Take-home Exercise 03
Erika Aldisa
10/23/2020 (updated: 2020-11-09)
IS415 Geospatial Analytics and Application
Instructor: Dr. Kam Tin Seong.
Assoc. Professor of Information Systems (Practice)
Delineating Industry Clusters by using Geographic Segmentation Approach
1. Overview
Task:
Preparing a series of choropleth maps showing the distribution of spatial specialisation by industry type, 2016 at municipality level.
Delineating industry specialisation clusters by using hierarchical clustering method and display their distribution by using appropriate thematic mapping technique.
Delineating industry specialisation clusters by using spatially constrained clustering method and display their distribution by using appropriate thematic mapping technique.
1.1. Data sets used
2016 Brazil Municipality boundary file and metropolitan boundary file. This is extracted using the geobr package
“BRAZIL_CITIES.csv” - This data file consists of 81 columns and 5573 rows. Each row representing one municipality.
“Data_Dictionary.csv” - This file provides meta data of each columns in BRAZIL_CITIES.csv.
Both BRAZIL_CITIES.csv and Data_Dictionary.csv can be downloaded from Kaggle.
1.2. Install & Load R packages
R packages used:
tidyverse - for reading, handling and visualizing attribute data (readr, ggplot2 & dplyr)
tmap - for choropleth mapping
sf, rgdal, raster - for handling spatial data
spdep - for spatial statistical analysis
geobr - access to official spatial data sets of Brazil as ‘sf’ objects in R
corrplot, ggpubr, heatmaply - multivariate data visualization and analysis
cluster - clustering analysis
packages = c('tidyverse', 'tmap','rgdal', 'spdep','raster', 'geobr', 'sf', 'ggpubr', 'cluster', 'factoextra', 'heatmaply', 'corrplot', 'psych')
for (p in packages){
if(!require(p, character.only = T)){
install.packages(p)
}
library(p, character.only = T)
}2. Geospatial data wrangling
2.1 Importing geospatial data
We want to segment São Paulo Macrometropolis at the municipality level by using data provided by Brazilian Institute of Geography and Statistics,IBGE.
We will first find out the available datasets/functions in the geobr package using list_geobr() function.
datasets <- list_geobr()
datasets## # A tibble: 23 x 4
## `function` geography years source
## <chr> <chr> <chr> <chr>
## 1 `read_country` Country 1872, 1900, 1911, 1920, 1933, ~ IBGE
## 2 `read_region` Region 2000, 2001, 2010, 2013, 2014, ~ IBGE
## 3 `read_state` States 1872, 1900, 1911, 1920, 1933, ~ IBGE
## 4 `read_meso_regi~ Meso region 2000, 2001, 2010, 2013, 2014, ~ IBGE
## 5 `read_micro_reg~ Micro region 2000, 2001, 2010, 2013, 2014, ~ IBGE
## 6 `read_intermedi~ Intermediate region 2017, 2019 IBGE
## 7 `read_immediate~ Immediate region 2017, 2019 IBGE
## 8 `read_weighting~ Census weighting are~ 2010 IBGE
## 9 `read_census_tr~ Census tract (setor ~ 2000, 2010 IBGE
## 10 `read_municipal~ Municipality seats (~ 1872, 1900, 1911, 1920, 1933, ~ IBGE
## # ... with 13 more rowsFrom my research, some findings are:
State - subnational entities with certain degree of autonomy, there are 26 states in Brazil
Municipality - states are divided into municipalities, there are 5,570 municipalities in Brazil, the average state in Brazil has 214 municipalities
São Paulo has 645 municipalities, grouped into 63 microregions, furthe grouped into 15 mesoregions.
Meso - meso region was a subdivision of the Brazilian states, grouping together various municipalities in proximity and with common characteristics. They were abolished in 2017 and replaced by “intermediary geographic regions”
Micro - micro region was a legally defined area consisting of a group of municipalities. They were abolished in 2017 and replaced by “immediate geographic regions”
Microregions and mesoregions were used primarily for statistical purposes by the IBGE.
Since we want to get the municipalities of São Paulo state as well as the metropolitan areas, we will use read_municipality() function and read_metro_area() function of geobr package.
municipality <- read_municipality(code_muni = "all", year = 2016)##
|
| | 0%
|
|=== | 4%
|
|===== | 7%
|
|======== | 11%
|
|========== | 15%
|
|============= | 19%
|
|================ | 22%
|
|================== | 26%
|
|===================== | 30%
|
|======================= | 33%
|
|========================== | 37%
|
|============================= | 41%
|
|=============================== | 44%
|
|================================== | 48%
|
|==================================== | 52%
|
|======================================= | 56%
|
|========================================= | 59%
|
|============================================ | 63%
|
|=============================================== | 67%
|
|================================================= | 70%
|
|==================================================== | 74%
|
|====================================================== | 78%
|
|========================================================= | 81%
|
|============================================================ | 85%
|
|============================================================== | 89%
|
|================================================================= | 93%
|
|=================================================================== | 96%
|
|======================================================================| 100%metro_area <- read_metro_area(year = 2016)##
|
| | 0%
|
|======================================================================| 100%
##
Downloading: 770 B
Downloading: 770 B
Downloading: 1.2 kB
Downloading: 1.2 kB
Downloading: 2.1 kB
Downloading: 2.1 kB
Downloading: 2.1 kB
Downloading: 2.1 kB
Downloading: 2.1 kB
Downloading: 2.1 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 10 kB
Downloading: 18 kB
Downloading: 18 kB
Downloading: 18 kB
Downloading: 18 kB
Downloading: 18 kB
Downloading: 18 kB
Downloading: 26 kB
Downloading: 26 kB
Downloading: 26 kB
Downloading: 26 kB
Downloading: 26 kB
Downloading: 26 kB
Downloading: 34 kB
Downloading: 34 kB
Downloading: 51 kB
Downloading: 51 kB
Downloading: 67 kB
Downloading: 67 kB
Downloading: 83 kB
Downloading: 83 kB
Downloading: 83 kB
Downloading: 83 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 91 kB
Downloading: 99 kB
Downloading: 99 kB
Downloading: 99 kB
Downloading: 99 kB
Downloading: 110 kB
Downloading: 110 kB
Downloading: 110 kB
Downloading: 110 kB
Downloading: 110 kB
Downloading: 110 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 120 kB
Downloading: 130 kB
Downloading: 130 kB
Downloading: 130 kB
Downloading: 130 kB
Downloading: 140 kB
Downloading: 140 kB
Downloading: 140 kB
Downloading: 140 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 150 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 160 kB
Downloading: 170 kB
Downloading: 170 kB
Downloading: 170 kB
Downloading: 170 kB
Downloading: 180 kB
Downloading: 180 kB
Downloading: 180 kB
Downloading: 180 kB
Downloading: 190 kB
Downloading: 190 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 200 kB
Downloading: 210 kB
Downloading: 210 kB
Downloading: 210 kB
Downloading: 210 kB
Downloading: 220 kB
Downloading: 220 kB
Downloading: 220 kB
Downloading: 220 kB
Downloading: 230 kB
Downloading: 230 kB
Downloading: 230 kB
Downloading: 230 kB
Downloading: 230 kB
Downloading: 230 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 240 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 250 kB
Downloading: 260 kB
Downloading: 260 kB
Downloading: 260 kB
Downloading: 260 kB
Downloading: 270 kB
Downloading: 270 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 280 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 290 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 300 kB
Downloading: 310 kB
Downloading: 310 kB
Downloading: 310 kB
Downloading: 310 kB
Downloading: 320 kB
Downloading: 320 kB
Downloading: 320 kB
Downloading: 320 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 330 kB
Downloading: 340 kB
Downloading: 340 kB
Downloading: 340 kB
Downloading: 340 kB
Downloading: 350 kB
Downloading: 350 kB
Downloading: 360 kB
Downloading: 360 kB
Downloading: 360 kB
Downloading: 360 kB
Downloading: 360 kB
Downloading: 360 kB
Downloading: 370 kB
Downloading: 370 kB
Downloading: 370 kB
Downloading: 370 kB
Downloading: 370 kB
Downloading: 370 kB
Downloading: 380 kB
Downloading: 380 kB
Downloading: 390 kB
Downloading: 390 kB
Downloading: 390 kB
Downloading: 390 kB
Downloading: 400 kB
Downloading: 400 kB
Downloading: 400 kB
Downloading: 400 kB
Downloading: 410 kB
Downloading: 410 kB
Downloading: 410 kB
Downloading: 410 kB
Downloading: 410 kB
Downloading: 410 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 420 kB
Downloading: 430 kB
Downloading: 430 kB
Downloading: 430 kB
Downloading: 430 kB
Downloading: 440 kB
Downloading: 440 kB
Downloading: 440 kB
Downloading: 440 kB
Downloading: 440 kB
Downloading: 440 kB
Downloading: 450 kB
Downloading: 450 kB
Downloading: 450 kB
Downloading: 450 kB
Downloading: 450 kB
Downloading: 450 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 460 kB
Downloading: 470 kB
Downloading: 470 kB
Downloading: 470 kB
Downloading: 470 kB
Downloading: 470 kB
Downloading: 470 kB
Downloading: 490 kB
Downloading: 490 kB
Downloading: 490 kB
Downloading: 490 kB
Downloading: 490 kB
Downloading: 490 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 500 kB
Downloading: 510 kB
Downloading: 510 kB
Downloading: 510 kB
Downloading: 510 kB
Downloading: 510 kB
Downloading: 510 kB
Downloading: 530 kB
Downloading: 530 kB
Downloading: 540 kB
Downloading: 540 kB
Downloading: 560 kB
Downloading: 560 kB
Downloading: 560 kB
Downloading: 560 kB
Downloading: 570 kB
Downloading: 570 kB
Downloading: 570 kB
Downloading: 570 kB
Downloading: 580 kB
Downloading: 580 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 590 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 600 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 610 kB
Downloading: 620 kB
Downloading: 620 kB
Downloading: 620 kB
Downloading: 620 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 630 kB
Downloading: 640 kB
Downloading: 640 kB
Downloading: 640 kB
Downloading: 640 kB
Downloading: 640 kB
Downloading: 640 kB
Downloading: 650 kB
Downloading: 650 kB
Downloading: 650 kB
Downloading: 650 kB
Downloading: 650 kB
Downloading: 650 kB
Downloading: 660 kB
Downloading: 660 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 670 kB
Downloading: 680 kB
Downloading: 680 kB
Downloading: 680 kB
Downloading: 680 kB
Downloading: 680 kB
Downloading: 680 kB
Downloading: 690 kB
Downloading: 690 kB
Downloading: 690 kB
Downloading: 690 kB
Downloading: 690 kB
Downloading: 690 kB
Downloading: 700 kB
Downloading: 700 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 710 kB
Downloading: 720 kB
Downloading: 720 kB
Downloading: 720 kB
Downloading: 720 kB
Downloading: 730 kB
Downloading: 730 kB
Downloading: 730 kB
Downloading: 730 kB
Downloading: 730 kB
Downloading: 730 kB
Downloading: 740 kB
Downloading: 740 kB
Downloading: 740 kB
Downloading: 740 kB
Downloading: 750 kB
Downloading: 750 kB
Downloading: 750 kB
Downloading: 750 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 760 kB
Downloading: 770 kB
Downloading: 770 kB
Downloading: 770 kB
Downloading: 770 kB
Downloading: 770 kB
Downloading: 770 kB
Downloading: 780 kB
Downloading: 780 kB
Downloading: 780 kB
Downloading: 780 kB
Downloading: 780 kB
Downloading: 780 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 790 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 800 kB
Downloading: 810 kB
Downloading: 810 kB
Downloading: 810 kB
Downloading: 810 kB
Downloading: 820 kB
Downloading: 820 kB
Downloading: 820 kB
Downloading: 820 kB
Downloading: 820 kB
Downloading: 820 kB
Downloading: 840 kB
Downloading: 840 kB
Downloading: 850 kB
Downloading: 850 kB
Downloading: 870 kB
Downloading: 870 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 880 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 890 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 900 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 910 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 920 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 930 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 940 kB
Downloading: 950 kB
Downloading: 950 kB
Downloading: 950 kB
Downloading: 950 kB
Downloading: 950 kB
Downloading: 950 kB
Downloading: 960 kB
Downloading: 960 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 970 kB
Downloading: 980 kB
Downloading: 980 kB
Downloading: 980 kB
Downloading: 980 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 990 kB
Downloading: 1,000 kB
Downloading: 1,000 kB
Downloading: 1,000 kB
Downloading: 1,000 kB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.1 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.2 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.3 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.4 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.5 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.6 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.7 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.8 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 1.9 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.1 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.2 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.3 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.4 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.5 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.6 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.7 MB
Downloading: 2.8 MB
Downloading: 2.8 MB
Downloading: 2.8 MB
Downloading: 2.8 MB
Downloading: 2.8 MB
Downloading: 2.8 MBSão Paulo Macrometropolis is one of the biggest urban agglomerations in the world.
Beyond the Greater São Paulo, the megalopolis encompasses the metropolitan areas of Campinas, Santos, Sorocaba and the Paraíba Valley, and other nearby cities, which include urban agglomerations in the conurbation process, as Jundiaí and Piracicaba.
Hence, we will extract the metro area of the Sao Paulo state.
metro_area_saopaulo <- metro_area %>%
filter(abbrev_state == "SP")
distinct(as.data.frame(metro_area_saopaulo$name_metro))## metro_area_saopaulo$name_metro
## 1 Aglomeração Urbana de Jundiaí
## 2 Aglomeração Urbana de Piracicaba-AU- Piracicaba
## 3 RM Baixada Santista
## 4 RM Campinas
## 5 RM de Sorocaba
## 6 RM do Vale do Paraíba e Litoral Norte
## 7 RM São Paulohead(as.data.frame(metro_area_saopaulo))## code_muni name_muni code_state abbrev_state
## 1 3508405 Cabreúva 35 SP
## 2 3509601 Campo Limpo Paulista 35 SP
## 3 3524006 Itupeva 35 SP
## 4 3525201 Jarinu 35 SP
## 5 3525904 Jundiaí 35 SP
## 6 3527306 Louveira 35 SP
## name_metro type subdivision legislation
## 1 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## 2 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## 3 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## 4 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## 5 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## 6 Aglomeração Urbana de Jundiaí AGLO NÃO TEM Lei Complementar 1.146
## legislation_date geom
## 1 24.08.2011 MULTIPOLYGON (((-47.09692 -...
## 2 24.08.2011 MULTIPOLYGON (((-46.78614 -...
## 3 24.08.2011 MULTIPOLYGON (((-47.04599 -...
## 4 24.08.2011 MULTIPOLYGON (((-46.71471 -...
## 5 24.08.2011 MULTIPOLYGON (((-46.85676 -...
## 6 24.08.2011 MULTIPOLYGON (((-46.91599 -...However, we are still missing one final region of the macrometropolis which is Regional Unit of Bragança Paulista city. We will get this area from the municipality dataframe.
