setwd("C:/Users/KOUKI/Documents/University/THESIS/data")
getwd()
library(tidyverse)
library(gt)
library(conflicted)
library(janitor)
library(plm)
library(ggplot2)
library(psych)
library(MASS)
library(corrplot)
library(car)
library(modelsummary)
library(skimr)
library(rstatix)
conflict_prefer("filter", "dplyr")
conflict_prefer("select", "dplyr")
conflict_prefer("lag", "dplyr")
library(httr)
library(estatapi)
appId <- "fa36d285e27be24a03967d0d29affdef3b1a63ea"presentation
1 Coding, table, and graph
1.1 Preparation
1.2 Collecting Data
1.2.1 School
stats_school <- GET(
url = "https://api.e-stat.go.jp/rest/3.0/app/getStatsData?cdArea=01100%2C01101%2C01102%2C01103%2C01104%2C01105%2C01106%2C01107%2C01108%2C01109%2C01110%2C01202%2C01203%2C01204%2C01205%2C01206%2C01207%2C01208%2C01209%2C01210%2C01211%2C01212%2C01213%2C01214%2C01215%2C01216%2C01217%2C01218%2C01219%2C01220%2C01221%2C01222%2C01223%2C01224%2C01225%2C01226%2C01227%2C01228%2C01229%2C01230%2C01231%2C01233%2C01234%2C01235%2C01236%2C01303%2C01304%2C01331%2C01332%2C01333%2C01334%2C01337%2C01343%2C01345%2C01346%2C01347%2C01361%2C01362%2C01363%2C01364%2C01367%2C01370%2C01371%2C01391%2C01392%2C01393%2C01394%2C01395%2C01396%2C01397%2C01398%2C01399%2C01400%2C01401%2C01402%2C01403%2C01404%2C01405%2C01406%2C01407%2C01408%2C01409%2C01423%2C01424%2C01425%2C01427%2C01428%2C01429%2C01430%2C01431%2C01432%2C01433%2C01434%2C01436%2C01437%2C01438%2C01452%2C01453%2C01454%2C01455&cdCat01=E1101%2CE2101%2CE3101%2CE4101&appId=&lang=J&statsDataId=0000020205&metaGetFlg=Y&cntGetFlg=N&explanationGetFlg=Y&annotationGetFlg=Y§ionHeaderFlg=1&replaceSpChars=0",
query = list(
appId = appId,
statsDataId = "0000020205")
)
result <- content(stats_school)
str(result, max.level = 4, list.len = 4)
school <- estat_getStatsData(
appId = appId,
statsDataId = "0000020205",
cdCat01 = list("E1101",
"E2101",
"E3101",
"E4101")
) %>%
select(-1,
-2,
-3,
-8,
-9,
-11) %>%
mutate(time_code = str_sub(time_code, 1, 4),
time_code = as.integer(time_code),
value = as.integer(value))
colnames(school) = c("subject","area_code","region","time","value")
school = school %>%
dplyr::select(region, area_code, time, everything())
school = school %>%
pivot_wider(names_from = "subject",
values_from = value)
colnames(school)[4:7] = c("E1101_kindergartens",
"E2101_elementaryschools",
"E3101_juniorhighschools",
"E4101_highschools")head(school)# A tibble: 6 x 7
region area_code time E1101_kindergartens E2101_elementaryschools
<chr> <chr> <int> <int> <int>
1 北海道 札幌市 01100 1980 120 160
2 北海道 札幌市 01100 1981 126 164
3 北海道 札幌市 01100 1982 130 171
4 北海道 札幌市 01100 1983 134 174
5 北海道 札幌市 01100 1984 137 178
6 北海道 札幌市 01100 1985 139 182
# i 2 more variables: E3101_juniorhighschools <int>, E4101_highschools <int>
1.2.2 Library
stats_library <- GET(
url = "https://api.e-stat.go.jp/rest/3.0/app/getStatsData?cdArea=01100%2C01101%2C01102%2C01103%2C01104%2C01105%2C01106%2C01107%2C01108%2C01109%2C01110%2C01202%2C01203%2C01204%2C01205%2C01206%2C01207%2C01208%2C01209%2C01210%2C01211%2C01212%2C01213%2C01214%2C01215%2C01216%2C01217%2C01218%2C01219%2C01220%2C01221%2C01222%2C01223%2C01224%2C01225%2C01226%2C01227%2C01228%2C01229%2C01230%2C01231%2C01233%2C01234%2C01235%2C01236%2C01303%2C01304%2C01331%2C01332%2C01333%2C01334%2C01337%2C01343%2C01345%2C01346%2C01347%2C01361%2C01362%2C01363%2C01364%2C01367%2C01370%2C01371%2C01391%2C01392%2C01393%2C01394%2C01395%2C01396%2C01397%2C01398%2C01399%2C01400%2C01401%2C01402%2C01403%2C01404%2C01405%2C01406%2C01407%2C01408%2C01409%2C01423%2C01424%2C01425%2C01427%2C01428%2C01429%2C01430%2C01431%2C01432%2C01433%2C01434%2C01436%2C01437%2C01438%2C01452%2C01453%2C01454%2C01455&cdCat01=G1401&appId=&lang=J&statsDataId=0000020207&metaGetFlg=Y&cntGetFlg=N&explanationGetFlg=Y&annotationGetFlg=Y§ionHeaderFlg=1&replaceSpChars=0",
query = list(
appId = appId,
statsDataId = "0000020207")
)
result <- content(stats_library)
str(result, max.level = 4, list.len = 4)
library <- estat_getStatsData(
appId = appId,
statsDataId = "0000020207",
cdCat01 = list("G1401")
) %>%
select(-1,
-2,
-3,
-8,
-9,
-11) %>%
mutate(time_code = str_sub(time_code, 1, 4),
time_code = as.integer(time_code),
value = as.integer(value))
colnames(library) = c("subject","area_code","region","time","value")
