Table: Korea youth, students, teachers, and schools
Source:vignettes/ffv_tab_korea_pop_teachers_schools.Rmd
ffv_tab_korea_pop_teachers_schools.Rmd
library(tibble)
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(tidyr)
library(stringr)
library(readr)
library(kableExtra)
#>
#> Attaching package: 'kableExtra'
#> The following object is masked from 'package:dplyr':
#>
#> group_rows
library(PrjCompPPTS)
# If resave outputs to data, only do this during development
bl_tex_save <- FALSE
verbose <- TRUE
# Latex output file
spt_path_res <- file.path("..", "res-tab", fsep = .Platform$file.sep)
spn_tex_out <- file.path(spt_path_res, "tab_korea_lrce.tex", fsep = .Platform$file.sep)Implement PrjCompPPTS-13, summaries for Korea.
Generate input file
Load prepped all location level files
Load file with interpolated data.
# Locaiton codes
ppts_code_wrk <- ppts_country_code
# We load in the global population data.
df_ppts <- ppts_easia_weuro_world_pchg
# location level types
df_ppts %>% distinct(location_level)
#> # A tibble: 4 × 1
#> location_level
#> <fct>
#> 1 country
#> 2 multicountry
#> 3 multiprovince
#> 4 province
df_ppts_sel <- df_ppts %>%
filter(location_level %in% c("province", "multiprovince"))
# Show all Korean locations
df_ppts_sel %>% distinct(location_code)
#> # A tibble: 19 × 1
#> location_code
#> <fct>
#> 1 KOR_Metro
#> 2 KOR_NonMetro
#> 3 KOR_Busan
#> 4 KOR_Chungbuk
#> 5 KOR_Chungnam
#> 6 KOR_Daegu
#> 7 KOR_Daejeon
#> 8 KOR_Gangwon
#> 9 KOR_Gwangju
#> 10 KOR_Gyeong-gi
#> 11 KOR_Gyeongbuk
#> 12 KOR_Gyeongnam
#> 13 KOR_Incheon
#> 14 KOR_Jeju
#> 15 KOR_Jeonbuk
#> 16 KOR_Jeonnam
#> 17 KOR_Sejong
#> 18 KOR_Seoul
#> 19 KOR_Ulsan
df_ppts_sel %>% distinct(variable)
#> # A tibble: 3 × 1
#> variable
#> <fct>
#> 1 school
#> 2 student
#> 3 teacher
# Korean locations into three groups
ls_korea <- list(
"KOR_Metro" = c("A1-Metro", "Location groups"),
"KOR_NonMetro" = c("C1-Non-metro", "Location groups"),
"KOR_Gyeong-gi" = c("A4-Gyeong-gi", "Capital"),
"KOR_Incheon" = c("A3-Incheon", "Capital"),
"KOR_Seoul" = c("A2-Seoul", "Capital"),
"KOR_Busan" = c("B1-Busan", "Metropolitan cities"),
"KOR_Daegu" = c("B2-Daegu", "Metropolitan cities"),
"KOR_Daejeon" = c("B3-Daejeon", "Metropolitan cities"),
"KOR_Gwangju" = c("B4-Gwangju", "Metropolitan cities"),
"KOR_Sejong" = c("B5-Sejong", "Metropolitan cities"),
"KOR_Ulsan" = c("B6-Ulsan", "Metropolitan cities"),
"KOR_Chungbuk" = c("D1-Chungbuk", "Non-metropolitan cities"),
"KOR_Chungnam" = c("D2-Chungnam", "Non-metropolitan cities"),
"KOR_Gyeongbuk" = c("D3-Gyeongbuk", "Non-metropolitan cities"),
"KOR_Gyeongnam" = c("D4-Gyeongnam", "Non-metropolitan cities"),
"KOR_Jeonnam" = c("D5-Jeonnam", "Non-metropolitan cities"),
"KOR_Gangwon" = c("E1-Gangwon", "Non-metropolitan cities"),
"KOR_Jeju" = c("E2-Jeju", "Non-metropolitan cities"),
"KOR_Jeonbuk" = c("E3-Jeonbuk", "Non-metropolitan cities")
)Run PrjCompPPTS functions
Run functions to generate FLR, FPC, and FEL files. Run FLR.
# Generate PLR
df_flr_korea <- PrjCompPPTS::ff_ppts_lrce_flr(
df_ppts_sel,
st_year_bins_type = "1940t2020i01",
ar_it_years = seq(1970, 2020, by = 10),
# c(1970, 1980, 1990, 2000, 2010, 2020),
ar_st_vars = c("student", "teacher", "school"),
ls_rat_vars = list(
"s2t" = c("student", "teacher"),
"s2s" = c("student", "school")
),
verbose = TRUE
)
#> F-713479, S1
#> [1] 1970 1980 1990 2000 2010 2020
#> F-713479, S2
#> dim of youth wide file: 114
#> dim of youth wide file: 6
#> F-713479, S2
#> [1] "var_rat_s2t"
#> [1] "var_lvl_student"
#> [1] "var_lvl_teacher"
#> dim FLR: 114
#> dim FLR: 7
#> F-713479, S2
#> [1] "var_rat_s2s"
#> [1] "var_lvl_student"
#> [1] "var_lvl_school"
#> dim FLR: 114
#> dim FLR: 8
#> F-713479, S3
#> [1] "location_code" "location_level" "year_bins" "var_lvl_school"
#> [5] "var_lvl_student" "var_lvl_teacher" "var_rat_s2t" "var_rat_s2s"
#> dim of youth wide ratio file: 114
#> dim of youth wide ratio file: 8
df_flr_korea %>% distinct(year_bins)
#> # A tibble: 6 × 1
#> year_bins
#> <dbl>
#> 1 1970
#> 2 1980
#> 3 1990
#> 4 2000
#> 5 2010
#> 6 2020Run FPC.
