl>, last_review <date>, reviews_per_month <dbl>,
## # calculated_host_listings_count <dbl>, availability_365 <dbl>listings$reviews_per_month[is.na(listings$reviews_per_month)] <- 0
listings$host_name[is.na(listings$host_name)] <- "Unknown"
listings$name[is.na(listings$name)] <- "Unknown"listings_sf <- st_as_sf(listings,
coords = c("longitude", "latitude"), crs=4326) test <- st_is_valid(listings_sf)
length(which(test==FALSE))## [1] 0listings_sf[rowSums(is.na(listings_sf))!=0,]## Simple feature collection with 2812 features and 14 fields
## geometry type: POINT
## dimension: XY
## bbox: xmin: 103.6782 ymin: 1.24387 xmax: 103.9717 ymax: 1.45459
## geographic CRS: WGS 84
## # A tibble: 2,812 x 15
## id name host_id host_name neighbourhood_g~ neighbourhood room_type price
## <dbl> <chr> <dbl> <chr> <chr> <chr> <chr> <dbl>
## 1 1.18e5 Priv~ 448620 Lynnity North-East Regi~ Sengkang Private ~ 67
## 2 3.56e5 Doub~ 1759905 Aresha Central Region Geylang Private ~ 80
## 3 4.82e5 Mast~ 2386154 Susan East Region Tampines Private ~ 38
## 4 6.43e5 BEST~ 3212572 Roger Central Region Rochor Private ~ 174
## 5 7.20e5 HDB ~ 3648224 Audrey Central Region Queenstown Shared r~ 217
## 6 7.34e5 Home~ 3824517 Shirlnet North-East Regi~ Serangoon Private ~ 26
## 7 7.56e5 Bedr~ 3981177 Sharon East Region Pasir Ris Private ~ 206
## 8 7.68e5 Comm~ 4053150 Immellym~ North-East Regi~ Punggol Private ~ 174
## 9 8.24e5 Apar~ 4177147 Tania East Region Bedok Private ~ 290
## 10 1.56e6 Delu~ 8270362 Domus Central Region Novena Private ~ 30
## # ... with 2,802 more rows, and 7 more variables: minimum_nights <dbl>,
## # number_of_reviews <dbl>, last_review <date>, reviews_per_month <dbl>,
## # calculated_host_listings_count <dbl>, availability_365 <dbl>,
## # geometry <POINT [°]>listings_sf <- listings_sf %>% select(room_type)
listings_sp <- as_Spatial(listings_sf)
listings_sp$room_type <- as.factor(listings_sp$room_type)
listings_sp <-spTransform(listings_sp, CRS("+init=epsg:3414"))class(listings_sp)## [1] "SpatialPointsDataFrame"
## attr(,"package")
## [1] "sp"Load Openstreetmap
sg_map<-getTiles(x = listings_sf, type = "osm")Overview of listings data
room_type <- table(listings_sf$room_type)
barplot(room_type, main="Listings by Room Type",
xlab="Room Type",
ylab="Count")
Mapping the geospatial layers
tmap_mode("plot")## tmap mode set to plottingtm_basemap("OpenStreetMap")+
tm_shape(listings_sf)+
tm_dots(col = "room_type", alpha = 0.7, id = "neighbourhood")
tmap_mode("plot")## tmap mode set to plottingWe can see that entire homes an private rooms take up the majority of listing types. This may be due to the affordability compared to hotel rooms and a more private experience compared to shared rooms. We will look at this further in the later parts of this study.
Section A:Nation-wide analysis
Mapping the geospatial layers
tmap_mode("plot")## tmap mode set to plottingtm_shape(sg_map)+
tm_layout(legend.outside = TRUE)+
tm_rgb()+
tm_shape(subzone)+
tm_borders(alpha=0.5, col = "black", lwd = 1)+
tm_shape(listings_sp)+
tm_dots(col = "room_type",
alpha=0.7,
size = 0.1,
border.col = "black",
border.lwd = 5,
palette=c("red","blue","yellow","green"))+
tm_facets(by="room_type")## Warning: Raster values found that are outside the range [0, 255]## Warning in CPL_crs_from_input(x): GDAL Message 1: +init=epsg:XXXX syntax is
## deprecated. It might return a CRS with a non-EPSG compliant axis order.
Hotel Rooms
For hotel rooms , we can see that they are located mainly in the central areas such as Balestier and Raffles Place with a few in the Northeast, SouthEast and SouthWest.
Entire Homes/Apartment
For entire homes, we can see that they are all around Singapore and are significant in numbers.They are mainly located in the central areas such as Tanjong Pagar and Geylang.
Private rooms
There is a significant number of private rooms located all around Singapore. They are more commonly located in central areas such as Little India and Kallang,
tmap_mode('plot')## tmap mode set to plottingConverting the generic sp format into spatstat’s ppp format
listings_ppp <- as(listings_sp, "ppp")
listings_ppp## Marked planar point pattern: 7713 points
## Multitype, with levels =
## Entire home/apt Hotel room Private room Shared room
## window: rectangle = [7215.57, 43401.32] x [25166.35, 48466.72] unitsHandling duplicate points
any(duplicated(listings_ppp))## [1] TRUEsum(multiplicity(listings_ppp) > 1)## [1] 230listings_ppp_jit <- rjitter(listings_ppp, retry=TRUE, nsim=1, drop=TRUE)
plot(listings_ppp_jit)
any(duplicated(listings_ppp_jit))## [1] FALSECreating owin
We should confine the analysis with a geographical area like Singapore boundary. In spatstat, an object called owin is specially designed to represent this polygonal region.
