-
Notifications
You must be signed in to change notification settings - Fork 10
/
District_Table_Unpacking.R
8948 lines (7730 loc) · 492 KB
/
District_Table_Unpacking.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
setwd("~/Google Drive/GitHub/pakistan_census")
library(pdftools)
library(XML)
library(rvest)
library(tidyverse)
rm(list = ls())
#
# Download district tables ----------------------------------
#
url <- read_html("https://www.pbs.gov.pk/content/district-wise-results-tables-census-2017")
district_links <- url %>% html_nodes("a") %>% html_attr("href")
district_links <- district_links[str_detect(district_links, "node")]
district_links <- district_links[!is.na(district_links)]
download_error_log <- list()
# Cycle through district pages to download tables for each district
for(n in 1:length(district_links)){
district_link <- paste0("https://www.pbs.gov.pk", district_links[n])
district_number <- str_split(district_link, "=")[[1]][2]
district_page <- read_html(district_link)
district_name <- district_page %>% html_nodes("h1") %>% html_text()
district_name <- trimws(district_name[2])
district_path <- paste0("./district_tables_raw/", district_name, "/")
# create the appropriate subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(district_path)), dir.create(file.path(district_path)), FALSE)
# load the district page and get links to all tables
table_links <- district_page %>% html_nodes("a") %>% html_attr("href")
table_links <- table_links[str_detect(table_links, ".pdf")]
table_links <- table_links[!is.na(table_links)]
# download the tables into district folders
for(i in 1:length(table_links)){
tryCatch(
download.file(paste0("https://www.pbs.gov.pk", table_links[i]), file.path(district_path, destfile = basename(table_links[i]))),
error = function(e){download_error_log <- c(download_error_log, table_links[i])} # this isn't logging properly
)
Sys.sleep(1.5)
}
}
# Process the pdfs ---------------------------------------------
rm(list = ls())
table_numbers <- str_pad(c(1:40), side = "left", width = 2, pad = "0")
district_subdirs <- list.files(path = "./district_tables_raw/")
missing_files <- tibble(
district_number = NA,
district_name = NA,
missing_table = NA
)
# province groupings based on district codes taken from PBS pdfs
kpk_codes <- tibble(
province_name = "KHYBER PAKTUNKHWA",
district_code = str_pad(1:25, width = 3, side = "left", pad = "0")
)
fata_codes <- tibble(
province_name = "FATA",
district_code = str_pad(26:38, width = 3, side = "left", pad = "0")
)
punjab_codes <- tibble(
province_name = "PUNJAB",
district_code = str_pad(39:74, width = 3, side = "left", pad = "0")
)
sindh_codes <- tibble(
province_name = "SINDH",
district_code = str_pad(75:103, width = 3, side = "left", pad = "0")
)
balochistan_codes <- tibble(
province_name = "BALOCHISTAN",
district_code = str_pad(104:134, width = 3, side = "left", pad = "0")
)
islamabad_codes <- tibble(
province_name = "ISLAMABAD CAPITAL TERRITORY",
district_code = str_pad(135, width = 3, side = "left", pad = "0")
)
all_codes <- full_join(kpk_codes, fata_codes) %>% full_join(punjab_codes) %>%