library = library %>%
dplyr::select(region, area_code, time, everything())
library = library %>%
pivot_wider(names_from = "subject",
values_from = value)
colnames(library)[4] = "G1401_libraries"head(library)# A tibble: 6 x 4
region area_code time G1401_libraries
<chr> <chr> <int> <int>
1 北海道 札幌市 01100 1995 10
2 北海道 札幌市 01100 1996 10
3 北海道 札幌市 01100 1997 10
4 北海道 札幌市 01100 1999 10
5 北海道 札幌市 01100 2002 17
6 北海道 札幌市 01100 2005 11
1.2.3 Hospital
stats_hospital <- GET(
url = "https://api.e-stat.go.jp/rest/3.0/app/getStatsData?cdArea=01100%2C01101%2C01102%2C01103%2C01104%2C01105%2C01106%2C01107%2C01108%2C01109%2C01110%2C01202%2C01203%2C01204%2C01205%2C01206%2C01207%2C01208%2C01209%2C01210%2C01211%2C01212%2C01213%2C01214%2C01215%2C01216%2C01217%2C01218%2C01219%2C01220%2C01221%2C01222%2C01223%2C01224%2C01225%2C01226%2C01227%2C01228%2C01229%2C01230%2C01231%2C01233%2C01234%2C01235%2C01236%2C01303%2C01304%2C01331%2C01332%2C01333%2C01334%2C01337%2C01343%2C01345%2C01346%2C01347%2C01361%2C01362%2C01363%2C01364%2C01367%2C01370%2C01371%2C01391%2C01392%2C01393%2C01394%2C01395%2C01396%2C01397%2C01398%2C01399%2C01400%2C01401%2C01402%2C01403%2C01404%2C01405%2C01406%2C01407%2C01408%2C01409%2C01423%2C01424%2C01425%2C01427%2C01428%2C01429%2C01430%2C01431%2C01432%2C01433%2C01434%2C01436%2C01437%2C01438%2C01452%2C01453%2C01454%2C01455&cdCat01=I5101%2CI5102&appId=&lang=J&statsDataId=0000020209&metaGetFlg=Y&cntGetFlg=N&explanationGetFlg=Y&annotationGetFlg=Y§ionHeaderFlg=1&replaceSpChars=0",
query = list(
appId = appId,
statsDataId = "0000020209")
)
result <- content(stats_hospital)
str(result, max.level = 4, list.len = 4)
hospital <- estat_getStatsData(
appId = appId,
statsDataId = "0000020209",
cdCat01 = list("I5101",
"I5102")
) %>%
select(-1,
-2,
-3,
-8,
-9,
-11) %>%
mutate(time_code = str_sub(time_code, 1, 4),
time_code = as.integer(time_code),
value = as.integer(value))
colnames(hospital) = c("subject","area_code","region","time","value")
hospital = hospital %>%
dplyr::select(region, area_code, time, everything())
hospital = hospital %>%
pivot_wider(names_from = "subject",
values_from = value)
colnames(hospital)[4:5] = c("I5101_hospitals","I5102_generalclinics")
head(hospital)1.2.4 Eonomic Entity
stats_economic <- GET(
url = "https://api.e-stat.go.jp/rest/3.0/app/getStatsData?cdArea=01100%2C01101%2C01102%2C01103%2C01104%2C01105%2C01106%2C01107%2C01108%2C01109%2C01110%2C01202%2C01203%2C01204%2C01205%2C01206%2C01207%2C01208%2C01209%2C01210%2C01211%2C01212%2C01213%2C01214%2C01215%2C01216%2C01217%2C01218%2C01219%2C01220%2C01221%2C01222%2C01223%2C01224%2C01225%2C01226%2C01227%2C01228%2C01229%2C01230%2C01231%2C01233%2C01234%2C01235%2C01236%2C01303%2C01304%2C01331%2C01332%2C01333%2C01334%2C01337%2C01343%2C01345%2C01346%2C01347%2C01361%2C01362%2C01363%2C01364%2C01367%2C01370%2C01371%2C01391%2C01392%2C01393%2C01394%2C01395%2C01396%2C01397%2C01398%2C01399%2C01400%2C01401%2C01402%2C01403%2C01404%2C01405%2C01406%2C01407%2C01408%2C01409%2C01423%2C01424%2C01425%2C01427%2C01428%2C01429%2C01430%2C01431%2C01432%2C01433%2C01434%2C01436%2C01437%2C01438%2C01452%2C01453%2C01454%2C01455&cdCat01=C210831%2CC210835%2CC210836%2CC210837%2CC210838%2CC210839%2CC210840%2CC210842%2CC210843%2CC210844%2CC210845%2CC210846%2CC210847%2CC210848%2CC210849%2CC210850%2CC210851%2CC210852&appId=&lang=J&statsDataId=0000020203&metaGetFlg=Y&cntGetFlg=N&explanationGetFlg=Y&annotationGetFlg=Y§ionHeaderFlg=1&replaceSpChars=0",
query = list(
appId = appId,
statsDataId = "0000020203")
)
result <- content(stats_economic)
str(result, max.level = 4, list.len = 4)
economic <- estat_getStatsData(
appId = appId,
statsDataId = "0000020203",
cdCat01 = list("C210832",
"C210833",
"C210835",
"C210836",
"C210837",
"C210838",
"C210839",
"C210840",
"C210842",
"C210843",
"C210844",
"C210845",
"C210846",
"C210847",
"C210848",
"C210849",
"C210850",
"C210851",
"C210852")
) %>%
select(-1,
-2,
-3,
-8,
-9,
-11) %>%
mutate(time_code = str_sub(time_code, 1, 4),
time_code = as.integer(time_code),
value = as.integer(value))
colnames(economic) = c("subject","area_code","region","time","value")
economic = economic %>%
dplyr::select(region, area_code, time, everything())
economic = economic %>%
pivot_wider(names_from = "subject",
values_from = value)