# Generate FPC
df_fpc_korea <- PrjCompPPTS::ff_ppts_lrce_fpc(
df_flr_korea,
ar_it_years_chg = seq(1970, 2020, by = 10),
ls_chg_years = list(
"chg_20v70" = c(1970, 2020),
# "chg_20v75" = c(1975, 2020),
"chg_20v80" = c(1980, 2020),
# "chg_20v85" = c(1985, 2020),
"chg_20v90" = c(1990, 2020),
# "chg_20v95" = c(1995, 2020),
"chg_20v00" = c(2000, 2020),
# "chg_20v05" = c(2005, 2020),
"chg_20v10" = c(2010, 2020)
# "chg_20v15" = c(2015, 2020)
), verbose = TRUE
)
#> F-376864, S1
#> dim of youth wide ratio file: 570
#> dim of youth wide ratio file: 6
#> F-376864, S2
#> dim of youth wide ratio file: 570
#> dim of youth wide ratio file: 6
#> F-376864, S3
#> dim of youth wide ratio file: 190
#> dim of youth wide ratio file: 10
#> F-376864, SD3
#> [1] "chg_20v70"
#> [1] "year1970"
#> [1] "year2020"
#> dim FPC: 190
#> dim FPC: 11
#> F-376864, SD3
#> [1] "chg_20v80"
#> [1] "year1980"
#> [1] "year2020"
#> dim FPC: 190
#> dim FPC: 12
#> F-376864, SD3
#> [1] "chg_20v90"
#> [1] "year1990"
#> [1] "year2020"
#> dim FPC: 190
#> dim FPC: 13
#> F-376864, SD3
#> [1] "chg_20v00"
#> [1] "year2000"
#> [1] "year2020"
#> dim FPC: 190
#> dim FPC: 14
#> F-376864, SD3
#> [1] "chg_20v10"
#> [1] "year2010"
#> [1] "year2020"
#> dim FPC: 190
#> dim FPC: 15
#> F-376864, S4
#> dim FPC: 190
#> dim FPC: 15
print(df_fpc_korea, n = 40)
#> # A tibble: 190 × 15
#> location_code location_level vartype variable year1970 year1980 year1990
#> <fct> <fct> <chr> <chr> <dbl> <dbl> <dbl>
#> 1 KOR_Metro multiprovince lvl school 1309 1525 1881
#> 2 KOR_Metro multiprovince lvl student 2531380 3004561 3109104
#> 3 KOR_Metro multiprovince lvl teacher 37375 51517 72501
#> 4 KOR_Metro multiprovince rat s2t 67.7 58.3 42.9
#> 5 KOR_Metro multiprovince rat s2s 1934. 1970. 1653.
#> 6 KOR_NonMetro multiprovince lvl school 4652 4962 4454
#> 7 KOR_NonMetro multiprovince lvl student 3217921 2653441 1759416
#> 8 KOR_NonMetro multiprovince lvl teacher 63720 67547 64299
#> 9 KOR_NonMetro multiprovince rat s2t 50.5 39.3 27.4
#> 10 KOR_NonMetro multiprovince rat s2s 692. 535. 395.
#> 11 KOR_Busan province lvl school 99 137 221
#> 12 KOR_Busan province lvl student 287059 446162 457057
#> 13 KOR_Busan province lvl teacher 4120 7420 10426
#> 14 KOR_Busan province rat s2t 69.7 60.1 43.8
#> 15 KOR_Busan province rat s2s 2900. 3257. 2068.
#> 16 KOR_Chungbuk province lvl school 372 397 337
#> 17 KOR_Chungbuk province lvl student 310348 222453 153273
#> 18 KOR_Chungbuk province lvl teacher 6043 6237 5353
#> 19 KOR_Chungbuk province rat s2t 51.4 35.7 28.6
#> 20 KOR_Chungbuk province rat s2s 834. 560. 455.
#> 21 KOR_Chungnam province lvl school 510 546 536
#> 22 KOR_Chungnam province lvl student 349484 279723 204769
#> 23 KOR_Chungnam province lvl teacher 7088 7427 7470
#> 24 KOR_Chungnam province rat s2t 49.3 37.7 27.4
#> 25 KOR_Chungnam province rat s2s 685. 512. 382.
#> 26 KOR_Daegu province lvl school 81 86 118
#> 27 KOR_Daegu province lvl student 282466 243379 255071
#> 28 KOR_Daegu province lvl teacher 3884 4196 5692
#> 29 KOR_Daegu province rat s2t 72.7 58.0 44.8
#> 30 KOR_Daegu province rat s2s 3487. 2830. 2162.
#> 31 KOR_Daejeon province lvl school 74 79 79
#> 32 KOR_Daejeon province lvl student 191964 153645 120318
#> 33 KOR_Daejeon province lvl teacher 2630 2756 2937
#> 34 KOR_Daejeon province rat s2t 73.0 55.7 41.0
#> 35 KOR_Daejeon province rat s2s 2594. 1945. 1523.
#> 36 KOR_Gangwon province lvl school 607 618 499
#> 37 KOR_Gangwon province lvl student 370844 292446 188114
#> 38 KOR_Gangwon province lvl teacher 7100 7514 7371
#> 39 KOR_Gangwon province rat s2t 52.2 38.9 25.5
#> 40 KOR_Gangwon province rat s2s 611. 473. 377.
#> # ℹ 150 more rows
#> # ℹ 8 more variables: year2000 <dbl>, year2010 <dbl>, year2020 <dbl>,
#> # chg_20v70 <dbl>, chg_20v80 <dbl>, chg_20v90 <dbl>, chg_20v00 <dbl>,
#> # chg_20v10 <dbl>Run FEL.