full_join(sindh_codes) %>% full_join(balochistan_codes) %>% full_join(islamabad_codes)
natl_table_01 <- tibble()
natl_table_02 <- tibble()
natl_table_03 <- tibble()
natl_table_04 <- tibble()
natl_table_05 <- tibble()
natl_table_06 <- tibble()
natl_table_07 <- tibble()
natl_table_08 <- tibble()
natl_table_09 <- tibble()
natl_table_10 <- tibble()
natl_table_11 <- tibble()
natl_table_12 <- tibble()
natl_table_13 <- tibble()
natl_table_14 <- tibble()
natl_table_15 <- tibble()
natl_table_16 <- tibble()
natl_table_17 <- tibble()
natl_table_18 <- tibble()
natl_table_19 <- tibble()
natl_table_20 <- tibble()
natl_table_21 <- tibble()
natl_table_22_literacy <- tibble()
natl_table_22_marital <- tibble()
natl_table_22_religion <- tibble()
natl_table_22_work <- tibble()
natl_table_23 <- tibble()
natl_table_24 <- tibble()
natl_table_25 <- tibble()
natl_table_26 <- tibble()
natl_table_27 <- tibble()
natl_table_28 <- tibble()
natl_table_29 <- tibble()
natl_table_30 <- tibble()
natl_table_31 <- tibble()
natl_table_32 <- tibble()
natl_table_33 <- tibble()
natl_table_34 <- tibble()
natl_table_35 <- tibble()
natl_table_36 <- tibble()
natl_table_37 <- tibble()
natl_table_38 <- tibble()
natl_table_39 <- tibble()
natl_table_40 <- tibble()
# identify administrative summary areas from the provisional results data
Pakistan_2017_Census_Provisional <- read_csv("~/Google Drive/GitHub/pakistan_census/Pakistan_2017_Census_Provisional.csv")
census_blocks <- unique(Pakistan_2017_Census_Provisional$census_block)
sublvl_01_list <- unique(Pakistan_2017_Census_Provisional$sublvl_01)
sublvl_02_list <- unique(Pakistan_2017_Census_Provisional$sublvl_02)
sublvl_03_list <- unique(Pakistan_2017_Census_Provisional$sublvl_03)
provisional_areas <- Pakistan_2017_Census_Provisional %>% dplyr::select(district, sublvl_01, sublvl_02, sublvl_03, sublvl_04) %>% unique()
administrative_areas <- unique(c(unique(provisional_areas$district),
unique(provisional_areas$sublvl_01), unique(provisional_areas$sublvl_02), unique(provisional_areas$sublvl_03)))
# following areas missing from provisional results list
administrative_areas <- c(administrative_areas,
"CHAUDHAWAN QH", "MANGHOPIR SUB-DIVISION", "DINO MAKO TC", "KALEKEY QH",
"SHADI PALI STC", "CHAK NO 004/R.D. PC", "IBRAHIM HYDRI SUB-DIVISION", "ORNACH SUB-TEHSIL", "SHAH MUREED SUB-DIVISION",
"SHAHGORI SUB-TEHSIL", "KASHMOR TC", "KHANO WALA PC", "ODERO LAL STC", "MURAD MEMON SUB-DIVISION",
"MULTAN CANTONMENT", "MAURIPUR SUB-DIVISION", "LORALAI\\BORI TEHSIL", "HURRAM ZAI SUB-TEHSIL", "SHORKOT CANTONMENT",
"ALIPUR MC", "AWARAN MC", "BARKHAN MC", "BARRI KOT MC", "BATKHELA MC", "BEHRAIN MC", "BELA MC", "BHAG MC", "BHAWANA MC", "BULAIDA MC", "CHAK JHUMRA MC",
"CHAUBARA MC", "CHITKAN MC", "CHITRAL MC", "DALBANDIN MC", "DAULTALA MC", "DERA BUGTI MC", "DERA DIN PANAH MC", "DERA ISMAIL KHAN MC",
"DERA MURAD JAMALI MC", "DHADAR MC", "DIJKOT MC DINGA MC", "DUKI MC DUREJI MC", "FATEH PUR MC", "FEROZEWALA MC", "GADDANI MC", "GANDAWA MC",
"GHUR GHUSHTI MC", "GUJAR MASHKAI MC", "GWADAR MC", "HANGU MC", "HARIPUR MC", "HARNAI MC", "HUB MC", "HURRAM ZAI MC",