sg_owin <- as(subzone, "owin")
plot(sg_owin)
summary(sg_owin)## Window: polygonal boundary
## 390 separate polygons (31 holes)
## vertices area relative.area
## polygon 1 156 1.63038e+06 2.52e-03
## polygon 2 305 5.59816e+05 8.65e-04
## polygon 3 47 1.60807e+05 2.48e-04
## polygon 4 47 5.95429e+05 9.20e-04
## polygon 5 48 3.87429e+05 5.98e-04
## polygon 6 59 1.03038e+06 1.59e-03
## polygon 7 83 5.51732e+05 8.52e-04
## polygon 8 70 2.90185e+05 4.48e-04
## polygon 9 217 1.08479e+06 1.68e-03
## polygon 10 42 6.31644e+05 9.76e-04
## polygon 11 226 1.82685e+06 2.82e-03
## polygon 12 53 2.93706e+05 4.54e-04
## polygon 13 256 1.84406e+06 2.85e-03
## polygon 14 165 3.92563e+05 6.06e-04
## polygon 15 240 5.06589e+05 7.83e-04
## polygon 16 1151 3.30122e+07 5.10e-02
## polygon 17 (hole) 26 -1.25665e+03 -1.94e-06
## polygon 18 478 2.06120e+06 3.18e-03
## polygon 19 266 1.50631e+06 2.33e-03
## polygon 20 65 8.42861e+04 1.30e-04
## polygon 21 47 3.82087e+04 5.90e-05
## polygon 22 22 6.74651e+03 1.04e-05
## polygon 23 234 2.08755e+06 3.22e-03
## polygon 24 227 1.10308e+06 1.70e-03
## polygon 25 145 9.61782e+05 1.49e-03
## polygon 26 19 3.09221e+04 4.78e-05
## polygon 27 37 1.29481e+04 2.00e-05
## polygon 28 10 6.60195e+03 1.02e-05
## polygon 29 30 4.28933e+03 6.63e-06
## polygon 30 4 9.47108e+01 1.46e-07
## polygon 31 1045 4.44510e+06 6.87e-03
## polygon 32 (hole) 13 -3.91907e+02 -6.05e-07
## polygon 33 234 4.72886e+05 7.31e-04
## polygon 34 15 4.03300e+04 6.23e-05
## polygon 35 14 5.86546e+03 9.06e-06
## polygon 36 64 3.43149e+04 5.30e-05
## polygon 37 (hole) 3 -5.12482e-03 -7.92e-12
## polygon 38 (hole) 3 -1.96410e-03 -3.03e-12
## polygon 39 (hole) 3 -1.98390e-03 -3.06e-12
## polygon 40 (hole) 3 -5.55856e-03 -8.59e-12
## polygon 41 (hole) 4 -1.13774e-02 -1.76e-11
## polygon 42 6 4.50259e+02 6.96e-07
## polygon 43 155 2.67502e+05 4.13e-04
## polygon 44 211 4.70521e+05 7.27e-04
## polygon 45 10 4.90942e+02 7.58e-07
## polygon 46 4 2.69313e+02 4.16e-07
## polygon 47 95 5.96187e+04 9.21e-05
## polygon 48 (hole) 4 -1.86410e-02 -2.88e-11
## polygon 49 1027 1.27782e+06 1.97e-03
## polygon 50 (hole) 3 -3.23310e-04 -4.99e-13
## polygon 51 (hole) 3 -1.16959e-03 -1.81e-12
## polygon 52 (hole) 3 -1.46474e-03 -2.26e-12
## polygon 53 132 9.53357e+04 1.47e-04
## polygon 54 75 1.73526e+04 2.68e-05
## polygon 55 106 3.04104e+03 4.70e-06
## polygon 56 83 5.28920e+03 8.17e-06
## polygon 57 1468 4.87083e+06 7.52e-03
## polygon 58 (hole) 7 -1.40545e-01 -2.17e-10
## polygon 59 (hole) 12 -8.36709e+01 -1.29e-07
## polygon 60 148 3.10395e+03 4.79e-06
## polygon 61 142 3.22293e+03 4.98e-06
## polygon 62 45 2.51218e+03 3.88e-06
## polygon 63 40 1.38607e+04 2.14e-05
## polygon 64 430 3.44964e+06 5.33e-03
## polygon 65 85 1.03238e+05 1.59e-04
## polygon 66 104 1.12730e+06 1.74e-03
## polygon 67 3 6.12658e-02 9.46e-11
## polygon 68 775 2.70301e+06 4.18e-03
## polygon 69 (hole) 20 -4.39069e+00 -6.78e-09
## polygon 70 (hole) 28 -1.99862e+01 -3.09e-08
## polygon 71 (hole) 48 -1.38338e+02 -2.14e-07
## polygon 72 (hole) 351 -1.21433e+03 -1.88e-06
## polygon 73 53 2.76827e+05 4.28e-04
## polygon 74 115 6.36650e+04 9.83e-05
## polygon 75 84 1.96620e+05 3.04e-04
## polygon 76 33 3.65333e+05 5.64e-04
## polygon 77 106 1.45483e+06 2.25e-03
## polygon 78 133 8.53207e+05 1.32e-03
## polygon 79 196 1.07072e+06 1.65e-03
## polygon 80 47 5.33017e+05 8.23e-04
## polygon 81 82 4.42503e+05 6.84e-04
## polygon 82 222 9.31404e+04 1.44e-04
## polygon 83 37 4.11723e+05 6.36e-04
## polygon 84 230 5.87223e+05 9.07e-04
## polygon 85 35 3.94379e+04 6.09e-05
## polygon 86 96 1.88767e+05 2.92e-04
## polygon 87 59 1.33007e+05 2.05e-04
## polygon 88 47 4.48128e+05 6.92e-04
## polygon 89 31 5.21201e+05 8.05e-04
## polygon 90 17 3.50788e+05 5.42e-04
## polygon 91 54 2.61844e+05 4.04e-04
## polygon 92 240 1.59034e+06 2.46e-03
## polygon 93 298 8.86955e+05 1.37e-03
## polygon 94 190 2.23207e+05 3.45e-04
## polygon 95 143 2.00053e+05 3.09e-04
## polygon 96 169 7.10569e+05 1.10e-03
## polygon 97 34 7.48684e+05 1.16e-03
## polygon 98 192 5.91779e+05 9.14e-04
## polygon 99 178 1.75595e+06 2.71e-03
## polygon 100 193 3.40743e+05 5.26e-04
## polygon 101 219 3.29438e+05 5.09e-04
## polygon 102 88 1.70664e+05 2.64e-04
## polygon 103 173 3.68483e+05 5.69e-04
## polygon 104 294 7.60189e+06 1.17e-02
## polygon 105 243 2.21973e+05 3.43e-04
## polygon 106 130 2.80175e+05 4.33e-04
## polygon 107 141 2.14250e+05 3.31e-04
## polygon 108 83 1.73122e+05 2.67e-04
## polygon 109 92 5.33671e+05 8.24e-04
## polygon 110 95 1.45519e+05 2.25e-04
## polygon 111 55 6.35704e+05 9.82e-04
## polygon 112 54 5.03221e+05 7.77e-04
## polygon 113 48 5.56813e+04 8.60e-05
## polygon 114 60 1.16330e+05 1.80e-04
## polygon 115 137 2.05165e+06 3.17e-03
## polygon 116 122 2.43459e+06 