# Generate FEL
df_fel_korea <- PrjCompPPTS::ff_ppts_lrce_fel(
df_fpc_korea,
ls_rat_vars = list(
# "y2t" = c("youthpop", "teacher"),
"s2t" = c("student", "teacher"),
# "y2s" = c("youthpop", "school"),
"s2s" = c("student", "school")
),
verbose = TRUE
)
#> F-307302, S1
#> dim df_fpc_base: 57
#> dim df_fpc_base: 8
#> F-307302, S2
#> dim df_fel_long: 285
#> dim df_fel_long: 5
#> F-307302, S3
#> dim df_fel_wide: 95
#> dim df_fel_wide: 6
#> F-307302, S3
#> [1] "var_elas_s2t"
#> [1] "var_chg_student"
#> [1] "var_chg_teacher"
#> dim FEL: 95
#> dim FEL: 7
#> F-307302, S3
#> [1] "var_elas_s2s"
#> [1] "var_chg_student"
#> [1] "var_chg_school"
#> dim FEL: 95
#> dim FEL: 8
#> F-307302, S4
#> dim df_fel_elas: 95
#> dim df_fel_elas: 8
#> F-307302, S4
#> dim FEL: 38
#> dim FEL: 8
print(df_fel_korea, n = 40)
#> # A tibble: 38 × 8
#> location_code location_level variable elas_20v70 elas_20v80 elas_20v90
#> <fct> <fct> <chr> <dbl> <dbl> <dbl>
#> 1 KOR_Metro multiprovince s2t -0.114 -0.272 -0.573
#> 2 KOR_Metro multiprovince s2s -0.185 -0.352 -0.586
#> 3 KOR_NonMetro multiprovince s2t -19.0 34.8 -17.8
#> 4 KOR_NonMetro multiprovince s2s 2.04 1.70 1.58
#> 5 KOR_Busan province s2t -0.318 -1.78 24.9
#> 6 KOR_Busan province s2s -0.225 -0.538 -1.77
#> 7 KOR_Chungbuk province s2t -6.41 -7.86 -1.73
#> 8 KOR_Chungbuk province s2s 2.37 1.76 1.90
#> 9 KOR_Chungnam province s2t -2.14 -2.31 -1.72
#> 10 KOR_Chungnam province s2s 3.35 2.29 1.76
#> 11 KOR_Daegu province s2t -0.438 -0.442 -0.920
#> 12 KOR_Daegu province s2s -0.308 -0.296 -0.547
#> 13 KOR_Daejeon province s2t -0.451 -0.404 -0.319
#> 14 KOR_Daejeon province s2s -0.584 -0.550 -0.385
#> 15 KOR_Gangwon province s2t 12.3 6.42 6.13
#> 16 KOR_Gangwon province s2s 1.87 1.71 2.00
#> 17 KOR_Gwangju province s2t -0.371 -0.367 -0.406
#> 18 KOR_Gwangju province s2s -0.260 -0.251 -0.412
#> 19 KOR_Gyeong-gi province s2t 0.137 0.145 0.0895
#> 20 KOR_Gyeong-gi province s2s 0.557 0.536 0.180
#> 21 KOR_Gyeongbuk province s2t 7.31 4.28 4.19
#> 22 KOR_Gyeongbuk province s2s 1.65 1.47 1.27
#> 23 KOR_Gyeongnam province s2t -0.977 -0.889 -1.09
#> 24 KOR_Gyeongnam province s2s 1.79 1.34 1.37
#> 25 KOR_Incheon province s2t 0.0381 0.0203 -0.201
#> 26 KOR_Incheon province s2s 0.0375 0.0167 -0.169
#> 27 KOR_Jeju province s2t -0.283 -0.563 -0.456
#> 28 KOR_Jeju province s2s -7.95 53.3 15.9
#> 29 KOR_Jeonbuk province s2t 6.48 4.74 34.4
#> 30 KOR_Jeonbuk province s2s 3.39 2.51 2.51
#> 31 KOR_Jeonnam province s2t 2.56 2.15 2.36
#> 32 KOR_Jeonnam province s2s 1.66 1.51 1.43
#> 33 KOR_Sejong province s2t -0.0306 0.0651 0.404
#> 34 KOR_Sejong province s2s -0.145 0.347 2.09
#> 35 KOR_Seoul province s2t -0.274 -1.09 -5.05
#> 36 KOR_Seoul province s2s -0.241 -0.598 -2.06
#> 37 KOR_Ulsan province s2t -1.03 -0.963 -1.22
#> 38 KOR_Ulsan province s2s -4.25 -8.69 -2.43
#> # ℹ 2 more variables: elas_20v00 <dbl>, elas_20v10 <dbl>Merge FPC and FEL, country and group
Now we combine the level and change information from FPC with the elasticity results from FEL.
We have the LRCE file, level, ratio, change, and elasticity.
df_lrce_korea <- df_fpc_korea %>% left_join(
df_fel_korea %>% mutate(vartype = "rat"),
by = (c(
"location_code" = "location_code",
"location_level" = "location_level",
"variable" = "variable",
"vartype" = "vartype"
))
)
print(glue::glue("dim df_lrce_korea: {dim(df_lrce_korea)}"))
#> dim df_lrce_korea: 190
#> dim df_lrce_korea: 20Finally, merge in country key info to FPC, country-level information.
# Create empty columns
df_lrce_korea <- df_lrce_korea %>%
mutate(location_name = "", location_region_group = "")
# Add content to dataframe
it_len_ls_korea <- length(ls_korea)
ar_st_locs <- names(ls_korea)
for (it_loc in seq(1, it_len_ls_korea)) {
# Get strings
st_location_code <- ar_st_locs[it_loc]
ar_st_location_display <- ls_korea[[it_loc]]
st_loc_name_disp <- ar_st_location_display[[1]]
st_loc_group <- ar_st_location_display[[2]]
# Add values
df_lrce_korea <- df_lrce_korea %>%
mutate(
location_name = case_when(
location_code == st_location_code ~ st_loc_name_disp,
TRUE ~ location_name
),
location_region_group = case_when(
location_code == st_location_code ~ st_loc_group,
TRUE ~ location_region_group
)
)
}
# reselect vars
df_lrce_korea <- df_lrce_korea %>%
select(location_code, location_level, location_name, location_region_group, everything())Global Population Table
Prep Table inputs
First, select level and percentage changes year by year for four variables. Also get ratio and elasticities.
