IS415_Take-Home_Ex03.RMD

1.0 Setting the Scene

Social area analysis (SAA), which is a generic name for a number of methods employing census and other data to classify small areas into similar socioeconomic groups, is an approach which quantifies data in a useful fashion and has important applications in regional development, urban planning, medical and health services research. The potentialities of the approach for Liveable City planning and Smart City preparedness, however, have yet to be explored.

2.0 The Task

In this take-home exercise, you are tasked to segment Singapore at the planning subzone level into homogeneous socioeconomic areas by combining geodemographic data extracted from Singapore Department of Statistics and urban functions extracted from the geospatial data provided. From the Singapore Residents by Planning Area Subzone, Age Group, Sex and Type of Dwelling, June 2011-2019 provide by Singapore Department of Statistics, you are required the extract the following indicators for 2019: Economy active population (i.e. age 25-64), Young group (i.e. age 0-24), Aged group (i.e 65 and above), Population density, HDB1-2RM dwellers, HDB3-4RM dwellers, HDB5RM-Ec dweller, Condominium and apartment dwellers and Landed property dwellers.

From the geospatial data provided, you are required to extract the following urban functions:

• Government including embassy
• Business
• Industry
• Shopping
• Financial
• Upmarket residential area

3.0 Datasets

• 1. Singapore Residents by Planning AreaSubzone, Age Group, Sex and Type of Dwelling, June 2011-2019: Singstat
• 2. URA Master Plan 2014 Planning Subzone boundary: URA Master Plan
• 3. Five geospatial data sets are also provided, namely: Govt_Embassy, Private residential, Shopping, Business and Financial.

4.0 Data Wrangling

4.1 Importing of Packages

packages = c('rgdal', 'spdep', 'ClustGeo',  'tmap', 'sf', 'ggpubr', 'cluster', 'heatmaply', 'corrplot', 'psych', 'tidyverse', 'dplyr', 'factoextra')
for (p in packages){
  if(!require(p, character.only = T)){
    install.packages(p)
    }
  library(p,character.only = T)
}

4.2 Importing the aspatial data

residential <- read_csv ("data/aspatial/respopagesextod2011to2019.csv")

Extract according to the following indicators:

• Economy active population (i.e. age 25-64)
• Young (i.e. age 0-24)
• Aged group (i.e. 65 and above)
• Population density
• HDB1-2RM dwellers
• HDB3-4RM dwellers
• HDB5RM-Ec dweller
• Condominium and apartment dwellers
• Landed property dwellers

resident_2019<-residential %>%
  filter (Time==2019) %>%
  mutate(SZ = toupper(SZ)) %>%
  group_by(SZ, TOD) %>%
  spread(AG, Pop) %>% 
  mutate(`YOUNG` = sum(`0_to_4` + `5_to_9` + `10_to_14` + `15_to_19` + `20_to_24`)) %>%
  mutate(`ECONOMY ACTIVE` = sum(`25_to_29` + `30_to_34` + `35_to_39` + `40_to_44` + `45_to_49` + `50_to_54` + `55_to_59` + `60_to_64`)) %>%
  mutate(`AGED`= sum(`65_to_69` + `70_to_74` + `75_to_79` + `80_to_84` + `85_to_89` + `90_and_over`)) %>%
  filter(Sex=="Males") %>%
  group_by(SZ,TOD) %>%
  mutate(`dwellers_by_room_and_sz` = sum(`YOUNG`, `AGED`, `ECONOMY ACTIVE`)) %>%
  group_by(SZ, PA) %>%
  mutate(`Subzone_pop` = sum(`dwellers_by_room_and_sz`)) %>%
  select (`PA`,`SZ`, `TOD`,`YOUNG`,`ECONOMY ACTIVE`,`AGED`,`dwellers_by_room_and_sz`,`Subzone_pop`)

resident_2019<-resident_2019 %>%
  spread(TOD, `dwellers_by_room_and_sz`) %>%
  select(`PA`,`SZ`,`YOUNG`,`ECONOMY ACTIVE`, `AGED`,`HDB 1- and 2-Room Flats`, `HDB 3-Room Flats`, `HDB 4-Room Flats`, `HDB 5-Room and Executive Flats`, `Condominiums and Other Apartments`, `Landed Properties`, `Subzone_pop`)

First step: Check for NA values

colSums(is.na(resident_2019))

##                                PA                                SZ 
##                                 0                                 0 
##                             YOUNG                    ECONOMY ACTIVE 
##                                 0                                 0 
##                              AGED           HDB 1- and 2-Room Flats 
##                                 0                               980 
##                  HDB 3-Room Flats                  HDB 4-Room Flats 
##                               980                               980 
##    HDB 5-Room and Executive Flats Condominiums and Other Apartments 
##                               980                               980 
##                 Landed Properties                       Subzone_pop 
##                               980                                 0

Second step: Replace NA values with value “0”.

resident_2019[is.na(resident_2019)] <- 0 

Third step: Check for NA values again to ensure the NA values are replaced already.

colSums(is.na(resident_2019))

##                                PA                                SZ 
##                                 0                                 0 
##                             YOUNG                    ECONOMY ACTIVE 
##                                 0                                 0 
##                              AGED           HDB 1- and 2-Room Flats 
##                                 0                                 0 
##                  HDB 3-Room Flats                  HDB 4-Room Flats 
##                                 0                                 0 
##    HDB 5-Room and Executive Flats Condominiums and Other Apartments 
##                                 0                                 0 
##                 Landed Properties                       Subzone_pop 
##                                 0                                 0

Fourth Step: To derive at the total count for HDB 3 and 4 room flats, it is necessary to sum them up.

resident_2019 <- resident_2019 %>%
  group_by(SZ,PA) %>%
  mutate(`HDB 3- and 4-Room Flats` = `HDB 3-Room Flats` + `HDB 4-Room Flats`) %>%
  select(`PA`, `SZ`, `YOUNG`, `ECONOMY ACTIVE`, `AGED`, `HDB 1- and 2-Room Flats`, `HDB 3- and 4-Room Flats`, `HDB 5-Room and Executive Flats`, `Condominiums and Other Apartments`, `Landed Properties`, `Subzone_pop`)

4.3 Importing the geospatial data - 2014 Planning subzone boundary

mpsz <- st_read(dsn = "data/geospatial", layer="MP14_SUBZONE_WEB_PL")

## Reading layer `MP14_SUBZONE_WEB_PL' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 323 features and 15 fields
## geometry type:  MULTIPOLYGON
## dimension:      XY
## bbox:           xmin: 2667.538 ymin: 15748.72 xmax: 56396.44 ymax: 50256.33
## proj4string:    +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

Combine both the mpsz data and residential data together.

residential_mpsz_total <- left_join(resident_2019, mpsz, by=c("SZ" = "SUBZONE_N"))

## Warning: Column `SZ`/`SUBZONE_N` joining character vector and factor, coercing
## into character vector

Determining the population density based on each subzone:

residential_mpsz <- residential_mpsz_total %>% 
  select(`PA`,`SZ`,`YOUNG`,`ECONOMY ACTIVE`,`AGED`,`HDB 1- and 2-Room Flats`, `HDB 3- and 4-Room Flats`, `HDB 5-Room and Executive Flats`, `Condominiums and Other Apartments`, `Landed Properties`, `Subzone_pop` ,`SHAPE_Area`) %>%
  mutate(`Pop_density`=`Subzone_pop`/`SHAPE_Area`)

Calculating the total count for each variable without geometry:

residential_mpsz <- residential_mpsz %>%
  group_by(SZ) %>%
  summarise (`YOUNG` = sum(`YOUNG`), `ECONOMY ACTIVE` = sum(`ECONOMY ACTIVE`), `AGED` = sum(`AGED`), `HDB 1- and 2-Room Flats` = sum(`HDB 1- and 2-Room Flats`),`HDB 3- and 4-Room Flats` = sum(`HDB 3- and 4-Room Flats`),`HDB 5-Room and Executive Flats` = sum(`HDB 5-Room and Executive Flats`), `Condominiums and Other Apartments` = sum(`Condominiums and Other Apartments`),`Landed Properties` = sum(`Landed Properties`), `Pop_density` = unique(`Pop_density`), `Subzone_pop` = unique(`Subzone_pop`))

Removing the subzones with population = 0, such as areas like Yio Chu Kang North:

residential_mpsz <- filter(residential_mpsz, `Subzone_pop`> 0)

Creating one with geometry data:

geo_residential_mpsz <- residential_mpsz_total %>% 
  select(`PA`,`SZ`,`YOUNG`,`ECONOMY ACTIVE`,`AGED`,`HDB 1- and 2-Room Flats`, `HDB 3- and 4-Room Flats`, `HDB 5-Room and Executive Flats`, `Condominiums and Other Apartments`, `Landed Properties`, `Subzone_pop` ,`SHAPE_Area`, `geometry`) %>%
  mutate(`Pop_density`=`Subzone_pop`/`SHAPE_Area`)

Creating the sum for the one with geometry data:

sum_geo_residential_mpsz <- geo_residential_mpsz %>%
  group_by(SZ, PA) %>%
  summarise (`YOUNG` = sum(`YOUNG`), `ECONOMY ACTIVE` = sum(`ECONOMY ACTIVE`), `AGED` = sum(`AGED`), `HDB 1- and 2-Room Flats` = sum(`HDB 1- and 2-Room Flats`),`HDB 3- and 4-Room Flats` = sum(`HDB 3- and 4-Room Flats`),`HDB 5-Room and Executive Flats` = sum(`HDB 5-Room and Executive Flats`), `Condominiums and Other Apartments` = sum(`Condominiums and Other Apartments`),`Landed Properties` = sum(`Landed Properties`), `Subzone_pop` = unique(`Subzone_pop`), `Pop_density` = unique(`Pop_density`), `SHAPE_Area` = unique(`SHAPE_Area`), `geometry` = unique(`geometry`))

sum_geo_residential_mpsz <- filter(sum_geo_residential_mpsz, `Subzone_pop`> 0)

Import the 5 geospatial datasets required:

govtembassy <- st_read(dsn="data/geospatial",layer="Govt_Embassy")

## Reading layer `Govt_Embassy' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 443 features and 5 fields
## geometry type:  POINT
## dimension:      XY
## bbox:           xmin: 103.6282 ymin: 1.24911 xmax: 103.9884 ymax: 1.45765
## CRS:            4326

business <- st_read(dsn="data/geospatial",layer="Business")

## Reading layer `Business' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 6550 features and 5 fields
## geometry type:  POINT
## dimension:      XY
## bbox:           xmin: 103.6147 ymin: 1.24605 xmax: 104.0044 ymax: 1.4698
## CRS:            4326

shopping <- st_read(dsn="data/geospatial",layer="Shopping")

## Reading layer `Shopping' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 511 features and 5 fields
## geometry type:  POINT
## dimension:      XY
## bbox:           xmin: 103.679 ymin: 1.24779 xmax: 103.9644 ymax: 1.4535
## CRS:            4326

financial <- st_read(dsn="data/geospatial",layer="Financial")

## Reading layer `Financial' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 3320 features and 29 fields
## geometry type:  POINT
## dimension:      XY
## bbox:           xmin: 103.6256 ymin: 1.24392 xmax: 103.9998 ymax: 1.46247
## CRS:            4326

upmarket_residential_area <- st_read(dsn="data/geospatial",layer="Private residential")

## Reading layer `Private residential' from data source `/Users/danstongoh/Desktop/SMU/Term 3A/Geospatial/Take Home Exercises/IS415_Take-Home_Ex03/data/geospatial' using driver `ESRI Shapefile'
## Simple feature collection with 3604 features and 5 fields
## geometry type:  POINT
## dimension:      XY
## bbox:           xmin: 103.6295 ymin: 1.23943 xmax: 103.9749 ymax: 1.45379
## CRS:            4326

Extracting the industry data from business data:

industry <- business %>% 
  filter(FAC_TYPE == 9991)
business <- business %>%
  filter(FAC_TYPE == 5000)

Before joining the industry urban functions with mpsz, check the CRS of mpsz first:

st_crs(mpsz)

## Coordinate Reference System:
##   No user input
##   wkt:
## PROJCS["SVY21",
##     GEOGCS["SVY21[WGS84]",
##         DATUM["WGS_1984",
##             SPHEROID["WGS_84",6378137.0,298.257223563]],
##         PRIMEM["Greenwich",0.0],
##         UNIT["Degree",0.0174532925199433]],
##     PROJECTION["Transverse_Mercator"],
##     PARAMETER["False_Easting",28001.642],
##     PARAMETER["False_Northing",38744.572],
##     PARAMETER["Central_Meridian",103.8333333333333],
##     PARAMETER["Scale_Factor",1.0],
##     PARAMETER["Latitude_Of_Origin",1.366666666666667],
##     UNIT["Meter",1.0]]

Since the crs of mpsz is in SVY21, it is necessary to transform it to EPSG 4326 for data join:

mpsz_4326 <- st_transform(mpsz, 4326)

After transforming, check again to see if it is successfully transformed:

st_crs(mpsz_4326)