"JAND MC", "JIWANI MC", "KABAL MC", "KALAT MC", "KALLAR SYEDAN MC", "KAMBAR MC", "KARAK MC", "KAROR LAL ESAN MC",
"KHALABAT MC", "KHANGARH MC", "KHANOZAI MC", "KHANQAH DOGRAN MC", "KHARAN MC", "KHARIAN MC", "KHAWAZA KHELA MC", "KHURIANWALA MC",
"KILLA ABDULLAH MC", "KILLA SAIFULLAH MC", "KOHAT MC", "KOHLU MC", "KOT ABDUL MALIK MC", "KULACHI MC", "KUNJAH MC",
"LAKKI MARWAT MC", "LORALAI MC", "MACH MC", "MALAKWAL MC", "MAMU KANJAN MC", "MANDI BAHAUDDIN MC", "MANSEHRA MC", "MASTUNG MC",
"MATTA MC", "MINGORA MC", "MUSAKHEL MC", "MUZAFFARGARH MC", "NAL MC", "NARANG MANDI MC", "NUSHKI MC", "ORMARA MC",
"PAHARPUR MC", "PASNI MC", "PROA MC", "QASIMABAD MC", "SAFDARABAD MC", "SAMMUNDRI MC", "SARAI ALAMGIR MC", "SARANAN MC", "SHAHRIG MC",
"SHARQPUR MC", "SIBI MC", "SOHBATPUR MC", "SUI MC", "SURAB MC", "TAKHT BHAI MC", "TALL MC", "TANK MC", "TASP MC", "TAUNSA MC",
"THUL MC", "TIMARGARA MC", "TUMP MC", "UTHAL MC", "WADH MC", "WASHUK MC", "WINDER MC", "ZEHRI MC", "ZIARAT MC",
"ATTOCK CANTONMENT", "KAMRA CANTONMENT", "SANJWAL CANTONMENT", "DERA GHAZI KHAN MUNICIPAL CORPORATION", "GUJRAT MUNICIPAL CORPORATION", "DINGA MC",
"KHARIAN CANTONMENT", "HYDERABAD CANTONMENT (PART OF HYDERABAD CITY TALUKA)", "HYDERABAD MUNICIPAL CORPORATION (PART OF HYDERABAD CITY TALUKA)",
"HYDERABAD CANTONMENT (PART OF LATIFABAD TALUKA)", "HYDERABAD MUNICIPAL CORPORATION (PART OF LATIFABAD TALUKA)",
"HYDERABAD CANTONMENT (PART OF QASIMABAD TALUKA)", "ISLAMABAD METROPOLITAN CORPORATION", "GARHI KHAIRO TC", "MIRPUR BURRIRO TC",
"GULBERG SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF GULBERG SUB-DIVISION)", "LIAQUATABAD SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF LIAQUATABAD SUB-DIVISION)", "NAZIMABAD SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NAZIMABAD SUB-DIVISION)", "NEW KARACHI SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NEW KARACHI SUB-DIVISION)", "NORTH NAZIMABAD SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NORTH NAZIMABAD SUB-DIVISION)", "FEROZABAD SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF FEROZABAD SUB-DIVISION)", "GULSHAN-E-IQBAL SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF GULSHAN-E-IQBAL SUB-DIVISION)",
"FAISAL CANTONMENT (PART OF GULSHAN-E-IQBAL SUB-DIVISION)", "GULZAR-E-HIJRI SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF GULZAR-E-HIJRI SUB-DIVISION)",
"MALIR CANTONMENT (PART OF GULZAR-E-HIJRI SUB-DIVISION)", "JAMSHED QUARTERS SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF JAMSHED QUARTERS SUB-DIVISION)",
"KARACHI CANTONMENT (PART OF JAMSHED QUARTERS SUB-DIVISION)",
"ARAM BAGH SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF ARAM BAGH SUB-DIVISION)", "CIVIL LINES SUB-DIVISION",
"CLIFTON CANTONMENT (PART OF CIVIL LINES SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF CIVIL LINES SUB-DIVISION)",
"KARACHI CANTONMENT (PART OF CIVIL LINES SUB-DIVISION)", "GARDEN SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF GARDEN SUB-DIVISION)",