# level
df_lvl_korea <- df_lrce_korea %>%
filter(vartype == "lvl") %>%
select(
location_code, location_level, location_name, location_region_group,
variable, contains("year")
)
# change
df_chg_korea <- df_lrce_korea %>%
filter(vartype == "lvl") %>%
select(
location_code, location_level, location_name, location_region_group,
variable, contains("chg")
)
# ratio
df_rat_korea <- df_lrce_korea %>%
filter(vartype == "rat") %>%
select(
location_code, location_level, location_name, location_region_group,
variable, contains("year")
)
# elasticity
df_elas_korea <- df_lrce_korea %>%
filter(vartype == "rat") %>%
select(
location_code, location_level, location_name, location_region_group,
variable, contains("elas")
)Second, reshape time variables from each table above from wide to long.
# level file
df_lvl_korea_long <- df_lvl_korea %>%
pivot_longer(
cols = starts_with("year"),
names_to = c("yearset"),
names_pattern = paste0("year(.*)"),
values_to = "stats"
) %>%
mutate(type = "1lvl")
# change file
df_chg_korea_long <- df_chg_korea %>%
pivot_longer(
cols = starts_with("chg"),
names_to = c("yearset"),
names_pattern = paste0("chg_(.*)"),
values_to = "stats"
) %>%
mutate(type = "2chg")
# ratio file
df_rat_korea_long <- df_rat_korea %>%
pivot_longer(
cols = starts_with("year"),
names_to = c("yearset"),
names_pattern = paste0("year(.*)"),
values_to = "stats"
) %>%
mutate(type = "3rat")
# elasticity file
df_elas_korea_long <- df_elas_korea %>%
pivot_longer(
cols = starts_with("elas"),
names_to = c("yearset"),
names_pattern = paste0("elas_(.*)"),
values_to = "stats"
) %>%
mutate(type = "4elas")Third, combine long files, and convert countries to columns, reshape to wide.
# combine all long files
df_korea_long_jnt <- bind_rows(
df_lvl_korea_long,
df_chg_korea_long,
df_rat_korea_long,
df_elas_korea_long
)
# reshape long to wide
df_korea_wide <- df_korea_long_jnt %>%
arrange(variable, yearset, location_name) %>%
pivot_wider(
id_cols = c("type", "variable", "yearset"),
names_from = location_name,
names_prefix = "j_",
values_from = stats
)Fourth, organize columns, and generate four subsets.
# Select variables
tab3_korea <- df_korea_wide %>%
select(
type, variable, yearset, everything()
)
# Four variables
tab3_korea_lvl <- tab3_korea %>% filter(type == "1lvl")
tab3_korea_chg <- tab3_korea %>% filter(type == "2chg")
tab3_korea_rat <- tab3_korea %>% filter(type == "3rat")
tab3_korea_elas <- tab3_korea %>% filter(type == "4elas")Fifth, format each type of variables separately.
# Format variables, level in millions
tab3_korea_lvl_school <- tab3_korea_lvl %>%
filter(variable == "school") %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(., 0),
nsmall = 0, big.mark = ","
)
))
)
tab3_korea_lvl_teacher <- tab3_korea_lvl %>%
filter(variable == "teacher") %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(. / 1000, 1),
nsmall = 0, big.mark = ","
)
))
)
tab3_korea_lvl_student <- tab3_korea_lvl %>%
filter(variable == "student") %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(. / 1000, 0),
nsmall = 0, big.mark = ","
)
))
)
# Change in percent
tab3_korea_chg <- tab3_korea_chg %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(., 2) * 100,
nsmall = 0,
big.mark = ","
),
"%"
))
)
# Change in ratio
tab3_korea_rat <- tab3_korea_rat %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(., 0), nsmall = 0, big.mark = ",")
))
)
# Change in ratio
tab3_korea_elas <- tab3_korea_elas %>%
mutate_at(
vars(contains("j_")),
list(~ paste0(
format(round(., 2), nsmall = 0, big.mark = ",")
))
)Sixth, combine all four stats again, now that formatting is done.
# combine
tab3_korea_jnt <- bind_rows(
tab3_korea_lvl_school,
tab3_korea_lvl_teacher,
tab3_korea_lvl_student,
tab3_korea_chg,
tab3_korea_rat,
# tab3_korea_elas
)
# replace variable names for sorting
tab3_korea_jnt <- tab3_korea_jnt %>%
mutate(variable_sort = case_when(
variable == "school" ~ "1school",
variable == "teacher" ~ "2teacher",
variable == "student" ~ "3student",
variable == "s2s" ~ "1s2s",
variable == "s2t" ~ "3s2t",
))
# Year sorting
tab3_korea_jnt <- tab3_korea_jnt %>%
mutate(yearset = case_when(
yearset == "20v00" ~ "2020 vs 2000",
yearset == "20v10" ~ "2020 vs 2010",
yearset == "20v60" ~ "2020 vs 1960",
yearset == "20v70" ~ "2020 vs 1970",
yearset == "20v80" ~ "2020 vs 1980",
yearset == "20v90" ~ "2020 vs 1990",
TRUE ~ yearset
))
# replace NAs
tab3_korea_jnt <- tab3_korea_jnt %>%
mutate_at(vars(starts_with("j_")), ~ str_replace(., "NA%", "")) %>%
mutate_at(vars(starts_with("j_")), ~ str_replace(., "NA", ""))
print(tab3_korea_jnt, n = 200)
#> # A tibble: 45 × 23
#> type variable yearset `j_A1-Metro` `j_A2-Seoul` `j_A3-Incheon`
#> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 1lvl school 1970 "1,309" "206" " 50"