Let’s find the code_state of São Paulo, which will be the starting 2 digit codes to find the municipalities, our study area.
state <- read_state(code_state = "all", year = 2016)##
|
| | 0%
|
|=== | 4%
|
|===== | 7%
|
|======== | 11%
|
|========== | 15%
|
|============= | 19%
|
|================ | 22%
|
|================== | 26%
|
|===================== | 30%
|
|======================= | 33%
|
|========================== | 37%
|
|============================= | 41%
|
|=============================== | 44%
|
|================================== | 48%
|
|==================================== | 52%
|
|======================================= | 56%
|
|========================================= | 59%
|
|============================================ | 63%
|
|=============================================== | 67%
|
|================================================= | 70%
|
|==================================================== | 74%
|
|====================================================== | 78%
|
|========================================================= | 81%
|
|============================================================ | 85%
|
|============================================================== | 89%
|
|================================================================= | 93%
|
|=================================================================== | 96%
|
|======================================================================| 100%state %>%
filter(name_state == "São Paulo")## Simple feature collection with 1 feature and 5 fields
## geometry type: MULTIPOLYGON
## dimension: XY
## bbox: xmin: -53.10986 ymin: -25.35794 xmax: -44.16137 ymax: -19.77966
## geographic CRS: SIRGAS 2000
## code_state abbrev_state name_state code_region name_region
## 1 35 SP São Paulo 3 Sudeste
## geom
## 1 MULTIPOLYGON (((-48.03716 -...We can see that the code_state of São Paulo is 35.
municipality_saopaulo <- municipality %>%
filter(code_state == 35)From searching of the municipalities of Regional Unit of Bragança Paulista city, we know that it is the same as the microregion of Bragança Paulista contains these municipalities:
Atibaia
Bom Jesus Dos Perdões
Bragança Paulista
Itatiba
Jarinu (although in the wiki, it’s part of Regional Unit of Bragança Paulista city, it is already part of Aglomeração Urbana de Jundiaí, returned from the dataset read_metro_area)
Joanópolis
Morungaba
Nazaré Paulista
Piracaia
Tuiuti
Vargem
so we will not filter for the municipality Jarinu to avoid double.
RU_Bragança_Paulista <- municipality_saopaulo %>%
filter(name_muni %in% c("Atibaia",
"Bom Jesus Dos Perdões",
"Bragança Paulista",
"Itatiba",
"Joanópolis",
"Morungaba",
"Nazaré Paulista",
"Piracaia",
"Tuiuti",
"Vargem")
)Now, let’s combine the study area. However, before that, we need to add the metro name of the Regional unit of Bragança Paulista.
RU_Bragança_Paulista <- RU_Bragança_Paulista %>%
mutate(name_metro = "Regional Unit of Bragança Paulista city")
head(as.data.frame(RU_Bragança_Paulista))## code_muni name_muni code_state abbrev_state
## 1 3504107 Atibaia 35 SP
## 2 3507100 Bom Jesus Dos Perdões 35 SP
## 3 3507605 Bragança Paulista 35 SP
## 4 3523404 Itatiba 35 SP
## 5 3525508 Joanópolis 35 SP
## 6 3532009 Morungaba 35 SP
## geom name_metro
## 1 MULTIPOLYGON (((-46.66146 -... Regional Unit of Bragança Paulista city
## 2 MULTIPOLYGON (((-46.47303 -... Regional Unit of Bragança Paulista city
## 3 MULTIPOLYGON (((-46.50858 -... Regional Unit of Bragança Paulista city
## 4 MULTIPOLYGON (((-46.76852 -... Regional Unit of Bragança Paulista city
## 5 MULTIPOLYGON (((-46.14383 -... Regional Unit of Bragança Paulista city
## 6 MULTIPOLYGON (((-46.80227 -... Regional Unit of Bragança Paulista citymetro_area_saopaulo <- metro_area_saopaulo %>%
select(code_muni, name_muni, code_state, abbrev_state, name_metro, geom)
macrometro_saopaulo <- rbind(metro_area_saopaulo, RU_Bragança_Paulista)Let’s check for duplicated values since we just use rbind() and not joining based on common values.
macrometro_saopaulo[duplicated(macrometro_saopaulo$code_muni),]## Simple feature collection with 2 features and 5 fields
## geometry type: MULTIPOLYGON
## dimension: XY
## bbox: xmin: -46.92735 ymin: -23.10682 xmax: -46.67038 ymax: -22.83401
## geographic CRS: SIRGAS 2000
## code_muni name_muni code_state abbrev_state
## 168 3523404 Itatiba 35 SP
## 170 3532009 Morungaba 35 SP
## name_metro geom
## 168 Regional Unit of Bragança Paulista city MULTIPOLYGON (((-46.76852 -...
## 170 Regional Unit of Bragança Paulista city MULTIPOLYGON (((-46.80227 -...We see that Itatiba and Morungaba are duplicates. Let’s filter for these municipalities.
macrometro_saopaulo %>%
filter(name_muni %in% c("Itatiba", "Morungaba"))## Simple feature collection with 4 features and 5 fields
## geometry type: MULTIPOLYGON
## dimension: XY
## bbox: xmin: -46.92735 ymin: -23.10682 xmax: -46.67038 ymax: -22.83401
## geographic CRS: SIRGAS 2000
## code_muni name_muni code_state abbrev_state
## 1 3523404 Itatiba 35 SP
## 2 3532009 Morungaba 35 SP
## 3 3523404 Itatiba 35 SP
## 4 3532009 Morungaba 35 SP
## name_metro geom
## 1 RM Campinas MULTIPOLYGON (((-46.76852 -...
## 2 RM Campinas MULTIPOLYGON (((-46.80227 -...
## 3 Regional Unit of Bragança Paulista city MULTIPOLYGON (((-46.76852 -...
## 4 Regional Unit of Bragança Paulista city MULTIPOLYGON (((-46.80227 -...Since Regional Unit of Bragança Paulista city has 10 municipalities according to wikipedia, we will remove the duplicated municipalities in the metropolitan region of Campinas.
macrometro_saopaulo <- macrometro_saopaulo[!(macrometro_saopaulo$name_muni %in% c("Itatiba", "Morungaba") & macrometro_saopaulo$name_metro == "RM Campinas"),]
macrometro_saopaulo[duplicated(macrometro_saopaulo$code_muni),]## Simple feature collection with 0 features and 5 fields
## bbox: xmin: NA ymin: NA xmax: NA ymax: NA
## geographic CRS: SIRGAS 2000
## [1] code_muni name_muni code_state abbrev_state name_metro
## [6] geom
## <0 rows> (or 0-length row.names)2.2 Base Map plot
tm_shape(macrometro_saopaulo)+
tm_fill(col = "name_metro") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "São Paulo Macrometropolis") +
tm_compass(type="8star", size = 2, position = c("left", "bottom")) +
tm_scale_bar(width = 0.15, position = c("left", "bottom"))## Some legend labels were too wide. These labels have been resized to 0.54. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.
2.3 Importing aspatial data
We will use read_csv2() function of readr package to import the csv data into R, read_cav2() function reads semicolon separated files (common in countries where , is used as the decimal place).
brazil_cities <- read_csv2("data/aspatial/BRAZIL_CITIES.csv")
brazil_cities <- brazil_cities %>%
filter(STATE == "SP")
glimpse(brazil_cities)## Rows: 645
## Columns: 81
## $ CITY <chr> "Adamantina", "Adolfo", "Aguaí", "Águas Da...
## $ STATE <chr> "SP", "SP", "SP", "SP", "SP", "SP", "SP", ...
## $ CAPITAL <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...
## $ IBGE_RES_POP <dbl> 33797, 3557, 32148, 7584, 17266, 5601, 270...
## $ IBGE_RES_POP_BRAS <dbl> 33769, 3557, 32126, 7549, 17206, 5585, 269...
## $ IBGE_RES_POP_ESTR <dbl> 28, 0, 22, 35, 60, 16, 14, 9, 8, 0, 0, 6, ...
## $ IBGE_DU <dbl> 11335, 1200, 9899, 2515, 5597, 1873, 990, ...
## $ IBGE_DU_URBAN <dbl> 10777, 1081, 8970, 2265, 5544, 1433, 990, ...
## $ IBGE_DU_RURAL <dbl> 558, 119, 929, 250, 53, 440, NA, 432, 391,...
## $ IBGE_POP <dbl> 31695, 3200, 28182, 6695, 6886, 4245, 2687...
## $ IBGE_1 <dbl> 333, 30, 363, 84, 71, 50, 19, 433, 49, 25,...
## $ `IBGE_1-4` <dbl> 1282, 149, 1569, 278, 293, 208, 95, 1767, ...
## $ `IBGE_5-9` <dbl> 1803, 206, 1943, 389, 405, 290, 135, 2250,...
## $ `IBGE_10-14` <dbl> 2089, 234, 2273, 436, 482, 375, 180, 2777,...
## $ `IBGE_15-59` <dbl> 20651, 2079, 18608, 4268, 4411, 2631, 1592...
## $ `IBGE_60+` <dbl> 5537, 502, 3426, 1240, 1224, 691, 666, 361...
## $ IBGE_PLANTED_AREA <dbl> 14699, 9755, 31346, 1387, 474, 16245, 0, 1...
## $ `IBGE_CROP_PRODUCTION_$` <dbl> 69644, 67479, 223900, 8630, 6287, 132857, ...
## $ `IDHM Ranking 2010` <dbl> 69, 1044, 1460, 124, 661, 427, 2, 662, 156...
## $ IDHM <chr> "0.79", "0.73", "0.715", "0.78", "0.745", ...
## $ IDHM_Renda <chr> "0.772", "0.71", "0.703", "0.75", "0.725",...
## $ IDHM_Longevidade <chr> "0.852", "0.844", "0.858", "0.886", "0.846...
## $ IDHM_Educacao <chr> "0.75", "0.648", "0.606", "0.716", "0.675"...
## $ LONG <dbl> -5107336475, -4964972143, -4697969311, -46...
## $ LAT <dbl> -2168831148, -2123272978, -22059684, -2193...
## $ ALT <chr> "451.12", "425.39", "662.48", "832.91", "8...
## $ PAY_TV <dbl> 1354, 520, 1389, 606, 2522, 685, 1033, 270...
## $ FIXED_PHONES <dbl> 7648, 271, 5019, 1803, 4393, 989, 1420, 52...
## $ AREA <dbl> 41199.00000, 21106.00000, 47455.00000, 142...
## $ REGIAO_TUR <chr> "Águas Do Oeste", "Coração Do Tietê", NA, ...
## $ CATEGORIA_TUR <chr> "C", "D", NA, "D", "B", "C", "C", "D", NA,...
## $ ESTIMATED_POP <dbl> 35023, 3571, 35954, 8137, 18599, 6040, 338...
## $ RURAL_URBAN <chr> "Urbano", "Rural Adjacente", "Urbano", "Ur...
## $ GVA_AGROPEC <chr> "41899.77", "29090.08", "115600.38", "1702...
## $ GVA_INDUSTRY <chr> "298402.33", "6.14", "146491.98", "16235.6...
## $ GVA_SERVICES <dbl> 58763655, 2772, 30715581, 690979, 28316922...
## $ GVA_PUBLIC <dbl> 15108903, 2101878, 11782249, 3094874, 7222...
## $ GVA_TOTAL <dbl> 107902768, 8398, 68707, 13330883, 42463029...
## $ TAXES <chr> "73.41", "2.49", "77216.87", "9345.48", "3...
## $ GDP <dbl> 115244122, 8647, 76428753, 14265432, 45527...
## $ POP_GDP <dbl> 35094, 3616, 35189, 8065, 18412, 5977, 320...
## $ GDP_CAPITA <dbl> 328387, 2391198, 217195, 1768807, 2472702,...
## $ GVA_MAIN <chr> "Demais serviços", "Agricultura, inclusive...
## $ MUN_EXPENDIT <dbl> 115703289, NA, NA, 22737457, NA, 25978262,...
## $ COMP_TOT <dbl> 1726, 81, 799, 212, 881, 216, 202, 840, 13...
## $ COMP_A <dbl> 272, 10, 149, 48, 11, 60, 2, 46, 61, 31, 4...
## $ COMP_B <dbl> 0, 2, 9, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, ...
## $ COMP_C <dbl> 102, 3, 54, 18, 168, 10, 4, 91, 14, 9, 3, ...
## $ COMP_D <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...
## $ COMP_E <dbl> 4, 0, 3, 0, 1, 0, 1, 3, 0, 0, 0, 1, 0, 0, ...
## $ COMP_F <dbl> 35, 2, 21, 9, 41, 7, 6, 38, 4, 3, 1, 25, 1...
## $ COMP_G <dbl> 663, 33, 333, 63, 328, 68, 99, 365, 31, 37...
## $ COMP_H <dbl> 102, 5, 44, 7, 11, 15, 3, 50, 3, 3, 8, 64,...
## $ COMP_I <dbl> 99, 4, 51, 21, 92, 19, 40, 64, 8, 3, 8, 54...
## $ COMP_J <dbl> 41, 0, 8, 7, 5, 1, 5, 3, 2, 0, 0, 7, 0, 2,...
## $ COMP_K <dbl> 21, 0, 2, 0, 8, 0, 2, 5, 0, 3, 0, 2, 0, 2,...
## $ COMP_L <dbl> 28, 0, 5, 3, 3, 2, 1, 4, 3, 1, 0, 3, 0, 1,...
## $ COMP_M <dbl> 75, 2, 21, 6, 24, 5, 9, 33, 0, 4, 1, 20, 4...
## $ COMP_N <dbl> 79, 2, 35, 10, 96, 8, 15, 36, 2, 6, 5, 23,...
## $ COMP_O <dbl> 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, ...
## $ COMP_P <dbl> 32, 3, 12, 3, 23, 4, 3, 23, 2, 0, 3, 13, 3...
## $ COMP_Q <dbl> 65, 1, 21, 2, 28, 1, 3, 27, 0, 0, 6, 11, 2...
## $ COMP_R <dbl> 20, 3, 10, 4, 10, 5, 2, 15, 0, 0, 0, 5, 2,...
## $ COMP_S <dbl> 86, 9, 19, 8, 30, 8, 4, 35, 5, 5, 17, 36, ...
## $ COMP_T <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...
## $ COMP_U <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...
## $ HOTELS <dbl> NA, NA, NA, NA, 4, NA, NA, NA, NA, NA, NA,...
## $ BEDS <dbl> NA, NA, NA, NA, 723, NA, NA, NA, NA, NA, N...
## $ Pr_Agencies <dbl> 3, 1, 3, 2, 3, 1, 1, 3, NA, 0, 1, 3, 0, 2,...
## $ Pu_Agencies <dbl> 2, 0, 2, 1, 2, 1, 2, 2, NA, 1, 0, 3, 1, 0,...
## $ Pr_Bank <dbl> 3, 1, 3, 2, 3, 1, 1, 3, NA, 0, 1, 2, 0, 2,...
## $ Pu_Bank <dbl> 2, 0, 2, 1, 2, 1, 2, 2, NA, 1, 0, 2, 1, 0,...
## $ Pr_Assets <dbl> 526179392, 32631770, 235543694, 61947294, ...
## $ Pu_Assets <dbl> 823567347, 0, 198861114, 21858555, 2991064...
## $ Cars <dbl> 14851, 1394, 11167, 2816, 7566, 2489, 1721...
## $ Motorcycles <dbl> 6481, 401, 5754, 945, 3644, 594, 340, 4808...
## $ Wheeled_tractor <dbl> 4, 0, 3, 0, 0, 0, 3, 9, 3, 0, 1, 0, 0, 8, ...
## $ UBER <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ MAC <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ `WAL-MART` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ POST_OFFICES <dbl> 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 2, 1, 3, 1, ...2.4 Combine geospatial and aspatial data
We will be using inner_join() function to join the 2 dataframe. We need to first join the by the city/municipality name then filter for the state of SP since there might be same city/municipality names in different states.
saopaulo <- inner_join(macrometro_saopaulo, brazil_cities, by = c("name_muni" = "CITY")) %>%
filter(code_state == "35" & STATE == "SP")nrow(saopaulo)## [1] 171nrow(macrometro_saopaulo)## [1] 172We can see that there’s difference in number of municipalities in the São Paulo Macrometropolis. Let’s plot the map using the combined dataframe to see the missing municipality.
tm_shape(saopaulo)+
tm_fill(col = "name_metro") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "São Paulo Macrometropolis") +
tm_compass(type="8star", size = 2, position = c("left", "bottom")) +
tm_scale_bar(width = 0.15, position = c("left", "bottom"))## Some legend labels were too wide. These labels have been resized to 0.54. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.