## Coordinate Reference System:
##   User input: EPSG:4326 
##   wkt:
## GEOGCS["WGS 84",
##     DATUM["WGS_1984",
##         SPHEROID["WGS 84",6378137,298.257223563,
##             AUTHORITY["EPSG","7030"]],
##         AUTHORITY["EPSG","6326"]],
##     PRIMEM["Greenwich",0,
##         AUTHORITY["EPSG","8901"]],
##     UNIT["degree",0.0174532925199433,
##         AUTHORITY["EPSG","9122"]],
##     AUTHORITY["EPSG","4326"]]

Filter the unique POI_ID from each urban function to ensure data accuracy since there may be duplicates:

govtembassy <- govtembassy %>% 
  filter(SEQ_NUM==1) %>% 
  count(POI_ID)

business <- business %>% 
  filter(SEQ_NUM==1) %>% 
  count(POI_ID)

shopping <- shopping %>% 
  filter(SEQ_NUM==1) %>%
  count(POI_ID)

financial <- financial %>% 
  filter(SEQ_NUM==1) %>% 
  count(POI_ID)

upmarket_residential_area <- upmarket_residential_area %>% 
  filter(SEQ_NUM==1) %>% 
  count(POI_ID)

industry <- industry %>% 
  filter(SEQ_NUM==1) %>% 
  count(POI_ID)

Combine the urban functions to the mpsz data:

mpsz_govt <- st_join(mpsz_4326, govtembassy)
mpsz_business <- st_join(mpsz_4326, business)
mpsz_industry <- st_join(mpsz_4326, industry)
mpsz_shopping <- st_join(mpsz_4326, shopping)
mpsz_financial <- st_join(mpsz_4326, financial)
mpsz_URA <- st_join(mpsz_4326, upmarket_residential_area)

Determining the number of each urban development type by subzone level by getting the sum of the number of each urban development in a subzone:

govt_count <- mpsz_govt %>%
  group_by(SUBZONE_N) %>%
  summarise(total_govt = sum(!is.na(n)))

govt_count <- filter(govt_count, total_govt>0)

business_count <- mpsz_business %>%
  group_by(SUBZONE_N) %>%
  summarise(total_business = sum(!is.na(n)))

business_count <- filter(business_count, total_business>0)

industry_count <- mpsz_industry %>%
  group_by(SUBZONE_N) %>%
  summarise(total_industry = sum(!is.na(n)))

industry_count <- filter(industry_count, total_industry>0)

shopping_count <- mpsz_shopping %>%
  group_by(SUBZONE_N) %>%
  summarise(total_shopping = sum(!is.na(n)))

shopping_count <- filter(shopping_count, total_shopping>0)

financial_count <- mpsz_financial %>%
  group_by(SUBZONE_N) %>%
  summarise(total_financial = sum(!is.na(n)))

financial_count <- filter(financial_count, total_financial>0)

URA_count <- mpsz_URA %>%
  group_by(SUBZONE_N) %>%
  summarise(total_URA = sum(!is.na(n)))

URA_count <- filter(URA_count, total_URA>0)

5.0 Geospatial Analysis

Part A: Delineate social areas using hierarchical clustering technique

5.1 Exploratory Data Analysis (EDA)

5.1.1 EDA using statistical graphics

economy_active <- ggplot(data=residential_mpsz, 
             aes(x= `ECONOMY ACTIVE`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

young <- ggplot(data=residential_mpsz, 
             aes(x= `YOUNG`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

aged <- ggplot(data=residential_mpsz, 
             aes(x= `AGED`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

hdb1_2 <- ggplot(data=residential_mpsz, 
             aes(x= `HDB 1- and 2-Room Flats`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

hdb3_4 <- ggplot(data=residential_mpsz, 
             aes(x= `HDB 3- and 4-Room Flats`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

hdb5 <- ggplot(data=residential_mpsz, 
             aes(x= `HDB 5-Room and Executive Flats`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

condo <- ggplot(data=residential_mpsz, 
             aes(x= `Condominiums and Other Apartments`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

landed <- ggplot(data=residential_mpsz, 
             aes(x= `Landed Properties`)) +
  geom_histogram(bins=20, 
                 color="black", 
                 fill="light blue")

Grouping these histograms together visually:

ggarrange(economy_active, young, aged, hdb1_2, hdb3_4, hdb5, condo, landed, 
          ncol = 3, 
          nrow = 2)

## $`1`

## 
## $`2`

## 
## attr(,"class")
## [1] "list"      "ggarrange"

Analysis: In the figure above, multiple histograms are plottted to reveal the distribution of the selected variables in the residential_mpsz data frame. As observed, the distribution of the graphs are mostly right skewed. Thus, standardization will be necessary. However, the z-score method should not be used as the requirement of this method is that the initial distribution should be normally distributed first.

5.1.2 Correlation Analysis

Initial:

cluster_vars.cor = cor(residential_mpsz[,c(3:10)])
corrplot.mixed(cluster_vars.cor,
         lower = "ellipse", 
               upper = "number",
               tl.pos = "lt",
               diag = "l",
               tl.col = "black")

Given the correlation plot above, it shows that:

• YOUNG and ECONOMY ACTIVE (0.98)
• YOUNG and AGED (0.80)
• YOUNG and HDB 3- and 4- Room Flats (0.89)
• YOUNG and HDB 5-Room and Executive Flats (0.91)
• ECONOMY ACTIVE and AGED (0.89)
• ECONOMY ACTIVE and HDB 3- and 4- Room Flats (0.94)
• ECONOMY ACTIVE and HDB 5- Room and Executive Flats (0.89)
• AGED and HDB 3- and 4- Room Flats (0.89)

Analysis: These variables are highly correlated (>0.80) as seen from the correlation score indicated above. Therefore, it is necessary to remove some of the variables for a more accurate depiction. As “YOUNG” and “ECONOMY ACTIVE” both have 4 occurrences each, one will be eliminated instead, which in this case will be “YOUNG”. As for “HDB 3- and 4- Room Flats”, the occurrence is equally high as “AGED”. However, it will be more accurate to remove “HDB 3- and 4- Room Flats” since it causes more variables to have higher correlation.

Eliminating the highly correlated variables:

cluster_vars.cor = cor(residential_mpsz[,c(5,6, 8:10)])
corrplot.mixed(cluster_vars.cor,
         lower = "ellipse", 
               upper = "number",
               tl.pos = "lt",
               diag = "l",
               tl.col = "black")

Given the correlation plot above, it shows that:

Analysis: The highly correlated variables are eliminated, making the correlation score for the variables shown to be less than 0.80, which is a benchmark to indicate that the variables are highly correlated. Thus, we will extract the clustering variables for further analysis later.

5.2 Hierarchy Cluster Analysis

5.2.1 Extracting Clustering Variables

cluster_vars <- residential_mpsz %>%
  select("SZ", "AGED", "Pop_density", "HDB 1- and 2-Room Flats","HDB 5-Room and Executive Flats","Condominiums and Other Apartments","Landed Properties")
head(cluster_vars,10)

## # A tibble: 10 x 7
##    SZ     AGED Pop_density `HDB 1- and 2-R… `HDB 5-Room and… `Condominiums a…
##    <chr> <dbl>       <dbl>            <dbl>            <dbl>            <dbl>
##  1 ADMI…  1360     0.0112              1140             6220                0
##  2 ALEX…  3310     0.0134              3910             3120                0
##  3 ALEX…   120     0.00722                0                0             2120
##  4 ALJU…  7510     0.0136              2120             6400            11930
##  5 ANAK…  3850     0.00804              160             3170             9020
##  6 ANCH…  3620     0.0311              1680            22650             5000
##  7 ANG …   740     0.0154                 0             1830             1930
##  8 BALE…  6090     0.0170              1790             4660             9610
##  9 BANG…  3550     0.0296                 0             5370             2290
## 10 BAYS…   930     0.00289                0                0             6800
## # … with 1 more variable: `Landed Properties` <dbl>

Notice that the final clustering variables list does not include variables ‘YOUNG’, ‘ECONOMY ACTIVE’ and ‘HDB 3- and 4- Room Flats’ because they are highly correlated with other variables.

Next, we will have to change the rows by subzone names instead.

row.names(cluster_vars) <- cluster_vars$"SZ"
head(cluster_vars,10)

## # A tibble: 10 x 7
##    SZ     AGED Pop_density `HDB 1- and 2-R… `HDB 5-Room and… `Condominiums a…
##    <chr> <dbl>       <dbl>            <dbl>            <dbl>            <dbl>
##  1 ADMI…  1360     0.0112              1140             6220                0
##  2 ALEX…  3310     0.0134              3910             3120                0
##  3 ALEX…   120     0.00722                0                0             2120
##  4 ALJU…  7510     0.0136              2120             6400            11930
##  5 ANAK…  3850     0.00804              160             3170             9020
##  6 ANCH…  3620     0.0311              1680            22650             5000
##  7 ANG …   740     0.0154                 0             1830             1930
##  8 BALE…  6090     0.0170              1790             4660             9610
##  9 BANG…  3550     0.0296                 0             5370             2290
## 10 BAYS…   930     0.00289                0                0             6800
## # … with 1 more variable: `Landed Properties` <dbl>

Removal of SZ column from the table above:

resident_2019_ict <- select(cluster_vars, c(2:7))
head(resident_2019_ict,10)

## # A tibble: 10 x 6
##     AGED Pop_density `HDB 1- and 2-R… `HDB 5-Room and… `Condominiums a…
##    <dbl>       <dbl>            <dbl>            <dbl>            <dbl>
##  1  1360     0.0112              1140             6220                0
##  2  3310     0.0134              3910             3120                0
##  3   120     0.00722                0                0             2120
##  4  7510     0.0136              2120             6400            11930
##  5  3850     0.00804              160             3170             9020
##  6  3620     0.0311              1680            22650             5000
##  7   740     0.0154                 0             1830             1930
##  8  6090     0.0170              1790             4660             9610
##  9  3550     0.0296                 0             5370             2290
## 10   930     0.00289                0                0             6800
## # … with 1 more variable: `Landed Properties` <dbl>

5.2.2 Data Standardisation

Min-Max Standardisation

resident_2019_ict.std <- normalize(resident_2019_ict)
summary(resident_2019_ict.std)

##       AGED          Pop_density     HDB 1- and 2-Room Flats
##  Min.   :0.00000   Min.   :0.0000   Min.   :0.0000         
##  1st Qu.:0.02505   1st Qu.:0.0881   1st Qu.:0.0000         
##  Median :0.10101   Median :0.2603   Median :0.0000         
##  Mean   :0.13217   Mean   :0.3217   Mean   :0.1592         
##  3rd Qu.:0.18810   3rd Qu.:0.5299   3rd Qu.:0.2745         
##  Max.   :1.00000   Max.   :1.0000   Max.   :1.0000         
##  HDB 5-Room and Executive Flats Condominiums and Other Apartments
##  Min.   :0.00000                Min.   :0.000000                 
##  1st Qu.:0.00000                1st Qu.:0.003131                 
##  Median :0.03857                Median :0.076625                 
##  Mean   :0.09490                Mean   :0.150378                 
##  3rd Qu.:0.11864                3rd Qu.:0.240161                 
##  Max.   :1.00000                Max.   :1.000000                 
##  Landed Properties
##  Min.   :0.00000  
##  1st Qu.:0.00000  
##  Median :0.00000  
##  Mean   :0.05676  
##  3rd Qu.:0.04716  
##  Max.   :1.00000

5.2.3 Computing proximity matrix

residential_proxmat <- dist(resident_2019_ict.std, method = 'euclidean')

5.2.4 Selecting the optimal clustering algorithm

m <- c( "average", "single", "complete", "ward")
names(m) <- c( "average", "single", "complete", "ward")

ac <- function(x) {
  agnes(resident_2019_ict, method = x)$ac
}

map_dbl(m, ac)

##   average    single  complete      ward 
## 0.9442788 0.8870851 0.9686369 0.9863490

5.2.5 Computing hierarchical clustering

hclust_ward <- hclust(residential_proxmat, method = 'ward.D')

Determining the optimal cluster

fviz_nbclust(resident_2019_ict.std, FUN=hcut, method="silhouette")

As seen from the graph above, the optimal number of clusters has been computer as k=5. This allows us to determine the figure k=5 for subsequent analysis, which means that we will analyse accordingly to 5 clusters for the choropleth map.