#> 2 1lvl school 1980 "1,525" "291" " 55"
#> 3 1lvl school 1990 "1,881" "463" "103"
#> 4 1lvl school 2000 "2,312" "532" "174"
#> 5 1lvl school 2010 "2,893" "587" "226"
#> 6 1lvl school 2020 "3,164" "607" "253"
#> 7 1lvl teacher 1970 " 37.4" "10.6" " 2.0"
#> 8 1lvl teacher 1980 " 51.5" "17.9" " 2.5"
#> 9 1lvl teacher 1990 " 72.5" "25.4" " 4.5"
#> 10 1lvl teacher 2000 " 86.7" "25.3" " 7.2"
#> 11 1lvl teacher 2010 "114.8" "29.3" " 9.5"
#> 12 1lvl teacher 2020 "123.1" "28.6" "10.1"
#> 13 1lvl student 1970 "2,531" " 770" "136"
#> 14 1lvl student 1980 "3,005" "1,169" "148"
#> 15 1lvl student 1990 "3,109" "1,142" "208"
#> 16 1lvl student 2000 "2,773" " 759" "246"
#> 17 1lvl student 2010 "2,277" " 566" "183"
#> 18 1lvl student 2020 "1,867" " 410" "157"
#> 19 2chg school 2020 vs 2000 " 37%" " 14%" " 45%"
#> 20 2chg school 2020 vs 2010 " 9%" " 3%" " 12%"
#> 21 2chg school 2020 vs 1970 "142%" "195%" "406%"
#> 22 2chg school 2020 vs 1980 "107%" "109%" "360%"
#> 23 2chg school 2020 vs 1990 " 68%" " 31%" "146%"
#> 24 2chg student 2020 vs 2000 "-33%" "-46%" "-36%"
#> 25 2chg student 2020 vs 2010 "-18%" "-28%" "-14%"
#> 26 2chg student 2020 vs 1970 "-26%" "-47%" " 15%"
#> 27 2chg student 2020 vs 1980 "-38%" "-65%" " 6%"
#> 28 2chg student 2020 vs 1990 "-40%" "-64%" "-25%"
#> 29 2chg teacher 2020 vs 2000 " 42%" " 13%" " 41%"
#> 30 2chg teacher 2020 vs 2010 " 7%" " -2%" " 6%"
#> 31 2chg teacher 2020 vs 1970 "229%" "171%" "400%"
#> 32 2chg teacher 2020 vs 1980 "139%" " 60%" "295%"
#> 33 2chg teacher 2020 vs 1990 " 70%" " 13%" "123%"
#> 34 3rat s2s 1970 "1,934" "3,739" "2,724"
#> 35 3rat s2s 1980 "1,970" "4,016" "2,692"
#> 36 3rat s2s 1990 "1,653" "2,466" "2,022"
#> 37 3rat s2s 2000 "1,199" "1,428" "1,412"
#> 38 3rat s2s 2010 " 787" " 964" " 811"
#> 39 3rat s2s 2020 " 590" " 675" " 620"
#> 40 3rat s2t 1970 " 68" " 73" " 68"
#> 41 3rat s2t 1980 " 58" " 65" " 58"
#> 42 3rat s2t 1990 " 43" " 45" " 46"
#> 43 3rat s2t 2000 " 32" " 30" " 34"
#> 44 3rat s2t 2010 " 20" " 19" " 19"
#> 45 3rat s2t 2020 " 15" " 14" " 16"
#> # ℹ 17 more variables: `j_A4-Gyeong-gi` <chr>, `j_B1-Busan` <chr>,
#> # `j_B2-Daegu` <chr>, `j_B3-Daejeon` <chr>, `j_B4-Gwangju` <chr>,
#> # `j_B5-Sejong` <chr>, `j_B6-Ulsan` <chr>, `j_C1-Non-metro` <chr>,
#> # `j_D1-Chungbuk` <chr>, `j_D2-Chungnam` <chr>, `j_D3-Gyeongbuk` <chr>,
#> # `j_D4-Gyeongnam` <chr>, `j_D5-Jeonnam` <chr>, `j_E1-Gangwon` <chr>,
#> # `j_E2-Jeju` <chr>, `j_E3-Jeonbuk` <chr>, variable_sort <chr>Finally, count by group, generate labeling string
# Group and arrange
tab3_korea_jnt <- tab3_korea_jnt %>%
arrange(
type, variable_sort, yearset,
)
# get counts
df_typevar_counts <- tab3_korea_jnt %>%
group_by(
type, variable_sort, variable,
) %>%
summarize(group_count = n()) %>%
ungroup() %>%
mutate(group_count_start = cumsum(group_count) - group_count + 1) %>%
mutate(group_count_end = cumsum(group_count)) %>%
select(group_count_start, group_count_end, everything())
#> `summarise()` has grouped output by 'type', 'variable_sort'. You can override
#> using the `.groups` argument.
# Generate group names
df_typevar_counts <- df_typevar_counts %>%
mutate(type_lab_supra = case_when(
type == "1lvl" ~ "Levels",
type == "2chg" ~ "Percentage changes over time",
type == "3rat" ~ "Ratios",
type == "4elas" ~ "Elasticities"
)) %>%
mutate(type_lab = case_when(
type == "1lvl" ~ "Number of",
type == "2chg" ~ "Percentage change in",
type == "3rat" ~ "Ratio",
type == "4elas" ~ "Elasticity"
)) %>%
mutate(variable_lab = case_when(
(type == "1lvl" & variable == "school") ~ "schools",
(type == "1lvl" & variable == "teacher") ~ "teachers (1000s)",
(type == "1lvl" & variable == "student") ~ "students (1000s)",
(type == "2chg" & variable == "school") ~ "schools",
(type == "2chg" & variable == "teacher") ~ "teachers",
(type == "2chg" & variable == "student") ~ "students",
(type == "2chg" & variable == "youthpop") ~ "youth 0-14",
(type == "3rat" & variable == "s2s") ~ "Student/School",
(type == "3rat" & variable == "s2t") ~ "Student/Teacher",
(type == "4elas" & variable == "s2s") ~ "$\\Delta$\\%Student/$\\Delta$\\%School",
(type == "4elas" & variable == "s2t") ~ "$\\Delta$\\%Student/$\\Delta$\\%Teacher"
)) %>%
unite(row_name, type_lab:variable_lab, sep = " ")
# print
print(df_typevar_counts, n = 100)
#> # A tibble: 8 × 8
#> group_count_start group_count_end type variable_sort variable group_count
#> <dbl> <int> <chr> <chr> <chr> <int>
#> 1 1 6 1lvl 1school school 6
#> 2 7 12 1lvl 2teacher teacher 6
#> 3 13 18 1lvl 3student student 6
#> 4 19 23 2chg 1school school 5
#> 5 24 28 2chg 2teacher teacher 5
#> 6 29 33 2chg 3student student 5
#> 7 34 39 3rat 1s2s s2s 6
#> 8 40 45 3rat 3s2t s2t 6
#> # ℹ 2 more variables: type_lab_supra <chr>, row_name <chr>Generate table
Now we generate the table.