colnames(economic)[4:22] = c("C210832_agriculture_forestry",
"C210833_fishing",
"C210835_mining_quarrying_gravel_extraction",
"C210836_construction",
"C210837_manufacturing",
"C210838_electricity_gas_heat_supply_water",
"C210839_information_and_communication",
"C210840_transportation_postal",
"C210842_wholesale_trade",
"C210843_retail_trade",
"C210844_financial",
"C210845_real_estate_goods_rental",
"C210846_academic_professional_services",
"C210847_lodging_food_beverage",
"C210848_life_related_service_entertainment",
"C210849_education",
"C210850_medical_care_welfare",
"C210851_complex_service",
"C210852_others_service") head(economic)# A tibble: 6 x 22
region area_code time C210832_agriculture_for~1 C210833_fishing
<chr> <chr> <int> <int> <int>
1 北海道 札幌市 01100 2011 82 3
2 北海道 札幌市 01100 2014 96 2
3 北海道 札幌市 01100 2016 93 2
4 北海道 札幌市 中央区 01101 2011 23 3
5 北海道 札幌市 中央区 01101 2014 29 2
6 北海道 札幌市 中央区 01101 2016 28 2
# i abbreviated name: 1: C210832_agriculture_forestry
# i 17 more variables: C210835_mining_quarrying_gravel_extraction <int>,
# C210836_construction <int>, C210837_manufacturing <int>,
# C210838_electricity_gas_heat_supply_water <int>,
# C210839_information_and_communication <int>,
# C210840_transportation_postal <int>, C210842_wholesale_trade <int>,
# C210843_retail_trade <int>, C210844_financial <int>, ...
1.3 Combining each data
diversity = full_join(school, hospital, by = c("region","area_code","time")) %>%
full_join(library, by = c("region","area_code","time")) %>%
full_join(economic, by = c("region","area_code","time")) %>%
mutate(sum = select(., c(4:29)) %>% rowSums(na.rm = TRUE), .before = 4)head(diversity)# A tibble: 6 x 30
region area_code time sum E1101_kindergartens E2101_elementaryscho~1
<chr> <chr> <int> <dbl> <int> <int>
1 北海道 札幌市 01100 1980 1340 120 160
2 北海道 札幌市 01100 1981 1377 126 164
3 北海道 札幌市 01100 1982 1397 130 171
4 北海道 札幌市 01100 1983 434 134 174
5 北海道 札幌市 01100 1984 1434 137 178
6 北海道 札幌市 01100 1985 1459 139 182
# i abbreviated name: 1: E2101_elementaryschools
# i 24 more variables: E3101_juniorhighschools <int>, E4101_highschools <int>,
# I5101_hospitals <int>, I5102_generalclinics <int>, G1401_libraries <int>,
# C210832_agriculture_forestry <int>, C210833_fishing <int>,
# C210835_mining_quarrying_gravel_extraction <int>,
# C210836_construction <int>, C210837_manufacturing <int>,
# C210838_electricity_gas_heat_supply_water <int>, ...
1.4 Processing data
all_city = diversity %>%
mutate(across(starts_with("E"), ~./sum, .names = "probability_{.col}")) %>%
mutate(across(starts_with("I"), ~./sum, .names = "probability_{.col}")) %>%
mutate(across(starts_with("G"), ~./sum, .names = "probability_{.col}")) %>%
mutate(across(starts_with("C"), ~./sum, .names = "probability_{.col}")) %>%
mutate(across(starts_with("probability"), log, .names = "log_{.col}")) %>%
mutate(multiply_E1101_kindergartens = probability_E1101_kindergartens * log_probability_E1101_kindergartens) %>%
mutate(multiply_E2101_elementaryschools = probability_E2101_elementaryschools * log_probability_E2101_elementaryschools) %>%
mutate(multiply_E3101_juniorhighschools = probability_E3101_juniorhighschools * log_probability_E3101_juniorhighschools) %>%
mutate(multiply_E4101_highschools = probability_E4101_highschools * log_probability_E4101_highschools) %>%
mutate(multiply_G1401_libraries = probability_G1401_libraries * log_probability_G1401_libraries) %>%
mutate(multiply_I5101_hospitals = probability_I5101_hospitals * log_probability_I5101_hospitals) %>%
mutate(multiply_I5102_generalclinics = probability_I5102_generalclinics * log_probability_I5102_generalclinics) %>%
mutate(multiply_C210832_agriculture_forestry = probability_C210832_agriculture_forestry * log_probability_C210832_agriculture_forestry) %>%
mutate(multiply_C210833_fishing = probability_C210833_fishing * log_probability_C210833_fishing) %>%
mutate(multiply_C210835_mining_quarrying_gravel_extraction = probability_C210835_mining_quarrying_gravel_extraction * log_probability_C210835_mining_quarrying_gravel_extraction) %>%