Interpreting the dendrograms

plot(hclust_ward, cex = 0.6)
rect.hclust(hclust_ward, k = 5, border = 2:6)

5.3 Visualizing the output

Transfrom the data frame in to a matrix to illustrate through the heatmap:

resident_2019_ict_mat <- data.matrix(resident_2019_ict)

Plotting interactive cluster heatmap using heatmaply():

heatmaply(resident_2019_ict_mat,
          Colv=NA,
          dist_method = "euclidean",
          hclust_method = "ward.D",
          seriate = "OLO",
          colors = Blues,
          k_row = 5,
          margins = c(NA,200,60,NA),
          fontsize_row = 4,
          fontsize_col = 5,
          main="Geographic Segmentation of Subzones by indicators",
          xlab = "Indicators",
          ylab = "Planning Subzones"
          )

Plotting the cluster maps:

groups <- as.factor(cutree(hclust_ward, k=5))

Conversion to SF object:

sum_geo_residential_mpsz_sf <- st_as_sf(sum_geo_residential_mpsz)

Check for Projection:

st_crs (sum_geo_residential_mpsz_sf)

## Coordinate Reference System: NA

Set Projection:

sum_geo_residential_mpsz_sf <- st_set_crs(sum_geo_residential_mpsz_sf, 3414)

Next, check for the projection:

st_crs(sum_geo_residential_mpsz_sf)

## Coordinate Reference System:
##   User input: EPSG:3414 
##   wkt:
## PROJCS["SVY21 / Singapore TM",
##     GEOGCS["SVY21",
##         DATUM["SVY21",
##             SPHEROID["WGS 84",6378137,298.257223563,
##                 AUTHORITY["EPSG","7030"]],
##             AUTHORITY["EPSG","6757"]],
##         PRIMEM["Greenwich",0,
##             AUTHORITY["EPSG","8901"]],
##         UNIT["degree",0.0174532925199433,
##             AUTHORITY["EPSG","9122"]],
##         AUTHORITY["EPSG","4757"]],
##     PROJECTION["Transverse_Mercator"],
##     PARAMETER["latitude_of_origin",1.366666666666667],
##     PARAMETER["central_meridian",103.8333333333333],
##     PARAMETER["scale_factor",1],
##     PARAMETER["false_easting",28001.642],
##     PARAMETER["false_northing",38744.572],
##     UNIT["metre",1,
##         AUTHORITY["EPSG","9001"]],
##     AUTHORITY["EPSG","3414"]]

resident_2019_sf_cluster <- cbind(sum_geo_residential_mpsz_sf, as.matrix(groups)) %>%
  rename(`CLUSTER`=`as.matrix.groups.`)

qtm(resident_2019_sf_cluster, "CLUSTER")

Part B: Delineate social areas using spatially constrained clustering technique and describe the analysis result

6.0 Spatially Constrained Clustering - SKATER approach

6.1 Converting into SpatialPolygonsDataFrame

resident_sp <- as_Spatial(sum_geo_residential_mpsz_sf)

6.2 Computing Neighbour List

resident.nb <- poly2nb(resident_sp)
summary(resident.nb)

## Neighbour list object:
## Number of regions: 234 
## Number of nonzero links: 1198 
## Percentage nonzero weights: 2.187888 
## Average number of links: 5.119658 
## Link number distribution:
## 
##  1  2  3  4  5  6  7  8  9 
##  4 10 25 36 69 41 33 11  5 
## 4 least connected regions:
## 34 105 134 174 with 1 link
## 5 most connected regions:
## 16 21 36 103 117 with 9 links

plot(resident_sp, border=grey(.5))
plot(resident.nb, coordinates(resident_sp), col="blue", add=TRUE)

6.3 Computing minimum spanning tree

6.3.1 Calculating edge costs

lcosts <- nbcosts(resident.nb, resident_2019_ict)

resident.w <- nb2listw(resident.nb, lcosts, style="B")
summary(resident.w)

## Characteristics of weights list object:
## Neighbour list object:
## Number of regions: 234 
## Number of nonzero links: 1198 
## Percentage nonzero weights: 2.187888 
## Average number of links: 5.119658 
## Link number distribution:
## 
##  1  2  3  4  5  6  7  8  9 
##  4 10 25 36 69 41 33 11  5 
## 4 least connected regions:
## 34 105 134 174 with 1 link
## 5 most connected regions:
## 16 21 36 103 117 with 9 links
## 
## Weights style: B 
## Weights constants summary:
##     n    nn      S0           S1           S2
## B 234 54756 9043408 262731206400 2.560782e+12

6.3.2 Computing minimum spanning tree

resident.mst <- mstree(resident.w)

class(resident.mst)

## [1] "mst"    "matrix"

plot(resident_sp, border=gray(.5))
plot.mst(resident.mst, coordinates(resident_sp), 
     col="blue", cex.lab=0.7, cex.circles=0.005, add=TRUE)

6.4 Computing spatially constrained clusters using SKATER method

clust5 <- skater(resident.mst[,1:2], resident_2019_ict, 4)

str(clust5)

## List of 8
##  $ groups      : num [1:234] 1 3 3 1 3 2 1 3 4 1 ...
##  $ edges.groups:List of 5
##   ..$ :List of 3
##   .. ..$ node: num [1:86] 143 1 145 166 67 168 228 112 97 180 ...
##   .. ..$ edge: num [1:85, 1:3] 1 166 67 168 228 97 98 128 180 165 ...
##   .. ..$ ssw : num 678039
##   ..$ :List of 3
##   .. ..$ node: num [1:4] 6 171 154 159
##   .. ..$ edge: num [1:3, 1:3] 6 154 171 171 159 ...
##   .. ..$ ssw : num 14097
##   ..$ :List of 3
##   .. ..$ node: num [1:109] 185 181 68 75 194 137 39 200 57 156 ...
##   .. ..$ edge: num [1:108, 1:3] 158 210 193 50 21 76 5 90 54 21 ...
##   .. ..$ ssw : num 336728
##   ..$ :List of 3
##   .. ..$ node: num [1:33] 27 69 78 23 28 19 172 198 234 95 ...
##   .. ..$ edge: num [1:32, 1:3] 19 234 150 95 69 198 216 41 172 19 ...
##   .. ..$ ssw : num 219752
##   ..$ :List of 3
##   .. ..$ node: num [1:2] 144 190
##   .. ..$ edge: num [1, 1:3] 144 190 21956
##   .. ..$ ssw : num 21956
##  $ not.prune   : NULL
##  $ candidates  : int [1:5] 1 2 3 4 5
##  $ ssto        : num 1623978
##  $ ssw         : num [1:5] 1623978 1514554 1428910 1329531 1270571
##  $ crit        : num [1:2] 1 Inf
##  $ vec.crit    : num [1:234] 1 1 1 1 1 1 1 1 1 1 ...
##  - attr(*, "class")= chr "skater"

ccs5 <- clust5$groups
ccs5

##   [1] 1 3 3 1 3 2 1 3 4 1 1 1 1 3 3 1 3 3 4 3 3 3 4 3 4 4 4 4 3 3 3 3 3 1 1 3 1
##  [38] 3 3 4 4 1 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 4 3 3 1 1 3 1 3 1 3 4 3 4 3 3 3
##  [75] 3 3 4 4 1 1 1 3 4 1 4 4 1 3 3 3 3 1 1 1 4 1 1 1 3 1 4 3 3 3 4 3 3 1 1 1 1
## [112] 1 3 1 3 1 3 1 3 1 1 3 1 3 3 3 3 1 3 3 3 1 3 1 1 1 3 3 3 3 3 3 1 5 1 1 3 3
## [149] 3 4 3 3 3 2 1 3 3 3 2 3 4 3 1 1 1 1 1 1 1 1 2 4 3 3 1 1 1 1 1 1 3 3 1 3 3
## [186] 3 1 1 4 5 1 1 3 3 3 1 4 4 3 3 3 3 3 3 3 4 1 1 1 3 3 1 1 3 1 4 3 4 1 1 1 1
## [223] 3 1 4 1 1 1 1 1 1 4 4 4

table(ccs5)

## ccs5
##   1   2   3   4   5 
##  86   4 109  33   2

plot(resident_sp, border=gray(.5))
plot(clust5, coordinates(resident_sp), cex.lab=.7,
     groups.colors=c("red","green","blue", "brown", "pink"), cex.circles=0.005, add=TRUE)

6.5 Visualising the clusters in choropleth map

groups_mat <- as.matrix(clust5$groups)
resident_2019_sf_spatialcluster <- cbind(resident_2019_sf_cluster, as.factor(groups_mat)) %>%
  rename(`SP_CLUSTER`=`as.factor.groups_mat.`)
qtm(resident_2019_sf_spatialcluster, "SP_CLUSTER")

In order to join both the industry_count and the resident_2019_sf_spatialcluster together, it is necessary to ensure that they have the same CRS. Thus, we have to convert the CRS of resident_2019_sf_spatialcluster.

resident_2019_sf_spatialcluster <- st_transform(resident_2019_sf_spatialcluster, 4326)

6.5.1 Urban Function 1: Industry and Residents

industry_residents <- st_join(resident_2019_sf_spatialcluster, industry_count, left = TRUE)

SP_Cluster 1:

industry_cluster1 <- industry_residents %>%
  filter(SP_CLUSTER == 1)
summary(industry_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:170         Length:170         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2030   1st Qu.: 4630  
##  Mode  :character   Mode  :character   Median : 5910   Median :14540  
##                                        Mean   : 6181   Mean   :14409  
##                                        3rd Qu.: 8380   3rd Qu.:20910  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0          
##  1st Qu.: 1180   1st Qu.:   0            1st Qu.:    0          
##  Median : 3175   Median : 110            Median :11360          
##  Mean   : 3754   Mean   :1029            Mean   :12106          
##  3rd Qu.: 5720   3rd Qu.:1688            3rd Qu.:17380          
##  Max.   :16050   Max.   :4700            Max.   :56850          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:    0                  1st Qu.:    0                    
##  Median : 3210                  Median : 1850                    
##  Mean   : 5391                  Mean   : 3517                    
##  3rd Qu.: 8680                  3rd Qu.: 6108                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.: 8040   1st Qu.:5.281e-03   1st Qu.:1262089  
##  Median :  490     Median :24945   Median :1.340e-02   Median :1878092  
##  Mean   : 2053     Mean   :24344   Mean   :1.366e-02   Mean   :2197114  
##  3rd Qu.: 3185     3rd Qu.:35520   3rd Qu.:2.154e-02   3rd Qu.:2809788  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER        SUBZONE_N   total_industry           geometry  
##  1:43    1:170      GEYLANG EAST:  9   Min.   :1.000   MULTIPOLYGON :170  
##  2: 8    2:  0      CHONG BOON  :  8   1st Qu.:1.000   epsg:4326    :  0  
##  3:52    3:  0      KAMPONG UBI :  8   Median :1.000   +proj=long...:  0  
##  4:36    4:  0      KEMBANGAN   :  7   Mean   :1.914                      
##  5:31    5:  0      ALJUNIED    :  6   3rd Qu.:2.000                      
##                     (Other)     :113   Max.   :5.000                      
##                     NA's        : 19   NA's   :19

SP_Cluster 2:

industry_cluster2 <- industry_residents %>%
  filter(SP_CLUSTER == 2)
summary(industry_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:4           Length:4           Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15768   1st Qu.:28235  
##  Mode  :character   Mode  :character   Median :16870   Median :32185  
##                                        Mean   :16838   Mean   :32382  
##                                        3rd Qu.:17940   3rd Qu.:36332  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4265   1st Qu.: 855            1st Qu.:16412          
##  Median :5180   Median :1330            Median :19635          
##  Mean   :5102   Mean   :1198            Mean   :19468          
##  3rd Qu.:6018   3rd Qu.:1672            3rd Qu.:22690          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:26820                  1st Qu.:4678                     
##  Median :28295                  Median :5205                     
##  Mean   :27865                  Mean   :5550                     
##  3rd Qu.:29340                  3rd Qu.:6078                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0       Min.   :46610   Min.   :0.03109   Min.   :1378710   1:0    
##  1st Qu.:  0       1st Qu.:48268   1st Qu.:0.03433   1st Qu.:1436308   2:0    
##  Median :125       Median :54510   Median :0.03689   Median :1477308   3:0    
##  Mean   :125       Mean   :54322   Mean   :0.03681   Mean   :1475590   4:4    
##  3rd Qu.:250       3rd Qu.:60565   3rd Qu.:0.03937   3rd Qu.:1516590   5:0    
##  Max.   :250       Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER                    SUBZONE_N total_industry          geometry
##  1:0        PASIR RIS WAFER FAB PARK:2   Min.   :3      MULTIPOLYGON :4  
##  2:4        ADMIRALTY               :0   1st Qu.:3      epsg:4326    :0  
##  3:0        AIRPORT ROAD            :0   Median :3      +proj=long...:0  
##  4:0        ALEXANDRA HILL          :0   Mean   :3                       
##  5:0        ALEXANDRA NORTH         :0   3rd Qu.:3                       
##             (Other)                 :0   Max.   :3                       
##             NA's                    :2   NA's   :2