ar_st_kableformat <- c("latex", "html")
for (st_kableformat in ar_st_kableformat) {
# j_China, j_Japan, j_Korea, j_Taiwan,
# j_Austria, j_Germany, j_France, j_Netherlands, j_Switzerland
# Column names
ar_st_colnames <- names(df_korea_wide)
ar_st_colnames_js <- ar_st_colnames[grepl("j_", ar_st_colnames)]
ar_st_clean <- stringr::str_replace(ar_st_colnames_js, "j_[[:alnum:]]+-", "")
ar_st_clean <- stringr::str_replace(ar_st_clean, "nam", "-nam")
ar_st_clean <- stringr::str_replace(ar_st_clean, "buk", "-buk")
ar_st_clean <- stringr::str_replace(ar_st_clean, "won", "-won")
ar_st_clean <- stringr::str_replace(ar_st_clean, "Non-metro", "All")
ar_st_clean <- stringr::str_replace(ar_st_clean, "Metro", "All")
ar_st_col_names <- c(
"Years",
ar_st_clean
)
# Define column groups, grouping the names above
# =1/3/2 are number of columns group title covers
ar_st_col_groups_l2 <- c(
" " = 1,
"All" = 1,
"Capital cities" = 3,
"Metropolitian cities" = 6,
"All" = 1,
"Provinces" = 5,
"Special provinces" = 3
)
ar_st_col_groups_l1 <- c(
" " = 1,
"Capital and metropolitan areas" = 10,
"Non-metropolitan areas" = 9
)
# select and sort
tab3_korea_jnt_kbl <- tab3_korea_jnt %>%
select(
-type, -variable, -variable_sort,
yearset, one_of(ar_st_colnames_js)
)
# Second, we construct main table, and add styling.
bk_korea <- kbl(
tab3_korea_jnt_kbl,
format = st_kableformat,
label = "main:tab:korea:pop:teachers:schools",
# escape = F,
linesep = "",
booktabs = T,
longtable = T,
align = "c",
caption = "Korea: Schools, Teachers, and Students",
col.names = ar_st_col_names
) %>%
# see https://cran.r-project.org/web/packages/kableExtra/vignettes/awesome_table_in_html.html#Bootstrap_table_classes
kable_styling(
bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = F, position = "left"
)
# Third, we add in column groups.
bk_korea <- bk_korea %>%
add_header_above(ar_st_col_groups_l2) %>%
add_header_above(ar_st_col_groups_l1)
# Fourth, we add in row groups.
st_supra_grp_cur <- ""
it_supra_grp_ctr <- 0
for (it_group in seq(1, dim(df_typevar_counts)[1])) {
# supra group variable
st_supra_grp <- as.character(df_typevar_counts[[it_group, "type_lab_supra"]])
# Reion full name info
st_loc <- as.character(df_typevar_counts[[it_group, "row_name"]])
# groups start and end
it_group_count_start <- df_typevar_counts[[it_group, "group_count_start"]]
it_group_count_end <- df_typevar_counts[[it_group, "group_count_end"]]
if (st_supra_grp != st_supra_grp_cur) {
it_supra_grp_ctr <- it_supra_grp_ctr + 1
st_supra_grp_cur <- st_supra_grp
bl_hline_before <- FALSE
if (it_supra_grp_ctr >= 2) {
bl_hline_before <- TRUE
}
# Heading group stats type
st_supra_text <- paste0(st_supra_grp_cur)
bk_korea <- bk_korea %>%
pack_rows(
st_supra_text, it_group_count_start, it_group_count_start,
latex_gap_space = "0.0em",
indent = FALSE,
latex_align = "c",
hline_after = TRUE,
hline_before = bl_hline_before
)
}
# Add to table
bk_korea <- bk_korea %>%
pack_rows(
st_loc, it_group_count_start, it_group_count_end,
latex_gap_space = "0.75em",
latex_align = "l",
hline_after = FALSE
)
}
# Fifth, column formatting.
fl_width_country <- 1.9
st_width_country <- paste0(fl_width_country, "cm")
bk_korea <- bk_korea %>%
column_spec(1, width = st_width_country) %>%
column_spec(2:dim(tab3_korea_jnt_kbl)[2], width = "0.75cm")
# Final adjustments
# Headings on all pages, note use `sub` to replace first midrule
st_headend <- paste0(
"\\midrule\\endhead\n",
"\\addlinespace[0.2em]\\hline\\addlinespace[0.2em]\n",
"\\multicolumn{", dim(tab3_korea_jnt_kbl)[2], "}{r}{\\emph{Continued on next page}}\\\\\n",
"\\endfoot\\endlastfoot"
)
bk_korea <- sub(bk_korea,
pattern = "\\midrule", replacement = st_headend,
fixed = TRUE
)
# country-names left-align
bk_korea <- gsub(bk_korea,
pattern = paste0("\\centering\\arraybackslash}p{", st_width_country, "}"),
replacement = paste0("\\raggedright\\arraybackslash}p{", st_width_country, "}"),
fixed = TRUE
)
# midrule replacing hline
bk_korea <- gsub(bk_korea,
pattern = "hline",
replacement = "midrule", fixed = TRUE
)
# Sixth, display.
# pl_bk_asset_count <- bk_asset_count %>% as_image()
# bk_korea
# Save tex to file.
if (st_kableformat == "html") {
print(dim(bk_korea))
} else {
if (bl_tex_save) {
fileConn <- file(spn_tex_out)
writeLines(bk_korea, fileConn)
close(fileConn)
if (verbose) {
print(glue::glue("F-945386, S1"))
print(glue::glue("Latex saved: {spn_tex_out}"))
}
}
}
}
#> Warning in pack_rows(., st_supra_text, it_group_count_start, it_group_count_start, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_supra_text, it_group_count_start, it_group_count_start, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_supra_text, it_group_count_start, it_group_count_start, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> Warning in pack_rows(., st_loc, it_group_count_start, it_group_count_end, : latex_align parameter is not used in HTML Mode,
#> use label_row_css instead.