"LYARI SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF LYARI SUB-DIVISION)", "SADDAR SUB-DIVISION", "CLIFTON CANTONMENT (PART OF SADDAR SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF SADDAR SUB-DIVISION)", "KARACHI CANTONMENT (PART OF SADAR SUB-DIVISION)", "BALDIA SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF BALDIA SUB-DIVISION)", "HARBOUR SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF HARBOUR SUB-DIVISION)",
"MANORA CANTONMENT (PART OF HARBOUR SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF MANGHOPIR)", "DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF MAURIPUR SUB-DIVISION)",
"MOMINABAD SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF MOMINABAD SUB-DIVISION)", "ORANGI SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF ORANGI SUB-DIVISION)", "SITE SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION DISTRICT WEST (PART OF S.I.T.E. SUB-DIVISION)",
"KHUZDAR MUNICIPAL CORPORATION", "JAMRUD TC", "LANDI KOTAL TC", "CHAMAN MUNICIPAL CORPORATION", "KOHAT CANTONMENT", "LACHI TC", "SHAKARDARA TC", "KORANGI SUB-DIVISION",
"CLIFTON CANTONMENT (PART OF KORANGI SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF KORANGI SUB-DIVISION)", "KORANGI CREEK", "LANDHI SUB-DIVISION",
"DISTRICT MUNICIPAL CORPORATION KORANGI (PART LANDHI SUB-DIVISION)", "MODEL COLONY SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF MODEL COLONY SUB-DIVISION)",
"SHAH FAISAL SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF SHAH FAISAL SUB-DIVISION)", "FAISAL CANTONMENT (PART OF SHAH FAISAL SUB-DIVISION)",
"SADDA TC", "PARACHINAR TC", "LAHORE CANTONMENT", "LAHORE METROPOLITAN CORPORATION (PART OF LAHORE CANTONMENT TEHSIL)", "WALTON CANTONMENT",
"LAHORE METROPOLITAN CORPORATION (PART OF LAHORE CITY TEHSIL)", "LAHORE METROPOLITAN CORPORATION (PART OF MODEL TOWN TEHSIL)", "LAHORE METROPOLITAN CORPORATION (PART OF RAIWIND TEHSIL)",
"LAHORE METROPOLITAN CORPORATION (PART OF SHALIMAR TEHSIL)", "DUKI MC", "SWAT RANI ZAI SUB-DIVISION", "AIRPORT SUB-DIVISION", "DISTRICT MUNICIPAL CORPORATION MALIR (PART OF AIRPORT SUB-DIVISION)",
"FAISAL CANTONMENT (PART OF AIRPORT SUB-DIVISION)", "MALIR CANTONMENT (PART OF AIRPORT SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION MALIR (PART OF IBRAHIM HYDRI SUB-DIVISION)",
"KORANGI CREEK CANTONMENT (PART OF IBRAHIM HYDRI SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION MALIR (PART OF MURAD MEMON SUB-DIVISION)",
"MALIR CANTONMENT (PART OF MURAD MEMON SUB-DIVISION)", "BAFFA TC", "MARDAN CANTONMENT", "TAKHT BHAI MC", "MIRAN SHAH TC", "PESHAWAR CANTONMENT", "PESHAWAR MUNICIPAL CORPORATION",
"SUKKUR MUNICIPAL CORPORATION (PART OF NEW SUKKUR TALUKA)", "PANO AQIL CANTONMENT", "SUKKUR MUNICIPAL CORPORATION (PART OF SUKKUR CITY TALUKA)", "DIR TC",
"SAZEEN U.C", "SIGLO U.C", "KUZPARO U.C", "MADA KHEL U.C", "CHAWADARA U.C", "BAN KHAD U.C", "JANDWALA PC",
"DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF FEROZABAD SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF GULSHAN-E-IQBAL SUB-DIVISION)",
"FAISAL CANTONMENT (PART OF GULSHAN-E-IQBAL SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KARACHI EAST (PART OF JAMSHED QUARTERS)",
"DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF ARAM BAGH SUB-DIVISION)", "CLIFTON CANTONMENT (PART OF CIVIL LINES SUB-DIVISION)",
"KARACHI CANTONMENT (PART OF CIVIL LINES SUB-DIVISION)", "DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF GARDEN SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF LYARI SUB-DIVISION)", "CLIFTON CANTONMENT (PART OF SADDAR SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI SOUTH (PART OF SADDAR SUB-DIVISION)", "KARACHI CANTONMENT (PART OF SADAR SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION MALIR (PART OF AIRPORT SUB-DIVISION)", "FAISAL CANTONMENT (PART OF AIRPORT SUB-DIVISION)",
"LUDHEWALA WARAICH MC", "QILA DIDAR SINGH MC", "GUJRANWALA CANTONMENT", "GUJRANWALA MUNICIPAL CORPORATION", "NOWSHERA VIRKAN MC",
"LARKANA MUNICIPAL CORPORATION", "AMANGARH TC", "CHERAT CANTONMENT", "NOWSHERA CANTONMENT", "RISALPUR CANTONMENT",
"LILLIANI MC", "SARGODHA CANTONMENT", "SARGODHA MUNICIPAL CORPORATION", "SUKKUR MUNICIPAL CORPORATION (PART OF NEW SUKKUR TALUKA)",
"SUKKUR MUNICIPAL CORPORATION (PART OF SUKKUR CITY TALUKA)", "COL. SHER KILLI/NAWAN KILLI TC",
"ABBOTTABAD MC", "AGRA TC", "AHMADPUR SIAL MC", "BAHAWALPUR CANTONMENT", "BAHAWALPUR MUNICIPAL CORPORATION", "BANNU MC",
"CHAKLALA CANTONMENT", "CHAWINDA TC", "CHOA SAIDAN SHAH MC", "CHUNIAN MC", "DARYA KHAN MARRI TC", "DHONKAL MC", "DIJKOT MC",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF LIAQUATABAD SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NAZIMABAD SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NEW KARACHI SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI CENTRAL (PART OF NORTH NAZIMABAD SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF MANGHOPIR SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KARACHI WEST (PART OF S.I.T.E SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF LANDHI SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF MODEL COLONY SUB-DIVISION)",
"DISTRICT MUNICIPAL CORPORATION KORANGI (PART OF SHAH FAISAL SUB-DIVISION)", "DOABA TC", "DONGA BONGA MC", "DUREJI MC",
"FAISALABAD MUNICIPAL CORPORATION", "FAZALPUR MC", "FORT ABBAS MC", "GARH MAHARAJA MC", "HAVELIAN MC",
"HYDERABAD MUNICIPAL CORPORATION (PART OF HYDERABAD CITY TALUKA)", "JALALPUR BHATTIAN MC", "JHELUM CANTONMENT", "JHELUM MC",
"KALEKEY TC", "KAMALIA MC", "KANGANPUR MC", "KHADIAN MC", "KHAIR PUR NATHAN SHAH MC", "KHEWRA MC", "KINGRI (PIRJO GOTH) MC",
"KOT MITHAN MC", "KOT RADHA KISHAN MC", "KOT SAMABA MC", "LAHORE METROPOLITAN CORPORATION (PART OF RAIWIND TEHSIL)", "LIAQATABAD MC",
"LIAQUATPUR MC", "MANGLA CANTONMENT", "MANORA CANTONMENT (PART OF HARBOUR SUB-DIVISION)", "MITHI MC", "MULTAN MUNICIPAL CORPORATION",
"MURREE HILLS CANTONMENT", "MURREE MUNICIPAL CORPORATION", "MUSLIM BAGH MC", "MUSTAFABAD MC", "NASIRPUR TC", "NAURANG TC",
"NAWAN SHEHR TC", "NEW SAEEDABAD TC", "NOORPUR MC", "ODERO LAL STATION TC", "PANYALA TC", "PHOOL NAGAR MC", "PIND DADAN KHAN MC",
"PINDI BHATTIAN MC", "PIR MAHAL MC", "PISHIN MUNICIPAL CORPORATION", "QUETTA METROPOLITAN CORPORATION", "RAJA JANG MC", "RAJANPUR MC",