SP_Cluster 3:

industry_cluster3 <- industry_residents %>%
  filter(SP_CLUSTER == 3)
summary(industry_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:129         Length:129         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 310   1st Qu.:  830  
##  Mode  :character   Mode  :character   Median :1510   Median : 3450  
##                                        Mean   :1709   Mean   : 4275  
##                                        3rd Qu.:2420   3rd Qu.: 6750  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 260   1st Qu.:   0.0          1st Qu.:    0          
##  Median :1020   Median :   0.0          Median :  610          
##  Mean   :1472   Mean   : 629.8          Mean   : 3475          
##  3rd Qu.:2550   3rd Qu.:1010.0          3rd Qu.: 7180          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0                   Min.   :    0                    
##  1st Qu.:   0                   1st Qu.:   30                    
##  Median :   0                   Median :  690                    
##  Mean   :1048                   Mean   : 1645                    
##  3rd Qu.:2030                   3rd Qu.: 2260                    
##  Max.   :7810                   Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.: 1450   1st Qu.:2.975e-03   1st Qu.: 368483  
##  Median :   0.0    Median : 6420   Median :8.037e-03   Median : 595429  
##  Mean   : 574.5    Mean   : 7456   Mean   :1.128e-02   Mean   : 943009  
##  3rd Qu.: 550.0    3rd Qu.:11720   3rd Qu.:1.827e-02   3rd Qu.:1053494  
##  Max.   :7600.0    Max.   :37090   Max.   :4.399e-02   Max.   :7601894  
##                                                                         
##  CLUSTER SP_CLUSTER          SUBZONE_N  total_industry           geometry  
##  1:43    1:  0      ALEXANDRA HILL: 8   Min.   :1.000   MULTIPOLYGON :129  
##  2: 7    2:  0      BUKIT MERAH   : 8   1st Qu.:1.000   epsg:4326    :  0  
##  3:66    3:129      ONE NORTH     : 8   Median :2.000   +proj=long...:  0  
##  4: 2    4:  0      HOLLAND DRIVE : 7   Mean   :1.985                      
##  5:11    5:  0      CITY TERMINALS: 6   3rd Qu.:2.500                      
##                     (Other)       :30   Max.   :5.000                      
##                     NA's          :62   NA's   :62

SP_Cluster 4:

industry_cluster4 <- industry_residents %>%
  filter(SP_CLUSTER == 4)
summary(industry_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:40          Length:40          Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 3218   1st Qu.: 7950  
##  Mode  :character   Mode  :character   Median : 5005   Median :11690  
##                                        Mean   : 6169   Mean   :13368  
##                                        3rd Qu.: 8482   3rd Qu.:17830  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1460   1st Qu.:   0.0          1st Qu.: 5862          
##  Median :2325   Median :   0.0          Median :10540          
##  Mean   :2656   Mean   : 561.5          Mean   :11215          
##  3rd Qu.:3650   3rd Qu.: 880.0          3rd Qu.:15722          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 3515                  1st Qu.:   0                     
##  Median : 6300                  Median : 985                     
##  Mean   : 8207                  Mean   :1786                     
##  3rd Qu.:11390                  3rd Qu.:2748                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:13028   1st Qu.:0.007734   1st Qu.:  772903  
##  Median :   0.0    Median :19955   Median :0.025999   Median : 1043336  
##  Mean   : 295.2    Mean   :22193   Mean   :0.021867   Mean   : 8467049  
##  3rd Qu.:   0.0    3rd Qu.:30160   3rd Qu.:0.032726   3rd Qu.: 1848651  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                       SUBZONE_N  total_industry 
##  1:20    1: 0       GALI BATU                  : 6   Min.   :1.000  
##  2: 1    2: 0       BUKIT BATOK SOUTH          : 5   1st Qu.:1.000  
##  3:13    3: 0       INTERNATIONAL BUSINESS PARK: 4   Median :1.000  
##  4: 5    4:40       KIAN TECK                  : 3   Mean   :1.731  
##  5: 1    5: 0       PANG SUA                   : 2   3rd Qu.:2.000  
##                     (Other)                    : 6   Max.   :4.000  
##                     NA's                       :14   NA's   :14     
##           geometry 
##  MULTIPOLYGON :40  
##  epsg:4326    : 0  
##  +proj=long...: 0  
##                    
##                    
##                    
## 

SP_Cluster 5:

industry_cluster5 <- industry_residents %>%
  filter(SP_CLUSTER == 5)
summary(industry_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:7           Length:7           Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:24990   1st Qu.:56430  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :28963   Mean   :66437  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.:12670   1st Qu.:2565            1st Qu.:48590          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :15323   Mean   :3309            Mean   :59909          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:39230                  1st Qu.:3495                     
##  Median :47960                  Median :5220                     
##  Mean   :42971                  Mean   :4234                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1:0    
##  1st Qu.:0         1st Qu.: 94090   1st Qu.:0.03062   1st Qu.:2989747   2:0    
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3:0    
##  Mean   :0         Mean   :110723   Mean   :0.03151   Mean   :3568351   4:7    
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03217   3rd Qu.:4339824   5:0    
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER         SUBZONE_N total_industry           geometry
##  1:0        FLORA DRIVE  :2   Min.   :1.000   MULTIPOLYGON :7  
##  2:0        CHANGI WEST  :1   1st Qu.:1.000   epsg:4326    :0  
##  3:0        LOYANG WEST  :1   Median :1.000   +proj=long...:0  
##  4:0        SIMEI        :1   Mean   :1.571                    
##  5:7        TAMPINES WEST:1   3rd Qu.:1.500                    
##             XILIN        :1   Max.   :4.000                    
##             (Other)      :0

tmap_mode("view")

Plotting the tmap for the total industry count on the SP clusters derived earlier.

tm_shape(industry_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_industry", col= "total_industry", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more industry counts:

Highest Industry Count to Lowest Industry Count

• Cluster 1 (170)
• Cluster 3 (129)
• Cluster 4 (40)
• Cluster 5 (7)
• Cluster 2 (4)

Key Highlights:

Highest: Cluster 1

Based on the industry count, Cluster 1 has the highest number of industries found, which stretches from the East of Singapore to the North side of Singapore. We can tell that there are more industries in the East side than the North, given that there is a stronger tone of red as depicted on the plot. Despite Cluster 1 having about 30% higher in space area than what Cluster 2 has, Cluster 2 has a population density (mean) of almost 3 times of that of Cluster 1, which makes Cluster 1 less dense in population, thus, making it more possible to hold more industries in the subzones included.

Lowest: Cluster 2

As for Cluster 2, it is located in the North-East area of Singapore at the Sengkang Area. It has a higher population density as compared to cluster 1, having a high amount of subzone population over a smaller area space. Given that the residents count is pretty high as compared to cluster 1, there is little space left for industries to be built, as the spaces are used to build residential buildings, making the industry count much lesser than Cluster 1.

tmap_mode("plot")

6.5.2 Urban Function 2: Business and Residents

business_residents <- st_join(resident_2019_sf_spatialcluster, business_count, left = TRUE)

SP_Cluster 1:

business_cluster1 <- business_residents %>%
  filter(SP_CLUSTER == 1)
summary(business_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:411         Length:411         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2410   1st Qu.: 5245  
##  Mode  :character   Mode  :character   Median : 6130   Median :14530  
##                                        Mean   : 6350   Mean   :14587  
##                                        3rd Qu.: 8350   3rd Qu.:20600  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0          
##  1st Qu.: 1310   1st Qu.:   0            1st Qu.:  370          
##  Median : 3230   Median : 250            Median :11330          
##  Mean   : 3707   Mean   : 963            Mean   :11863          
##  3rd Qu.: 5720   3rd Qu.:1525            3rd Qu.:16520          
##  Max.   :16050   Max.   :4700            Max.   :56850          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:    0                  1st Qu.:    0                    
##  Median : 3870                  Median : 3050                    
##  Mean   : 5557                  Mean   : 3675                    
##  3rd Qu.: 8900                  3rd Qu.: 6140                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.: 8955   1st Qu.:6.448e-03   1st Qu.:1086103  
##  Median :  460     Median :24950   Median :1.358e-02   Median :1713623  
##  Mean   : 2348     Mean   :24645   Mean   :1.508e-02   Mean   :2041761  
##  3rd Qu.: 3820     3rd Qu.:34240   3rd Qu.:2.296e-02   3rd Qu.:2553464  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER                  SUBZONE_N   total_business  
##  1:131   1:411      BEDOK NORTH           :  9   Min.   :  1.00  
##  2: 12   2:  0      FRANKEL               :  9   1st Qu.:  2.00  
##  3: 94   3:  0      GEYLANG EAST          :  9   Median :  6.00  
##  4: 84   4:  0      SERANGOON GARDEN      :  9   Mean   : 28.71  
##  5: 90   5:  0      ANG MO KIO TOWN CENTRE:  8   3rd Qu.: 28.00  
##                     CHONG BOON            :  8   Max.   :224.00  
##                     (Other)               :359                   
##           geometry  
##  MULTIPOLYGON :411  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 2:

business_cluster2 <- business_residents %>%
  filter(SP_CLUSTER == 2)
summary(business_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:14          Length:14          Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15940   1st Qu.:28400  
##  Mode  :character   Mode  :character   Median :17800   Median :35970  
##                                        Mean   :17024   Mean   :32942  
##                                        3rd Qu.:17800   3rd Qu.:35970  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4480   1st Qu.: 990            1st Qu.:14678          
##  Median :5880   Median :1330            Median :21990          
##  Mean   :5354   Mean   :1216            Mean   :19580          
##  3rd Qu.:6430   3rd Qu.:1670            3rd Qu.:21990          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:28210                  1st Qu.:5000                     
##  Median :28295                  Median :5410                     
##  Mean   :28324                  Mean   :5941                     
##  3rd Qu.:28380                  3rd Qu.:8080                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0.0     Min.   :46610   Min.   :0.03109   Min.   :1378710   1: 0   
##  1st Qu.:  0.0     1st Qu.:48820   1st Qu.:0.03541   1st Qu.:1397910   2: 0   
##  Median :250.0     Median :60200   Median :0.03837   Median :1477308   3: 0   
##  Mean   :142.9     Mean   :55320   Mean   :0.03734   Mean   :1480340   4:14   
##  3rd Qu.:250.0     3rd Qu.:60200   3rd Qu.:0.03837   3rd Qu.:1569035   5: 0   
##  Max.   :250.0     Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER                    SUBZONE_N total_business            geometry 
##  1: 0       COMPASSVALE             :3   Min.   : 1.000   MULTIPOLYGON :14  
##  2:14       PUNGGOL FIELD           :3   1st Qu.: 1.000   epsg:4326    : 0  
##  3: 0       RIVERVALE               :3   Median : 1.000   +proj=long...: 0  
##  4: 0       PASIR RIS WAFER FAB PARK:2   Mean   : 3.214                     
##  5: 0       FERNVALE                :1   3rd Qu.: 5.000                     
##             KANGKAR                 :1   Max.   :10.000                     
##             (Other)                 :1

SP_Cluster 3:

business_cluster3 <- business_residents %>%
  filter(SP_CLUSTER == 3)
summary(business_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:616         Length:616         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 250   1st Qu.:  730  
##  Mode  :character   Mode  :character   Median :1270   Median : 3070  
##                                        Mean   :1607   Mean   : 4032  
##                                        3rd Qu.:2330   3rd Qu.: 6240  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 210   1st Qu.:   0.0          1st Qu.:    0          
##  Median : 870   Median :   0.0          Median :  170          
##  Mean   :1368   Mean   : 631.2          Mean   : 3094          
##  3rd Qu.:2300   3rd Qu.: 660.0          3rd Qu.: 5790          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0.0                 Min.   :    0                    
##  1st Qu.:   0.0                 1st Qu.:  140                    
##  Median :   0.0                 Median :  690                    
##  Mean   : 933.8                 Mean   : 1668                    
##  3rd Qu.:1580.0                 3rd Qu.: 2310                    
##  Max.   :7810.0                 Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.: 1200   1st Qu.:2.672e-03   1st Qu.: 329438  
##  Median :   0.0    Median : 5480   Median :7.413e-03   Median : 587223  
##  Mean   : 590.9    Mean   : 7006   Mean   :1.023e-02   Mean   : 933765  
##  3rd Qu.: 550.0    3rd Qu.:10760   3rd Qu.:1.530e-02   3rd Qu.:1074241  
##  Max.   :7600.0    Max.   :37090   Max.   :4.399e-02   Max.   :7601894  
##                                                                         
##  CLUSTER SP_CLUSTER          SUBZONE_N   total_business            geometry  
##  1:170   1:  0      BOULEVARD     : 10   Min.   :  1.00   MULTIPOLYGON :616  
##  2: 42   2:  0      CHATSWORTH    : 10   1st Qu.:  2.00   epsg:4326    :  0  
##  3:344   3:616      LEEDON PARK   : 10   Median :  5.00   +proj=long...:  0  
##  4: 13   4:  0      MARGARET DRIVE: 10   Mean   : 12.03                      
##  5: 47   5:  0      LEONIE HILL   :  9   3rd Qu.: 13.00                      
##                     NASSIM        :  9   Max.   :191.00                      
##                     (Other)       :558