We can see that the missing municipality is part of the Metropolitan Region of Campinas, hence we shall derive the missing municipality.
campinas_saopaulo <- saopaulo %>%
select(code_muni, name_muni, name_metro, STATE, CAPITAL, geom) %>%
filter(name_metro == "RM Campinas")
campinas_saopaulo$name_muni## [1] "Americana" "Artur Nogueira" "Campinas"
## [4] "Cosmópolis" "Engenheiro Coelho" "Holambra"
## [7] "Hortolândia" "Indaiatuba" "Jaguariúna"
## [10] "Monte Mor" "Nova Odessa" "Paulínia"
## [13] "Pedreira" "Santo Antônio De Posse" "Sumaré"
## [16] "Valinhos" "Vinhedo"campinas_macrometro <- macrometro_saopaulo %>%
filter(name_metro == "RM Campinas")
campinas_macrometro$name_muni## [1] "Americana" "Artur Nogueira" "Campinas"
## [4] "Cosmópolis" "Engenheiro Coelho" "Holambra"
## [7] "Hortolândia" "Indaiatuba" "Jaguariúna"
## [10] "Monte Mor" "Nova Odessa" "Paulínia"
## [13] "Pedreira" "Santa Bárbara D'oeste" "Santo Antônio De Posse"
## [16] "Sumaré" "Valinhos" "Vinhedo"We can see that the missing municipality from the combined dataframe is “Santa Bárbara D’oeste”.
macrometro_saopaulo %>%
filter(name_muni == "Santa Bárbara D'oeste")## Simple feature collection with 1 feature and 5 fields
## geometry type: MULTIPOLYGON
## dimension: XY
## bbox: xmin: -47.53053 ymin: -22.90827 xmax: -47.34182 ymax: -22.69927
## geographic CRS: SIRGAS 2000
## code_muni name_muni code_state abbrev_state name_metro
## 1 3545803 Santa Bárbara D'oeste 35 SP RM Campinas
## geom
## 1 MULTIPOLYGON (((-47.38612 -...brazil_cities %>%
filter(CITY == "Santa Bárbara D'Oeste")## # A tibble: 1 x 81
## CITY STATE CAPITAL IBGE_RES_POP IBGE_RES_POP_BR~ IBGE_RES_POP_ES~ IBGE_DU
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Sant~ SP 0 180009 179727 282 54955
## # ... with 74 more variables: IBGE_DU_URBAN <dbl>, IBGE_DU_RURAL <dbl>,
## # IBGE_POP <dbl>, IBGE_1 <dbl>, `IBGE_1-4` <dbl>, `IBGE_5-9` <dbl>,
## # `IBGE_10-14` <dbl>, `IBGE_15-59` <dbl>, `IBGE_60+` <dbl>,
## # IBGE_PLANTED_AREA <dbl>, `IBGE_CROP_PRODUCTION_$` <dbl>, `IDHM Ranking
## # 2010` <dbl>, IDHM <chr>, IDHM_Renda <chr>, IDHM_Longevidade <chr>,
## # IDHM_Educacao <chr>, LONG <dbl>, LAT <dbl>, ALT <chr>, PAY_TV <dbl>,
## # FIXED_PHONES <dbl>, AREA <dbl>, REGIAO_TUR <chr>, CATEGORIA_TUR <chr>,
## # ESTIMATED_POP <dbl>, RURAL_URBAN <chr>, GVA_AGROPEC <chr>,
## # GVA_INDUSTRY <chr>, GVA_SERVICES <dbl>, GVA_PUBLIC <dbl>, GVA_TOTAL <dbl>,
## # TAXES <chr>, GDP <dbl>, POP_GDP <dbl>, GDP_CAPITA <dbl>, GVA_MAIN <chr>,
## # MUN_EXPENDIT <dbl>, COMP_TOT <dbl>, COMP_A <dbl>, COMP_B <dbl>,
## # COMP_C <dbl>, COMP_D <dbl>, COMP_E <dbl>, COMP_F <dbl>, COMP_G <dbl>,
## # COMP_H <dbl>, COMP_I <dbl>, COMP_J <dbl>, COMP_K <dbl>, COMP_L <dbl>,
## # COMP_M <dbl>, COMP_N <dbl>, COMP_O <dbl>, COMP_P <dbl>, COMP_Q <dbl>,
## # COMP_R <dbl>, COMP_S <dbl>, COMP_T <dbl>, COMP_U <dbl>, HOTELS <dbl>,
## # BEDS <dbl>, Pr_Agencies <dbl>, Pu_Agencies <dbl>, Pr_Bank <dbl>,
## # Pu_Bank <dbl>, Pr_Assets <dbl>, Pu_Assets <dbl>, Cars <dbl>,
## # Motorcycles <dbl>, Wheeled_tractor <dbl>, UBER <dbl>, MAC <dbl>,
## # `WAL-MART` <dbl>, POST_OFFICES <dbl>The problem is that the spelling of the municipality is different in the aspatial dataframe brazil_cities.
The spelling is “Santa Bárbara D’Oeste” in brazil_cities and “Santa Bárbara D’oeste” in macrometro_saopaulo.
Let’s fix this!
macrometro_saopaulo$name_muni[macrometro_saopaulo$name_muni == "Santa Bárbara D'oeste"] <- "Santa Bárbara D'Oeste"saopaulo <- inner_join(macrometro_saopaulo, brazil_cities, by = c("name_muni" = "CITY")) %>%
filter(code_state == "35" & STATE == "SP")nrow(saopaulo)## [1] 172nrow(macrometro_saopaulo)## [1] 172Let’s plot the map once again.
tm_shape(saopaulo)+
tm_fill(col = "name_metro") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "São Paulo Macrometropolis") +
tm_compass(type="8star", size = 2, position = c("left", "bottom")) +
tm_scale_bar(width = 0.15, position = c("left", "bottom"))## Some legend labels were too wide. These labels have been resized to 0.54. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.
2.5 Deriving Industry Location Quotient (LQ)
Since we want to analyse the distribution of spatial specialisation by industry type at municipality level in 2016, we can use Location Quotient to do that.
Location Quotient - quantifying how concentrated a particular industry, cluster, occupation, or demographic group is in a region as compared to the nation.
Assuming you are calculating LQ for industry a for municipality i. The formula is:
(number of industry a in municipality i / sum of all industry in municipality i)/(number of industry a in Greater Sao Paulo/sum of all industry in Greater Sao Paulo)
Our variables of interest related to industry specialisation would be renamed below.
saopaulo <- saopaulo %>%
rename("AGRI_INDUSTRY" = "COMP_A",
"EXTRACTIVE_INDUSTRY" = "COMP_B",
"TRANSFORMATION_INDUSTRY" = "COMP_C",
"ENERGY_INDUSTRY" = "COMP_D",
"WATER_INDUSTRY" = "COMP_E",
"CONSTRUCTION_INDUSTRY" = "COMP_F",
"TRADE_REPAIR_INDUSTRY" = "COMP_G",
"LOGISTICS_INDUSTRY" = "COMP_H",
"ACCOMS_FOOD_INDUSTRY" = "COMP_I",
"ICT_INDUSTRY" = "COMP_J",
"FINANCIAL_INDUSTRY" = "COMP_K",
"REALESTATE_INDUSTRY" = "COMP_L",
"PROFESSIONAL_TECHNICAL_INDUSTRY" = "COMP_M",
"ADMINISTRATIVE_INDUSTRY" = "COMP_N",
"PUBLIC_INDUSTRY" = "COMP_O",
"EDUCATION_INDUSTRY" = "COMP_P",
"HEALTHCARE_INDUSTRY" = "COMP_Q",
"ARTS_RECREATION_INDUSTRY" = "COMP_R",
"OTHER_SERVICES_INDUSTRY" = "COMP_S",
"DOMESTIC_INDUSTRY" = "COMP_T",
"INTL_INDUSTRY" = "COMP_U")head(as.data.frame(saopaulo))## code_muni name_muni code_state abbrev_state
## 1 3508405 Cabreúva 35 SP
## 2 3509601 Campo Limpo Paulista 35 SP
## 3 3524006 Itupeva 35 SP
## 4 3525201 Jarinu 35 SP
## 5 3525904 Jundiaí 35 SP
## 6 3527306 Louveira 35 SP
## name_metro STATE CAPITAL IBGE_RES_POP IBGE_RES_POP_BRAS
## 1 Aglomeração Urbana de Jundiaí SP 0 41604 41513
## 2 Aglomeração Urbana de Jundiaí SP 0 74074 73873
## 3 Aglomeração Urbana de Jundiaí SP 0 44859 44736
## 4 Aglomeração Urbana de Jundiaí SP 0 23847 23759
## 5 Aglomeração Urbana de Jundiaí SP 0 370126 368648
## 6 Aglomeração Urbana de Jundiaí SP 0 37125 37062
## IBGE_RES_POP_ESTR IBGE_DU IBGE_DU_URBAN IBGE_DU_RURAL IBGE_POP IBGE_1
## 1 91 11922 10203 1719 37633 586
## 2 201 22030 22030 NA 72014 1044
## 3 123 13300 11624 1676 38667 613
## 4 88 7097 5511 1586 18402 260
## 5 1478 118317 113645 4672 323621 3698
## 6 63 11056 10671 385 28260 432
## IBGE_1-4 IBGE_5-9 IBGE_10-14 IBGE_15-59 IBGE_60+ IBGE_PLANTED_AREA
## 1 2392 3115 3471 24994 3075 245
## 2 4131 5264 6142 48767 6666 0
## 3 2373 3014 3268 26496 2903 1390
## 4 1077 1420 1535 12095 2015 706
## 5 14800 18897 21530 219514 45182 2430
## 6 1661 1897 2127 20038 2105 568
## IBGE_CROP_PRODUCTION_$ IDHM Ranking 2010 IDHM IDHM_Renda IDHM_Longevidade
## 1 2572 832 0.738 0.717 0.828
## 2 0 243 0.769 0.733 0.84
## 3 5970 339 0.762 0.75 0.844
## 4 9454 954 0.733 0.723 0.826
## 5 63824 11 0.82 0.834 0.866
## 6 27733 161 0.777 0.783 0.861
## IDHM_Educacao LONG LAT ALT PAY_TV FIXED_PHONES AREA
## 1 0.678 -4713365837 -2331267439 656.6 5656 7994 26023
## 2 0.739 -4676381923 -2320939643 765.88 9589 13766 7940
## 3 0.699 -4705570115 -2315340963 672.33 10517 12333 20082
## 4 0.659 -4673827094 -231030625 794.68 5871 4655 20755
## 5 0.768 -4688527397 -23187668 760.16 92215 166371 43121
## 6 0.697 -4694644022 -230867785 690.69 4519 6929 5513
## REGIAO_TUR CATEGORIA_TUR ESTIMATED_POP RURAL_URBAN GVA_AGROPEC
## 1 Roteiro Dos Bandeirantes C 48966 Urbano 25784.75
## 2 <NA> <NA> 83735 Urbano 7.87
## 3 Circuito Das Frutas C 59649 Urbano 39554.78
## 4 Circuito Das Frutas C 29456 Urbano 41414.02
## 5 Circuito Das Frutas B 414810 Urbano 130551.25
## 6 Circuito Das Frutas D 47748 Urbano 29487.12
## GVA_INDUSTRY GVA_SERVICES GVA_PUBLIC GVA_TOTAL TAXES GDP POP_GDP
## 1 1035198.8 201958537 19076721 327133614 870.2 414153889 47210
## 2 378706.96 81152238 28791258 148600707 189987.65 167599472 81693
## 3 1448072.53 193407002 2681091 368980641 995666.13 468547255 55596
## 4 210690 128741711 12318979 166271091 315429.36 197814027 28012
## 5 7409989.1 2311000969 184282 3249336974 7289.37 3978273572 405740
## 6 2396464.9 614022 2803914 884656 2416575.9 1126313622 44904
## GDP_CAPITA GVA_MAIN
## 1 8772588 Comércio e reparação de veículos automotores e motocicletas
## 2 2051577 Demais serviços
## 3 8427715 Demais serviços
## 4 706176 Comércio e reparação de veículos automotores e motocicletas
## 5 9804982 Demais serviços
## 6 25082701 Comércio e reparação de veículos automotores e motocicletas
## MUN_EXPENDIT COMP_TOT AGRI_INDUSTRY EXTRACTIVE_INDUSTRY
## 1 174166075 1062 23 2
## 2 158830071 1198 16 0
## 3 NA 1773 39 3
## 4 94435667 802 29 2
## 5 1630920489 16395 198 11
## 6 350285129 1230 34 0
## TRANSFORMATION_INDUSTRY ENERGY_INDUSTRY WATER_INDUSTRY CONSTRUCTION_INDUSTRY
## 1 180 0 6 54
## 2 151 0 2 76
## 3 274 1 9 95
## 4 73 0 2 41
## 5 1030 2 42 742
## 6 145 0 6 70
## TRADE_REPAIR_INDUSTRY LOGISTICS_INDUSTRY ACCOMS_FOOD_INDUSTRY ICT_INDUSTRY
## 1 375 109 69 12
## 2 459 52 81 38
## 3 584 101 134 33
## 4 298 52 71 27
## 5 5431 833 1152 648
## 6 492 106 102 21
## FINANCIAL_INDUSTRY REALESTATE_INDUSTRY PROFESSIONAL_TECHNICAL_INDUSTRY
## 1 24 17 30
## 2 9 18 56
## 3 25 64 79
## 4 5 8 35
## 5 310 458 1292
## 6 8 24 39
## ADMINISTRATIVE_INDUSTRY PUBLIC_INDUSTRY EDUCATION_INDUSTRY
## 1 62 2 18
## 2 73 2 84
## 3 150 4 61
## 4 76 2 37
## 5 1904 9 586
## 6 65 4 39
## HEALTHCARE_INDUSTRY ARTS_RECREATION_INDUSTRY OTHER_SERVICES_INDUSTRY
## 1 35 4 40
## 2 31 10 40
## 3 21 22 74
## 4 15 11 18
## 5 802 230 715
## 6 19 13 43
## DOMESTIC_INDUSTRY INTL_INDUSTRY HOTELS BEDS Pr_Agencies Pu_Agencies Pr_Bank
## 1 0 0 NA NA 4 2 3
## 2 0 0 NA NA 5 2 3
## 3 0 0 NA NA 3 2 3
## 4 0 0 1 33 2 2 2
## 5 0 0 2 344 45 20 6
## 6 0 0 NA NA 4 2 2
## Pu_Bank Pr_Assets Pu_Assets Cars Motorcycles Wheeled_tractor UBER MAC
## 1 2 348511458 257008134 17888 5821 7 NA NA
## 2 2 521638595 515426440 30308 8982 8 NA NA
## 3 2 573783053 507848296 22239 6200 12 NA 1
## 4 2 132978829 200672827 11381 4077 2 NA NA
## 5 2 11139673441 10586167152 212118 51368 152 NA 5
## 6 2 474799597 396958740 17829 7180 3 NA NA
## WAL-MART POST_OFFICES geom
## 1 NA 4 MULTIPOLYGON (((-47.09692 -...
## 2 NA 2 MULTIPOLYGON (((-46.78614 -...
## 3 NA 1 MULTIPOLYGON (((-47.04599 -...
## 4 NA 2 MULTIPOLYGON (((-46.71471 -...
## 5 NA 7 MULTIPOLYGON (((-46.85676 -...
## 6 NA 2 MULTIPOLYGON (((-46.91599 -...Computing total number of industry in the macrometropolis and the total number of each type of industry in the macrometropolis.