"RAWALPINDI CANTONMENT", "RAWALPINDI MUNICIPAL CORPORATION", "ROJHAN MC", "SAHIWAL MUNICIPAL CORPORATION", "SHAHKOT MC",
"SHORKOT MC", "SIALKOT CANTONMENT", "SIALKOT MUNICIPAL CORPORATION", "SOBHO DERO TC", "SOHAWA MC", "SUKHEKE MC", "TANDO BAGO MC",
"TAXILA CANTONMENT", "THARI MOHABAT TC", "THERHI-I TC", "TRINDA SAWAI KHAN MC", "TULAMBA MC", "TURBAT MUNICIPAL CORPORATION",
"UCH SHARIF MC", "USTA MUHAMMAD MC", "WAH CANTONMENT", "WARBURTON MC", "ZAHIRPIR MC", "ZHOB MC",
"KARACHI CANTONMENT (PART OF SADDAR SUB-DIVISION)", "KORANGI CREEK CANTONMENT (PART OF KORANGI SUB-DIVISION)",
"NILI PC"
)
# iterate through all district subfolders to extract data from available pdfs
for(d in 1:length(district_subdirs)){
# get the list of files in the district subdirectory
table_files <- list.files(path = paste0("./district_tables_raw/", district_subdirs[d], "/"))
table_count <- str_sub(table_files, 4, 5)
missing_tables <- table_numbers[!(table_numbers %in% table_count)]
district_name <- district_subdirs[d]
district_number <- str_sub(table_files[1], 1, 3)
# Process Table 1 ---
# make sure the pdf is present before proceeding, if not add it to the missing tables log
if("01" %in% missing_tables){
missing_files <- rbind(missing_files,
tibble(district_number = district_number, district_name = district_name, missing_table = "01.pdf"))
} else {
# load the pdf file
target <- paste0("./district_tables_raw/", district_name, "/", district_number, "01.pdf")
pdf_import <- pdf_text(target)
pdf_text <- toString(pdf_import)
pdf_text <- read_lines(pdf_text)
pdf_text <- gsub("(?<=\\d)\\s(?=\\d)", " ", pdf_text, perl = T)
pdf_text <- gsub("KASHMORE", "KASHMOR", pdf_text)
if(d == 2){
pdf_text[18] <- "RURAL 1,395,470 688,077 707,315 78 97.28 6.08 1,003,843 1.75"
pdf_text[19] <- "URBAN 490,908 250,573 240,282 53 104.28 6.13 271,092 3.17"
}
if(d == 26){
pdf_text[13] <- "TRIBAL AREA ADJ. LAKKI MARWAT DISTRICT 132 26,394 13,685 12,709 - 107.68 199.95 - 7.84 6,987 7.23"
pdf_text[14:15] <- ""
pdf_text <- pdf_text[pdf_text != ""]
}
if(d == 65){
pdf_text[15] <- "RURAL 784711 424643 360055 13 117.94 - - 7.84 472570 2.70"
pdf_text[19] <- "DASSU SUB-DIVISION - 223436 121177 102259 - 118.50 - - 8.28 137519 2.58"
pdf_text[20] <- "RURAL 223436 121177 102259 - 118.50 - - 8.28 137519 2.58"
pdf_text[24] <- "KANDIA SUB-DIVISION - 83850 45597 38245 8 119.22 - - 7.74 47227 3.06"
pdf_text[29] <- "PALAS SUB-DIVISION - 274923 149104 125814 5 118.51 - - 7.64 165613 2.70"
pdf_text[34] <- "PATTAN SUB-DIVISION - 202502 108765 93737 0 116.03 - - 7.70 122211 2.69"
}
if(d == 99){
pdf_text <- pdf_text[1:27]
}
if(d == 118){
pdf_text[15] <- ""
pdf_text[16] <- "SOUTH WAZIRISTAN AGENCY 6,620 675,215 355,611 319,554 50 111.28 102.00 - 7.98 429,841 2.4"
}
# remove headers and footers from document
header_end <- as.integer(grep(district_name, pdf_text)) - 1
pdf_trimmed <- str_to_upper(pdf_text[- c(1:header_end)])
pdf_trimmed <- pdf_trimmed[pdf_trimmed != ""]
# find the breaks for each administrative area - each is a total, rural, and urban row
area_start <- as.integer(grep("RURAL", pdf_trimmed) - 1)
area_end <- as.integer(grep("RURAL", pdf_trimmed) + 1)