mutate(multiply_C210836_construction = probability_C210836_construction * log_probability_C210836_construction) %>%
mutate(multiply_C210837_manufacturing = probability_C210837_manufacturing * log_probability_C210837_manufacturing) %>%
mutate(multiply_C210838_electricity_gas_heat_supply_water = probability_C210838_electricity_gas_heat_supply_water * log_probability_C210838_electricity_gas_heat_supply_water) %>%
mutate(multiply_C210839_information_and_communication = probability_C210839_information_and_communication * log_probability_C210839_information_and_communication) %>%
mutate(multiply_C210840_transportation_postal = probability_C210840_transportation_postal * log_probability_C210840_transportation_postal) %>%
mutate(multiply_C210842_wholesale_trade = probability_C210842_wholesale_trade * log_probability_C210842_wholesale_trade) %>%
mutate(multiply_C210843_retail_trade = probability_C210843_retail_trade * log_probability_C210843_retail_trade) %>%
mutate(multiply_C210844_financial = probability_C210844_financial * log_probability_C210844_financial) %>%
mutate(multiply_C210845_real_estate_goods_rental = probability_C210845_real_estate_goods_rental * log_probability_C210845_real_estate_goods_rental) %>%
mutate(multiply_C210846_academic_professional_services = probability_C210846_academic_professional_services * log_probability_C210846_academic_professional_services) %>%
mutate(multiply_C210847_lodging_food_beverage = probability_C210847_lodging_food_beverage * log_probability_C210847_lodging_food_beverage) %>%
mutate(multiply_C210848_life_related_service_entertainment = probability_C210848_life_related_service_entertainment * log_probability_C210848_life_related_service_entertainment) %>%
mutate(multiply_C210849_education = probability_C210849_education * log_probability_C210849_education) %>%
mutate(multiply_C210850_medical_care_welfare = probability_C210850_medical_care_welfare * log_probability_C210850_medical_care_welfare) %>%
mutate(multiply_C210851_complex_service = probability_C210851_complex_service * log_probability_C210851_complex_service) %>%
mutate(multiply_C210852_others_service = probability_C210852_others_service * log_probability_C210852_others_service) %>%
mutate(sum_log = -rowSums(across(starts_with("multiply")), na.rm = TRUE), .before = 5)head(all_city)# A tibble: 6 x 109
region area_code time sum sum_log E1101_kindergartens
<chr> <chr> <int> <dbl> <dbl> <int>
1 北海道 札幌市 01100 1980 1340 0.978 120
2 北海道 札幌市 01100 1981 1377 0.979 126
3 北海道 札幌市 01100 1982 1397 0.990 130
4 北海道 札幌市 01100 1983 434 1.28 134
5 北海道 札幌市 01100 1984 1434 1.02 137
6 北海道 札幌市 01100 1985 1459 1.02 139
# i 103 more variables: E2101_elementaryschools <int>,
# E3101_juniorhighschools <int>, E4101_highschools <int>,
# I5101_hospitals <int>, I5102_generalclinics <int>, G1401_libraries <int>,
# C210832_agriculture_forestry <int>, C210833_fishing <int>,
# C210835_mining_quarrying_gravel_extraction <int>,
# C210836_construction <int>, C210837_manufacturing <int>,
# C210838_electricity_gas_heat_supply_water <int>, ...
1.5 Descriptive statistics
skim(all_city)Warning: There was 1 warning in `dplyr::summarize()`.
i In argument: `dplyr::across(tidyselect::any_of(variable_names),
mangled_skimmers$funs)`.
i In group 0: .
Caused by warning:
! There were 26 warnings in `dplyr::summarize()`.
The first warning was:
i In argument: `dplyr::across(tidyselect::any_of(variable_names),
mangled_skimmers$funs)`.
Caused by warning in `inline_hist()`:
! Variable contains Inf or -Inf value(s) that were converted to NA.
i Run `dplyr::last_dplyr_warnings()` to see the 25 remaining warnings.
| Name | all_city |
| Number of rows | 80427 |
| Number of columns | 109 |
| _______________________ | |
| Column type frequency: | |
| character | 2 |
| numeric | 107 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| region | 0 | 1 | 6 | 14 | 0 | 1917 | 0 |