SP_Cluster 4:

business_cluster4 <- business_residents %>%
  filter(SP_CLUSTER == 4)
summary(business_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:115         Length:115         Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 2760   1st Qu.: 7920  
##  Mode  :character   Mode  :character   Median : 5320   Median :11980  
##                                        Mean   : 6229   Mean   :13566  
##                                        3rd Qu.: 8610   3rd Qu.:18260  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1460   1st Qu.:   0.0          1st Qu.: 5570          
##  Median :2490   Median :   0.0          Median :11150          
##  Mean   :2842   Mean   : 611.7          Mean   :11852          
##  3rd Qu.:3710   3rd Qu.: 950.0          3rd Qu.:16065          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 2570                  1st Qu.:   0                     
##  Median : 6130                  Median : 790                     
##  Mean   : 7920                  Mean   :1807                     
##  3rd Qu.:11720                  3rd Qu.:2630                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:12870   1st Qu.:0.005910   1st Qu.:  788221  
##  Median :   0.0    Median :20450   Median :0.026926   Median : 1097299  
##  Mean   : 338.7    Mean   :22637   Mean   :0.020911   Mean   : 6563137  
##  3rd Qu.:   0.0    3rd Qu.:30660   3rd Qu.:0.032313   3rd Qu.: 2206305  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                   SUBZONE_N  total_business  
##  1:50    1:  0      WESTERN WATER CATCHMENT: 8   Min.   :  1.00  
##  2: 4    2:  0      JELEBU                 : 7   1st Qu.:  2.00  
##  3:42    3:  0      LAKESIDE               : 7   Median :  8.00  
##  4:17    4:115      CHOA CHU KANG CENTRAL  : 6   Mean   : 33.22  
##  5: 2    5:  0      GALI BATU              : 6   3rd Qu.: 35.00  
##                     GUILIN                 : 6   Max.   :217.00  
##                     (Other)                :75                   
##           geometry  
##  MULTIPOLYGON :115  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 5:

business_cluster5 <- business_residents %>%
  filter(SP_CLUSTER == 5)
summary(business_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:9           Length:9           Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:15720   1st Qu.:33080  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :28080   Mean   :64213  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.: 6480   1st Qu.: 830            1st Qu.:22180          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :14733   Mean   :3143            Mean   :57393          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:30500                  1st Qu.:1770                     
##  Median :47960                  Median :5220                     
##  Mean   :42140                  Mean   :4070                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1:0    
##  1st Qu.:0         1st Qu.: 55280   1st Qu.:0.03062   1st Qu.:1639669   2:0    
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3:0    
##  Mean   :0         Mean   :107027   Mean   :0.03165   Mean   :3439772   4:9    
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03371   3rd Qu.:4339824   5:0    
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER          SUBZONE_N total_business            geometry
##  1:0        TAMPINES EAST :2   Min.   : 12.00   MULTIPOLYGON :9  
##  2:0        TAMPINES NORTH:2   1st Qu.: 15.00   epsg:4326    :0  
##  3:0        CHANGI WEST   :1   Median : 18.00   +proj=long...:0  
##  4:0        LOYANG WEST   :1   Mean   : 56.56                    
##  5:9        SIMEI         :1   3rd Qu.: 69.00                    
##             TAMPINES WEST :1   Max.   :224.00                    
##             (Other)       :1

tmap_mode("view")

Plotting the tmap for the total business count on the SP clusters derived earlier.

tm_shape(business_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_business", col= "total_business", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more business counts:

Highest Business Count to Lowest Business Count

• Cluster 3 (616)
• Cluster 1 (411)
• Cluster 4 (115)
• Cluster 2 (14)
• Cluster 5 (9)

Key Highlights:

Highest: Cluster 3

Cluster 3 has the highest in business counts as the subzones are less densely populated given that the mean (0.015) for the population density is 2 times lesser than that of Cluster 5 (0.03165), which has the lowest in business counts. Given that the subzones are less densly populated, more businesses can be set up in the neighbouring areas as the areas are not used up for residential purposes. Hence, this attributes to a higher count in business units set up in the subzones of Cluster 3.

Lowest: Cluster 5

With a higher mean in population density as compared to Cluster 3 above, it shows that the subzones in Cluster 5 are very populated with residents. This results in Cluster 5 having a higher mean in the HDB counts as compared to Cluster 3, which took up the space in the subzones for residential stay rather than business needs, thereby having lesser business count.

tmap_mode("plot")

6.5.3 Urban Function 3: Govt Embassy and Residents

govtembassy_residents <- st_join(resident_2019_sf_spatialcluster, govt_count, left = TRUE)

SP_Cluster 1:

govt_cluster1 <- govtembassy_residents %>%
  filter(SP_CLUSTER == 1)
summary(govt_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:282         Length:282         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2620   1st Qu.: 5870  
##  Mode  :character   Mode  :character   Median : 6340   Median :15300  
##                                        Mean   : 6479   Mean   :15212  
##                                        3rd Qu.: 8380   3rd Qu.:20600  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0.0        
##  1st Qu.: 1448   1st Qu.:   0            1st Qu.:  827.5        
##  Median : 3480   Median : 250            Median :11805.0        
##  Mean   : 4008   Mean   : 987            Mean   :12692.0        
##  3rd Qu.: 5778   3rd Qu.:1610            3rd Qu.:17635.0        
##  Max.   :16050   Max.   :4700            Max.   :56850.0        
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:  565                  1st Qu.:    0                    
##  Median : 3920                  Median : 2920                    
##  Mean   : 5621                  Mean   : 3809                    
##  3rd Qu.: 8900                  3rd Qu.: 6430                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.:10210   1st Qu.:7.187e-03   1st Qu.:1078622  
##  Median :  440     Median :25630   Median :1.445e-02   Median :1713623  
##  Mean   : 2355     Mean   :25699   Mean   :1.577e-02   Mean   :2039076  
##  3rd Qu.: 3820     3rd Qu.:35520   3rd Qu.:2.336e-02   3rd Qu.:2553464  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER                  SUBZONE_N     total_govt   
##  1:90    1:282      BEDOK NORTH           :  9   Min.   :1.000  
##  2: 8    2:  0      GEYLANG EAST          :  9   1st Qu.:1.000  
##  3:61    3:  0      SERANGOON GARDEN      :  9   Median :1.000  
##  4:57    4:  0      ANG MO KIO TOWN CENTRE:  8   Mean   :1.647  
##  5:66    5:  0      HOUGANG WEST          :  8   3rd Qu.:2.000  
##                     (Other)               :235   Max.   :5.000  
##                     NA's                  :  4   NA's   :4      
##           geometry  
##  MULTIPOLYGON :282  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 2:

govt_cluster2 <- govtembassy_residents %>%
  filter(SP_CLUSTER == 2)
summary(govt_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:4           Length:4           Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15768   1st Qu.:28235  
##  Mode  :character   Mode  :character   Median :16870   Median :32185  
##                                        Mean   :16838   Mean   :32382  
##                                        3rd Qu.:17940   3rd Qu.:36332  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4265   1st Qu.: 855            1st Qu.:16412          
##  Median :5180   Median :1330            Median :19635          
##  Mean   :5102   Mean   :1198            Mean   :19468          
##  3rd Qu.:6018   3rd Qu.:1672            3rd Qu.:22690          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:26820                  1st Qu.:4678                     
##  Median :28295                  Median :5205                     
##  Mean   :27865                  Mean   :5550                     
##  3rd Qu.:29340                  3rd Qu.:6078                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0       Min.   :46610   Min.   :0.03109   Min.   :1378710   1:0    
##  1st Qu.:  0       1st Qu.:48268   1st Qu.:0.03433   1st Qu.:1436308   2:0    
##  Median :125       Median :54510   Median :0.03689   Median :1477308   3:0    
##  Mean   :125       Mean   :54322   Mean   :0.03681   Mean   :1475590   4:4    
##  3rd Qu.:250       3rd Qu.:60565   3rd Qu.:0.03937   3rd Qu.:1516590   5:0    
##  Max.   :250       Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER           SUBZONE_N   total_govt           geometry
##  1:0        RIVERVALE      :3   Min.   :1.0   MULTIPOLYGON :4  
##  2:4        FERNVALE       :1   1st Qu.:2.5   epsg:4326    :0  
##  3:0        ADMIRALTY      :0   Median :3.0   +proj=long...:0  
##  4:0        AIRPORT ROAD   :0   Mean   :2.5                    
##  5:0        ALEXANDRA HILL :0   3rd Qu.:3.0                    
##             ALEXANDRA NORTH:0   Max.   :3.0                    
##             (Other)        :0

SP_Cluster 3:

govt_cluster3 <- govtembassy_residents %>%
  filter(SP_CLUSTER == 3)
summary(govt_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:442         Length:442         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 200   1st Qu.:  590  
##  Mode  :character   Mode  :character   Median :1100   Median : 2750  
##                                        Mean   :1587   Mean   : 3923  
##                                        3rd Qu.:2350   3rd Qu.: 6200  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 120   1st Qu.:   0.0          1st Qu.:    0          
##  Median : 650   Median :   0.0          Median :    0          
##  Mean   :1315   Mean   : 567.6          Mean   : 2921          
##  3rd Qu.:2110   3rd Qu.: 537.5          3rd Qu.: 5330          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0.0                 Min.   :    0                    
##  1st Qu.:   0.0                 1st Qu.:  190                    
##  Median :   0.0                 Median :  770                    
##  Mean   : 864.3                 Mean   : 1779                    
##  3rd Qu.:1540.0                 3rd Qu.: 2810                    
##  Max.   :7810.0                 Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop       Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50.0   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.:  957.5   1st Qu.:1.533e-03   1st Qu.: 350788  
##  Median :   0.0    Median : 4430.0   Median :6.324e-03   Median : 587223  
##  Mean   : 609.5    Mean   : 6825.5   Mean   :9.328e-03   Mean   : 968307  
##  3rd Qu.: 585.0    3rd Qu.:10760.0   3rd Qu.:1.405e-02   3rd Qu.:1234400  
##  Max.   :7600.0    Max.   :37090.0   Max.   :4.399e-02   Max.   :7601894  
##                                                                           
##  CLUSTER SP_CLUSTER        SUBZONE_N     total_govt              geometry  
##  1:110   1:  0      BOULEVARD   : 10   Min.   : 1.000   MULTIPOLYGON :442  
##  2: 26   2:  0      CHATSWORTH  : 10   1st Qu.: 1.000   epsg:4326    :  0  
##  3:256   3:442      LEEDON PARK : 10   Median : 3.000   +proj=long...:  0  
##  4:  9   4:  0      LEONIE HILL :  9   Mean   : 4.122                      
##  5: 41   5:  0      NASSIM      :  9   3rd Qu.: 5.000                      
##                     PEARL'S HILL:  9   Max.   :17.000                      
##                     (Other)     :385

SP_Cluster 4:

govt_cluster4 <- govtembassy_residents %>%
  filter(SP_CLUSTER == 4)
summary(govt_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:83          Length:83          Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 2760   1st Qu.: 7920  
##  Mode  :character   Mode  :character   Median : 5320   Median :13640  
##                                        Mean   : 6279   Mean   :13734  
##                                        3rd Qu.: 8610   3rd Qu.:19120  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1460   1st Qu.:   0.0          1st Qu.: 5570          
##  Median :3030   Median :   0.0          Median :11150          
##  Mean   :2890   Mean   : 725.4          Mean   :12071          
##  3rd Qu.:3720   3rd Qu.:1355.0          3rd Qu.:18650          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 2570                  1st Qu.:   0                     
##  Median : 6130                  Median :1180                     
##  Mean   : 7664                  Mean   :2045                     
##  3rd Qu.:11500                  3rd Qu.:3545                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:12870   1st Qu.:0.005910   1st Qu.:  800299  
##  Median :   0.0    Median :22590   Median :0.026926   Median : 1088638  
##  Mean   : 301.9    Mean   :22903   Mean   :0.021143   Mean   : 4200728  
##  3rd Qu.:   0.0    3rd Qu.:31660   3rd Qu.:0.031612   3rd Qu.: 1806553  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                   SUBZONE_N    total_govt   
##  1:36    1: 0       WESTERN WATER CATCHMENT: 8   Min.   :1.000  
##  2: 4    2: 0       GOMBAK                 : 7   1st Qu.:1.000  
##  3:28    3: 0       LAKESIDE               : 7   Median :1.000  
##  4:13    4:83       BUKIT BATOK CENTRAL    : 6   Mean   :1.354  
##  5: 2    5: 0       CHOA CHU KANG CENTRAL  : 6   3rd Qu.:1.750  
##                     (Other)                :48   Max.   :6.000  
##                     NA's                   : 1   NA's   :1      
##           geometry 
##  MULTIPOLYGON :83  
##  epsg:4326    : 0  
##  +proj=long...: 0  
##                    
##                    
##                    
## 

SP_Cluster 5:

govt_cluster5 <- govtembassy_residents %>%
  filter(SP_CLUSTER == 5)
summary(govt_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:9           Length:9           Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:15720   1st Qu.:33080  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :28080   Mean   :64213  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.: 6480   1st Qu.: 830            1st Qu.:22180          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :14733   Mean   :3143            Mean   :57393          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:30500                  1st Qu.:1770                     
##  Median :47960                  Median :5220                     
##  Mean   :42140                  Mean   :4070                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1:0    
##  1st Qu.:0         1st Qu.: 55280   1st Qu.:0.03062   1st Qu.:1639669   2:0    
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3:0    
##  Mean   :0         Mean   :107027   Mean   :0.03165   Mean   :3439772   4:9    
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03371   3rd Qu.:4339824   5:0    
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER             SUBZONE_N   total_govt             geometry
##  1:0        PASIR RIS CENTRAL:2   Min.   :1.000   MULTIPOLYGON :9  
##  2:0        PASIR RIS DRIVE  :2   1st Qu.:1.000   epsg:4326    :0  
##  3:0        TAMPINES EAST    :2   Median :1.000   +proj=long...:0  
##  4:0        CHANGI WEST      :1   Mean   :1.778                    
##  5:9        SIMEI            :1   3rd Qu.:2.000                    
##             TAMPINES WEST    :1   Max.   :4.000                    
##             (Other)          :0

tmap_mode("view")

Plotting the tmap for the total government embassy count on the SP clusters derived earlier.

tm_shape(govtembassy_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_govt", col= "total_govt", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more government embassy counts:

Highest Government Embassy Count to Lowest Government Embassy Count

• Cluster 3 (442)
• Cluster 1 (282)
• Cluster 4 (83)
• Cluster 5 (9)
• Cluster 2 (4)

Key Highlights:

Highest: Cluster 3

Cluster 3 has the highest in government embassy count as the location for the subzones is mainly central area of Singapore, which makes it convenient for Singaporeans to travel to the embassy. The subzones in cluster 3 also have lesser residential properties as compared to cluster 2, except for the landed properties. The population density of the Cluster 2 is also 4 times more than that of Cluster 3, making cluster 3 a lot less densly populated. This allows the area to become more commercialized rather than making it more of an area for residential spaces. Thus, this explains why Cluster 3 will be a spot for more government embassies to built at.