3.76e-03
## polygon 117 114 1.71362e+06 2.65e-03
## polygon 118 55 3.10514e+05 4.80e-04
## polygon 119 95 1.38664e+06 2.14e-03
## polygon 120 127 1.95187e+06 3.02e-03
## polygon 121 266 4.52472e+05 6.99e-04
## polygon 122 79 6.97502e+05 1.08e-03
## polygon 123 119 1.71721e+05 2.65e-04
## polygon 124 277 1.09783e+06 1.70e-03
## polygon 125 136 1.05349e+06 1.63e-03
## polygon 126 304 2.79601e+06 4.32e-03
## polygon 127 (hole) 3 -2.18000e-06 -3.37e-15
## polygon 128 556 3.04972e+06 4.71e-03
## polygon 129 (hole) 3 -6.62377e-01 -1.02e-09
## polygon 130 (hole) 3 -2.09065e-03 -3.23e-12
## polygon 131 139 3.36221e+05 5.19e-04
## polygon 132 62 7.41438e+05 1.15e-03
## polygon 133 322 4.60550e+05 7.11e-04
## polygon 134 199 5.43484e+05 8.40e-04
## polygon 135 52 2.78304e+05 4.30e-04
## polygon 136 544 1.76950e+06 2.73e-03
## polygon 137 150 3.85093e+05 5.95e-04
## polygon 138 120 5.58761e+05 8.63e-04
## polygon 139 88 5.67581e+06 8.77e-03
## polygon 140 212 2.09609e+06 3.24e-03
## polygon 141 89 7.22589e+05 1.12e-03
## polygon 142 279 2.55046e+06 3.94e-03
## polygon 143 34 2.04263e+06 3.16e-03
## polygon 144 70 3.26040e+06 5.04e-03
## polygon 145 216 1.34615e+06 2.08e-03
## polygon 146 25 1.71334e+05 2.65e-04
## polygon 147 84 4.96260e+04 7.67e-05
## polygon 148 199 1.93992e+05 3.00e-04
## polygon 149 77 1.20171e+05 1.86e-04
## polygon 150 272 8.50854e+05 1.31e-03
## polygon 151 99 1.02647e+06 1.59e-03
## polygon 152 154 1.67537e+05 2.59e-04
## polygon 153 81 1.16002e+06 1.79e-03
## polygon 154 32 2.56100e+06 3.96e-03
## polygon 155 112 7.35502e+05 1.14e-03
## polygon 156 124 9.48159e+05 1.46e-03
## polygon 157 134 1.32109e+06 2.04e-03
## polygon 158 59 2.99731e+06 4.63e-03
## polygon 159 123 1.37683e+06 2.13e-03
## polygon 160 129 1.92662e+06 2.98e-03
## polygon 161 522 3.20331e+06 4.95e-03
## polygon 162 93 2.34938e+06 3.63e-03
## polygon 163 85 9.63199e+05 1.49e-03
## polygon 164 36 4.85022e+05 7.49e-04
## polygon 165 82 1.88131e+06 2.91e-03
## polygon 166 103 1.42508e+06 2.20e-03
## polygon 167 60 2.38728e+06 3.69e-03
## polygon 168 114 1.07899e+06 1.67e-03
## polygon 169 71 4.59546e+05 7.10e-04
## polygon 170 91 2.47888e+05 3.83e-04
## polygon 171 107 2.13582e+05 3.30e-04
## polygon 172 207 2.47266e+06 3.82e-03
## polygon 173 (hole) 3 -4.95057e-02 -7.65e-11
## polygon 174 (hole) 3 -3.65501e-03 -5.65e-12
## polygon 175 (hole) 36 -7.79904e+03 -1.20e-05
## polygon 176 4 1.41753e-02 2.19e-11
## polygon 177 579 1.94069e+06 3.00e-03
## polygon 178 (hole) 4 -2.05611e-02 -3.18e-11
## polygon 179 349 2.11850e+06 3.27e-03
## polygon 180 109 4.85047e+05 7.49e-04
## polygon 181 102 7.57908e+05 1.17e-03
## polygon 182 120 3.51242e+05 5.43e-04
## polygon 183 69 1.31292e+06 2.03e-03
## polygon 184 (hole) 3 -3.99521e-02 -6.17e-11
## polygon 185 63 9.46651e+05 1.46e-03
## polygon 186 100 7.48043e+05 1.16e-03
## polygon 187 111 1.02229e+06 1.58e-03
## polygon 188 95 4.10995e+05 6.35e-04
## polygon 189 73 8.39489e+05 1.30e-03
## polygon 190 173 1.22849e+06 1.90e-03
## polygon 191 43 5.54624e+05 8.57e-04
## polygon 192 130 3.39290e+06 5.24e-03
## polygon 193 97 1.87809e+06 2.90e-03
## polygon 194 40 8.67750e+05 1.34e-03
## polygon 195 55 6.39144e+05 9.87e-04
## polygon 196 39 3.26015e+06 5.04e-03
## polygon 197 54 4.11404e+05 6.36e-04
## polygon 198 75 4.18657e+05 6.47e-04
## polygon 199 104 2.09818e+06 3.24e-03
## polygon 200 92 1.52455e+06 2.36e-03
## polygon 201 79 8.13383e+05 1.26e-03
## polygon 202 94 1.48430e+06 2.29e-03
## polygon 203 118 3.10802e+06 4.80e-03
## polygon 204 97 1.03728e+06 1.60e-03
## polygon 205 157 2.82017e+06 4.36e-03
## polygon 206 53 9.24762e+05 1.43e-03
## polygon 207 118 1.80655e+06 2.79e-03
## polygon 208 64 1.40454e+06 2.17e-03
## polygon 209 91 2.37933e+06 3.68e-03
## polygon 210 111 2.07780e+06 3.21e-03
## polygon 211 134 3.14295e+06 4.86e-03
## polygon 212 195 2.63648e+06 4.07e-03
## polygon 213 80 1.05717e+06 1.63e-03
## polygon 214 56 1.28795e+06 1.99e-03
## polygon 215 69 4.39647e+05 6.79e-04
## polygon 216 51 7.46882e+05 1.15e-03
## polygon 217 61 4.46242e+05 6.89e-04
## polygon 218 72 5.72502e+05 8.84e-04
## polygon 219 152 2.95937e+06 4.57e-03
## polygon 220 119 2.15829e+06 3.33e-03
## polygon 221 140 1.34746e+06 2.08e-03
## polygon 222 60 2.33891e+06 3.61e-03
## polygon 223 111 4.29714e+06 6.64e-03
## polygon 224 105 9.91040e+05 1.53e-03
## polygon 225 202 2.04955e+06 3.17e-03
## polygon 226 127 2.57909e+06 3.98e-03
## polygon 227 91 3.18758e+06 4.92e-03
## polygon 228 40 9.06317e+05 1.40e-03
## polygon 229 41 3.80202e+05 5.87e-04
## polygon 230 93 5.26383e+05 8.13e-04
## polygon 231 77 8.00299e+05 1.24e-03
## polygon 232 124 8.98561e+05 1.39e-03
## polygon 233 172 1.79346e+06 2.77e-03
## polygon 234 378 3.18810e+06 4.92e-03
## polygon 235 85 