| area_code | 0 | 1 | 5 | 5 | 0 | 1917 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time | 0 | 1.00 | 2000.52 | 12.12 | 1980.00 | 1990.00 | 2001.00 | 2011.00 | 2021.00 | ▇▇▇▇▇ |
| sum | 0 | 1.00 | 359.53 | 4005.99 | 0.00 | 14.00 | 38.00 | 110.00 | 533906.00 | ▇▁▁▁▁ |
| sum_log | 0 | 1.00 | 1.30 | 0.41 | 0.00 | 1.11 | 1.27 | 1.42 | 2.74 | ▁▂▇▁▁ |
| E1101_kindergartens | 2270 | 0.97 | 8.83 | 25.32 | 0.00 | 1.00 | 3.00 | 10.00 | 1012.00 | ▇▁▁▁▁ |
| E2101_elementaryschools | 1599 | 0.98 | 14.12 | 28.97 | 0.00 | 4.00 | 8.00 | 16.00 | 978.00 | ▇▁▁▁▁ |
| E3101_juniorhighschools | 1728 | 0.98 | 6.79 | 16.38 | 0.00 | 2.00 | 4.00 | 8.00 | 590.00 | ▇▁▁▁▁ |
| E4101_highschools | 2519 | 0.97 | 3.36 | 9.44 | 0.00 | 1.00 | 1.00 | 4.00 | 343.00 | ▇▁▁▁▁ |
| I5101_hospitals | 34881 | 0.57 | 5.69 | 15.74 | 0.00 | 1.00 | 2.00 | 6.00 | 468.00 | ▇▁▁▁▁ |
| I5102_generalclinics | 6703 | 0.92 | 62.86 | 257.44 | 0.00 | 5.00 | 17.00 | 53.00 | 10720.00 | ▇▁▁▁▁ |
| G1401_libraries | 62064 | 0.23 | 1.78 | 5.71 | 0.00 | 0.00 | 1.00 | 2.00 | 239.00 | ▇▁▁▁▁ |
| C210832_agriculture_forestry | 74689 | 0.07 | 15.68 | 20.71 | 0.00 | 4.00 | 9.00 | 19.00 | 258.00 | ▇▁▁▁▁ |
| C210833_fishing | 74689 | 0.07 | 1.87 | 5.41 | 0.00 | 0.00 | 0.00 | 1.00 | 83.00 | ▇▁▁▁▁ |
| C210835_mining_quarrying_gravel_extraction | 74689 | 0.07 | 1.15 | 2.74 | 0.00 | 0.00 | 0.00 | 1.00 | 84.00 | ▇▁▁▁▁ |
| C210836_construction | 74689 | 0.07 | 331.43 | 904.71 | 0.00 | 55.00 | 149.00 | 356.00 | 29856.00 | ▇▁▁▁▁ |
| C210837_manufacturing | 74689 | 0.07 | 315.06 | 1153.92 | 0.00 | 38.00 | 117.00 | 307.00 | 42370.00 | ▇▁▁▁▁ |
| C210838_electricity_gas_heat_supply_water | 74689 | 0.07 | 2.81 | 8.95 | 0.00 | 0.00 | 1.00 | 3.00 | 328.00 | ▇▁▁▁▁ |
| C210839_information_and_communication | 74689 | 0.07 | 55.30 | 504.55 | 0.00 | 1.00 | 4.50 | 20.00 | 20413.00 | ▇▁▁▁▁ |
| C210840_transportation_postal | 74689 | 0.07 | 91.90 | 375.25 | 0.00 | 11.00 | 31.00 | 80.00 | 14382.00 | ▇▁▁▁▁ |
| C210842_wholesale_trade | 74689 | 0.07 | 277.18 | 1416.60 | 0.00 | 15.00 | 56.00 | 184.75 | 50195.00 | ▇▁▁▁▁ |
| C210843_retail_trade | 74689 | 0.07 | 675.71 | 2177.05 | 0.00 | 92.00 | 271.50 | 670.00 | 76609.00 | ▇▁▁▁▁ |
| C210844_financial | 74689 | 0.07 | 60.53 | 258.05 | 0.00 | 4.00 | 15.00 | 47.00 | 9540.00 | ▇▁▁▁▁ |
| C210845_real_estate_goods_rental | 74689 | 0.07 | 270.02 | 1289.30 | 0.00 | 10.00 | 54.00 | 211.00 | 49995.00 | ▇▁▁▁▁ |
| C210846_academic_professional_services | 74689 | 0.07 | 168.05 | 964.25 | 0.00 | 8.00 | 33.00 | 109.00 | 36882.00 | ▇▁▁▁▁ |
| C210847_lodging_food_beverage | 74689 | 0.07 | 494.59 | 2029.20 | 0.00 | 47.00 | 152.00 | 437.00 | 74387.00 | ▇▁▁▁▁ |
| C210848_life_related_service_entertainment | 74689 | 0.07 | 318.58 | 1020.94 | 0.00 | 39.00 | 121.50 | 320.00 | 36030.00 | ▇▁▁▁▁ |
| C210849_education | 74689 | 0.07 | 112.52 | 371.05 | 0.00 | 8.00 | 33.00 | 113.00 | 12767.00 | ▇▁▁▁▁ |
| C210850_medical_care_welfare | 74689 | 0.07 | 275.49 | 974.26 | 0.00 | 26.00 | 86.00 | 264.00 | 35165.00 | ▇▁▁▁▁ |
| C210851_complex_service | 74689 | 0.07 | 20.71 | 41.02 | 0.00 | 5.00 | 12.00 | 23.00 | 1261.00 | ▇▁▁▁▁ |
| C210852_others_service | 74689 | 0.07 | 239.49 | 883.88 | 0.00 | 32.00 | 89.00 | 213.00 | 32547.00 | ▇▁▁▁▁ |
| probability_E1101_kindergartens | 2286 | 0.97 | 0.09 | 0.09 | 0.00 | 0.02 | 0.08 | 0.13 | 1.00 | ▇▁▁▁▁ |
| probability_E2101_elementaryschools | 1615 | 0.98 | 0.24 | 0.15 | 0.00 | 0.13 | 0.21 | 0.33 | 1.00 | ▇▆▂▁▁ |
| probability_E3101_juniorhighschools | 1744 | 0.98 | 0.11 | 0.08 | 0.00 | 0.06 | 0.09 | 0.14 | 1.00 | ▇▁▁▁▁ |
| probability_E4101_highschools | 2535 | 0.97 | 0.04 | 0.04 | 0.00 | 0.00 | 0.04 | 0.06 | 1.00 | ▇▁▁▁▁ |
| probability_I5101_hospitals | 34881 | 0.57 | 0.05 | 0.04 | 0.00 | 0.00 | 0.04 | 0.07 | 0.44 | ▇▁▁▁▁ |
| probability_I5102_generalclinics | 6703 | 0.92 | 0.45 | 0.20 | 0.00 | 0.33 | 0.49 | 0.60 | 1.00 | ▂▅▇▅▁ |
| probability_G1401_libraries | 62064 | 0.23 | 0.02 | 0.04 | 0.00 | 0.00 | 0.01 | 0.03 | 1.00 | ▇▁▁▁▁ |