total_saopaulo_comp = sum(saopaulo$COMP_TOT)
total_agri_industry = sum(saopaulo$AGRI_INDUSTRY)
total_extractive_industry = sum(saopaulo$EXTRACTIVE_INDUSTRY)
total_transform_industry = sum(saopaulo$TRANSFORMATION_INDUSTRY)
total_energy_industry = sum(saopaulo$ENERGY_INDUSTRY)
total_water_industry = sum(saopaulo$WATER_INDUSTRY)
total_construction_industry = sum(saopaulo$CONSTRUCTION_INDUSTRY)
total_trade_repair_industry = sum(saopaulo$TRADE_REPAIR_INDUSTRY)
total_logistics_industry = sum(saopaulo$LOGISTICS_INDUSTRY)
total_accoms_food_industry = sum(saopaulo$ACCOMS_FOOD_INDUSTRY)
total_ict_industry = sum(saopaulo$ICT_INDUSTRY)
total_financial_industry = sum(saopaulo$FINANCIAL_INDUSTRY)
total_realestate_industry = sum(saopaulo$REALESTATE_INDUSTRY)
total_prof_technical_industry = sum(saopaulo$PROFESSIONAL_TECHNICAL_INDUSTRY)
total_admin_industry = sum(saopaulo$ADMINISTRATIVE_INDUSTRY)
total_public_industry = sum(saopaulo$PUBLIC_INDUSTRY)
total_education_industry = sum(saopaulo$EDUCATION_INDUSTRY)
total_healthcare_industry = sum(saopaulo$HEALTHCARE_INDUSTRY)
total_arts_recreation_industry = sum(saopaulo$ARTS_RECREATION_INDUSTRY)
total_other_services_industry = sum(saopaulo$OTHER_SERVICES_INDUSTRY)
total_domestic_industry = sum(saopaulo$DOMESTIC_INDUSTRY)
total_intl_industry = sum(saopaulo$INTL_INDUSTRY)Computing Location Quotient of the different industries.
saopaulo <- saopaulo %>%
mutate(LQ_AGRI_INDUSTRY = (AGRI_INDUSTRY/COMP_TOT)/(total_agri_industry/total_saopaulo_comp)) %>%
mutate(LQ_EXTRACTIVE_INDUSTRY = (EXTRACTIVE_INDUSTRY/COMP_TOT)/(total_extractive_industry/total_saopaulo_comp)) %>%
mutate(LQ_TRANSFORM_INDUSTRY = (TRANSFORMATION_INDUSTRY/COMP_TOT)/(total_transform_industry/total_saopaulo_comp)) %>%
mutate(LQ_ENERGY_INDUSTRY = (ENERGY_INDUSTRY/COMP_TOT)/(total_energy_industry/total_saopaulo_comp)) %>%
mutate(LQ_WATER_INDUSTRY = (WATER_INDUSTRY/COMP_TOT)/(total_water_industry/total_saopaulo_comp)) %>%
mutate(LQ_CONSTRUCTION_INDUSTRY = (CONSTRUCTION_INDUSTRY/COMP_TOT)/(total_construction_industry/total_saopaulo_comp)) %>%
mutate(LQ_TRADE_REPAIR_INDUSTRY = (TRADE_REPAIR_INDUSTRY/COMP_TOT)/(total_trade_repair_industry/total_saopaulo_comp)) %>%
mutate(LQ_LOGISTICS_INDUSTRY = (LOGISTICS_INDUSTRY/COMP_TOT)/(total_logistics_industry/total_saopaulo_comp)) %>%
mutate(LQ_ACCOMS_FOOD_INDUSTRY = (ACCOMS_FOOD_INDUSTRY/COMP_TOT)/(total_accoms_food_industry/total_saopaulo_comp)) %>%
mutate(LQ_ICT_INDUSTRY = (ICT_INDUSTRY/COMP_TOT)/(total_ict_industry/total_saopaulo_comp)) %>%
mutate(LQ_FINANCIAL_INDUSTRY = (FINANCIAL_INDUSTRY/COMP_TOT)/(total_financial_industry/total_saopaulo_comp)) %>%
mutate(LQ_REALESTATE_INDUSTRY = (REALESTATE_INDUSTRY/COMP_TOT)/(total_realestate_industry/total_saopaulo_comp)) %>%
mutate(LQ_PROF_TECHNICAL_INDUSTRY = (PROFESSIONAL_TECHNICAL_INDUSTRY/COMP_TOT)/(total_prof_technical_industry/total_saopaulo_comp)) %>%
mutate(LQ_ADMIN_INDUSTRY = (ADMINISTRATIVE_INDUSTRY/COMP_TOT)/(total_admin_industry/total_saopaulo_comp)) %>%
mutate(LQ_PUBLIC_INDUSTRY = (PUBLIC_INDUSTRY/COMP_TOT)/(total_public_industry/total_saopaulo_comp)) %>%
mutate(LQ_EDUCATION_INDUSTRY = (EDUCATION_INDUSTRY/COMP_TOT)/(total_education_industry/total_saopaulo_comp)) %>%
mutate(LQ_HEALTHCARE_INDUSTRY = (HEALTHCARE_INDUSTRY/COMP_TOT)/(total_healthcare_industry/total_saopaulo_comp)) %>%
mutate(LQ_ARTS_RECREATION_INDUSTRY = (ARTS_RECREATION_INDUSTRY/COMP_TOT)/(total_arts_recreation_industry/total_saopaulo_comp)) %>%
mutate(LQ_OTHER_SERVICES_INDUSTRY = (OTHER_SERVICES_INDUSTRY/COMP_TOT)/(total_other_services_industry/total_saopaulo_comp)) %>%
mutate(LQ_DOMESTIC_INDUSTRY = (DOMESTIC_INDUSTRY/COMP_TOT)/(total_domestic_industry/total_saopaulo_comp)) %>%
mutate(LQ_INTL_INDUSTRY = (INTL_INDUSTRY/COMP_TOT)/(total_intl_industry/total_saopaulo_comp))Since the domestic industry variable only has 0 as it’s value, we will drop it from our saopaulo dataframe.
saopaulo <- saopaulo %>%
select(-DOMESTIC_INDUSTRY, -LQ_DOMESTIC_INDUSTRY)head(as.data.frame(saopaulo)[85:105])## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## 1 1.6967505 3.647449 2.4430635
## 2 1.0463521 0.000000 1.8167991
## 3 1.7233383 3.277149 2.2275559
## 4 2.8329460 4.829913 1.3120043
## 5 0.9461684 1.299466 0.9055503
## 6 2.1656510 0.000000 1.6992202
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## 1 0.0000000 2.8858388 1.0267469
## 2 0.0000000 0.8527437 1.2810053
## 3 1.5906631 2.5928602 1.0819546
## 4 0.0000000 1.2737992 1.0322946
## 5 0.3440373 1.3085285 0.9138747
## 6 0.0000000 2.4916754 1.1491774
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## 1 1.087693 2.342976 1.003421
## 2 1.180199 0.990860 1.044208
## 3 1.014620 1.300404 1.167226
## 4 1.144567 1.480113 1.367234
## 5 1.020394 1.159843 1.085175
## 6 1.232138 1.967282 1.280719
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## 1 0.2177898 0.7511227 0.7174177
## 2 0.6113749 0.2496950 0.6733849
## 3 0.3587452 0.4686574 1.6177781
## 4 0.6488888 0.2072143 0.4470574
## 5 0.7618061 0.6284554 1.2519926
## 6 0.3290751 0.2161768 0.8744880
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## 1 0.3866436 0.4603496 3.0144632
## 2 0.6398015 0.4804926 2.6722537
## 3 0.6098632 0.6671188 3.6112351
## 4 0.5973209 0.7472396 3.9917206
## 5 1.0786117 0.9157484 0.8786898
## 6 0.4339838 0.4167052 5.2054632
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## 1 0.5311049 0.8930439 0.3053556
## 2 2.1971252 0.7011875 0.6767271
## 3 1.0780861 0.3209518 1.0059683
## 4 1.4456384 0.5068112 1.1119588
## 5 1.1200013 1.3255381 1.1373307
## 6 0.9935548 0.4185793 0.8568575
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## 1 0.8132191 0 MULTIPOLYGON (((-47.09692 -...
## 2 0.7209004 0 MULTIPOLYGON (((-46.78614 -...
## 3 0.9011458 0 MULTIPOLYGON (((-47.04599 -...
## 4 0.4845853 0 MULTIPOLYGON (((-46.71471 -...
## 5 0.9416006 0 MULTIPOLYGON (((-46.85676 -...
## 6 0.7548062 0 MULTIPOLYGON (((-46.91599 -...3. Exploratory Data Analysis (EDA)
3.1 EDA using statistical graphics
We will plot the overall distribution of the newly derived variables of Location Quotient using Histogram, geom_histogram() function of ggplot2 package.
LQ_AGRI <- ggplot(data = saopaulo,
aes(x = `LQ_AGRI_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.7)
LQ_EXTRACTIVE <- ggplot(data = saopaulo,
aes(x = `LQ_EXTRACTIVE_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.7)
LQ_TRANSFORM <- ggplot(data = saopaulo,
aes(x = `LQ_TRANSFORM_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_ENERGY <- ggplot(data = saopaulo,
aes(x = `LQ_ENERGY_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.7)
LQ_WATER <- ggplot(data = saopaulo,
aes(x = `LQ_WATER_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.5)
LQ_CONSTRUCTION <- ggplot(data = saopaulo,
aes(x = `LQ_CONSTRUCTION_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_TRADE_REPAIR <- ggplot(data = saopaulo,
aes(x = `LQ_TRADE_REPAIR_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_LOGISTICS <- ggplot(data = saopaulo,
aes(x = `LQ_LOGISTICS_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_ACCOMS_FOOD <- ggplot(data = saopaulo,
aes(x = `LQ_ACCOMS_FOOD_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_ICT <- ggplot(data = saopaulo,
aes(x = `LQ_ICT_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.3)
LQ_FINANCIAL <- ggplot(data = saopaulo,
aes(x = `LQ_FINANCIAL_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_REALESTATE <- ggplot(data = saopaulo,
aes(x = `LQ_REALESTATE_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_PROF_TECHNICAL <- ggplot(data = saopaulo,
aes(x = `LQ_PROF_TECHNICAL_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_ADMIN <- ggplot(data = saopaulo,
aes(x = `LQ_ADMIN_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_PUBLIC <- ggplot(data = saopaulo,
aes(x = `LQ_PUBLIC_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.8)
LQ_EDUCATION <- ggplot(data = saopaulo,
aes(x = `LQ_EDUCATION_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_HEALTHCARE <- ggplot(data = saopaulo,
aes(x = `LQ_HEALTHCARE_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_ARTS_RECREATION <- ggplot(data = saopaulo,
aes(x = `LQ_ARTS_RECREATION_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_OTHER_SERVICES <- ggplot(data = saopaulo,
aes(x = `LQ_OTHER_SERVICES_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.1)
LQ_INTL <- ggplot(data = saopaulo,
aes(x = `LQ_INTL_INDUSTRY`)) +
geom_histogram(color = "blue", fill = "light blue", binwidth = 0.3) We will display the plots using ggarange() function of ggpubr package.
We can see differing overall distributions of the Location Quotient of the variables. Some are really skewed to the right such as LQ_ICT_INDUSTRY, LQ_AGRI_INDUSTRY and LQ_EXTRACTIVE_INDUSTRY. Some are more normally distributed such as LQ_CONSTRUCTION_INDUSTRY, LQ_TRANSFORM_INDUSTRY and LQ_TRADE_REPAIR_INDUSTRY
3.2 EDA with choropleth maps
To plot the choropleth maps, we will use tmap functions while changing the col value for tm_fill as well as the title of the plots.
AGRI.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_AGRI_INDUSTRY",
style = "pretty",
title = "Agriculture LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Agriculture Industry LQ",
main.title.position = "center",
main.title.size = 1)
EXTRACTIVE.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_EXTRACTIVE_INDUSTRY",
style = "pretty",
title = "Extractive LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Extractive Industry LQ",
main.title.position = "center",
main.title.size = 1)
TRANSFORM.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_TRANSFORM_INDUSTRY",
style = "pretty",
title = "Transformation LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Transformation Industry LQ",
main.title.position = "center",
main.title.size = 1)
ENERGY.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_ENERGY_INDUSTRY",
style = "pretty",
title = "Energy LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Energy Industry LQ",
main.title.position = "center",
main.title.size = 1)
WATER.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_WATER_INDUSTRY",
style = "pretty",
title = "Water LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Water Industry LQ",
main.title.position = "center",
main.title.size = 1)
CONSTRUCTION.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_CONSTRUCTION_INDUSTRY",
style = "pretty",
title = "Construction LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Construction Industry LQ",
main.title.position = "center",
main.title.size = 1)
TRADEREPAIR.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_TRADE_REPAIR_INDUSTRY",
style = "pretty",
title = "Trade & Repair LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Trade & Repair Industry LQ",
main.title.position = "center",
main.title.size = 1)
LOGISTICS.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_LOGISTICS_INDUSTRY",
style = "pretty",
title = "Logistics LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Logistics Industry LQ",
main.title.position = "center",
main.title.size = 1)
ACCOMSFOOD.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_ACCOMS_FOOD_INDUSTRY",
style = "pretty",
title = "Accoms & Food LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Accoms & Food Industry LQ",
main.title.position = "center",
main.title.size = 1)
ICT.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_ICT_INDUSTRY",
style = "pretty",
title = "ICT LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "ICT Industry LQ",
main.title.position = "center",
main.title.size = 1)
FINANCIAL.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_FINANCIAL_INDUSTRY",
style = "pretty",
title = "Financial LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Financial Industry LQ",
main.title.position = "center",
main.title.size = 1)
REALESTATE.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_REALESTATE_INDUSTRY",
style = "pretty",
title = "Real Estate LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Real Estate Industry LQ",
main.title.position = "center",
main.title.size = 1)
PROFTECHNICAL.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_PROF_TECHNICAL_INDUSTRY",
style = "pretty",
title = "Professional Technical LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Professional, Technical Industry LQ",
main.title.position = "center",
main.title.size = 1)
ADMIN.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_ADMIN_INDUSTRY",
style = "pretty",
title = "Administrative LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Administrative Industry LQ",
main.title.position = "center",
main.title.size = 1)
PUBLIC.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_PUBLIC_INDUSTRY",
style = "pretty",
title = "Public admin LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Public administrative Industry LQ",
main.title.position = "center",
main.title.size = 1)
EDUCATION.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_EDUCATION_INDUSTRY",
style = "pretty",
title = "Education LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Education Industry LQ",
main.title.position = "center",
main.title.size = 1)
HEALTHCARE.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_HEALTHCARE_INDUSTRY",
style = "pretty",
title = "Healthcare LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Healthcare & social Industry LQ",
main.title.position = "center",
main.title.size = 1)
ARTSRECREATION.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_ARTS_RECREATION_INDUSTRY",
style = "pretty",
title = "Arts & Recreation LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Arts, Recreation Industry LQ",
main.title.position = "center",
main.title.size = 1)
OTHERSERVICES.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_OTHER_SERVICES_INDUSTRY",
style = "pretty",
title = "Other Services LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "Other Services Industry LQ",
main.title.position = "center",
main.title.size = 1)
INTL.map <- tm_shape(saopaulo)+
tm_fill(col = "LQ_INTL_INDUSTRY",
style = "pretty",
title = "International institutions LQ value") +
tm_borders(lwd=0.5)+
tm_layout(legend.height = 0.45,
legend.width = 0.35,
frame = FALSE,
main.title = "International institutions Industry LQ",
main.title.position = "center",
main.title.size = 1)
3.3 Correlation Analysis
Before performing cluster analysis, it is important for us to ensure that the chosen cluster variables are not highly correlated. We will do this using corrplot.mixed() function of corrplot package to visualise and analyse the correlation of the input variables.