#> NULL
bk_korea| Years | All | Seoul | Incheon | Gyeong-gi | Busan | Daegu | Daejeon | Gwangju | Sejong | Ulsan | All | Chung-buk | Chung-nam | Gyeong-buk | Gyeong-nam | Jeon-nam | Gang-won | Jeju | Jeon-buk |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Levels | |||||||||||||||||||
| Number of schools | |||||||||||||||||||
| 1970 | 1,309 | 206 | 50 | 613 | 99 | 81 | 74 | 50 | 32 | 105 | 4,652 | 372 | 510 | 890 | 731 | 881 | 607 | 108 | 553 |
| 1980 | 1,525 | 291 | 55 | 676 | 137 | 86 | 79 | 54 | 34 | 113 | 4,962 | 397 | 546 | 948 | 782 | 954 | 618 | 114 | 603 |
| 1990 | 1,881 | 463 | 103 | 684 | 221 | 118 | 79 | 83 | 29 | 101 | 4,454 | 337 | 536 | 890 | 701 | 821 | 499 | 115 | 555 |
| 2000 | 2,312 | 532 | 174 | 835 | 267 | 178 | 110 | 109 | 22 | 85 | 2,955 | 247 | 410 | 492 | 449 | 462 | 367 | 106 | 422 |
| 2010 | 2,893 | 587 | 226 | 1,145 | 298 | 214 | 138 | 145 | 22 | 118 | 2,961 | 259 | 408 | 494 | 495 | 433 | 353 | 106 | 413 |
| 2020 | 3,164 | 607 | 253 | 1,298 | 304 | 230 | 148 | 155 | 49 | 120 | 2,956 | 258 | 410 | 473 | 505 | 429 | 347 | 113 | 421 |
| Number of teachers (1000s) | |||||||||||||||||||
| 1970 | 37.4 | 10.6 | 2.0 | 8.4 | 4.1 | 3.9 | 2.6 | 2.4 | 0.6 | 2.7 | 63.7 | 6.0 | 7.1 | 11.5 | 8.8 | 12.4 | 7.1 | 1.2 | 9.4 |
| 1980 | 51.5 | 17.9 | 2.5 | 10.6 | 7.4 | 4.2 | 2.8 | 2.7 | 0.6 | 2.8 | 67.5 | 6.2 | 7.4 | 12.5 | 9.0 | 13.5 | 7.5 | 1.6 | 9.8 |
| 1990 | 72.5 | 25.4 | 4.5 | 16.7 | 10.4 | 5.7 | 2.9 | 3.2 | 0.5 | 3.1 | 64.3 | 5.4 | 7.5 | 12.0 | 10.2 | 11.6 | 7.4 | 1.8 | 8.4 |
| 2000 | 86.7 | 25.3 | 7.2 | 26.5 | 9.8 | 6.5 | 3.9 | 3.8 | 0.4 | 3.3 | 53.3 | 4.9 | 6.5 | 9.5 | 9.9 | 8.1 | 5.7 | 1.9 | 6.9 |
| 2010 | 114.8 | 29.3 | 9.5 | 40.4 | 11.0 | 8.7 | 5.6 | 5.6 | 0.5 | 4.2 | 62.0 | 5.9 | 8.0 | 10.4 | 12.6 | 8.3 | 6.5 | 2.4 | 7.9 |
| 2020 | 123.1 | 28.6 | 10.1 | 46.8 | 10.1 | 8.9 | 6.0 | 6.0 | 2.1 | 4.3 | 66.2 | 6.7 | 9.3 | 10.3 | 13.8 | 8.3 | 6.6 | 2.9 | 8.3 |
| Number of students (1000s) | |||||||||||||||||||
| 1970 | 2,531 | 770 | 136 | 469 | 287 | 282 | 192 | 191 | 32 | 172 | 3,218 | 310 | 349 | 570 | 428 | 630 | 371 | 64 | 494 |
| 1980 | 3,005 | 1,169 | 148 | 510 | 446 | 243 | 154 | 163 | 26 | 146 | 2,653 | 222 | 280 | 491 | 364 | 538 | 292 | 76 | 389 |
| 1990 | 3,109 | 1,142 | 208 | 656 | 457 | 255 | 120 | 134 | 12 | 124 | 1,759 | 153 | 205 | 318 | 309 | 290 | 188 | 56 | 240 |
| 2000 | 2,773 | 759 | 246 | 889 | 295 | 216 | 126 | 127 | 8 | 107 | 1,247 | 124 | 143 | 218 | 269 | 164 | 123 | 47 | 160 |
| 2010 | 2,277 | 566 | 183 | 848 | 197 | 168 | 109 | 116 | 8 | 82 | 1,022 | 105 | 131 | 164 | 228 | 124 | 100 | 44 | 127 |
| 2020 | 1,867 | 410 | 157 | 762 | 154 | 123 | 80 | 86 | 29 | 67 | 826 | 85 | 120 | 129 | 191 | 92 | 73 | 41 | 95 |
| Percentage changes over time | |||||||||||||||||||
| Percentage change in schools | |||||||||||||||||||
| 2020 vs 1970 | 142% | 195% | 406% | 112% | 207% | 184% | 100% | 210% | 53% | 14% | -36% | -31% | -20% | -47% | -31% | -51% | -43% | 5% | -24% |
| 2020 vs 1980 | 107% | 109% | 360% | 92% | 122% | 167% | 87% | 187% | 44% | 6% | -40% | -35% | -25% | -50% | -35% | -55% | -44% | -1% | -30% |
| 2020 vs 1990 | 68% | 31% | 146% | 90% | 38% | 95% | 87% | 87% | 69% | 19% | -34% | -23% | -24% | -47% | -28% | -48% | -30% | -2% | -24% |