| probability_C210832_agriculture_forestry | 74689 | 0.07 | 0.01 | 0.02 | 0.00 | 0.00 | 0.01 | 0.02 | 0.29 | ▇▁▁▁▁ |
| probability_C210833_fishing | 74689 | 0.07 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.21 | ▇▁▁▁▁ |
| probability_C210835_mining_quarrying_gravel_extraction | 74689 | 0.07 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.03 | ▇▁▁▁▁ |
| probability_C210836_construction | 74689 | 0.07 | 0.11 | 0.04 | 0.00 | 0.09 | 0.11 | 0.13 | 0.34 | ▁▇▂▁▁ |
| probability_C210837_manufacturing | 74689 | 0.07 | 0.10 | 0.05 | 0.00 | 0.06 | 0.08 | 0.12 | 0.44 | ▇▆▁▁▁ |
| probability_C210838_electricity_gas_heat_supply_water | 74689 | 0.07 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.06 | ▇▁▁▁▁ |
| probability_C210839_information_and_communication | 74689 | 0.07 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.01 | 0.09 | ▇▁▁▁▁ |
| probability_C210840_transportation_postal | 74689 | 0.07 | 0.03 | 0.02 | 0.00 | 0.02 | 0.02 | 0.03 | 0.30 | ▇▁▁▁▁ |
| probability_C210842_wholesale_trade | 74689 | 0.07 | 0.05 | 0.03 | 0.00 | 0.03 | 0.04 | 0.06 | 0.24 | ▇▅▁▁▁ |
| probability_C210843_retail_trade | 74689 | 0.07 | 0.20 | 0.04 | 0.00 | 0.17 | 0.20 | 0.22 | 0.40 | ▁▂▇▁▁ |
| probability_C210844_financial | 74689 | 0.07 | 0.01 | 0.01 | 0.00 | 0.01 | 0.01 | 0.02 | 0.05 | ▅▇▂▁▁ |
| probability_C210845_real_estate_goods_rental | 74689 | 0.07 | 0.05 | 0.03 | 0.00 | 0.02 | 0.04 | 0.07 | 0.22 | ▇▅▁▁▁ |
| probability_C210846_academic_professional_services | 74689 | 0.07 | 0.03 | 0.01 | 0.00 | 0.02 | 0.03 | 0.03 | 0.16 | ▇▃▁▁▁ |
| probability_C210847_lodging_food_beverage | 74689 | 0.07 | 0.12 | 0.06 | 0.00 | 0.09 | 0.11 | 0.14 | 0.70 | ▇▂▁▁▁ |
| probability_C210848_life_related_service_entertainment | 74689 | 0.07 | 0.09 | 0.02 | 0.00 | 0.08 | 0.09 | 0.10 | 0.25 | ▁▇▂▁▁ |
| probability_C210849_education | 74689 | 0.07 | 0.03 | 0.01 | 0.00 | 0.02 | 0.02 | 0.03 | 0.08 | ▃▇▃▁▁ |
| probability_C210850_medical_care_welfare | 74689 | 0.07 | 0.07 | 0.02 | 0.00 | 0.05 | 0.07 | 0.08 | 0.17 | ▁▇▇▁▁ |
| probability_C210851_complex_service | 74689 | 0.07 | 0.01 | 0.01 | 0.00 | 0.00 | 0.01 | 0.02 | 0.12 | ▇▁▁▁▁ |
| probability_C210852_others_service | 74689 | 0.07 | 0.07 | 0.02 | 0.00 | 0.05 | 0.07 | 0.08 | 0.19 | ▁▇▂▁▁ |
| log_probability_E1101_kindergartens | 2286 | 0.97 | -Inf | NaN | -Inf | -3.78 | -2.52 | -2.01 | 0.00 | ▁▁▁▇▂ |
| log_probability_E2101_elementaryschools | 1615 | 0.98 | -Inf | NaN | -Inf | -2.03 | -1.55 | -1.12 | 0.00 | ▁▁▁▅▇ |
| log_probability_E3101_juniorhighschools | 1744 | 0.98 | -Inf | NaN | -Inf | -2.80 | -2.40 | -1.95 | 0.00 | ▁▁▁▇▂ |
| log_probability_E4101_highschools | 2535 | 0.97 | -Inf | NaN | -Inf | -6.55 | -3.35 | -2.89 | 0.00 | ▁▁▁▇▁ |
| log_probability_I5101_hospitals | 34881 | 0.57 | -Inf | NaN | -Inf | -6.66 | -3.14 | -2.67 | -0.81 | ▁▁▁▇▂ |
| log_probability_I5102_generalclinics | 6703 | 0.92 | -Inf | NaN | -Inf | -1.10 | -0.72 | -0.51 | 0.00 | ▁▁▁▁▇ |
| log_probability_G1401_libraries | 62064 | 0.23 | -Inf | NaN | -Inf | -Inf | -4.32 | -3.37 | 0.00 | ▁▁▃▇▁ |
| log_probability_C210832_agriculture_forestry | 74689 | 0.07 | -Inf | NaN | -Inf | -6.12 | -4.94 | -4.09 | -1.23 | ▁▃▇▇▁ |
| log_probability_C210833_fishing | 74689 | 0.07 | -Inf | NaN | -Inf | -Inf | -Inf | -7.11 | -1.56 | ▁▃▇▅▁ |
| log_probability_C210835_mining_quarrying_gravel_extraction | 74689 | 0.07 | -Inf | NaN | -Inf | -Inf | -Inf | -7.12 | -3.38 | ▁▂▇▇▁ |
| log_probability_C210836_construction | 74689 | 0.07 | -Inf | NaN | -Inf | -2.44 | -2.24 | -2.01 | -1.08 | ▁▁▇▇▁ |
| log_probability_C210837_manufacturing | 74689 | 0.07 | -Inf | NaN | -Inf | -2.84 | -2.48 | -2.11 | -0.81 | ▁▂▇▇▁ |
| log_probability_C210838_electricity_gas_heat_supply_water | 74689 | 0.07 | -Inf | NaN | -Inf | -Inf | -7.52 | -6.60 | -2.89 | ▁▇▆▂▁ |
| log_probability_C210839_information_and_communication | 74689 | 0.07 | -Inf | NaN | -Inf | -6.45 | -5.55 | -5.02 | -2.41 | ▁▅▇▂▁ |
| log_probability_C210840_transportation_postal | 74689 | 0.07 | -Inf | NaN | -Inf | -4.10 | -3.80 | -3.50 | -1.21 | ▁▃▇▁▁ |