Before that, we also select the desired cluster variables and also remove the geom variable (sf object) because we only want the variables in tibble/dataframe format.
cluster_var <- saopaulo %>%
select(name_muni, name_metro, contains("LQ_"))
cluster_var <- st_set_geometry(cluster_var, NULL)cluster_vars.cor = cor(as.tibble(cluster_var[,3:22]))
corrplot.mixed(cluster_vars.cor,
lower = "ellipse",
upper = "number",
tl.pos = "lt",
diag = "l",
tl.col = "black",
tl.cex = 0.5,
number.cex = 0.5)
We can see that there are only a few correlation that results in a value of higher than 0.6 such as the correlation between professional, technical industry LQ and the financial industry LQ (0.61) and the correlation between trade, repair industry LQ and the agricultural industry LQ (0.62). However, since these values are still relatively low, we will not remove them from our clustering variables.
4. Hierarchy Cluster Analysis
4.1 Data standardisation
In order to avoid cluster analysis result to be biased to the clustering variables with large values, it’s useful to standardise the input variables before performing cluster analysis.
We will use the Min-Max standardisation method to standardise the variables into a range between 0 to 1.
row.names(cluster_var) <- cluster_var$name_muni
saopaulo_industry <- select(cluster_var, c(3:22))
head(as.data.frame(saopaulo_industry))## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY
## Cabreúva 1.6967505 3.647449
## Campo Limpo Paulista 1.0463521 0.000000
## Itupeva 1.7233383 3.277149
## Jarinu 2.8329460 4.829913
## Jundiaí 0.9461684 1.299466
## Louveira 2.1656510 0.000000
## LQ_TRANSFORM_INDUSTRY LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY
## Cabreúva 2.4430635 0.0000000 2.8858388
## Campo Limpo Paulista 1.8167991 0.0000000 0.8527437
## Itupeva 2.2275559 1.5906631 2.5928602
## Jarinu 1.3120043 0.0000000 1.2737992
## Jundiaí 0.9055503 0.3440373 1.3085285
## Louveira 1.6992202 0.0000000 2.4916754
## LQ_CONSTRUCTION_INDUSTRY LQ_TRADE_REPAIR_INDUSTRY
## Cabreúva 1.0267469 1.087693
## Campo Limpo Paulista 1.2810053 1.180199
## Itupeva 1.0819546 1.014620
## Jarinu 1.0322946 1.144567
## Jundiaí 0.9138747 1.020394
## Louveira 1.1491774 1.232138
## LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Cabreúva 2.342976 1.003421
## Campo Limpo Paulista 0.990860 1.044208
## Itupeva 1.300404 1.167226
## Jarinu 1.480113 1.367234
## Jundiaí 1.159843 1.085175
## Louveira 1.967282 1.280719
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY
## Cabreúva 0.2177898 0.7511227
## Campo Limpo Paulista 0.6113749 0.2496950
## Itupeva 0.3587452 0.4686574
## Jarinu 0.6488888 0.2072143
## Jundiaí 0.7618061 0.6284554
## Louveira 0.3290751 0.2161768
## LQ_REALESTATE_INDUSTRY LQ_PROF_TECHNICAL_INDUSTRY
## Cabreúva 0.7174177 0.3866436
## Campo Limpo Paulista 0.6733849 0.6398015
## Itupeva 1.6177781 0.6098632
## Jarinu 0.4470574 0.5973209
## Jundiaí 1.2519926 1.0786117
## Louveira 0.8744880 0.4339838
## LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY LQ_EDUCATION_INDUSTRY
## Cabreúva 0.4603496 3.0144632 0.5311049
## Campo Limpo Paulista 0.4804926 2.6722537 2.1971252
## Itupeva 0.6671188 3.6112351 1.0780861
## Jarinu 0.7472396 3.9917206 1.4456384
## Jundiaí 0.9157484 0.8786898 1.1200013
## Louveira 0.4167052 5.2054632 0.9935548
## LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Cabreúva 0.8930439 0.3053556
## Campo Limpo Paulista 0.7011875 0.6767271
## Itupeva 0.3209518 1.0059683
## Jarinu 0.5068112 1.1119588
## Jundiaí 1.3255381 1.1373307
## Louveira 0.4185793 0.8568575
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY
## Cabreúva 0.8132191 0
## Campo Limpo Paulista 0.7209004 0
## Itupeva 0.9011458 0
## Jarinu 0.4845853 0
## Jundiaí 0.9416006 0
## Louveira 0.7548062 0saopaulo_industry.std <- normalize(saopaulo_industry)
#summary(saopaulo_industry.std)
head(saopaulo_industry.std)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY
## Cabreúva 0.02672078 0.03954802
## Campo Limpo Paulista 0.01647817 0.00000000
## Itupeva 0.02713949 0.03553299
## Jarinu 0.04461382 0.05236908
## Jundiaí 0.01490045 0.01408966
## Louveira 0.03410512 0.00000000
## LQ_TRANSFORM_INDUSTRY LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY
## Cabreúva 0.6719128 0.000000000 0.21280603
## Campo Limpo Paulista 0.4996721 0.000000000 0.06288258
## Itupeva 0.6126420 0.033276932 0.19120135
## Jarinu 0.3608390 0.000000000 0.09393184
## Jundiaí 0.2490524 0.007197316 0.09649283
## Louveira 0.4673345 0.000000000 0.18373984
## LQ_CONSTRUCTION_INDUSTRY LQ_TRADE_REPAIR_INDUSTRY
## Cabreúva 0.5159912 0.4414358
## Campo Limpo Paulista 0.6437686 0.4899604
## Itupeva 0.5437357 0.4031055
## Jarinu 0.5187791 0.4712696
## Jundiaí 0.4592673 0.4061340
## Louveira 0.5775186 0.5172052
## LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Cabreúva 0.5918707 0.1694573
## Campo Limpo Paulista 0.2503061 0.1791364
## Itupeva 0.3285016 0.2083299
## Jarinu 0.3738986 0.2557939
## Jundiaí 0.2929938 0.1888584
## Louveira 0.4969648 0.2352630
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY
## Cabreúva 0.02708077 0.34485325
## Campo Limpo Paulista 0.07602056 0.11463924
## Itupeva 0.04460766 0.21516859
## Jarinu 0.08068516 0.09513564
## Jundiaí 0.09472570 0.28853458
## Louveira 0.04091838 0.09925045
## LQ_REALESTATE_INDUSTRY LQ_PROF_TECHNICAL_INDUSTRY
## Cabreúva 0.3881827 0.1563147
## Campo Limpo Paulista 0.3643573 0.2586630
## Itupeva 0.8753525 0.2465593
## Jarinu 0.2418953 0.2414887
## Jundiaí 0.6774321 0.4360680
## Louveira 0.4731707 0.1754537
## LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY LQ_EDUCATION_INDUSTRY
## Cabreúva 0.1741319 0.020097326 0.2417272
## Campo Limpo Paulista 0.1817511 0.017580076 1.0000000
## Itupeva 0.2523443 0.024487105 0.4906803
## Jarinu 0.2826508 0.027285909 0.6579682
## Jundiaí 0.3463910 0.004386845 0.5097576
## Louveira 0.1576229 0.036214048 0.4522067
## LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Cabreúva 0.4909701 0.1603892
## Campo Limpo Paulista 0.3854929 0.3554535
## Itupeva 0.1764502 0.5283888
## Jarinu 0.2786303 0.5840607
## Jundiaí 0.7287431 0.5973874
## Louveira 0.2301230 0.4500678
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY
## Cabreúva 0.2955586 0
## Campo Limpo Paulista 0.2545483 0
## Itupeva 0.3346178 0
## Jarinu 0.1495713 0
## Jundiaí 0.3525888 0
## Louveira 0.2696101 0describe(saopaulo_industry.std)## vars n mean sd median trimmed mad min max
## LQ_AGRI_INDUSTRY 1 172 0.11 0.19 0.03 0.06 0.04 0 1
## LQ_EXTRACTIVE_INDUSTRY 2 172 0.06 0.12 0.02 0.03 0.02 0 1
## LQ_TRANSFORM_INDUSTRY 3 172 0.34 0.19 0.30 0.32 0.17 0 1
## LQ_ENERGY_INDUSTRY 4 172 0.01 0.08 0.00 0.00 0.00 0 1
## LQ_WATER_INDUSTRY 5 172 0.11 0.13 0.09 0.09 0.08 0 1
## LQ_CONSTRUCTION_INDUSTRY 6 172 0.46 0.20 0.46 0.45 0.17 0 1
## LQ_TRADE_REPAIR_INDUSTRY 7 172 0.47 0.14 0.48 0.48 0.09 0 1
## LQ_LOGISTICS_INDUSTRY 8 172 0.30 0.19 0.25 0.27 0.13 0 1
## LQ_ACCOMS_FOOD_INDUSTRY 9 172 0.22 0.14 0.18 0.20 0.07 0 1
## LQ_ICT_INDUSTRY 10 172 0.06 0.09 0.04 0.04 0.02 0 1
## LQ_FINANCIAL_INDUSTRY 11 172 0.17 0.14 0.15 0.16 0.09 0 1
## LQ_REALESTATE_INDUSTRY 12 172 0.32 0.20 0.31 0.31 0.22 0 1
## LQ_PROF_TECHNICAL_INDUSTRY 13 172 0.22 0.12 0.20 0.20 0.09 0 1
## LQ_ADMIN_INDUSTRY 14 172 0.22 0.16 0.20 0.20 0.11 0 1
## LQ_PUBLIC_INDUSTRY 15 172 0.05 0.10 0.02 0.03 0.02 0 1
## LQ_EDUCATION_INDUSTRY 16 172 0.45 0.19 0.46 0.45 0.21 0 1
## LQ_HEALTHCARE_INDUSTRY 17 172 0.34 0.20 0.31 0.32 0.16 0 1
## LQ_ARTS_RECREATION_INDUSTRY 18 172 0.47 0.21 0.49 0.48 0.17 0 1
## LQ_OTHER_SERVICES_INDUSTRY 19 172 0.34 0.15 0.34 0.33 0.12 0 1
## LQ_INTL_INDUSTRY 20 172 0.01 0.09 0.00 0.00 0.00 0 1
## range skew kurtosis se
## LQ_AGRI_INDUSTRY 1 2.61 7.05 0.01
## LQ_EXTRACTIVE_INDUSTRY 1 3.82 20.35 0.01
## LQ_TRANSFORM_INDUSTRY 1 0.80 0.39 0.01
## LQ_ENERGY_INDUSTRY 1 10.74 126.44 0.01
## LQ_WATER_INDUSTRY 1 3.70 20.23 0.01
## LQ_CONSTRUCTION_INDUSTRY 1 0.09 -0.04 0.02
## LQ_TRADE_REPAIR_INDUSTRY 1 -0.33 2.51 0.01
## LQ_LOGISTICS_INDUSTRY 1 1.44 2.08 0.01
## LQ_ACCOMS_FOOD_INDUSTRY 1 2.38 7.54 0.01
## LQ_ICT_INDUSTRY 1 7.61 71.15 0.01
## LQ_FINANCIAL_INDUSTRY 1 2.11 9.18 0.01
## LQ_REALESTATE_INDUSTRY 1 0.44 -0.06 0.02
## LQ_PROF_TECHNICAL_INDUSTRY 1 2.07 9.16 0.01
## LQ_ADMIN_INDUSTRY 1 2.28 7.46 0.01
## LQ_PUBLIC_INDUSTRY 1 6.19 52.96 0.01
## LQ_EDUCATION_INDUSTRY 1 0.11 -0.12 0.01
## LQ_HEALTHCARE_INDUSTRY 1 0.81 0.88 0.02
## LQ_ARTS_RECREATION_INDUSTRY 1 -0.37 0.28 0.02
## LQ_OTHER_SERVICES_INDUSTRY 1 0.85 2.09 0.01
## LQ_INTL_INDUSTRY 1 9.84 104.39 0.01We also standardize the clustering variables using Z-score method in case it is needed, Z-score method deals with anomalies better even though the resulting clustering variables will not come in a range between 0 to 1.