4.94504e+05 7.64e-04
## polygon 236 79 1.06189e+06 1.64e-03
## polygon 237 75 1.79446e+06 2.77e-03
## polygon 238 96 3.47521e+06 5.37e-03
## polygon 239 74 1.22567e+06 1.89e-03
## polygon 240 139 1.97437e+06 3.05e-03
## polygon 241 159 1.08508e+06 1.68e-03
## polygon 242 90 1.96413e+06 3.03e-03
## polygon 243 43 1.97494e+06 3.05e-03
## polygon 244 141 4.14132e+06 6.40e-03
## polygon 245 164 4.33982e+06 6.70e-03
## polygon 246 131 1.79606e+06 2.77e-03
## polygon 247 130 2.25116e+06 3.48e-03
## polygon 248 124 7.76142e+05 1.20e-03
## polygon 249 105 2.20631e+06 3.41e-03
## polygon 250 107 1.18013e+06 1.82e-03
## polygon 251 73 1.22989e+06 1.90e-03
## polygon 252 101 9.64683e+05 1.49e-03
## polygon 253 75 1.26341e+06 1.95e-03
## polygon 254 51 3.69771e+05 5.71e-04
## polygon 255 83 3.20366e+06 4.95e-03
## polygon 256 96 1.10727e+06 1.71e-03
## polygon 257 81 1.28739e+06 1.99e-03
## polygon 258 32 8.42668e+05 1.30e-03
## polygon 259 61 1.33353e+06 2.06e-03
## polygon 260 50 1.00741e+06 1.56e-03
## polygon 261 147 8.94516e+05 1.38e-03
## polygon 262 76 9.11208e+05 1.41e-03
## polygon 263 43 1.14381e+06 1.77e-03
## polygon 264 95 1.32888e+06 2.05e-03
## polygon 265 111 6.09895e+05 9.42e-04
## polygon 266 66 7.63183e+05 1.18e-03
## polygon 267 164 2.76835e+06 4.28e-03
## polygon 268 134 3.46704e+06 5.36e-03
## polygon 269 401 7.83399e+06 1.21e-02
## polygon 270 80 2.77864e+06 4.29e-03
## polygon 271 54 8.62737e+05 1.33e-03
## polygon 272 105 1.58344e+06 2.45e-03
## polygon 273 43 8.46137e+05 1.31e-03
## polygon 274 122 1.74439e+06 2.69e-03
## polygon 275 89 1.00159e+06 1.55e-03
## polygon 276 82 1.09730e+06 1.70e-03
## polygon 277 251 4.84852e+06 7.49e-03
## polygon 278 53 6.68454e+05 1.03e-03
## polygon 279 69 6.24878e+05 9.65e-04
## polygon 280 85 6.74992e+05 1.04e-03
## polygon 281 123 2.33068e+06 3.60e-03
## polygon 282 68 1.09321e+06 1.69e-03
## polygon 283 83 1.86187e+06 2.88e-03
## polygon 284 45 9.09419e+05 1.40e-03
## polygon 285 108 2.11479e+06 3.27e-03
## polygon 286 204 3.33419e+06 5.15e-03
## polygon 287 59 1.51553e+06 2.34e-03
## polygon 288 60 9.44998e+05 1.46e-03
## polygon 289 189 1.99079e+06 3.08e-03
## polygon 290 83 1.64141e+06 2.54e-03
## polygon 291 173 1.65255e+05 2.55e-04
## polygon 292 91 1.49663e+04 2.31e-05
## polygon 293 71 8.18750e+03 1.26e-05
## polygon 294 83 2.25924e+06 3.49e-03
## polygon 295 221 3.86032e+06 5.96e-03
## polygon 296 58 8.59179e+05 1.33e-03
## polygon 297 63 5.46404e+05 8.44e-04
## polygon 298 71 1.94861e+06 3.01e-03
## polygon 299 87 1.07862e+06 1.67e-03
## polygon 300 99 6.87930e+05 1.06e-03
## polygon 301 151 3.02315e+06 4.67e-03
## polygon 302 35 4.41733e+05 6.82e-04
## polygon 303 62 9.70068e+05 1.50e-03
## polygon 304 93 1.23590e+06 1.91e-03
## polygon 305 100 1.63967e+06 2.53e-03
## polygon 306 107 2.54311e+06 3.93e-03
## polygon 307 83 9.55710e+05 1.48e-03
## polygon 308 58 3.16882e+05 4.90e-04
## polygon 309 94 1.04642e+06 1.62e-03
## polygon 310 63 9.21431e+05 1.42e-03
## polygon 311 149 7.37056e+06 1.14e-02
## polygon 312 52 6.84704e+05 1.06e-03
## polygon 313 127 1.51149e+06 2.33e-03
## polygon 314 151 2.45910e+06 3.80e-03
## polygon 315 191 7.03481e+06 1.09e-02
## polygon 316 158 3.65203e+06 5.64e-03
## polygon 317 285 1.71970e+06 2.66e-03
## polygon 318 (hole) 3 -2.83151e-01 -4.37e-10
## polygon 319 87 1.08864e+06 1.68e-03
## polygon 320 81 1.56903e+06 2.42e-03
## polygon 321 176 1.67003e+06 2.58e-03
## polygon 322 79 2.39108e+06 3.69e-03
## polygon 323 52 1.37871e+06 2.13e-03
## polygon 324 101 9.23215e+05 1.43e-03
## polygon 325 246 5.32542e+06 8.23e-03
## polygon 326 92 1.41828e+06 2.19e-03
## polygon 327 50 1.48925e+06 2.30e-03
## polygon 328 117 5.18613e+06 8.01e-03
## polygon 329 537 3.50960e+07 5.42e-02
## polygon 330 80 1.46328e+06 2.26e-03
## polygon 331 258 9.95945e+05 1.54e-03
## polygon 332 55 1.45551e+06 2.25e-03
## polygon 333 44 1.49911e+06 2.32e-03
## polygon 334 68 9.24866e+05 1.43e-03
## polygon 335 127 1.34017e+06 2.07e-03
## polygon 336 353 8.50444e+06 1.31e-02
## polygon 337 (hole) 317 -5.11280e+04 -7.90e-05
## polygon 338 210 1.36000e+06 2.10e-03
## polygon 339 67 1.43138e+05 2.21e-04
## polygon 340 64 4.36369e+05 6.74e-04
## polygon 341 134 1.25974e+06 1.95e-03
## polygon 342 4 6.49287e-01 1.00e-09
## polygon 343 112 3.29141e+06 5.08e-03
## polygon 344 102 1.57600e+06 2.43e-03
## polygon 345 122 1.66547e+06 2.57e-03
## polygon 346 94 1.76709e+06 2.73e-03
## polygon 347 95 2.05005e+06 3.17e-03
## polygon 348 129 1.51777e+06 2.34e-03
## polygon 349 117 5.95652e+05 9.20e-04
## polygon 350 263 3.28413e+06 5.07e-03
## polygon 351 118 2.55346e+06 3.94e-03
## polygon 352 50 9.62437e+05 1.49e-03
## polygon 353 112 1.28130e+06 1.98e-03
## polygon 354 26 7.58123e+05 1.17e-03
## polygon 355 76 