| log_probability_C210842_wholesale_trade | 74689 | 0.07 | -Inf | NaN | -Inf | -3.47 | -3.15 | -2.87 | -1.42 | ▁▁▅▇▁ |
| log_probability_C210843_retail_trade | 74689 | 0.07 | -Inf | NaN | -Inf | -1.76 | -1.63 | -1.52 | -0.91 | ▁▁▁▇▁ |
| log_probability_C210844_financial | 74689 | 0.07 | -Inf | NaN | -Inf | -4.75 | -4.45 | -4.19 | -3.06 | ▁▁▇▇▁ |
| log_probability_C210845_real_estate_goods_rental | 74689 | 0.07 | -Inf | NaN | -Inf | -3.88 | -3.24 | -2.71 | -1.49 | ▁▁▃▇▂ |
| log_probability_C210846_academic_professional_services | 74689 | 0.07 | -Inf | NaN | -Inf | -4.02 | -3.66 | -3.40 | -1.84 | ▁▁▇▇▁ |
| log_probability_C210847_lodging_food_beverage | 74689 | 0.07 | -Inf | NaN | -Inf | -2.38 | -2.17 | -1.99 | -0.36 | ▁▁▇▂▁ |
| log_probability_C210848_life_related_service_entertainment | 74689 | 0.07 | -Inf | NaN | -Inf | -2.58 | -2.43 | -2.32 | -1.39 | ▁▁▂▇▁ |
| log_probability_C210849_education | 74689 | 0.07 | -Inf | NaN | -Inf | -4.10 | -3.71 | -3.42 | -2.50 | ▁▁▃▇▂ |
| log_probability_C210850_medical_care_welfare | 74689 | 0.07 | -Inf | NaN | -Inf | -2.97 | -2.73 | -2.53 | -1.79 | ▁▁▁▇▃ |
| log_probability_C210851_complex_service | 74689 | 0.07 | -Inf | NaN | -Inf | -5.32 | -4.74 | -4.20 | -2.08 | ▁▇▇▃▁ |
| log_probability_C210852_others_service | 74689 | 0.07 | -Inf | NaN | -Inf | -2.90 | -2.72 | -2.56 | -1.65 | ▁▁▁▇▁ |
| multiply_E1101_kindergartens | 16353 | 0.80 | -0.22 | 0.09 | -0.37 | -0.28 | -0.23 | -0.17 | 0.00 | ▆▇▇▂▂ |
| multiply_E2101_elementaryschools | 1659 | 0.98 | -0.29 | 0.09 | -0.37 | -0.36 | -0.32 | -0.26 | 0.00 | ▇▃▁▁▁ |
| multiply_E3101_juniorhighschools | 2098 | 0.97 | -0.22 | 0.09 | -0.37 | -0.28 | -0.22 | -0.17 | 0.00 | ▅▆▇▂▂ |
| multiply_E4101_highschools | 18968 | 0.76 | -0.14 | 0.06 | -0.37 | -0.17 | -0.13 | -0.10 | 0.00 | ▁▂▅▇▂ |
| multiply_G1401_libraries | 67061 | 0.17 | -0.10 | 0.07 | -0.37 | -0.14 | -0.09 | -0.05 | 0.00 | ▁▁▃▇▇ |
| multiply_I5101_hospitals | 44929 | 0.44 | -0.15 | 0.07 | -0.37 | -0.20 | -0.16 | -0.12 | 0.00 | ▁▂▇▆▃ |
| multiply_I5102_generalclinics | 7011 | 0.91 | -0.30 | 0.08 | -0.37 | -0.36 | -0.33 | -0.28 | 0.00 | ▇▂▁▁▁ |
| multiply_C210832_agriculture_forestry | 74956 | 0.07 | -0.05 | 0.05 | -0.36 | -0.07 | -0.04 | -0.02 | 0.00 | ▁▁▁▂▇ |
| multiply_C210833_fishing | 78180 | 0.03 | -0.02 | 0.03 | -0.33 | -0.03 | -0.01 | 0.00 | 0.00 | ▁▁▁▁▇ |
| multiply_C210835_mining_quarrying_gravel_extraction | 77958 | 0.03 | -0.01 | 0.01 | -0.12 | -0.01 | -0.01 | 0.00 | 0.00 | ▁▁▁▁▇ |
| multiply_C210836_construction | 74702 | 0.07 | -0.24 | 0.04 | -0.37 | -0.27 | -0.24 | -0.21 | -0.08 | ▁▆▇▂▁ |
| multiply_C210837_manufacturing | 74702 | 0.07 | -0.21 | 0.06 | -0.37 | -0.26 | -0.21 | -0.17 | -0.04 | ▂▅▇▅▁ |
| multiply_C210838_electricity_gas_heat_supply_water | 76847 | 0.04 | -0.01 | 0.01 | -0.16 | -0.01 | -0.01 | 0.00 | 0.00 | ▁▁▁▁▇ |
| multiply_C210839_information_and_communication | 75834 | 0.06 | -0.03 | 0.02 | -0.22 | -0.04 | -0.03 | -0.02 | 0.00 | ▁▁▁▁▇ |
| multiply_C210840_transportation_postal | 74747 | 0.07 | -0.09 | 0.04 | -0.36 | -0.11 | -0.09 | -0.07 | -0.02 | ▁▁▁▇▇ |
| multiply_C210842_wholesale_trade | 74794 | 0.07 | -0.14 | 0.05 | -0.34 | -0.16 | -0.14 | -0.11 | -0.01 | ▁▁▆▇▁ |
| multiply_C210843_retail_trade | 74695 | 0.07 | -0.32 | 0.02 | -0.37 | -0.33 | -0.32 | -0.30 | -0.12 | ▇▇▁▁▁ |
| multiply_C210844_financial | 74921 | 0.07 | -0.05 | 0.02 | -0.14 | -0.06 | -0.05 | -0.04 | -0.01 | ▁▁▃▇▂ |
| multiply_C210845_real_estate_goods_rental | 74940 | 0.07 | -0.14 | 0.06 | -0.34 | -0.18 | -0.13 | -0.09 | -0.01 | ▁▃▇▇▃ |
| multiply_C210846_academic_professional_services | 74893 | 0.07 | -0.10 | 0.03 | -0.29 | -0.11 | -0.10 | -0.08 | -0.01 | ▁▁▂▇▂ |
| multiply_C210847_lodging_food_beverage | 74698 | 0.07 | -0.25 | 0.04 | -0.37 | -0.27 | -0.25 | -0.22 | -0.07 | ▂▇▇▂▁ |
| multiply_C210848_life_related_service_entertainment | 74713 | 0.07 | -0.21 | 0.03 | -0.35 | -0.23 | -0.21 | -0.20 | -0.05 | ▁▂▇▁▁ |