Lowest: Cluster 2

Cluster 2 is a rather densely populated area, with the mean subzone population of about 9 times of that of Cluster 3. This led to the assumption that more residential spaces will be build for the subzones in Cluster 2 to accommodate the higher number of residents staying, which made it less possible for government embassies to be built, thus having a lesser count in government embassies as compared to Cluster 3.

tmap_mode("plot")

6.5.4 Urban Function 4: Financial and Residents

financial_residents <- st_join(resident_2019_sf_spatialcluster, financial_count, left = TRUE)

SP_Cluster 1:

fin_cluster1 <- financial_residents %>%
  filter(SP_CLUSTER == 1)
summary(fin_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:511         Length:511         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2490   1st Qu.: 5450  
##  Mode  :character   Mode  :character   Median : 6340   Median :15070  
##                                        Mean   : 6655   Mean   :15172  
##                                        3rd Qu.: 8900   3rd Qu.:20730  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0          
##  1st Qu.: 1420   1st Qu.:   0            1st Qu.:  925          
##  Median : 3320   Median : 360            Median :11720          
##  Mean   : 3803   Mean   :1010            Mean   :12459          
##  3rd Qu.: 5720   3rd Qu.:1610            3rd Qu.:17380          
##  Max.   :16050   Max.   :4700            Max.   :56850          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:  580                  1st Qu.:  120                    
##  Median : 3920                  Median : 2920                    
##  Mean   : 5811                  Mean   : 3760                    
##  3rd Qu.: 9485                  3rd Qu.: 6160                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.: 9390   1st Qu.:7.293e-03   1st Qu.:1078622  
##  Median :  460     Median :25170   Median :1.543e-02   Median :1583440  
##  Mean   : 2353     Mean   :25629   Mean   :1.621e-02   Mean   :1953678  
##  3rd Qu.: 3555     3rd Qu.:35520   3rd Qu.:2.343e-02   3rd Qu.:2496945  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER                  SUBZONE_N   total_financial
##  1:174   1:511      BEDOK NORTH           :  9   Min.   : 1.00  
##  2: 15   2:  0      FRANKEL               :  9   1st Qu.: 5.00  
##  3:106   3:  0      GEYLANG EAST          :  9   Median :11.00  
##  4:105   4:  0      SERANGOON GARDEN      :  9   Mean   :14.87  
##  5:111   5:  0      ANG MO KIO TOWN CENTRE:  8   3rd Qu.:18.00  
##                     CHONG BOON            :  8   Max.   :79.00  
##                     (Other)               :459                  
##           geometry  
##  MULTIPOLYGON :511  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 2:

fin_cluster2 <- financial_residents %>%
  filter(SP_CLUSTER == 2)
summary(fin_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:23          Length:23          Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15940   1st Qu.:28400  
##  Mode  :character   Mode  :character   Median :17800   Median :35970  
##                                        Mean   :16907   Mean   :32584  
##                                        3rd Qu.:18080   3rd Qu.:36695  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4480   1st Qu.: 720            1st Qu.:15545          
##  Median :5880   Median : 990            Median :21990          
##  Mean   :5167   Mean   :1177            Mean   :19563          
##  3rd Qu.:6155   3rd Qu.:1670            3rd Qu.:23390          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:28210                  1st Qu.:4355                     
##  Median :28380                  Median :5410                     
##  Mean   :28092                  Mean   :5574                     
##  3rd Qu.:30300                  3rd Qu.:6745                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0.0     Min.   :46610   Min.   :0.03109   Min.   :1378710   1: 0   
##  1st Qu.:  0.0     1st Qu.:48820   1st Qu.:0.03541   1st Qu.:1417109   2: 0   
##  Median :250.0     Median :60200   Median :0.03837   Median :1455508   3: 0   
##  Mean   :130.4     Mean   :54658   Mean   :0.03706   Mean   :1474568   4:23   
##  3rd Qu.:250.0     3rd Qu.:60930   3rd Qu.:0.04037   3rd Qu.:1534072   5: 0   
##  Max.   :250.0     Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER                SUBZONE_N total_financial           geometry 
##  1: 0       MATILDA             :4   Min.   : 1.000   MULTIPOLYGON :23  
##  2:23       SENGKANG TOWN CENTRE:4   1st Qu.: 4.000   epsg:4326    : 0  
##  3: 0       COMPASSVALE         :3   Median : 8.000   +proj=long...: 0  
##  4: 0       PUNGGOL FIELD       :3   Mean   : 9.783                     
##  5: 0       RIVERVALE           :3   3rd Qu.:12.000                     
##             ANCHORVALE          :2   Max.   :24.000                     
##             (Other)             :4

SP_Cluster 3:

fin_cluster3 <- financial_residents %>%
  filter(SP_CLUSTER == 3)
summary(fin_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:716         Length:716         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 300   1st Qu.:  770  
##  Mode  :character   Mode  :character   Median :1450   Median : 3450  
##                                        Mean   :1768   Mean   : 4383  
##                                        3rd Qu.:2658   3rd Qu.: 6360  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 260   1st Qu.:   0.0          1st Qu.:    0          
##  Median : 995   Median :   0.0          Median :  180          
##  Mean   :1490   Mean   : 640.5          Mean   : 3436          
##  3rd Qu.:2450   3rd Qu.:1010.0          3rd Qu.: 6080          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0                   Min.   :    0                    
##  1st Qu.:   0                   1st Qu.:  110                    
##  Median :   0                   Median :  770                    
##  Mean   :1029                   Mean   : 1787                    
##  3rd Qu.:1970                   3rd Qu.: 2520                    
##  Max.   :7810                   Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.: 1350   1st Qu.:2.975e-03   1st Qu.: 368483  
##  Median :   0.0    Median : 6420   Median :8.036e-03   Median : 639144  
##  Mean   : 654.9    Mean   : 7641   Mean   :1.072e-02   Mean   : 992140  
##  3rd Qu.: 690.0    3rd Qu.:11140   3rd Qu.:1.700e-02   3rd Qu.:1229894  
##  Max.   :7600.0    Max.   :37090   Max.   :4.399e-02   Max.   :7601894  
##                                                                         
##  CLUSTER SP_CLUSTER          SUBZONE_N   total_financial           geometry  
##  1:214   1:  0      BOULEVARD     : 10   Min.   :  1.00   MULTIPOLYGON :716  
##  2: 45   2:  0      CHATSWORTH    : 10   1st Qu.:  4.00   epsg:4326    :  0  
##  3:375   3:716      LEEDON PARK   : 10   Median :  8.00   +proj=long...:  0  
##  4: 16   4:  0      MARGARET DRIVE: 10   Mean   : 15.12                      
##  5: 66   5:  0      LEONIE HILL   :  9   3rd Qu.: 18.25                      
##                     NASSIM        :  9   Max.   :132.00                      
##                     (Other)       :658

SP_Cluster 4:

fin_cluster4 <- financial_residents %>%
  filter(SP_CLUSTER == 4)
summary(fin_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:200         Length:200         Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 3572   1st Qu.: 8710  
##  Mode  :character   Mode  :character   Median : 6100   Median :13660  
##                                        Mean   : 6627   Mean   :14357  
##                                        3rd Qu.: 8610   3rd Qu.:19120  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1500   1st Qu.:   0.0          1st Qu.: 5960          
##  Median :2490   Median :  15.0          Median :11150          
##  Mean   :2918   Mean   : 691.6          Mean   :12302          
##  3rd Qu.:3720   3rd Qu.:1342.5          3rd Qu.:16220          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 3830                  1st Qu.:   0                     
##  Median : 6300                  Median :1200                     
##  Mean   : 8408                  Mean   :1992                     
##  3rd Qu.:11720                  3rd Qu.:3100                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:14325   1st Qu.:0.008342   1st Qu.:  794260  
##  Median :   0.0    Median :22610   Median :0.026982   Median : 1085080  
##  Mean   : 406.4    Mean   :23902   Mean   :0.022933   Mean   : 4444446  
##  3rd Qu.:  60.0    3rd Qu.:31660   3rd Qu.:0.032726   3rd Qu.: 1806553  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                   SUBZONE_N   total_financial 
##  1:97    1:  0      WESTERN WATER CATCHMENT:  8   Min.   : 1.000  
##  2: 7    2:  0      BUKIT BATOK WEST       :  7   1st Qu.: 4.000  
##  3:59    3:  0      GOMBAK                 :  7   Median : 6.000  
##  4:31    4:200      JELEBU                 :  7   Mean   : 9.295  
##  5: 6    5:  0      LAKESIDE               :  7   3rd Qu.:14.000  
##                     TECK WHYE              :  7   Max.   :55.000  
##                     (Other)                :157                   
##           geometry  
##  MULTIPOLYGON :200  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 5:

fin_cluster5 <- financial_residents %>%
  filter(SP_CLUSTER == 5)
summary(fin_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:15          Length:15          Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:15720   1st Qu.:33080  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :25608   Mean   :57987  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.: 6480   1st Qu.: 830            1st Qu.:22180          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :13083   Mean   :2681            Mean   :50351          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:30500                  1st Qu.:1770                     
##  Median :47960                  Median :5220                     
##  Mean   :39812                  Mean   :3610                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1: 0   
##  1st Qu.:0         1st Qu.: 55280   1st Qu.:0.03062   1st Qu.:1639669   2: 0   
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3: 0   
##  Mean   :0         Mean   : 96677   Mean   :0.03207   Mean   :3079752   4:15   
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03371   3rd Qu.:4339824   5: 0   
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER             SUBZONE_N total_financial          geometry 
##  1: 0       FLORA DRIVE      :2   Min.   : 1.00   MULTIPOLYGON :15  
##  2: 0       PASIR RIS CENTRAL:2   1st Qu.: 4.00   epsg:4326    : 0  
##  3: 0       PASIR RIS DRIVE  :2   Median :11.00   +proj=long...: 0  
##  4: 0       TAMPINES EAST    :2   Mean   :18.73                     
##  5:15       TAMPINES NORTH   :2   3rd Qu.:18.50                     
##             LOYANG WEST      :1   Max.   :79.00                     
##             (Other)          :4

tmap_mode("view")

Plotting the tmap for the total financial count on the SP clusters derived earlier.

tm_shape(financial_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_financial", col= "total_financial", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more financial counts:

Highest Financial Count to Lowest Financial Count

• Cluster 3 (716)
• Cluster 1 (511)
• Cluster 4 (200)
• Cluster 2 (23)
• Cluster 5 (15)

Key Highlights:

Highest: Cluster 3

As Cluster 3 has high in business and government embassy counts, this can be attributable to the high in financial needs around these areas as well, making the financial count for Cluster 3 the highest among all other clusters. The needs for ATM and other financial needs for businesses and government embassies can be more prevalent than that of other clusters where daily withdrawal for purchases is the main financial need. As Cluster 3 is very less densely populated, it has more subzones that are commercialized which made financial needs more essential in these areas, thus having more financial count.