9.05921e+05 1.40e-03
## polygon 356 285 1.61128e+06 2.49e-03
## polygon 357 66 1.26165e+06 1.95e-03
## polygon 358 1605 1.74949e+07 2.70e-02
## polygon 359 (hole) 3 -8.83647e-03 -1.37e-11
## polygon 360 164 3.45046e+06 5.33e-03
## polygon 361 65 1.74196e+06 2.69e-03
## polygon 362 74 1.39487e+06 2.15e-03
## polygon 363 141 1.07438e+06 1.66e-03
## polygon 364 711 1.28815e+07 1.99e-02
## polygon 365 (hole) 3 -3.41405e-01 -5.27e-10
## polygon 366 668 5.40368e+07 8.35e-02
## polygon 367 77 3.29939e+05 5.10e-04
## polygon 368 44 2.26577e+03 3.50e-06
## polygon 369 181 7.23581e+06 1.12e-02
## polygon 370 193 2.14708e+06 3.32e-03
## polygon 371 90 1.51100e+06 2.33e-03
## polygon 372 125 9.36416e+05 1.45e-03
## polygon 373 148 1.64863e+06 2.55e-03
## polygon 374 102 1.09939e+06 1.70e-03
## polygon 375 77 2.20921e+06 3.41e-03
## polygon 376 79 1.26438e+06 1.95e-03
## polygon 377 75 2.20670e+06 3.41e-03
## polygon 378 40 1.26592e+06 1.96e-03
## polygon 379 111 3.91607e+06 6.05e-03
## polygon 380 148 2.17538e+06 3.36e-03
## polygon 381 132 3.62184e+06 5.59e-03
## polygon 382 80 1.43291e+06 2.21e-03
## polygon 383 112 4.38713e+06 6.78e-03
## polygon 384 145 1.20080e+06 1.85e-03
## polygon 385 532 2.45079e+06 3.79e-03
## polygon 386 (hole) 3 -2.05920e-03 -3.18e-12
## polygon 387 (hole) 3 -2.21090e+00 -3.42e-09
## polygon 388 125 1.54073e+06 2.38e-03
## polygon 389 379 1.63581e+06 2.53e-03
## polygon 390 357 2.24139e+06 3.46e-03
## enclosing rectangle: [4453.85, 56396.44] x [15748.72, 50256.33] units
## (51940 x 34510 units)
## Window area = 647338000 square units
## Fraction of frame area: 0.361Combining airbnb points and the study area
listings_ppp_SG <- listings_ppp_jit[sg_owin]
plot(listings_ppp_SG)
Next, we will observe the room types with the study area separately
listings_ppp_pr <- listings_ppp_SG[listings_ppp_SG$marks == "Private room"]
listings_ppp_eh <- listings_ppp_SG[listings_ppp_SG$marks == "Entire home/apt"]
listings_ppp_sr <- listings_ppp_SG[listings_ppp_SG$marks == "Shared room"]
listings_ppp_hr <- listings_ppp_SG[listings_ppp_SG$marks == "Hotel room"]par(mfrow=c(2,2))
plot(listings_ppp_pr, main = "Private room")
plot(listings_ppp_eh, main = "Entire home/apt")
plot(listings_ppp_sr, main = "Shared room")
plot(listings_ppp_hr, main = "Hotel room")
Similar to the previous analysis , we can see that the hotel rooms are located mainly in the central areas with a few in the Northeast, SouthEast and SouthWest. For entire homes, we can see that they are all around Singapore and are significant in numbers and are mainly located in the central areas. For shared rooms, they are scattered sparsely around Singapore and are located mainly in central areas.Lastly,the private rooms located all around Singapore and are significant in numbers.
Quadrat analysis
The test hypotheses are : Ho = The distribution of airbnb listings in Singapore are randomly distributed.
H1= The distribution of airbnb listings in Singapore are not randomly distributed.
Confidence interval: 95%
Chi-squared test
qt_t <- quadrat.test(listings_ppp_SG,
nx = 20, ny = 15)## Warning: Some expected counts are small; chi^2 approximation may be inaccurateqt_t##
## Chi-squared test of CSR using quadrat counts
##
## data: listings_ppp_SG
## X2 = 62038, df = 179, p-value < 2.2e-16
## alternative hypothesis: two.sided
##
## Quadrats: 180 tiles (irregular windows)Since the p-value is 2.2e-16, we reject the null hypothesis at 95% confidence level. The high X2 value may indicate clustering of airbnb data points. The chi-square approximation may be inaccurate. Hence we will now conduct a monte-carlo test.
Conditional Monte Carlo test of CSR using quadrat counts
qt <-quadrat.test(listings_ppp_SG,
nx = 20, ny = 15,
method="M",
nsim=999)
qt##
## Conditional Monte Carlo test of CSR using quadrat counts
## Test statistic: Pearson X2 statistic
##
## data: listings_ppp_SG
## X2 = 62038, p-value = 0.002
## alternative hypothesis: two.sided
##
## Quadrats: 180 tiles (irregular windows)plot(listings_ppp_SG)
plot(qt, add = TRUE, cex =.1)
Since p-value = 0.002<0.05, we reject the null hypothesis at 0.05 significance level. This is consistent with our chi-squared test.
Nearest Neighbour Analysis
clarkevans.test(listings_ppp_SG,
correction="none",
clipregion="sg_owin",
alternative=c("two.sided"),
nsim=99)##
## Clark-Evans test
## No edge correction
## Monte Carlo test based on 99 simulations of CSR with fixed n
##
## data: listings_ppp_SG
## R = 0.36251, p-value = 0.02
## alternative hypothesis: two-sidedThe nearest neighbour index value is 0.30875 which is less than 1, indicating clustering is exibited.
Hence, the quadrat and nearest neighbour analysis allows us to conclude that the distribution of airbnbs in Singapore exhibit clustering.