| multiply_C210849_education | 74962 | 0.07 | -0.09 | 0.03 | -0.20 | -0.11 | -0.09 | -0.07 | -0.02 | ▁▂▇▇▂ |
| multiply_C210850_medical_care_welfare | 74722 | 0.07 | -0.18 | 0.04 | -0.30 | -0.20 | -0.18 | -0.15 | -0.02 | ▁▆▇▂▁ |
| multiply_C210851_complex_service | 74698 | 0.07 | -0.05 | 0.03 | -0.26 | -0.06 | -0.04 | -0.03 | -0.01 | ▁▁▁▃▇ |
| multiply_C210852_others_service | 74713 | 0.07 | -0.18 | 0.03 | -0.32 | -0.20 | -0.18 | -0.16 | -0.03 | ▁▂▇▂▁ |
get_summary_stats(all_city)# A tibble: 107 x 13
variable n min max median q1 q3 iqr mad mean sd
<fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 time 80427 1980 2.02e3 2.00e3 1.99e3 2.01e3 21 14.8 2.00e3 1.21e+1
2 sum 80427 0 5.34e5 3.8 e1 1.4 e1 1.1 e2 96 43.0 3.60e2 4.01e+3
3 sum_log 80427 0 2.74e0 1.27e0 1.11e0 1.42e0 0.304 0.225 1.30e0 4.15e-1
4 E1101_k~ 78157 0 1.01e3 3 e0 1 e0 1 e1 9 4.45 8.83e0 2.53e+1
5 E2101_e~ 78828 0 9.78e2 8 e0 4 e0 1.6 e1 12 7.41 1.41e1 2.90e+1
6 E3101_j~ 78699 0 5.9 e2 4 e0 2 e0 8 e0 6 4.45 6.79e0 1.64e+1
7 E4101_h~ 77908 0 3.43e2 1 e0 1 e0 4 e0 3 1.48 3.36e0 9.44e+0
8 I5101_h~ 45546 0 4.68e2 2 e0 1 e0 6 e0 5 2.96 5.68e0 1.57e+1
9 I5102_g~ 73724 0 1.07e4 1.7 e1 5 e0 5.3 e1 48 20.8 6.29e1 2.57e+2
10 G1401_l~ 18363 0 2.39e2 1 e0 0 2 e0 2 1.48 1.78e0 5.71e+0
# i 97 more rows
# i 2 more variables: se <dbl>, ci <dbl>
1.6 Selecting areas
big_city = filter(all_city, area_code %in% c("13100","23100","27100","01100","04100","11100","12100","14100","14130","14150","15100","22100","22130","26100","27140","28100","33100","34100","40100","43100","40130"))
tokyo <- big_city %>%
filter(area_code %in% "13100")
sendai <- big_city %>%
filter(area_code %in% "04100")1.7 Visualizing
1.7.1 All cities
hist(all_city$sum_log, main = "Histogram of diversity index", xlab = "diversity index")ggplot(data = all_city,
mapping = aes(x=time,
y=sum_log)) +
geom_point() +
geom_smooth(method = "lm") +
scale_x_continuous(name = "time") +
scale_y_continuous(name = "divercity index") +
theme(axis.title.x = element_text(size = 12, hjust = 0.5), #font size and adjust
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12),
axis.title.y=element_text(size=12, vjust = 0.8)
) `geom_smooth()` using formula = 'y ~ x'
1.7.2 Ordinance designed cities
hist(big_city$sum_log, main = "Histogram of diversity index", xlab = "diversity index")ggplot(data = big_city,
mapping = aes(x=region,
y=sum_log,
fill=region)) +
geom_boxplot()ggplot(data = big_city,
mapping = aes(x=time,
y=sum_log)) +
geom_point() +
geom_smooth(method = "lm") +
scale_x_continuous(name = "time") +
scale_y_continuous(name = "divercity index")+
ggtitle("Ordinance Designed Cities")+
labs(caption = "bachelor thesis")+
theme(axis.title.x = element_text(size = 12, hjust = 0.5), #font size and adjust
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12),
axis.title.y=element_text(size=12, vjust = 0.8)
) `geom_smooth()` using formula = 'y ~ x'
1.7.3 Sendai
hist(sendai$sum_log, main = "Histogram of diversity index", xlab = "diversity index")ggplot(data = sendai,
mapping = aes(x=time,
y=sum_log)) +
geom_point() +
geom_smooth(method = "lm") +
scale_x_continuous(name = "time") +
scale_y_continuous(name = "divercity index") +
ggtitle("Sendai")+
labs(caption = "bachelor thesis")+
theme(axis.title.x = element_text(size = 12, hjust = 0.5), #font size and adjust
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12),
axis.title.y=element_text(size=12, vjust = 0.8)
) `geom_smooth()` using formula = 'y ~ x'
1.7.4 Tokyo
hist(tokyo$sum_log, main = "Histogram of diversity index", xlab = "diversity index")ggplot(data = tokyo,
mapping = aes(x=time,
y=sum_log)) +
geom_point() +
geom_smooth(method = "lm") +
scale_x_continuous(name = "time") +
scale_y_continuous(name = "divercity index") +
ggtitle("Tokyo")+
labs(caption = "bachelor thesis")+
theme(axis.title.x = element_text(size = 12, hjust = 0.5), #font size and adjust
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12),
axis.title.y=element_text(size=12, vjust = 0.8)
) `geom_smooth()` using formula = 'y ~ x'