Lowest: Cluster 5

For Cluster 5, it has lesser financial count because the subzones are densely populated and thus have more residential buildings to meet the population in the subzones. With more buildings built for stay, and lesser business flows happening, there is a lesser need for financial services or lesser urgent financial needs, thereby making the subzones have a lesser financial count as compared to Cluster 3, which is densely populated with businesses.

tmap_mode("plot")

6.5.5 Urban Function 5: Shopping and Residents

shopping_residents <- st_join(resident_2019_sf_spatialcluster, shopping_count, left = TRUE)

SP_Cluster 1:

shopping_cluster1 <- shopping_residents %>%
  filter(SP_CLUSTER == 1)
summary(shopping_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:302         Length:302         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2852   1st Qu.: 7480  
##  Mode  :character   Mode  :character   Median : 6590   Median :15470  
##                                        Mean   : 7421   Mean   :16616  
##                                        3rd Qu.: 9680   3rd Qu.:21600  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0          
##  1st Qu.: 1640   1st Qu.:   0            1st Qu.: 1700          
##  Median : 3400   Median : 495            Median :11890          
##  Mean   : 4053   Mean   :1088            Mean   :13350          
##  3rd Qu.: 5720   3rd Qu.:1700            3rd Qu.:17380          
##  Max.   :16050   Max.   :4700            Max.   :56850          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:  905                  1st Qu.:  235                    
##  Median : 4290                  Median : 3995                    
##  Mean   : 6715                  Mean   : 4186                    
##  3rd Qu.:11250                  3rd Qu.: 6950                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.:12110   1st Qu.:7.823e-03   1st Qu.:1082547  
##  Median :  440     Median :26930   Median :1.595e-02   Median :1616035  
##  Mean   : 2520     Mean   :28089   Mean   :1.725e-02   Mean   :1940477  
##  3rd Qu.: 4038     3rd Qu.:36480   3rd Qu.:2.359e-02   3rd Qu.:2543107  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER                  SUBZONE_N   total_shopping  
##  1:97    1:302      BEDOK NORTH           :  9   Min.   : 1.000  
##  2: 8    2:  0      FRANKEL               :  9   1st Qu.: 1.000  
##  3:48    3:  0      GEYLANG EAST          :  9   Median : 2.000  
##  4:71    4:  0      SERANGOON GARDEN      :  9   Mean   : 2.557  
##  5:78    5:  0      ANG MO KIO TOWN CENTRE:  8   3rd Qu.: 3.000  
##                     (Other)               :252   Max.   :10.000  
##                     NA's                  :  6   NA's   :6       
##           geometry  
##  MULTIPOLYGON :302  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 2:

shopping_cluster2 <- shopping_residents %>%
  filter(SP_CLUSTER == 2)
summary(shopping_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:13          Length:13          Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15940   1st Qu.:28400  
##  Mode  :character   Mode  :character   Median :15940   Median :28400  
##                                        Mean   :16822   Mean   :32127  
##                                        3rd Qu.:17800   3rd Qu.:35970  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4480   1st Qu.: 990            1st Qu.:13810          
##  Median :4480   Median : 990            Median :17280          
##  Mean   :5121   Mean   :1128            Mean   :18765          
##  3rd Qu.:5880   3rd Qu.:1670            3rd Qu.:21990          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:28210                  1st Qu.:5000                     
##  Median :28380                  Median :5410                     
##  Mean   :28345                  Mean   :5571                     
##  3rd Qu.:28380                  3rd Qu.:5410                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0.0     Min.   :46610   Min.   :0.03109   Min.   :1378710   1: 0   
##  1st Qu.:  0.0     1st Qu.:48820   1st Qu.:0.03541   1st Qu.:1378710   2: 0   
##  Median :  0.0     Median :48820   Median :0.03541   Median :1455508   3: 0   
##  Mean   :115.4     Mean   :54069   Mean   :0.03703   Mean   :1458877   4:13   
##  3rd Qu.:250.0     3rd Qu.:60200   3rd Qu.:0.03837   3rd Qu.:1499109   5: 0   
##  Max.   :250.0     Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER                SUBZONE_N total_shopping           geometry 
##  1: 0       SENGKANG TOWN CENTRE:4   Min.   :1.000   MULTIPOLYGON :13  
##  2:13       PUNGGOL FIELD       :3   1st Qu.:1.000   epsg:4326    : 0  
##  3: 0       RIVERVALE           :3   Median :2.000   +proj=long...: 0  
##  4: 0       FERNVALE            :1   Mean   :1.846                     
##  5: 0       PUNGGOL TOWN CENTRE :1   3rd Qu.:2.000                     
##             WATERWAY EAST       :1   Max.   :3.000                     
##             (Other)             :0

SP_Cluster 3:

shopping_cluster3 <- shopping_residents %>%
  filter(SP_CLUSTER == 3)
summary(shopping_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:444         Length:444         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 200   1st Qu.:  690  
##  Mode  :character   Mode  :character   Median :1100   Median : 2795  
##                                        Mean   :1619   Mean   : 3970  
##                                        3rd Qu.:2420   3rd Qu.: 6200  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 170   1st Qu.:   0.0          1st Qu.:    0          
##  Median : 810   Median :   0.0          Median :    0          
##  Mean   :1329   Mean   : 579.1          Mean   : 2917          
##  3rd Qu.:2130   3rd Qu.: 530.0          3rd Qu.: 5180          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0.0                 Min.   :    0                    
##  1st Qu.:   0.0                 1st Qu.:  190                    
##  Median :   0.0                 Median :  730                    
##  Mean   : 849.4                 Mean   : 1800                    
##  3rd Qu.:1360.0                 3rd Qu.: 2810                    
##  Max.   :7810.0                 Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.: 1190   1st Qu.:2.149e-03   1st Qu.: 324707  
##  Median :   0.0    Median : 4825   Median :6.687e-03   Median : 639144  
##  Mean   : 678.7    Mean   : 6919   Mean   :9.216e-03   Mean   : 997216  
##  3rd Qu.: 730.0    3rd Qu.:10760   3rd Qu.:1.337e-02   3rd Qu.:1231396  
##  Max.   :7600.0    Max.   :37090   Max.   :4.399e-02   Max.   :7601894  
##                                                                         
##  CLUSTER SP_CLUSTER          SUBZONE_N   total_shopping            geometry  
##  1:104   1:  0      BOULEVARD     : 10   Min.   : 1.000   MULTIPOLYGON :444  
##  2: 30   2:  0      CHATSWORTH    : 10   1st Qu.: 1.000   epsg:4326    :  0  
##  3:257   3:444      LEEDON PARK   : 10   Median : 2.000   +proj=long...:  0  
##  4:  9   4:  0      MARGARET DRIVE: 10   Mean   : 4.296                      
##  5: 44   5:  0      NASSIM        :  9   3rd Qu.: 6.000                      
##                     (Other)       :394   Max.   :27.000                      
##                     NA's          :  1   NA's   :1

SP_Cluster 4:

shopping_cluster4 <- shopping_residents %>%
  filter(SP_CLUSTER == 4)
summary(shopping_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:112         Length:112         Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 3640   1st Qu.: 8960  
##  Mode  :character   Mode  :character   Median : 6420   Median :14650  
##                                        Mean   : 6958   Mean   :14771  
##                                        3rd Qu.: 9570   3rd Qu.:19250  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1500   1st Qu.:   0.0          1st Qu.: 6870          
##  Median :2490   Median :   0.0          Median :11150          
##  Mean   :2848   Mean   : 673.8          Mean   :12089          
##  3rd Qu.:3712   3rd Qu.:1342.5          3rd Qu.:15988          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 4602                  1st Qu.:   0                     
##  Median : 8100                  Median :1200                     
##  Mean   : 9092                  Mean   :2134                     
##  3rd Qu.:12200                  3rd Qu.:3990                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:14740   1st Qu.:0.008342   1st Qu.:  862737  
##  Median :   0.0    Median :24720   Median :0.028496   Median : 1088638  
##  Mean   : 475.4    Mean   :24577   Mean   :0.023643   Mean   : 5664065  
##  3rd Qu.: 680.0    3rd Qu.:32440   3rd Qu.:0.032726   3rd Qu.: 1806553  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                   SUBZONE_N  total_shopping 
##  1:51    1:  0      WESTERN WATER CATCHMENT: 8   Min.   :1.000  
##  2: 4    2:  0      BUKIT BATOK WEST       : 7   1st Qu.:1.000  
##  3:31    3:  0      JELEBU                 : 7   Median :1.000  
##  4:20    4:112      TECK WHYE              : 7   Mean   :1.616  
##  5: 6    5:  0      BOON LAY PLACE         : 6   3rd Qu.:2.000  
##                     BUKIT BATOK CENTRAL    : 6   Max.   :5.000  
##                     (Other)                :71                  
##           geometry  
##  MULTIPOLYGON :112  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 5:

shopping_cluster5 <- shopping_residents %>%
  filter(SP_CLUSTER == 5)
summary(shopping_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:12          Length:12          Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:15720   1st Qu.:33080  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :26535   Mean   :60322  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.: 6480   1st Qu.: 830            1st Qu.:22180          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :13702   Mean   :2854            Mean   :52992          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:30500                  1st Qu.:1770                     
##  Median :47960                  Median :5220                     
##  Mean   :40685                  Mean   :3782                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1: 0   
##  1st Qu.:0         1st Qu.: 55280   1st Qu.:0.03062   1st Qu.:1639669   2: 0   
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3: 0   
##  Mean   :0         Mean   :100558   Mean   :0.03191   Mean   :3214760   4:12   
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03371   3rd Qu.:4339824   5: 0   
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER             SUBZONE_N total_shopping            geometry 
##  1: 0       PASIR RIS CENTRAL:2   Min.   : 1.000   MULTIPOLYGON :12  
##  2: 0       PASIR RIS DRIVE  :2   1st Qu.: 1.000   epsg:4326    : 0  
##  3: 0       TAMPINES EAST    :2   Median : 2.000   +proj=long...: 0  
##  4: 0       TAMPINES NORTH   :2   Mean   : 3.583                     
##  5:12       PASIR RIS PARK   :1   3rd Qu.: 4.500                     
##             SIMEI            :1   Max.   :10.000                     
##             (Other)          :2

tmap_mode("view")

Plotting the tmap for the total shopping count on the SP clusters derived earlier.

tm_shape(shopping_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_shopping", col= "total_shopping", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more shopping counts:

Highest Shopping Count to Lowest Shopping Count

• Cluster 3 (444)
• Cluster 1 (302)
• Cluster 4 (112)
• Cluster 2 (13)
• Cluster 5 (12)

Key Highlights:

Highest: Cluster 3

As explained in the previous indicators, Cluster 3 is less densely populated than Cluster 5, making it an area for commercialism to happen. This results in Cluster 3 having more financial, business and government embassy units. With the results above, it also shows that Cluster 3 has more shopping units as well due to the result of it being a more commercialized area. However, as seen from the above results, despite Cluster 3 having lesser HDB counts, the landed properties’ count is much higher than that of Cluster 5, which shows that the residents would probably have a higher purchasing power in general. This could be the driving factor for more shopping units to grow in Cluster 3 as businesses can thrive as the purchasing power of the residents in the subzones are higher.

Lowest: Cluster 5

For Cluster 5, there are more residents staying in HDB apartments than that of Cluster 3. Hence, purchasing power of these residents are lower than that of Cluster 3, making Cluster 5 less attractive for shopping units to be set up at. Moreover, commercialism can drive human traffic which can lead to greater sales, an area like Cluster 5 that is less commercialized will not be an ideal spot for shopping units to prosper, therefore it has a lesser shopping count as compared to Cluster 3.

tmap_mode("plot")

6.5.6 Urban Function 6: Upmarket Residential Area and Residents

ura_residents <- st_join(resident_2019_sf_spatialcluster, URA_count, left = TRUE)

SP_Cluster 1:

ura_cluster1 <- ura_residents %>%
  filter(SP_CLUSTER == 1)
summary(ura_cluster1)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:507         Length:507         Min.   :    0   Min.   :   10  
##  Class :character   Class :character   1st Qu.: 2490   1st Qu.: 5450  
##  Mode  :character   Mode  :character   Median : 6130   Median :14550  
##                                        Mean   : 6652   Mean   :15145  
##                                        3rd Qu.: 8850   3rd Qu.:20730  
##                                        Max.   :31690   Max.   :59340  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   20   Min.   :   0            Min.   :    0          
##  1st Qu.: 1360   1st Qu.:   0            1st Qu.:  730          
##  Median : 3280   Median : 360            Median :11720          
##  Mean   : 3756   Mean   :1009            Mean   :12538          
##  3rd Qu.: 5680   3rd Qu.:1610            3rd Qu.:17380          
##  Max.   :16050   Max.   :4700            Max.   :56850          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :    0                    
##  1st Qu.:  550                  1st Qu.:  175                    
##  Median : 3920                  Median : 3050                    
##  Mean   : 5741                  Mean   : 3798                    
##  3rd Qu.: 9105                  3rd Qu.: 6160                    
##  Max.   :41850                  Max.   :14960                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :    0     Min.   :  190   Min.   :6.639e-05   Min.   : 143138  
##  1st Qu.:    0     1st Qu.: 9390   1st Qu.:7.293e-03   1st Qu.:1078622  
##  Median :  440     Median :24950   Median :1.543e-02   Median :1517767  
##  Mean   : 2237     Mean   :25553   Mean   :1.632e-02   Mean   :1932365  
##  3rd Qu.: 3290     3rd Qu.:35520   3rd Qu.:2.343e-02   3rd Qu.:2434594  
##  Max.   :18820     Max.   :98620   Max.   :3.944e-02   Max.   :8453312  
##                                                                         
##  CLUSTER SP_CLUSTER                  SUBZONE_N     total_URA     
##  1:173   1:507      BEDOK NORTH           :  9   Min.   :  1.00  
##  2: 13   2:  0      FRANKEL               :  9   1st Qu.:  5.00  
##  3:105   3:  0      GEYLANG EAST          :  9   Median : 10.00  
##  4:108   4:  0      SERANGOON GARDEN      :  9   Mean   : 22.09  
##  5:108   5:  0      ANG MO KIO TOWN CENTRE:  8   3rd Qu.: 21.50  
##                     CHONG BOON            :  8   Max.   :215.00  
##                     (Other)               :455                   
##           geometry  
##  MULTIPOLYGON :507  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 2:

ura_cluster2 <- ura_residents %>%
  filter(SP_CLUSTER == 2)
summary(ura_cluster2)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:24          Length:24          Min.   :15250   Min.   :27740  
##  Class :character   Class :character   1st Qu.:15940   1st Qu.:28400  
##  Mode  :character   Mode  :character   Median :17800   Median :35970  
##                                        Mean   :16944   Mean   :32725  
##                                        3rd Qu.:17940   3rd Qu.:36332  
##                                        Max.   :18360   Max.   :37420  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :3620   Min.   : 450            Min.   :13810          
##  1st Qu.:4480   1st Qu.: 855            1st Qu.:16412          
##  Median :5880   Median :1330            Median :21990          
##  Mean   :5220   Mean   :1197            Mean   :19664          
##  3rd Qu.:6430   3rd Qu.:1670            3rd Qu.:22690          
##  Max.   :6430   Max.   :1680            Max.   :24790          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :22650                  Min.   :3710                     
##  1st Qu.:28210                  1st Qu.:4678                     
##  Median :28295                  Median :5410                     
##  Mean   :28097                  Mean   :5678                     
##  3rd Qu.:29340                  3rd Qu.:8080                     
##  Max.   :32220                  Max.   :8080                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density        SHAPE_Area      CLUSTER
##  Min.   :  0.0     Min.   :46610   Min.   :0.03109   Min.   :1378710   1: 0   
##  1st Qu.:  0.0     1st Qu.:48820   1st Qu.:0.03541   1st Qu.:1436308   2: 0   
##  Median :250.0     Median :60200   Median :0.03837   Median :1477308   3: 0   
##  Mean   :135.4     Mean   :54889   Mean   :0.03711   Mean   :1478504   4:24   
##  3rd Qu.:250.0     3rd Qu.:60565   3rd Qu.:0.03937   3rd Qu.:1569035   5: 0   
##  Max.   :250.0     Max.   :61660   Max.   :0.04236   Max.   :1569035          
##                                                                               
##  SP_CLUSTER                SUBZONE_N   total_URA              geometry 
##  1: 0       MATILDA             :4   Min.   : 5.00   MULTIPOLYGON :24  
##  2:24       SENGKANG TOWN CENTRE:4   1st Qu.: 9.00   epsg:4326    : 0  
##  3: 0       COMPASSVALE         :3   Median :12.00   +proj=long...: 0  
##  4: 0       PUNGGOL FIELD       :3   Mean   :12.29                     
##  5: 0       RIVERVALE           :3   3rd Qu.:12.50                     
##             ANCHORVALE          :2   Max.   :24.00                     
##             (Other)             :5

SP_Cluster 3:

ura_cluster3 <- ura_residents %>%
  filter(SP_CLUSTER == 3)
summary(ura_cluster3)

##       SZ                 PA                YOUNG      ECONOMY.ACTIVE 
##  Length:728         Length:728         Min.   :   0   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 300   1st Qu.:  770  
##  Mode  :character   Mode  :character   Median :1440   Median : 3420  
##                                        Mean   :1744   Mean   : 4313  
##                                        3rd Qu.:2620   3rd Qu.: 6360  
##                                        Max.   :7930   Max.   :21950  
##                                                                      
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :   0   Min.   :   0.0          Min.   :    0          
##  1st Qu.: 220   1st Qu.:   0.0          1st Qu.:    0          
##  Median : 960   Median :   0.0          Median :  165          
##  Mean   :1452   Mean   : 619.9          Mean   : 3330          
##  3rd Qu.:2320   3rd Qu.: 790.0          3rd Qu.: 5990          
##  Max.   :7210   Max.   :4520.0          Max.   :23090          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :   0.0                 Min.   :    0                    
##  1st Qu.:   0.0                 1st Qu.:  150                    
##  Median :   0.0                 Median :  770                    
##  Mean   : 998.9                 Mean   : 1828                    
##  3rd Qu.:1900.0                 3rd Qu.: 2520                    
##  Max.   :7810.0                 Max.   :16770                    
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density          SHAPE_Area     
##  Min.   :   0.0    Min.   :   50   Min.   :6.580e-06   Min.   :  49626  
##  1st Qu.:   0.0    1st Qu.: 1350   1st Qu.:2.899e-03   1st Qu.: 365333  
##  Median :   0.0    Median : 6420   Median :7.413e-03   Median : 631644  
##  Mean   : 640.1    Mean   : 7509   Mean   :1.057e-02   Mean   : 952340  
##  3rd Qu.: 690.0    3rd Qu.:11140   3rd Qu.:1.690e-02   3rd Qu.:1228488  
##  Max.   :7600.0    Max.   :37090   Max.   :4.399e-02   Max.   :7601894  
##                                                                         
##  CLUSTER SP_CLUSTER          SUBZONE_N     total_URA               geometry  
##  1:208   1:  0      BOULEVARD     : 10   Min.   :  1.00   MULTIPOLYGON :728  
##  2: 46   2:  0      CHATSWORTH    : 10   1st Qu.:  3.00   epsg:4326    :  0  
##  3:388   3:728      LEEDON PARK   : 10   Median :  7.00   +proj=long...:  0  
##  4: 16   4:  0      MARGARET DRIVE: 10   Mean   : 17.11                      
##  5: 70   5:  0      LEONIE HILL   :  9   3rd Qu.: 21.00                      
##                     NASSIM        :  9   Max.   :140.00                      
##                     (Other)       :670

SP_Cluster 4:

ura_cluster4 <- ura_residents %>%
  filter(SP_CLUSTER == 4)
summary(ura_cluster4)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:180         Length:180         Min.   :   20   Min.   :   40  
##  Class :character   Class :character   1st Qu.: 3370   1st Qu.: 7960  
##  Mode  :character   Mode  :character   Median : 5360   Median :13640  
##                                        Mean   : 6259   Mean   :13650  
##                                        3rd Qu.: 8440   3rd Qu.:17830  
##                                        Max.   :19400   Max.   :41080  
##                                                                       
##       AGED      HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   :  10   Min.   :   0.0          Min.   :    0          
##  1st Qu.:1500   1st Qu.:   0.0          1st Qu.: 5960          
##  Median :2490   Median :   0.0          Median :11150          
##  Mean   :2811   Mean   : 651.6          Mean   :11781          
##  3rd Qu.:3710   3rd Qu.:1330.0          3rd Qu.:15910          
##  Max.   :8740   Max.   :3700.0          Max.   :35950          
##                                                                
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :    0                  Min.   :   0                     
##  1st Qu.: 3830                  1st Qu.:   0                     
##  Median : 6300                  Median :1200                     
##  Mean   : 7745                  Mean   :2044                     
##  3rd Qu.:10882                  3rd Qu.:3100                     
##  Max.   :38700                  Max.   :8670                     
##                                                                  
##  Landed.Properties  Subzone_pop     Pop_density         SHAPE_Area      
##  Min.   :   0.0    Min.   :   70   Min.   :0.000004   Min.   :  380202  
##  1st Qu.:   0.0    1st Qu.:13080   1st Qu.:0.008342   1st Qu.:  800299  
##  Median :   0.0    Median :22590   Median :0.026954   Median : 1085080  
##  Mean   : 395.9    Mean   :22720   Mean   :0.022401   Mean   : 4404281  
##  3rd Qu.: 240.0    3rd Qu.:30160   3rd Qu.:0.032726   3rd Qu.: 1806553  
##  Max.   :3590.0    Max.   :68200   Max.   :0.046058   Max.   :69748299  
##                                                                         
##  CLUSTER SP_CLUSTER                   SUBZONE_N     total_URA     
##  1:90    1:  0      WESTERN WATER CATCHMENT:  8   Min.   : 1.000  
##  2: 5    2:  0      BUKIT BATOK WEST       :  7   1st Qu.: 3.000  
##  3:55    3:  0      GOMBAK                 :  7   Median : 4.000  
##  4:24    4:180      JELEBU                 :  7   Mean   : 5.344  
##  5: 6    5:  0      LAKESIDE               :  7   3rd Qu.: 6.000  
##                     TECK WHYE              :  7   Max.   :49.000  
##                     (Other)                :137                   
##           geometry  
##  MULTIPOLYGON :180  
##  epsg:4326    :  0  
##  +proj=long...:  0  
##                     
##                     
##                     
## 

SP_Cluster 5:

ura_cluster5 <- ura_residents %>%
  filter(SP_CLUSTER == 5)
summary(ura_cluster5)

##       SZ                 PA                YOUNG       ECONOMY.ACTIVE 
##  Length:14          Length:14          Min.   :15720   Min.   :33080  
##  Class :character   Class :character   1st Qu.:15720   1st Qu.:33080  
##  Mode  :character   Mode  :character   Median :34260   Median :79780  
##                                        Mean   :26314   Mean   :59766  
##                                        3rd Qu.:34260   3rd Qu.:79780  
##                                        Max.   :34260   Max.   :79780  
##                                                                       
##       AGED       HDB.1..and.2.Room.Flats HDB.3..and.4.Room.Flats
##  Min.   : 6480   Min.   : 830            Min.   :22180          
##  1st Qu.: 6480   1st Qu.: 830            1st Qu.:22180          
##  Median :18860   Median :4300            Median :75000          
##  Mean   :13554   Mean   :2813            Mean   :52363          
##  3rd Qu.:18860   3rd Qu.:4300            3rd Qu.:75000          
##  Max.   :18860   Max.   :4300            Max.   :75000          
##                                                                 
##  HDB.5.Room.and.Executive.Flats Condominiums.and.Other.Apartments
##  Min.   :30500                  Min.   :1770                     
##  1st Qu.:30500                  1st Qu.:1770                     
##  Median :47960                  Median :5220                     
##  Mean   :40477                  Mean   :3741                     
##  3rd Qu.:47960                  3rd Qu.:5220                     
##  Max.   :47960                  Max.   :5220                     
##                                                                  
##  Landed.Properties  Subzone_pop      Pop_density        SHAPE_Area      CLUSTER
##  Min.   :0         Min.   : 55280   Min.   :0.03062   Min.   :1639669   1: 0   
##  1st Qu.:0         1st Qu.: 55280   1st Qu.:0.03062   1st Qu.:1639669   2: 0   
##  Median :0         Median :132900   Median :0.03062   Median :4339824   3: 0   
##  Mean   :0         Mean   : 99634   Mean   :0.03195   Mean   :3182615   4:14   
##  3rd Qu.:0         3rd Qu.:132900   3rd Qu.:0.03371   3rd Qu.:4339824   5: 0   
##  Max.   :0         Max.   :132900   Max.   :0.03371   Max.   :4339824          
##                                                                                
##  SP_CLUSTER             SUBZONE_N   total_URA              geometry 
##  1: 0       FLORA DRIVE      :2   Min.   : 1.00   MULTIPOLYGON :14  
##  2: 0       PASIR RIS CENTRAL:2   1st Qu.: 3.00   epsg:4326    : 0  
##  3: 0       PASIR RIS DRIVE  :2   Median :13.50   +proj=long...: 0  
##  4: 0       TAMPINES EAST    :2   Mean   :13.29                     
##  5:14       CHANGI WEST      :1   3rd Qu.:21.00                     
##             LOYANG WEST      :1   Max.   :27.00                     
##             (Other)          :4

tmap_mode("view")

Plotting the tmap for the total URA count on the SP clusters derived earlier.

tm_shape(ura_residents) +
  tm_fill(col = "SP_CLUSTER") +
  tm_borders(lwd=1,lty="solid") +
  tm_bubbles(size = "total_URA", col= "total_URA", alpha=0.9, border.lwd = 0, border.alpha = 0, palette="Reds", id="SUBZONE_N")

Analysis of the map above:

As seen from the plotted map, we can tell that which clusters have more shopping counts:

Highest Shopping Count to Lowest Shopping Count

• Cluster 3 (728)
• Cluster 1 (507)
• Cluster 4 (180)
• Cluster 2 (24)
• Cluster 5 (14)

Key Highlights:

Highest: Cluster 3

Given that Cluster 3 has higher in business, financial, government embassies and shopping counts, the subzones in this cluster are more susceptible to having costlier residences. This is due to the fact that there are little residential units built due to other buildings occupying the spaces, and there are also many amenities nearby which mark up the price greatly. The costly residences are mainly due to the convenience that residents can obtain if they purchase these residential units such as the private properties in Singapore, especially when the location is near to the central and that there are many available services nearby for them to seek for. Thus, this results in Cluster 3 having a higher upmarket residential area count since the subzones are centrally located as well.

Lowest: Cluster 5

As for Cluster 5, given that there are many residential buildings for residents to purchase, and that it is densely populated with little commercialized buildings, it has the lowest upmarket residential area count. The subzones in this cluster have more HDB buildings, which make the income levels of the residents staying in this cluster more or less the same. Thus, this will not boost the need for a upmarket residential area to a large extent since purchasing power is limited. Furthermore, it is not as accessible as compared to the subzones in Cluster 3.

tmap_mode("plot")