Kernel density maps for each room types
Check of there are enough observations for each room type(2 or more observations are required)
listings_ppp_pr$n## [1] 3200listings_ppp_eh$n## [1] 3704listings_ppp_sr$n## [1] 272listings_ppp_hr$n## [1] 507Hence, there is sufficient observations and we can do the kde analysis,
We will be analysis the room types separately first , followed by visualising them together.
tmap_mode("plot")## tmap mode set to plottinggetKernelDensityMap <- function(ppp, ppp_str) {
ppp.km <- rescale(ppp, 1000, "km")
kde_1000 <- density(ppp.km, sigma=1, edge=TRUE, kernel="gaussian")
gridded_kde_1000_bw <- as.SpatialGridDataFrame.im(kde_1000)
kde_1000_bw_raster <- raster(gridded_kde_1000_bw)
projection(kde_1000_bw_raster) <- crs("+init=EPSG:3414 +datum=WGS84 +units=km")
tm_shape(sg_map)+
tm_layout(legend.outside = TRUE, title=ppp_str)+
tm_rgb()+
tm_shape(subzone)+
tm_polygons(alpha = 0, border.col = "black", border.alpha = 0.5)+
tm_shape(kde_1000_bw_raster) +
tm_raster("v", alpha=0.5,
palette = "YlOrRd")
}eh_kdm <- getKernelDensityMap(listings_ppp_eh, "Entire home/apt")
hr_kdm <- getKernelDensityMap(listings_ppp_hr, "Hotel room")
pr_kdm <- getKernelDensityMap(listings_ppp_pr, "Private room")
sr_kdm <- getKernelDensityMap(listings_ppp_sr, "Shared room")Private room
pr_kdm## Warning: Raster values found that are outside the range [0, 255]
For private room , we can see that there are more rooms in the central area, in particular , the lavender subzone
Entire homes
eh_kdm## Warning: Raster values found that are outside the range [0, 255]
For entire homes , we can see that there are more rooms in the central area. There is a cluster in Balestier/LAvender, Tanjong Pagar subzone and Aljunied subzone . The popularity of entire homes may be due to the homely experience that tourists might want to experience in Singapore
Hotel room
hr_kdm## Warning: Raster values found that are outside the range [0, 255]
For hotel rooms , we can see that there are more rooms in the central area, in particular Tanjong Pagar area. This may be because Tanjong Pagar is more centralised and in the office area and more affluent people can afford.
Shared Room
sr_kdm## Warning: Raster values found that are outside the range [0, 255]
For entire homes , we can see that there are more rooms in the central area, in particular the lavender subzone.
tmap_arrange(eh_kdm, hr_kdm, pr_kdm, sr_kdm)## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
## Warning: Raster values found that are outside the range [0, 255]
For all the plots, the room types are clustered around the central region. This is most likely due to the convenience and accessibility for tourists.
Advantage of kernel density map over point map
In Kernel density maps, we are able to identify precisely the location and intensity of the Airbnb listings. Kernity density maps provide a quantitative and visual aspect that shows the concentration of points.Points maps however,does not enable the viewing of exact locations and are less accurate than kernel density maps.
Section B:Planning subzones
Extract study areas
al <- subzone[subzone@data$SUBZONE_N == "ALJUNIED",]
ba <- subzone[subzone@data$SUBZONE_N == "BALESTIER",]
la <- subzone[subzone@data$SUBZONE_N == "LAVENDER",]
tp <- subzone[subzone@data$SUBZONE_N == "TANJONG PAGAR",]Load osm
al_map<-getTiles(x = al, type = "osm")
ba_map<-getTiles(x = ba, type = "osm")
la_map<-getTiles(x = la, type = "osm")
tp_map<-getTiles(x = tp, type = "osm")Plotting study areas
par(mfrow=c(2,2))
plot(al, main = "ALJUNIED")
plot(ba, main = "BALESTIER")
plot(la, main = "LAVENDER")
plot(tp, main = "TANJONG PAGAR")
Converting the spatial point data frame into generic sp forma
al_sp <- as(al, "SpatialPolygons")
ba_sp <- as(ba, "SpatialPolygons")
la_sp <- as(la, "SpatialPolygons")
tp_sp <- as(tp, "SpatialPolygons")Convert SpatialPolygons objects into owin objects
al_owin = as(al_sp, "owin")
ba_owin = as(ba_sp, "owin")
la_owin = as(la_sp, "owin")
tp_owin = as(tp_sp, "owin")Combining private points and study area
listings_al_ppp <- listings_ppp_jit[al_owin]
listings_ba_ppp <- listings_ppp_jit[ba_owin]
listings_la_ppp <- listings_ppp_jit[la_owin]
listings_tp_ppp <- listings_ppp_jit[tp_owin]Plotting listings by subzone
par(mfrow=c(2,2))
plot(listings_al_ppp, main="Aljunied")
plot(listings_ba_ppp, main="Balestier")
plot(listings_la_ppp, main="Lavender")
plot(listings_tp_ppp, main="Tanjong Pagar")
From the plot,we see clusterings in certain regions of each study area. For aljunied, the listings are concentrated in the central area . For balestier, the listings are more sparse in the eastern and north-eastern part of balestier. For lavender, the listings are relatively evenly spread out with the exception of the south and south western parts of lavender where listings are sparse. For tanjong pagar, the listings are cencentrated in the south western part of tanjong pagar.
Distribution of room types within Aljunied
listings_al_eh_ppp <- listings_ppp_eh[al_owin]
listings_al_hr_ppp <- listings_ppp_hr[al_owin]
listings_al_pr_ppp <- listings_ppp_pr[al_owin]
listings_al_sr_ppp <- listings_ppp_sr[al_owin]listings_al_pr_ppp$n## [1] 226listings_al_sr_ppp$n## [1] 10listings_al_hr_ppp$n## [1] 17listings_al_eh_ppp$n## [1] 579par(mfrow=c(2,2))
plot(listings_al_eh_ppp, main="Aljunied - Entire home")
plot(listings_al_hr_ppp, main="Aljunied - Hotel room")
plot(listings_al_pr_ppp, main="Aljunied - Private room")
plot(listings_al_sr_ppp, main="Aljunied - Shared room")
There is significantly more private rooms and entire homes in aljunied and they are located in central aljunied.Hotel rooms are also mostly located in the central aljunied but are less in numbers than the previous 2 room types. Shared rooms are spread sparsely in the central and eastern part of aljunied.
Distribution of room types within Balestier
listings_ba_eh_ppp <- listings_ppp_eh[ba_owin]
listings_ba_hr_ppp <- listings_ppp_hr[ba_owin]
listings_ba_pr_ppp <- listings_ppp_pr[ba_owin]
listings_ba_sr_ppp <- listings_ppp_sr[ba_owin]listings_ba_pr_ppp$n## [1] 60listings_ba_sr_ppp$n## [1] 1listings_ba_hr_ppp$n## [1] 40listings_ba_eh_ppp$n## [1] 373par(mfrow=c(2,2))
plot(listings_ba_eh_ppp, main="Balestier - Entire home/apt")
plot(listings_ba_hr_ppp, main="Balestier - Hotel room")
plot(listings_ba_pr_ppp, main="Balestier - Private room")
plot(listings_ba_sr_ppp, main="Balestier - Shared room")
From the plots, balestier has a the most number of entire homes among the room types and they are located in the south and western parts of balestier. For hotel and private rooms, they are most common in the central parts of balestier. There is a relatively insignificant number of shared rooms in balestier
Distribution of room types within Lavender
listings_la_eh_ppp = listings_ppp_eh[la_owin]
listings_la_hr_ppp = listings_ppp_hr[la_owin]
listings_la_pr_ppp = listings_ppp_pr[la_owin]
listings_la_sr_ppp = listings_ppp_sr[la_owin]listings_la_pr_ppp$n## [1] 281listings_la_sr_ppp$n## [1] 51listings_la_hr_ppp$n## [1] 42listings_la_eh_ppp$n## [1] 123par(mfrow=c(2,2))
plot(listings_la_eh_ppp, main="Lavender - Entire home/apt")
plot(listings_la_hr_ppp, main="Lavender - Hotel room")
plot(listings_la_pr_ppp, main="Lavender - Private room")
plot(listings_la_sr_ppp, main="Lavender - Shared room")
From the plots, lavender has a significant number of private rooms and they mainly located in the eastern parts of lavender. Lavender also has a significant number of entire homes and they are mainly located in the northern part of lavender. Hotel and shared rooms are less in numbers than the other 2 room types and are mainly located in the northern and central parts of lavender.