saopaulo_industry.z <- scale(saopaulo_industry)
describe(saopaulo_industry.z)## vars n mean sd median trimmed mad min max
## LQ_AGRI_INDUSTRY 1 172 0 1 -0.43 -0.25 0.19 -0.58 4.69
## LQ_EXTRACTIVE_INDUSTRY 2 172 0 1 -0.39 -0.24 0.18 -0.51 7.63
## LQ_TRANSFORM_INDUSTRY 3 172 0 1 -0.21 -0.08 0.89 -1.74 3.42
## LQ_ENERGY_INDUSTRY 4 172 0 1 -0.18 -0.16 0.00 -0.18 12.21
## LQ_WATER_INDUSTRY 5 172 0 1 -0.19 -0.15 0.60 -0.89 7.11
## LQ_CONSTRUCTION_INDUSTRY 6 172 0 1 0.01 -0.01 0.85 -2.31 2.76
## LQ_TRADE_REPAIR_INDUSTRY 7 172 0 1 0.04 0.04 0.67 -3.46 3.87
## LQ_LOGISTICS_INDUSTRY 8 172 0 1 -0.24 -0.15 0.67 -1.56 3.71
## LQ_ACCOMS_FOOD_INDUSTRY 9 172 0 1 -0.25 -0.16 0.49 -1.53 5.42
## LQ_ICT_INDUSTRY 10 172 0 1 -0.16 -0.15 0.24 -0.62 10.49
## LQ_FINANCIAL_INDUSTRY 11 172 0 1 -0.13 -0.09 0.67 -1.27 6.11
## LQ_REALESTATE_INDUSTRY 12 172 0 1 -0.02 -0.04 1.09 -1.56 3.34
## LQ_PROF_TECHNICAL_INDUSTRY 13 172 0 1 -0.15 -0.10 0.73 -1.76 6.32
## LQ_ADMIN_INDUSTRY 14 172 0 1 -0.15 -0.14 0.72 -1.41 4.98
## LQ_PUBLIC_INDUSTRY 15 172 0 1 -0.31 -0.20 0.25 -0.52 9.82
## LQ_EDUCATION_INDUSTRY 16 172 0 1 0.05 -0.01 1.09 -2.34 2.82
## LQ_HEALTHCARE_INDUSTRY 17 172 0 1 -0.11 -0.07 0.83 -1.70 3.36
## LQ_ARTS_RECREATION_INDUSTRY 18 172 0 1 0.11 0.05 0.81 -2.27 2.56
## LQ_OTHER_SERVICES_INDUSTRY 19 172 0 1 -0.05 -0.05 0.80 -2.23 4.26
## LQ_INTL_INDUSTRY 20 172 0 1 -0.12 -0.12 0.00 -0.12 11.53
## range skew kurtosis se
## LQ_AGRI_INDUSTRY 5.26 2.61 7.05 0.08
## LQ_EXTRACTIVE_INDUSTRY 8.14 3.82 20.35 0.08
## LQ_TRANSFORM_INDUSTRY 5.16 0.80 0.39 0.08
## LQ_ENERGY_INDUSTRY 12.38 10.74 126.44 0.08
## LQ_WATER_INDUSTRY 8.00 3.70 20.23 0.08
## LQ_CONSTRUCTION_INDUSTRY 5.07 0.09 -0.04 0.08
## LQ_TRADE_REPAIR_INDUSTRY 7.33 -0.33 2.51 0.08
## LQ_LOGISTICS_INDUSTRY 5.28 1.44 2.08 0.08
## LQ_ACCOMS_FOOD_INDUSTRY 6.95 2.38 7.54 0.08
## LQ_ICT_INDUSTRY 11.11 7.61 71.15 0.08
## LQ_FINANCIAL_INDUSTRY 7.38 2.11 9.18 0.08
## LQ_REALESTATE_INDUSTRY 4.89 0.44 -0.06 0.08
## LQ_PROF_TECHNICAL_INDUSTRY 8.08 2.07 9.16 0.08
## LQ_ADMIN_INDUSTRY 6.39 2.28 7.46 0.08
## LQ_PUBLIC_INDUSTRY 10.34 6.19 52.96 0.08
## LQ_EDUCATION_INDUSTRY 5.16 0.11 -0.12 0.08
## LQ_HEALTHCARE_INDUSTRY 5.06 0.81 0.88 0.08
## LQ_ARTS_RECREATION_INDUSTRY 4.84 -0.37 0.28 0.08
## LQ_OTHER_SERVICES_INDUSTRY 6.49 0.85 2.09 0.08
## LQ_INTL_INDUSTRY 11.66 9.84 104.39 0.084.2 Visualising standardised clustering variables
minmax_agri <- ggplot(as.data.frame(saopaulo_industry.std),
aes(x = `LQ_AGRI_INDUSTRY`)) +
geom_histogram(color = "red",
fill = "pink",
binwidth = 0.1) +
ggtitle("Min-Max Standardisation")
z_agri <- ggplot(as.data.frame(saopaulo_industry.z),
aes(x = `LQ_AGRI_INDUSTRY`)) +
geom_histogram(color = "red",
fill = "pink",
binwidth = 0.1) +
ggtitle("Z-score Standardisation")
minmax_extract <- ggplot(as.data.frame(saopaulo_industry.std),
aes(x = `LQ_EXTRACTIVE_INDUSTRY`)) +
geom_histogram(color = "red",
fill = "pink",
binwidth = 0.1) +
ggtitle("Min-Max Standardisation")
z_extract <- ggplot(as.data.frame(saopaulo_industry.z),
aes(x = `LQ_EXTRACTIVE_INDUSTRY`)) +
geom_histogram(color = "red",
fill = "pink",
binwidth = 0.1) +
ggtitle("Z-score Standardisation")
ggarrange(LQ_AGRI, minmax_agri, z_agri, LQ_EXTRACTIVE, minmax_extract, z_extract,
ncol = 3,
nrow = 2)
These 2 Industry Location Quotient, agriculture industry LQ and extractive industry LQ, were very skewed before data standardization. However, both are still skewed after standardization using both min-max method and z-score method. However, these are due to outliers which are normal since different municipalities have different industry specialization.
4.3 Computing proximity matrix
We will calculate the distance matrix using dist() of Base R, where method to be used is “euclidean”.
proxmat <- dist(saopaulo_industry, method = "euclidean")4.4 Computing hierarchical clustering
Next, we will use hclust() of stats package to perform hierarchical cluster analysis of the proximity matrix using “ward.D” for its clustering algorithm.
hclust_ward <- hclust(proxmat, method = "ward.D")
plot(hclust_ward, cex = 0.4)
4.5 Selecting optimal clustering algorithm
We will use the agnes() function of cluster package to get the agglomerative coefficient of different clustering algorithms.
m <- c( "average", "single", "complete", "ward")
names(m) <- c( "average", "single", "complete", "ward")
ac <- function(x) {
agnes(saopaulo_industry, method = x)$ac
}
map_dbl(m, ac)## average single complete ward
## 0.9561122 0.9511566 0.9585075 0.9705217We caan see that all the hierarchical clustering algorithms perform well but we will choose the one with the highest result which is ward. Hence, ward method will be used.
4.6 Determining optimal clusters
To determine the optimal clusters, we will use the gap statistic method, which compares the total within intra-cluster variation for different values of k with their expected values under null reference distribution of the data.
This will return the gap statistic, the largest gap statistic means that the clusters are far away from the random uniform distribution of points.
We will use clusGap() function of cluster package to compute the gap statistics. B argument is the number of monte carlo samples while K.max is the maximum number of clusters to consider.
set.seed(12345)
gap_stat <- clusGap(saopaulo_industry, FUN = hcut, nstart = 25, K.max = 20, B = 100)
print(gap_stat, method = "firstmax")## Clustering Gap statistic ["clusGap"] from call:
## clusGap(x = saopaulo_industry, FUNcluster = hcut, K.max = 20, B = 100, nstart = 25)
## B=100 simulated reference sets, k = 1..20; spaceH0="scaledPCA"
## --> Number of clusters (method 'firstmax'): 2
## logW E.logW gap SE.sim
## [1,] 6.818823 8.120307 1.301484 0.02203295
## [2,] 6.553872 7.946781 1.392909 0.02625644
## [3,] 6.473871 7.843966 1.370095 0.02281273
## [4,] 6.309323 7.755602 1.446279 0.02366855
## [5,] 6.256093 7.681333 1.425239 0.02281774
## [6,] 6.201907 7.615371 1.413464 0.02123337
## [7,] 6.072386 7.559672 1.487286 0.01863795
## [8,] 5.992717 7.511456 1.518738 0.01746740
## [9,] 5.909477 7.468575 1.559098 0.01656932
## [10,] 5.867516 7.430681 1.563166 0.01661111
## [11,] 5.820004 7.395299 1.575295 0.01683447
## [12,] 5.775048 7.362825 1.587778 0.01675116
## [13,] 5.684131 7.331864 1.647733 0.01672285
## [14,] 5.645991 7.302874 1.656883 0.01659002
## [15,] 5.612908 7.275251 1.662343 0.01671317
## [16,] 5.551638 7.248844 1.697206 0.01681075
## [17,] 5.506684 7.223094 1.716411 0.01750255
## [18,] 5.466653 7.198399 1.731746 0.01787528
## [19,] 5.432633 7.174559 1.741926 0.01820935
## [20,] 5.401688 7.151390 1.749702 0.01839030Then, we will visualize the gap statistics generated by the clusGap() function of cluster package using fviz_gap_stat() function of factoextraa package
fviz_gap_stat(gap_stat)
We can see that the recommended cluster is 2 but we know that it’s too small to get insights from the analysis.
We can also observe that from k = 9 onward, the gap statistic keeps on increasing and anything beyong 10 clusters will give heterogeneous clusters so we shall set our cluster k to 9.
4.7 Interactive cluster heatmap
We will visualize the hierarchical clustering analysis result in another way, which is by interactive heatmap using the heatmaply() function of heatmaply package.
saopaulo_industry_matrix <- data.matrix(saopaulo_industry)
heatmaply(normalize(saopaulo_industry_matrix),
Colv = NA,
dist_method = "euclidean",
hclust_method = "ward.D",
seriate = "OLO",
colors = Blues,
krow = 9,
margins = c(NA, 200,60,NA),
fontsize_row = 3,
fontsize_col = 5,
main = "Geo Segmentation of Industry Specializations in São Paulo Macrometropolis",
xlab = "Industry Location Quotient",
ylab = "Municipalities in São Paulo")4.8 Mapping the clusters
cutree() function of stats package cuts the tree (dendogram), result of hclust function, into several groups by specifying the number of groups/clusters.
groups <- as.factor(cutree(hclust_ward, k =9))Now, we need to join the groups to the saopaulo sf dataframe.
saopaulo_cluster <- cbind(saopaulo, as.matrix(groups)) %>%
rename(`CLUSTER` = `as.matrix.groups.`)Now, we can use qtm() function of tmap package to quickly plot the 7 clusters of industry specializations in São Paulo Macrometropolis.
qtm(saopaulo_cluster, "CLUSTER")
We can see that the hierarchical clustering analysis plot is very fragmented, which is one limitation of non-spatially clustering analysis method.
5. Spatially Constrained Clustering - SKATER method
5.1 Computing Neighbour List
Before we use poly2nb() function to compute the neighbours list based on regions with contiguous boundaries, where default method to define contiguity is Queen’s method, we have to convert the saopaulo from sf dataframe into sp object, SpatialPolygonsDataFrame.
saopaulo_sp <- as_Spatial(saopaulo)
saopaulo.nb <- poly2nb(saopaulo_sp, queen = TRUE, snap = 0.02)
summary(saopaulo.nb)## Neighbour list object:
## Number of regions: 172
## Number of nonzero links: 974
## Percentage nonzero weights: 3.29232
## Average number of links: 5.662791
## Link number distribution:
##
## 1 2 3 4 5 6 7 8 9 10 12 13 27
## 4 9 11 34 34 31 18 14 7 5 3 1 1
## 4 least connected regions:
## 8 9 36 98 with 1 link
## 1 most connected region:
## 159 with 27 linksWe can see that the number of average link is 5, the most connected municipality has 27 neighbours.
Let us plot the neighbour list.
plot(saopaulo_sp, border = grey(0.5))
plot(saopaulo.nb, coordinates(saopaulo_sp), col = "red", add = TRUE)
5.2 Computing weights list
Next, we will compute the cost of each edge using nbcosts() function of spdep package, the cost is the distance between each nodes.
lcosts <- nbcosts(saopaulo.nb, saopaulo_industry)Basically, lcosts is the notion of a generalised weight for a spatial weights matrix.
Next, we will incorporate these spatial weights/costs into a weights object by converting the neighbour list to a list weights object.
We will use nb2listw() function of spdep package to do this and we specify the style as B (basic binary coding) to make sure the cost values are not row-standardised.
saopaulo.weights <- nb2listw(saopaulo.nb, lcosts, style = "B")
summary(saopaulo.weights)## Characteristics of weights list object:
## Neighbour list object:
## Number of regions: 172
## Number of nonzero links: 974
## Percentage nonzero weights: 3.29232
## Average number of links: 5.662791
## Link number distribution:
##
## 1 2 3 4 5 6 7 8 9 10 12 13 27
## 4 9 11 34 34 31 18 14 7 5 3 1 1
## 4 least connected regions:
## 8 9 36 98 with 1 link
## 1 most connected region:
## 159 with 27 links
##
## Weights style: B
## Weights constants summary:
## n nn S0 S1 S2
## B 172 29584 14682.63 1053909 91405175.3 Computing Minimum Spanning Tree
We compute the minimum spanning tree by using mstree() function of spdep package.
saopaulo.mst <- mstree(saopaulo.weights)
dim(saopaulo.mst)## [1] 171 3The dimension is 171 and not the total numer of rows, 172, because minimum spanning tree consists of n-1 edges/links to traverse all the nodes.
plot(saopaulo_sp, border = gray(0.5))
plot.mst(saopaulo.mst, coordinates(saopaulo_sp), col = "blue", cex.lab = 0.7, cex.circles = 0.005, add = TRUE)
5.4 Computing SKATER spatially constrained clusters
To compute the spatially constrained cluster, we use skater() function of spdep package which takes in 3 mandatory arguments:
first two columns of the minimum spanning tree matrix
the data matrix to be updated
number of cuts (one less than the number of clusters)
clust9 <- skater(saopaulo.mst[,1:2], saopaulo_industry, method = "euclidean", 8)
str(clust9)## List of 8
## $ groups : num [1:172] 1 1 1 1 1 1 1 9 6 1 ...
## $ edges.groups:List of 9
## ..$ :List of 3
## .. ..$ node: num [1:113] 23 168 55 24 51 53 165 170 1 163 ...
## .. ..$ edge: num [1:112, 1:3] 168 24 163 170 165 1 165 83 11 144 ...
## .. ..$ ssw : num 761
## ..$ :List of 3
## .. ..$ node: num [1:6] 116 95 118 101 88 105
## .. ..$ edge: num [1:5, 1:3] 95 95 118 116 118 116 118 101 88 105 ...
## .. ..$ ssw : num 71.5
## ..$ :List of 3
## .. ..$ node: num 87
## .. ..$ edge: num[0 , 1:3]
## .. ..$ ssw : num 0
## ..$ :List of 3
## .. ..$ node: num 102
## .. ..$ edge: num[0 , 1:3]
## .. ..$ ssw : num 0
## ..$ :List of 3
## .. ..$ node: num [1:15] 82 19 68 64 63 73 70 79 58 65 ...
## .. ..$ edge: num [1:14, 1:3] 19 73 63 63 73 68 19 64 68 63 ...
## .. ..$ ssw : num 257
## ..$ :List of 3
## .. ..$ node: num [1:2] 15 9
## .. ..$ edge: num [1, 1:3] 15 9 3.87
## .. ..$ ssw : num 3.87
## ..$ :List of 3
## .. ..$ node: num [1:28] 113 99 121 90 106 152 103 117 89 120 ...
## .. ..$ edge: num [1:27, 1:3] 121 90 121 106 120 90 114 100 113 152 ...
## .. ..$ ssw : num 443
## ..$ :List of 3
## .. ..$ node: num 86
## .. ..$ edge: num[0 , 1:3]
## .. ..$ ssw : num 0
## ..$ :List of 3
## .. ..$ node: num [1:5] 30 17 12 29 8
## .. ..$ edge: num [1:4, 1:3] 30 30 30 30 17 ...
## .. ..$ ssw : num 74.5
## $ not.prune : NULL
## $ candidates : int [1:9] 1 2 3 4 5 6 7 8 9
## $ ssto : num 2624
## $ ssw : num [1:9] 2624 2370 2213 2089 1965 ...
## $ crit : num [1:2] 1 Inf
## $ vec.crit : num [1:172] 1 1 1 1 1 1 1 1 1 1 ...
## - attr(*, "class")= chr "skater"The groups frequency:
table(clust9$groups)##
## 1 2 3 4 5 6 7 8 9
## 113 6 1 1 15 2 28 1 5plot(saopaulo_sp, border=gray(.5))
plot(clust9, coordinates(saopaulo_sp), cex.lab=.7,
groups.colors=c("red","green","purple", "yellow", "blue", "brown", "pink"), cex.circles=0.005, add=TRUE)
5.5 Visualizing SKATER spatially constrained clusters
groups_mat <- as.matrix(clust9$groups)
saopaolu_spatialcluster <- cbind(saopaulo_cluster, as.factor(groups_mat)) %>%
rename(`SP_CLUSTER`=`as.factor.groups_mat.`)
qtm(saopaolu_spatialcluster, "SP_CLUSTER")
Finally, the clusters are not fragmented and we can see that Cluster 1 covers big area, 113 municipalities in exact while there are 3 clusters who only contains 1 municipality, indicating that the cluster have an industry specialization. Let’s see the summary of the Location Quotient of industries in each cluster.