| 2020 vs 2000 | 37% | 14% | 45% | 55% | 14% | 29% | 35% | 42% | 123% | 41% | 0% | 4% | 0% | -4% | 12% | -7% | -5% | 7% | 0% |
| 2020 vs 2010 | 9% | 3% | 12% | 13% | 2% | 7% | 7% | 7% | 123% | 2% | 0% | 0% | 0% | -4% | 2% | -1% | -2% | 7% | 2% |
| Percentage change in teachers | |||||||||||||||||||
| 2020 vs 1970 | 229% | 171% | 400% | 456% | 146% | 129% | 129% | 147% | 251% | 59% | 4% | 11% | 31% | -11% | 57% | -33% | -7% | 130% | -12% |
| 2020 vs 1980 | 139% | 60% | 295% | 340% | 37% | 112% | 119% | 128% | 235% | 56% | -2% | 8% | 25% | -17% | 54% | -39% | -12% | 83% | -16% |
| 2020 vs 1990 | 70% | 13% | 123% | 180% | -3% | 56% | 105% | 88% | 357% | 37% | 3% | 26% | 24% | -14% | 35% | -29% | -10% | 61% | -2% |
| 2020 vs 2000 | 42% | 13% | 41% | 77% | 4% | 36% | 55% | 58% | 426% | 29% | 24% | 37% | 43% | 9% | 40% | 2% | 16% | 55% | 20% |
| 2020 vs 2010 | 7% | -2% | 6% | 16% | -7% | 2% | 9% | 8% | 328% | 3% | 7% | 14% | 16% | 0% | 10% | 0% | 2% | 21% | 4% |
| Percentage change in students | |||||||||||||||||||
| 2020 vs 1970 | -26% | -47% | 15% | 62% | -47% | -57% | -58% | -55% | -8% | -61% | -74% | -73% | -66% | -77% | -55% | -85% | -80% | -37% | -81% |
| 2020 vs 1980 | -38% | -65% | 6% | 49% | -66% | -50% | -48% | -47% | 15% | -54% | -69% | -62% | -57% | -74% | -48% | -83% | -75% | -47% | -76% |
| 2020 vs 1990 | -40% | -64% | -25% | 16% | -66% | -52% | -34% | -36% | 144% | -46% | -53% | -44% | -41% | -59% | -38% | -68% | -61% | -28% | -61% |
| 2020 vs 2000 | -33% | -46% | -36% | -14% | -48% | -43% | -37% | -32% | 249% | -37% | -34% | -31% | -16% | -41% | -29% | -44% | -40% | -13% | -41% |
| 2020 vs 2010 | -18% | -28% | -14% | -10% | -22% | -27% | -27% | -25% | 282% | -17% | -19% | -19% | -8% | -21% | -16% | -25% | -26% | -8% | -25% |
| Ratios | |||||||||||||||||||
| Ratio Student/School | |||||||||||||||||||
| 1970 | 1,934 | 3,739 | 2,724 | 766 | 2,900 | 3,487 | 2,594 | 3,811 | 998 | 1,635 | 692 | 834 | 685 | 641 | 586 | 715 | 611 | 594 | 894 |
| 1980 | 1,970 | 4,016 | 2,692 | 755 | 3,257 | 2,830 | 1,945 | 3,016 | 752 | 1,292 | 535 | 560 | 512 | 518 | 466 | 564 | 473 | 668 | 644 |
| 1990 | 1,653 | 2,466 | 2,022 | 959 | 2,068 | 2,162 | 1,523 | 1,620 | 417 | 1,228 | 395 | 455 | 382 | 357 | 441 | 353 | 377 | 487 | 432 |
| 2000 | 1,199 | 1,428 | 1,412 | 1,065 | 1,105 | 1,216 | 1,143 | 1,163 | 384 | 1,254 | 422 | 503 | 349 | 442 | 599 | 354 | 334 | 441 | 378 |
| 2010 | 787 | 964 | 811 | 741 | 662 | 783 | 790 | 799 | 350 | 692 | 345 | 406 | 320 | 332 | 460 | 286 | 283 | 415 | 307 |
| 2020 | 590 | 675 | 620 | 587 | 505 | 533 | 539 | 558 | 602 | 562 | 280 | 330 | 293 | 273 | 378 | 215 | 212 | 359 | 225 |
| Ratio Student/Teacher | |||||||||||||||||||
| 1970 | 68 | 73 | 68 | 56 | 70 | 73 | 73 | 78 | 52 | 64 | 51 | 51 | 49 | 49 | 48 | 51 | 52 | 52 | 52 |
| 1980 | 58 | 65 | 58 | 48 | 60 | 58 | 56 | 61 | 40 | 53 | 39 | 36 | 38 | 39 | 40 | 40 | 39 | 49 | 40 |
| 1990 | 43 | 45 | 46 | 39 | 44 | 45 | 41 | 42 | 26 | 40 | 27 | 29 | 27 | 26 | 30 | 25 | 26 | 31 | 29 |
| 2000 | 32 | 30 | 34 | 34 | 30 | 33 | 32 | 33 | 21 | 32 | 23 | 25 | 22 | 23 | 27 | 20 | 22 | 25 | 23 |
| 2010 | 20 | 19 | 19 | 21 | 18 | 19 | 20 | 21 | 15 | 19 | 17 | 18 | 16 | 16 | 18 | 15 | 15 | 19 | 16 |
| 2020 | 15 | 14 | 16 | 16 | 15 | 14 | 13 | 14 | 14 | 16 | 12 | 13 | 13 | 13 | 14 | 11 | 11 | 14 | 11 |