Distribution of room types within Tanjong Pagar
listings_tp_eh_ppp = listings_ppp_eh[tp_owin]
listings_tp_hr_ppp = listings_ppp_hr[tp_owin]
listings_tp_pr_ppp = listings_ppp_pr[tp_owin]
listings_tp_sr_ppp = listings_ppp_sr[tp_owin]listings_tp_pr_ppp$n## [1] 20listings_tp_sr_ppp$n## [1] 0listings_tp_hr_ppp$n## [1] 2listings_tp_eh_ppp$n## [1] 148par(mfrow=c(2,2))
plot(listings_tp_eh_ppp, main="Tanjong Pagar - Entire home")
plot(listings_tp_hr_ppp, main="Tanjong Pagar - Hotel room")
plot(listings_tp_pr_ppp, main="Tanjong Pagar - Private room")
plot(listings_tp_sr_ppp, main="Tanjong Pagar - Shared room")
There is a large number of entire homes in Tanjong Pagar which are mainly located in the south-western part of tanjong pagar. The private rooms are spread out in Tanjong Pagar rather evenly and there are only a few hotel rooms which are located in the eastern part of tanjong pagar. Shared rooms are rather insignificant in Tanjong Pagar.
Perform second order anaysis With reference to the spatial point patterns observed
Determine function
Aljunied_nnd <- nndist.ppp(listings_al_ppp)
Balestier_nnd <- nndist.ppp(listings_ba_ppp)
Lavender_nnd <- nndist.ppp(listings_la_ppp)
TanjongPagar_nnd <- nndist.ppp(listings_tp_ppp)
range(Aljunied_nnd)## [1] 0.4823623 305.6527962range(Aljunied_nnd)## [1] 0.4823623 305.6527962range(Balestier_nnd)## [1] 0.7013138 558.1480528range(Lavender_nnd)## [1] 0.7127891 148.0174823range(TanjongPagar_nnd)## [1] 0.9127245 64.7492573Using the K-function will not be ideal due to the shape of our study areas (we can assume they have identical values of a property in all directions.) . There is a big difference betwwen the ranges of values for Aljunied and Balestier which may be a problem when using the G-function as the G-functionis cummulative in nature. Hence , for our analysis , we will be using the F-function.
Aljunied
The hypothesis and test are as follows: Ho = The distribution of rooms at Aljunied are randomly distributed. H1= The distribution of rooms at Aljunied are not randomly distributed.
fal.csr <- envelope(listings_al_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fal_EH.csr <- envelope(listings_al_eh_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fal_HR.csr <- envelope(listings_al_hr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fal_PR.csr <- envelope(listings_al_pr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fal_SR.csr <- envelope(listings_al_sr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.plot(fal.csr)
We reject the null hypothesis at 95% confidence interval.
par(mfrow=c(2,2))
plot(fal_EH.csr)
plot(fal_HR.csr)
plot(fal_PR.csr)
plot(fal_SR.csr)
We can see that for entire homes and private room listings , they are overall clustered .This may be due to double listings or tourist hotspots for the two room types. We reject the null hypothesis for entire homes and private rooms and do not reject the null hypothesis for hotel and shared rooms.
Balestier
The hypothesis and test are as follows: Ho = The distribution of rooms at Balestier are randomly distributed. H1= The distribution of rooms at Balestier are not randomly distributed.
fba.csr <- envelope(listings_ba_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fba_EH.csr <- envelope(listings_ba_eh_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fba_HR.csr <- envelope(listings_ba_hr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fba_PR.csr <- envelope(listings_ba_pr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fba_SR.csr <- envelope(listings_ba_sr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.plot(fba.csr)
We reject the null hypothesis at 95% confidence interval.
par(mfrow=c(2,2))
plot(fba_EH.csr)
plot(fba_HR.csr)
plot(fba_PR.csr)
plot(fba_SR.csr)
We reject the null hypothesis for entire homes and private rooms and do not reject the null hypothesis for hotel and shared rooms.We can see that for entire homes and private room listings , they are overall clustered, more evidently in entire homes. For shared rooms , the plot may be due to the lack of data points .
Lavender
The hypothesis and test are as follows: Ho = The distribution of rooms at Lavender are randomly distributed. H1= The distribution of rooms at Lavender are not randomly distributed.
fla.csr <- envelope(listings_la_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fla_EH.csr <- envelope(listings_la_eh_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fla_HR.csr <- envelope(listings_la_hr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fla_PR.csr <- envelope(listings_la_pr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.fla_SR.csr <- envelope(listings_la_sr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.plot(fla.csr)
We reject the null hypothesis at 95% confidence interval.
par(mfrow=c(2,2))
plot(fla_EH.csr)
plot(fla_HR.csr)
plot(fla_PR.csr)
plot(fla_SR.csr)
We reject the null hypothesis for entire homes and private rooms and hotel rooms and do not reject the null hypothesis for shared rooms.
Tanjong Pagar
The hypothesis and test are as follows: Ho = The distribution of rooms at Tanjong Pagar are randomly distributed. H1= The distribution of rooms at Tanjong Pagar are not randomly distributed.
ftp.csr <- envelope(listings_tp_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.ftp_EH.csr <- envelope(listings_tp_eh_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.ftp_HR.csr <- envelope(listings_tp_hr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.ftp_PR.csr <- envelope(listings_tp_pr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.ftp_SR.csr <- envelope(listings_tp_sr_ppp, Fest, nsim = 999)## Generating 999 simulations of CSR ...