cluster1 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 1) %>%
select(contains("LQ_"))
summary(cluster1)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. : 0.0000 Min. : 0.0000 Min. :0.2110
## 1st Qu.: 0.1826 1st Qu.: 0.0000 1st Qu.:0.8944
## Median : 0.7866 Median : 0.7365 Median :1.3120
## Mean : 2.6753 Mean : 2.7391 Mean :1.3754
## 3rd Qu.: 2.3497 3rd Qu.: 2.4975 3rd Qu.:1.7789
## Max. :60.9939 Max. :26.1729 Max. :3.2620
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0.0000 Min. : 0.0000 Min. :0.1355
## 1st Qu.:0.0000 1st Qu.: 0.9589 1st Qu.:0.8170
## Median :0.0000 Median : 1.3603 Median :1.0092
## Mean :0.4494 Mean : 1.6365 Mean :1.0310
## 3rd Qu.:0.1841 3rd Qu.: 1.9824 3rd Qu.:1.1938
## Max. :8.6511 Max. :11.3510 Max. :1.9899
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.3032 Min. :0.1743 Min. :0.3086
## 1st Qu.:1.0755 1st Qu.:0.8370 1st Qu.:0.9463
## Median :1.1647 Median :1.0451 Median :1.0471
## Mean :1.1668 Mean :1.2307 Mean :1.1552
## 3rd Qu.:1.2860 3rd Qu.:1.5293 3rd Qu.:1.2421
## Max. :1.6397 Max. :3.4181 Max. :4.5032
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.2734 1st Qu.:0.2535 1st Qu.:0.4535
## Median :0.3611 Median :0.3847 Median :0.6776
## Mean :0.5579 Mean :0.4403 Mean :0.7012
## 3rd Qu.:0.5590 3rd Qu.:0.5534 3rd Qu.:0.9251
## Max. :8.0422 Max. :2.1781 Max. :1.8481
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.0000 Min. :0.0882 Min. : 0.2823
## 1st Qu.:0.4019 1st Qu.:0.4659 1st Qu.: 0.9902
## Median :0.5272 Median :0.6063 Median : 2.3539
## Mean :0.5960 Mean :0.7052 Mean : 3.6170
## 3rd Qu.:0.6944 3rd Qu.:0.7732 3rd Qu.: 4.4035
## Max. :2.4735 Max. :2.6437 Max. :35.5707
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.8443 1st Qu.:0.4577 1st Qu.:0.7766
## Median :1.0378 Median :0.6029 Median :0.9449
## Mean :1.0652 Mean :0.6405 Mean :0.9534
## 3rd Qu.:1.3303 3rd Qu.:0.7792 3rd Qu.:1.1544
## Max. :2.1971 Max. :1.7038 Max. :1.9038
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.3551 Min. :0.00000 MULTIPOLYGON :113
## 1st Qu.:0.7704 1st Qu.:0.00000 epsg:4674 : 0
## Median :0.9388 Median :0.00000 +proj=long...: 0
## Mean :0.9637 Mean :0.06302
## 3rd Qu.:1.1262 3rd Qu.:0.00000
## Max. :2.3990 Max. :4.33767Cluster 1 covers the entire central, north area and bottom of the east area of São Paulo Macrometropolis.
From the LQ, Cluster 1 seems to specialize in agriculture industry, with quite many extractive industry companies and public administration industries as well. Cluster 1 also seems to have a growing ICT sector and growing water supply and treatment industries.
cluster2 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 2) %>%
select(contains("LQ_"))
summary(cluster2)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. :35.43 Min. :0.000 Min. :0.2045
## 1st Qu.:39.94 1st Qu.:0.000 1st Qu.:0.2399
## Median :49.69 Median :2.268 Median :0.2570
## Mean :48.61 Mean :2.366 Mean :0.3234
## 3rd Qu.:54.90 3rd Qu.:4.568 3rd Qu.:0.3779
## Max. :63.50 Max. :5.083 Max. :0.5694
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0 Min. :0.0000 Min. :0.1432
## 1st Qu.:0 1st Qu.:0.0000 1st Qu.:0.2286
## Median :0 Median :0.0000 Median :0.2908
## Mean :0 Mean :0.2234 Mean :0.2925
## 3rd Qu.:0 3rd Qu.:0.0000 3rd Qu.:0.3715
## Max. :0 Max. :1.3407 Max. :0.4240
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.2461 Min. :0.1985 Min. :0.2893
## 1st Qu.:0.3712 1st Qu.:0.2663 1st Qu.:0.4114
## Median :0.5574 Median :0.3514 Median :0.7739
## Mean :0.5410 Mean :0.3816 Mean :0.8059
## 3rd Qu.:0.7187 3rd Qu.:0.5096 3rd Qu.:1.2168
## Max. :0.8036 Max. :0.5881 Max. :1.3430
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.00000 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.02732 1st Qu.:0.00000 1st Qu.:0.02558
## Median :0.06714 Median :0.01964 Median :0.10998
## Mean :0.09178 Mean :0.09834 Mean :0.15994
## 3rd Qu.:0.09092 3rd Qu.:0.20610 3rd Qu.:0.18685
## Max. :0.30353 Max. :0.28902 Max. :0.52976
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.0625 Min. :0.09233 Min. : 3.613
## 1st Qu.:0.1916 1st Qu.:0.10876 1st Qu.: 4.665
## Median :0.2174 Median :0.13431 Median : 7.403
## Mean :0.2013 Mean :0.13810 Mean : 9.741
## 3rd Qu.:0.2346 3rd Qu.:0.15485 3rd Qu.: 8.176
## Max. :0.2874 Max. :0.20570 Max. :27.838
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.07338 Min. :0.06187 Min. :0.1851
## 1st Qu.:0.14435 1st Qu.:0.13075 1st Qu.:0.2110
## Median :0.32081 Median :0.18894 Median :0.3289
## Mean :0.45260 Mean :0.20851 Mean :0.4781
## 3rd Qu.:0.49472 3rd Qu.:0.25109 3rd Qu.:0.4150
## Max. :1.36240 Max. :0.42818 Max. :1.4099
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.1479 Min. :0 MULTIPOLYGON :6
## 1st Qu.:0.3205 1st Qu.:0 epsg:4674 :0
## Median :0.3536 Median :0 +proj=long...:0
## Mean :0.4067 Mean :0
## 3rd Qu.:0.4764 3rd Qu.:0
## Max. :0.7585 Max. :0Cluster 2 covers the east area of São Paulo Macrometropolis. Cluster 2 is another cluster that’s specialized in agriculture with decent LQ for public administration industry as well.
cluster3 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 3) %>%
select(contains("LQ_"))
summary(cluster3)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. :3.334 Min. :0 Min. :0.3067
## 1st Qu.:3.334 1st Qu.:0 1st Qu.:0.3067
## Median :3.334 Median :0 Median :0.3067
## Mean :3.334 Mean :0 Mean :0.3067
## 3rd Qu.:3.334 3rd Qu.:0 3rd Qu.:0.3067
## Max. :3.334 Max. :0 Max. :0.3067
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0 Min. :0 Min. :0.4296
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.4296
## Median :0 Median :0 Median :0.4296
## Mean :0 Mean :0 Mean :0.4296
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.4296
## Max. :0 Max. :0 Max. :0.4296
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :1.573 Min. :0.4857 Min. :2.3
## 1st Qu.:1.573 1st Qu.:0.4857 1st Qu.:2.3
## Median :1.573 Median :0.4857 Median :2.3
## Mean :1.573 Mean :0.4857 Mean :2.3
## 3rd Qu.:1.573 3rd Qu.:0.4857 3rd Qu.:2.3
## Max. :1.573 Max. :0.4857 Max. :2.3
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :0 Max. :0 Max. :0
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.2912 Min. :0.3355 Min. :136.2
## 1st Qu.:0.2912 1st Qu.:0.3355 1st Qu.:136.2
## Median :0.2912 Median :0.3355 Median :136.2
## Mean :0.2912 Mean :0.3355 Mean :136.2
## 3rd Qu.:0.2912 3rd Qu.:0.3355 3rd Qu.:136.2
## Max. :0.2912 Max. :0.3355 Max. :136.2
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.6667 Min. :1.153 Min. :0
## 1st Qu.:0.6667 1st Qu.:1.153 1st Qu.:0
## Median :0.6667 Median :1.153 Median :0
## Mean :0.6667 Mean :1.153 Mean :0
## 3rd Qu.:0.6667 3rd Qu.:1.153 3rd Qu.:0
## Max. :0.6667 Max. :1.153 Max. :0
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.4594 Min. :0 MULTIPOLYGON :1
## 1st Qu.:0.4594 1st Qu.:0 epsg:4674 :0
## Median :0.4594 Median :0 +proj=long...:0
## Mean :0.4594 Mean :0
## 3rd Qu.:0.4594 3rd Qu.:0
## Max. :0.4594 Max. :0Cluster 3 is a single municipality cluster, located on top of cluster 2, covers the east area of São Paulo Macrometropolis.
We can see that it’s LQ for Public administration industry is very high, indicating that it’s specialized in public administration, defense and social security, probably where the police offices and government offices are located.
cluster4 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 4) %>%
select(contains("LQ_"))
summary(cluster4)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. :19.59 Min. :92.23 Min. :0.6864
## 1st Qu.:19.59 1st Qu.:92.23 1st Qu.:0.6864
## Median :19.59 Median :92.23 Median :0.6864
## Mean :19.59 Mean :92.23 Mean :0.6864
## 3rd Qu.:19.59 3rd Qu.:92.23 3rd Qu.:0.6864
## Max. :19.59 Max. :92.23 Max. :0.6864
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0 Min. :0 Min. :0.2404
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.2404
## Median :0 Median :0 Median :0.2404
## Mean :0 Mean :0 Mean :0.2404
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.2404
## Max. :0 Max. :0 Max. :0.2404
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.9534 Min. :0.2718 Min. :1.471
## 1st Qu.:0.9534 1st Qu.:0.2718 1st Qu.:1.471
## Median :0.9534 Median :0.2718 Median :1.471
## Mean :0.9534 Mean :0.2718 Mean :1.471
## 3rd Qu.:0.9534 3rd Qu.:0.2718 3rd Qu.:1.471
## Max. :0.9534 Max. :0.2718 Max. :1.471
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.2295 Min. :0.7914 Min. :0
## 1st Qu.:0.2295 1st Qu.:0.7914 1st Qu.:0
## Median :0.2295 Median :0.7914 Median :0
## Mean :0.2295 Mean :0.7914 Mean :0
## 3rd Qu.:0.2295 3rd Qu.:0.7914 3rd Qu.:0
## Max. :0.2295 Max. :0.7914 Max. :0
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.1629 Min. :0.1877 Min. :38.11
## 1st Qu.:0.1629 1st Qu.:0.1877 1st Qu.:38.11
## Median :0.1629 Median :0.1877 Median :38.11
## Mean :0.1629 Mean :0.1877 Mean :38.11
## 3rd Qu.:0.1629 3rd Qu.:0.1877 3rd Qu.:38.11
## Max. :0.1629 Max. :0.1877 Max. :38.11
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :1.119 Min. :0.9678 Min. :0.9651
## 1st Qu.:1.119 1st Qu.:0.9678 1st Qu.:0.9651
## Median :1.119 Median :0.9678 Median :0.9651
## Mean :1.119 Mean :0.9678 Mean :0.9651
## 3rd Qu.:1.119 3rd Qu.:0.9678 3rd Qu.:0.9651
## Max. :1.119 Max. :0.9678 Max. :0.9651
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :1.028 Min. :0 MULTIPOLYGON :1
## 1st Qu.:1.028 1st Qu.:0 epsg:4674 :0
## Median :1.028 Median :0 +proj=long...:0
## Mean :1.028 Mean :0
## 3rd Qu.:1.028 3rd Qu.:0
## Max. :1.028 Max. :0Cluster 4 is another single municipality cluster, located to the left of cluster 2, covers the east area of São Paulo Macrometropolis.
We can see that it’s LQ for extractive industry is very high, indicating that it’s specialized in extractive industry, probably where the mining for minerals, drilling and pumping for oil and other activities take place.
cluster5 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 5) %>%
select(contains("LQ_"))
summary(cluster5)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. : 3.021 Min. : 0.000 Min. :0.5976
## 1st Qu.: 8.723 1st Qu.: 2.160 1st Qu.:0.7131
## Median :18.573 Median : 2.940 Median :0.8490
## Mean :18.617 Mean : 9.067 Mean :1.1560
## 3rd Qu.:25.101 3rd Qu.:13.059 3rd Qu.:1.1916
## Max. :38.037 Max. :34.897 Max. :3.6360
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0.0000 Min. :0.0000 Min. :0.2109
## 1st Qu.:0.0000 1st Qu.:0.3192 1st Qu.:0.5078
## Median :0.0000 Median :0.9792 Median :0.7277
## Mean :0.5271 Mean :1.2230 Mean :0.7440
## 3rd Qu.:0.0000 3rd Qu.:1.2372 3rd Qu.:0.9348
## Max. :7.0506 Max. :6.9496 Max. :1.4058
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.5273 Min. :0.4084 Min. :0.5969
## 1st Qu.:0.8575 1st Qu.:0.5161 1st Qu.:0.7999
## Median :1.0685 Median :0.7704 Median :0.9671
## Mean :1.0736 Mean :0.8486 Mean :1.0481
## 3rd Qu.:1.1935 3rd Qu.:1.1609 3rd Qu.:1.0882
## Max. :1.6942 Max. :1.4322 Max. :2.3113
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.1220 1st Qu.:0.1978 1st Qu.:0.2667
## Median :0.2168 Median :0.3623 Median :0.3049
## Mean :0.1846 Mean :0.3637 Mean :0.4104
## 3rd Qu.:0.2581 3rd Qu.:0.4440 3rd Qu.:0.5528
## Max. :0.3607 Max. :0.8350 Max. :0.9814
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.0000 Min. :0.09801 Min. : 1.458
## 1st Qu.:0.2003 1st Qu.:0.19879 1st Qu.: 2.323
## Median :0.3328 Median :0.21626 Median : 4.002
## Mean :0.3049 Mean :0.27571 Mean : 8.931
## 3rd Qu.:0.3806 3rd Qu.:0.33296 3rd Qu.: 7.243
## Max. :0.5343 Max. :0.56831 Max. :43.262
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.2823 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.5154 1st Qu.:0.2043 1st Qu.:0.5597
## Median :0.8278 Median :0.5518 Median :0.6842
## Mean :0.8722 Mean :0.4674 Mean :0.6518
## 3rd Qu.:1.1673 3rd Qu.:0.6340 3rd Qu.:0.8454
## Max. :1.7053 Max. :1.1121 Max. :1.1155
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.5011 Min. :0 MULTIPOLYGON :15
## 1st Qu.:0.6142 1st Qu.:0 epsg:4674 : 0
## Median :0.7383 Median :0 +proj=long...: 0
## Mean :0.8395 Mean :0
## 3rd Qu.:0.8986 3rd Qu.:0
## Max. :1.7625 Max. :0Cluster 5 totally cover the entire west region of São Paulo Macrometropolis. It is quite big in area.
Looking at the LQ, cluster 5 is quite specialized in public administration industry, agriculture industry and extractive industry, although not as quite as cluster 4 for extractive industry and cluster 3 for public administration industry.
cluster6 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 6) %>%
select(contains("LQ_"))
summary(cluster6)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. :17.41 Min. :35.87 Min. :0.7118
## 1st Qu.:17.49 1st Qu.:36.04 1st Qu.:0.9418
## Median :17.57 Median :36.20 Median :1.1718
## Mean :17.57 Mean :36.20 Mean :1.1718
## 3rd Qu.:17.66 3rd Qu.:36.37 3rd Qu.:1.4018
## Max. :17.74 Max. :36.54 Max. :1.6318
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0 Min. :0.0000 Min. :0.2540
## 1st Qu.:0 1st Qu.:0.8031 1st Qu.:0.3775
## Median :0 Median :1.6063 Median :0.5009
## Mean :0 Mean :1.6063 Mean :0.5009
## 3rd Qu.:0 3rd Qu.:2.4094 3rd Qu.:0.6244
## Max. :0 Max. :3.2125 Max. :0.7479
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.7416 Min. :3.446 Min. :1.263
## 1st Qu.:0.7596 1st Qu.:3.500 1st Qu.:1.424
## Median :0.7776 Median :3.555 Median :1.585
## Mean :0.7776 Mean :3.555 Mean :1.585
## 3rd Qu.:0.7956 3rd Qu.:3.609 3rd Qu.:1.746
## Max. :0.8137 Max. :3.664 Max. :1.907
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.00000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.08923 1st Qu.:0.2090 1st Qu.:0.2767
## Median :0.17847 Median :0.4181 Median :0.5533
## Mean :0.17847 Mean :0.4181 Mean :0.5533
## 3rd Qu.:0.26770 3rd Qu.:0.6271 3rd Qu.:0.8300
## Max. :0.35693 Max. :0.8362 Max. :1.1066
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.1722 Min. :0.1947 Min. :19.76
## 1st Qu.:0.2559 1st Qu.:0.2204 1st Qu.:19.85
## Median :0.3395 Median :0.2461 Median :19.95
## Mean :0.3395 Mean :0.2461 Mean :19.95
## 3rd Qu.:0.4232 3rd Qu.:0.2718 3rd Qu.:20.04
## Max. :0.5069 Max. :0.2976 Max. :20.13
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.00000 Min. :0.00000 Min. :0
## 1st Qu.:0.04927 1st Qu.:0.08363 1st Qu.:0
## Median :0.09854 Median :0.16727 Median :0
## Mean :0.09854 Mean :0.16727 Mean :0
## 3rd Qu.:0.14781 3rd Qu.:0.25090 3rd Qu.:0
## Max. :0.19708 Max. :0.33454 Max. :0
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.3998 Min. :0 MULTIPOLYGON :2
## 1st Qu.:0.4696 1st Qu.:0 epsg:4674 :0
## Median :0.5394 Median :0 +proj=long...:0
## Mean :0.5394 Mean :0
## 3rd Qu.:0.6092 3rd Qu.:0
## Max. :0.6790 Max. :0Cluster 6 is a two municipality cluster located at the top most northern area of São Paulo Macrometropolis.
cluster7 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 7) %>%
select(contains("LQ_"))
summary(cluster7)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. : 0.3332 Min. : 0.0000 Min. :0.3242
## 1st Qu.: 1.5473 1st Qu.: 0.7559 1st Qu.:0.6301
## Median : 2.8782 Median : 4.9575 Median :0.8780
## Mean : 6.6818 Mean : 9.6251 Mean :0.9585
## 3rd Qu.:10.1813 3rd Qu.:10.5828 3rd Qu.:1.1624
## Max. :29.3796 Max. :47.2389 Max. :2.2960
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0.0000 Min. : 0.0000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.: 0.0000 1st Qu.:0.4956
## Median :0.0000 Median : 0.5477 Median :0.7579
## Mean :0.3867 Mean : 1.4639 Mean :0.7765
## 3rd Qu.:0.0000 3rd Qu.: 1.4439 3rd Qu.:1.0790
## Max. :6.1577 Max. :13.5609 Max. :1.4423
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.5134 Min. :0.0000 Min. :0.7595
## 1st Qu.:1.1050 1st Qu.:0.6850 1st Qu.:1.0955
## Median :1.2074 Median :0.8498 Median :1.2882
## Mean :1.2520 Mean :1.0604 Mean :1.5614
## 3rd Qu.:1.4030 3rd Qu.:1.2146 3rd Qu.:1.7269
## Max. :2.1525 Max. :3.1809 Max. :3.5927
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.1870 1st Qu.:0.0000 1st Qu.:0.0963
## Median :0.2776 Median :0.2284 Median :0.3429
## Mean :0.3041 Mean :0.2117 Mean :0.3954
## 3rd Qu.:0.3845 3rd Qu.:0.3356 3rd Qu.:0.6816
## Max. :0.8351 Max. :0.6358 Max. :1.0799
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.0000 Min. :0.09134 Min. : 0.4593
## 1st Qu.:0.3090 1st Qu.:0.23622 1st Qu.: 1.6058
## Median :0.5070 Median :0.41050 Median : 9.7160
## Mean :0.5056 Mean :0.44635 Mean :10.6088
## 3rd Qu.:0.6707 3rd Qu.:0.58642 3rd Qu.:15.1702
## Max. :1.0838 Max. :0.99811 Max. :38.5706
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.2568 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.5686 1st Qu.:0.2496 1st Qu.:0.8696
## Median :1.0798 Median :0.6020 Median :0.9934
## Mean :0.9985 Mean :0.7184 Mean :0.9654
## 3rd Qu.:1.4216 3rd Qu.:1.1292 3rd Qu.:1.2027
## Max. :1.9195 Max. :1.8189 Max. :1.8083
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.2999 Min. :0.00000 MULTIPOLYGON :28
## 1st Qu.:0.7611 1st Qu.:0.00000 epsg:4674 : 0
## Median :1.0388 Median :0.00000 +proj=long...: 0
## Mean :1.0009 Mean :0.02826
## 3rd Qu.:1.1329 3rd Qu.:0.00000
## Max. :1.9107 Max. :0.79133Cluster 7 is a relatively bigger municipality cluster located at the eastern side of São Paulo Macrometropolis.
Cluster 7, being a big area, is specialized in agriculture, extractive, public administration industries. Something new would be a growing energy industry and water supply and treatment industry.
cluster8 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 8) %>%
select(contains("LQ_"))
summary(cluster8)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. :31.87 Min. :0 Min. :0
## 1st Qu.:31.87 1st Qu.:0 1st Qu.:0
## Median :31.87 Median :0 Median :0
## Mean :31.87 Mean :0 Mean :0
## 3rd Qu.:31.87 3rd Qu.:0 3rd Qu.:0
## Max. :31.87 Max. :0 Max. :0
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :47.8 Min. :0 Min. :0
## 1st Qu.:47.8 1st Qu.:0 1st Qu.:0
## Median :47.8 Median :0 Median :0
## Mean :47.8 Mean :0 Mean :0
## 3rd Qu.:47.8 3rd Qu.:0 3rd Qu.:0
## Max. :47.8 Max. :0 Max. :0
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :1.096 Min. :0.3869 Min. :0.7853
## 1st Qu.:1.096 1st Qu.:0.3869 1st Qu.:0.7853
## Median :1.096 Median :0.3869 Median :0.7853
## Mean :1.096 Mean :0.3869 Mean :0.7853
## 3rd Qu.:1.096 3rd Qu.:0.3869 3rd Qu.:0.7853
## Max. :1.096 Max. :0.3869 Max. :0.7853
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.3267 Min. :0 Min. :0.7596
## 1st Qu.:0.3267 1st Qu.:0 1st Qu.:0.7596
## Median :0.3267 Median :0 Median :0.7596
## Mean :0.3267 Mean :0 Mean :0.7596
## 3rd Qu.:0.3267 3rd Qu.:0 3rd Qu.:0.7596
## Max. :0.3267 Max. :0 Max. :0.7596
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.232 Min. :0 Min. :54.26
## 1st Qu.:0.232 1st Qu.:0 1st Qu.:54.26
## Median :0.232 Median :0 Median :54.26
## Mean :0.232 Mean :0 Mean :54.26
## 3rd Qu.:0.232 3rd Qu.:0 3rd Qu.:54.26
## Max. :0.232 Max. :0 Max. :54.26
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :1.593 Min. :0 Min. :0
## 1st Qu.:1.593 1st Qu.:0 1st Qu.:0
## Median :1.593 Median :0 Median :0
## Mean :1.593 Mean :0 Mean :0
## 3rd Qu.:1.593 3rd Qu.:0 3rd Qu.:0
## Max. :1.593 Max. :0 Max. :0
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.3659 Min. :0 MULTIPOLYGON :1
## 1st Qu.:0.3659 1st Qu.:0 epsg:4674 :0
## Median :0.3659 Median :0 +proj=long...:0
## Mean :0.3659 Mean :0
## 3rd Qu.:0.3659 3rd Qu.:0
## Max. :0.3659 Max. :0Cluster 8 is another single municipality cluster, located to the right of cluster 2, covers the east area of São Paulo Macrometropolis, surrounded by cluster 2.
We can see that it’s LQ for energy and public administration industries are very high, this cluster definitely specializes in energy sector such as providing electricity and gas.
cluster9 <- saopaolu_spatialcluster %>%
filter(SP_CLUSTER == 9) %>%
select(contains("LQ_"))
summary(cluster9)## LQ_AGRI_INDUSTRY LQ_EXTRACTIVE_INDUSTRY LQ_TRANSFORM_INDUSTRY
## Min. : 0.7757 Min. : 9.588 Min. :0.2854
## 1st Qu.: 2.4237 1st Qu.:11.195 1st Qu.:0.9165
## Median : 6.3401 Median :17.170 Median :1.0726
## Mean : 8.5756 Mean :19.719 Mean :1.1071
## 3rd Qu.: 8.3346 3rd Qu.:19.433 3rd Qu.:1.1756
## Max. :25.0039 Max. :41.208 Max. :2.0854
## LQ_ENERGY_INDUSTRY LQ_WATER_INDUSTRY LQ_CONSTRUCTION_INDUSTRY
## Min. :0 Min. :0.000 Min. :0.0000
## 1st Qu.:0 1st Qu.:2.135 1st Qu.:0.5998
## Median :0 Median :2.174 Median :0.6086
## Mean :0 Mean :1.958 Mean :0.5864
## 3rd Qu.:0 3rd Qu.:2.529 3rd Qu.:0.6922
## Max. :0 Max. :2.953 Max. :1.0311
## LQ_TRADE_REPAIR_INDUSTRY LQ_LOGISTICS_INDUSTRY LQ_ACCOMS_FOOD_INDUSTRY
## Min. :0.8356 Min. :0.3390 Min. :0.6249
## 1st Qu.:0.9437 1st Qu.:0.9925 1st Qu.:0.7229
## Median :1.0880 Median :2.1371 Median :0.7667
## Mean :1.1371 Mean :1.9307 Mean :1.3625
## 3rd Qu.:1.3084 3rd Qu.:2.2261 3rd Qu.:1.6400
## Max. :1.5097 Max. :3.9586 Max. :3.0582
## LQ_ICT_INDUSTRY LQ_FINANCIAL_INDUSTRY LQ_REALESTATE_INDUSTRY
## Min. :0.08202 Min. :0.0000 Min. :0.2219
## 1st Qu.:0.23922 1st Qu.:0.0000 1st Qu.:0.2384
## Median :0.33424 Median :0.2829 Median :0.2591
## Mean :0.30065 Mean :0.2280 Mean :0.3707
## 3rd Qu.:0.37066 3rd Qu.:0.3291 3rd Qu.:0.5621
## Max. :0.47709 Max. :0.5280 Max. :0.5721
## LQ_PROF_TECHNICAL_INDUSTRY LQ_ADMIN_INDUSTRY LQ_PUBLIC_INDUSTRY
## Min. :0.3495 Min. :0.1957 Min. : 4.015
## 1st Qu.:0.4611 1st Qu.:0.2013 1st Qu.: 5.676
## Median :0.6098 Median :0.5209 Median :13.623
## Mean :0.7558 Mean :0.4283 Mean :11.533
## 3rd Qu.:0.6180 3rd Qu.:0.5855 3rd Qu.:15.848
## Max. :1.7406 Max. :0.6381 Max. :18.505
## LQ_EDUCATION_INDUSTRY LQ_HEALTHCARE_INDUSTRY LQ_ARTS_RECREATION_INDUSTRY
## Min. :0.4654 Min. :0.1153 Min. :0.8027
## 1st Qu.:0.6667 1st Qu.:0.2402 1st Qu.:0.8625
## Median :0.7245 Median :0.3133 Median :0.9372
## Mean :0.7514 Mean :0.3411 Mean :1.1083
## 3rd Qu.:0.8000 3rd Qu.:0.4024 3rd Qu.:1.3799
## Max. :1.1004 Max. :0.6344 Max. :1.5591
## LQ_OTHER_SERVICES_INDUSTRY LQ_INTL_INDUSTRY geom
## Min. :0.4275 Min. :0 MULTIPOLYGON :5
## 1st Qu.:0.4594 1st Qu.:0 epsg:4674 :0
## Median :0.7041 Median :0 +proj=long...:0
## Mean :0.6701 Mean :0
## 3rd Qu.:0.7488 3rd Qu.:0
## Max. :1.0106 Max. :0Lastly, cluster 9 is a mini cluster at the most north-west side of São Paulo Macrometropolis, surrounded by cluster 1.
Cluster 9 is again specialized in extractive industry, agriculture industry, public administration industry. It’s growing industry would be logistics and accomodation+food industries.
5.6 Conclusion
We can conclude that many of the clusters indicate industry specialization in agriculture, extractive and public administration industries, which indicates that São Paulo Macrometropolis is a developing region that relies heavily on it’s natural resources.
Other industry specializations such as services, logistics, ICT, financial, arts recreation are all in need of improvement.
Yet, priorities should still go to the development of education, financial, water, energy and healthcare industry specializations are these industries will provide the basic needs for the municipalities.