## 1, 2, 3, ......10.........20.........30.........40.........50.........60........
## .70.........80.........90.........100.........110.........120.........130......
## ...140.........150.........160.........170.........180.........190.........200....
## .....210.........220.........230.........240.........250.........260.........270..
## .......280.........290.........300.........310.........320.........330.........340
## .........350.........360.........370.........380.........390.........400........
## .410.........420.........430.........440.........450.........460.........470......
## ...480.........490.........500.........510.........520.........530.........540....
## .....550.........560.........570.........580.........590.........600.........610..
## .......620.........630.........640.........650.........660.........670.........680
## .........690.........700.........710.........720.........730.........740........
## .750.........760.........770.........780.........790.........800.........810......
## ...820.........830.........840.........850.........860.........870.........880....
## .....890.........900.........910.........920.........930.........940.........950..
## .......960.........970.........980.........990........ 999.
##
## Done.plot(ftp.csr)
We reject the null hypothesis at 95% confidence interval.
par(mfrow=c(2,2))
plot(ftp_EH.csr)
plot(ftp_HR.csr)
plot(ftp_PR.csr)
plot(ftp_SR.csr)
## Error in yp[whole] <- yp[whole] + epsilon :
## NAs are not allowed in subscripted assignmentsWe reject the null hypothesis for entire homes and private rooms s and do not reject the null hypothesis for and hotel rooms. Analysis for shared rooms cannot be done as there are no points for Tanjong Pagar,
Kernel Density Maps of listings by room type
getmap <- function(osm, sz, ppp, ppp_str) {
ppp.km <- rescale(ppp, 1000, "km")
kde <- density(ppp.km, sigma=0.20, edge=TRUE, kernel="gaussian")
gridded_kde_bw <- as.SpatialGridDataFrame.im(kde)
kde_bw_raster <- raster(gridded_kde_bw)
projection(kde_bw_raster) <- crs("+init=EPSG:3414 +datum=WGS84 +units=km")
tm_shape(osm)+
tm_layout(legend.outside = TRUE, title=ppp_str)+
tm_rgb()+
tm_shape(sz)+
tm_borders(col = "darkblue", lwd = 2, lty="longdash")+
tm_shape(kde_bw_raster) +
tm_raster("v", alpha=0.5,
palette = "YlOrRd")
}tmap_mode("plot")## tmap mode set to plottingAljunied
checking if can proceed with analysis
listings_al_pr_ppp$n## [1] 226listings_al_sr_ppp$n## [1] 10listings_al_hr_ppp$n## [1] 17listings_al_eh_ppp$n## [1] 579Entire Home
getmap(al_map, al, listings_al_eh_ppp, "Aljunied Entire home/apt")## Warning: Raster values found that are outside the range [0, 255]
For entire homes , there is a main cluster in the east and central of aljunied.
Shared room
getmap(al_map, al, listings_al_sr_ppp, "Aljunied Shared room")## Warning: Raster values found that are outside the range [0, 255]
For Shared rooms , there is a cluster in the central/north of aljunied
Private room
getmap(al_map, al, listings_al_pr_ppp, "Aljunied Private room")## Warning: Raster values found that are outside the range [0, 255]
For private room , there is a cluster in the central of aljunied
Hotel room
getmap(al_map, al, listings_al_hr_ppp, "Aljunied Hotel room")## Warning: Raster values found that are outside the range [0, 255]
For hotel room , there is a main cluster in the west of aljunied as well as a smaller cluster in the central
From the plots and scales, there are the most entire in Aljunied.This may be due to the fact that tourists may want a local experience by staying in homes . The cluster on the west which is closer to the central of Singapore may be due to the accessibility to town.
Balestier
listings_ba_pr_ppp$n## [1] 60listings_ba_sr_ppp$n## [1] 1listings_ba_hr_ppp$n## [1] 40listings_ba_eh_ppp$n## [1] 373Entire Home
getmap(ba_map, ba, listings_ba_eh_ppp, "Balestier Entire home/apt")## Warning: Raster values found that are outside the range [0, 255]
For entire homes , there is a main cluster in the south of Balestier
Private room
getmap(ba_map, ba, listings_ba_pr_ppp, "Balestier Private room")## Warning: Raster values found that are outside the range [0, 255]
For private room , there is a cluster in the central and south of Balestier
Hotel room
getmap(ba_map, ba, listings_ba_hr_ppp, "Balestier Hotel room")## Warning: Raster values found that are outside the range [0, 255]
For hotel room , there is a cluster in the central.south of Balestier
Based on the plots and scale,balestier has the highest number of entire homes.All the room types have higher numbers in the central and south areas of balestier.Tourists may want to feel what it is like to live in Singapore as a local as Balestier is a residential area. As seen from our listings check, there is not enough observations for balestier shared room listings.
Lavender
listings_la_pr_ppp$n## [1] 281listings_la_sr_ppp$n## [1] 51listings_la_hr_ppp$n## [1] 42listings_la_eh_ppp$n## [1] 123Entire Home
getmap(la_map, la, listings_la_eh_ppp, "Lavender Entire home/apt")## Warning: Raster values found that are outside the range [0, 255]
For entire homes , there is a main cluster in the north west of Lavender
Shared room
getmap(la_map, la, listings_la_sr_ppp, "Lavender Shared room")## Warning: Raster values found that are outside the range [0, 255]
For Shared rooms , there is a cluster in the north west of Lavender
Private room
getmap(la_map, la, listings_la_pr_ppp, "Lavender Private room")## Warning: Raster values found that are outside the range [0, 255]
For private room , there is a cluster in the east of Lavender
Hotel room
getmap(la_map, la, listings_la_hr_ppp, "Aljunied Hotel room")## Warning: Raster values found that are outside the range [0, 255]
For hotel room , there is a cluster in the north west of Lavender
Lavender has a highest number of private rooms among the room types. The rest of the room types are located in the north west of Lavender. An interesting point to point out is that there is a hospital located at the north west of Lavender which may be related to the high numbers of room types.
Tanjong Pagar
listings_tp_pr_ppp$n## [1] 20listings_tp_sr_ppp$n## [1] 0listings_tp_hr_ppp$n## [1] 2listings_tp_eh_ppp$n## [1] 148Entire Home
getmap(tp_map, tp, listings_tp_eh_ppp, "Tanjong Pagar Entire home/apt")## Warning: Raster values found that are outside the range [0, 255]
For entire homes , there is a main cluster in the south of Tanjong Pagar
Private room
getmap(tp_map, tp, listings_tp_pr_ppp, "Tanjong Pagar Private room")## Warning: Raster values found that are outside the range [0, 255]
For private room , there is a cluster in the south of Tanjong Pagar
There is the most entire homes in tanjong pagar. Tourists may want to feel what it is like to live in Singapore as a local . We will not perform analysis for shared and hotel rooms as there are not enough observations available.
Overall analysis
We can see that tourists prefer staying in listings that are entire homes or private rooms. This may be due to the ‘local experience’ that tourists are attracted to.Furthermore,we can deduce that tourists are more likely to stay in the central regions of Singapore which is most likely due to the convenience of the location. The number of shared rooms overall is very low which may be due to tourists not being comfortable with the idea of shared space. The number of hotel rooms are also relatively low which may be due to the price and the idea that tourists may want a more homely experience and experience local life.