# break down each administrative area
table_01 <- tibble()
for(k in 1:length(area_start)){
row_extract <- pdf_trimmed[area_start[k]:area_end[k]]
row_total <- strsplit(trimws(row_extract[1]), "\\s{2,}")
if(d == 37 & k %in% c(4,5)){
row_total <- list(c(row_total[[1]][1:9], "-", row_total[[1]][10:11]))
}
if(d == 55 & k %in% c(2)){
row_total <- list(c(row_total[[1]][1:8], "-", row_total[[1]][9:11]))
}
row_out <- tibble(
area_name = row_total[[1]][1],
area_type = "TOTAL",
area_sq_km = row_total[[1]][2],
total_pop = row_total[[1]][3],
total_male = row_total[[1]][4],
total_female = row_total[[1]][5],
total_trans = row_total[[1]][6],
sex_ratio = row_total[[1]][7],
pop_density = row_total[[1]][8],
pct_urban = row_total[[1]][9],
avg_hh_size = row_total[[1]][10],
total_pop_98 = row_total[[1]][11],
avg_annual_growth = row_total[[1]][12]
)
row_rural <- strsplit(trimws(row_extract[2]), "\\s{2,}")
# try to find the positions of the sex ratio, hh size and growth rate to ensure columns land correctly
# Lahore correction for change to rural area designations
if(d == 69){
sr_pos <- NA
hh_pos <- NA
gr_pos <- NA
} else {
sr_pos <- ifelse(any(grepl("\\.", row_rural[[1]])),
grep("\\.", row_rural[[1]])[[1]],
NA)
hh_pos <- ifelse(any(grepl("\\.", row_rural[[1]])),
grep("\\.", row_rural[[1]])[[2]],
NA)
gr_pos <- ifelse(any(grepl("\\.", row_rural[[1]])),
grep("\\.", row_rural[[1]])[[3]],
NA)
}
rural_out <- tibble(
area_name = row_total[[1]][1],
area_type = "RURAL",
area_sq_km = NA,
total_pop = row_rural[[1]][2],
total_male = row_rural[[1]][3],
total_female = row_rural[[1]][4],
total_trans = row_rural[[1]][5],
sex_ratio = ifelse(!is.na(sr_pos), row_rural[[1]][sr_pos], NA),
pop_density = NA,
pct_urban = NA,
avg_hh_size = ifelse(!is.na(hh_pos), row_rural[[1]][hh_pos], NA),
total_pop_98 = ifelse(d == 69,
row_rural[[1]][8],
ifelse(!is.na(gr_pos), row_rural[[1]][gr_pos - 1], NA)),
avg_annual_growth = ifelse(d == 69,
row_rural[[1]][9],
ifelse(!is.na(gr_pos), row_rural[[1]][gr_pos], NA))
)
row_urban <- strsplit(trimws(row_extract[3]), "\\s{2,}")
row_urban <- gsub("0\\.00", "-", row_urban[[1]])
sr_pos <- ifelse(any(grepl("\\.", row_urban)),
grep("\\.", row_urban)[[1]],
NA)
hh_pos <- ifelse(any(grepl("\\.", row_urban)),
grep("\\.", row_urban)[[2]],
NA)
gr_pos <- ifelse(any(grepl("\\.", row_urban)),
ifelse(length(grep("\\.", row_urban)) == 3,
grep("\\.", row_urban)[[3]], NA),
NA)
urban_out <- tibble(
area_name = row_total[[1]][1],
area_type = "URBAN",
area_sq_km = NA,
total_pop = row_urban[2],
total_male = row_urban[3],
total_female = row_urban[4],
total_trans = row_urban[5],
sex_ratio = ifelse(!is.na(sr_pos), row_urban[sr_pos], NA),
pop_density = NA,
pct_urban = NA,
avg_hh_size = ifelse(!is.na(hh_pos), row_urban[hh_pos], NA),
total_pop_98 = ifelse(!is.na(gr_pos), row_urban[gr_pos - 1], NA),
avg_annual_growth = ifelse(!is.na(gr_pos), row_urban[gr_pos], NA)
)
row_out <- rbind(row_out, rural_out) %>%
rbind(urban_out)
table_01 <- rbind(table_01, row_out)
}
# cleanup numerics
table_01 <- cbind(table_01 %>% dplyr::select(1:2),
table_01 %>% dplyr::select(3:13) %>%
mutate_all(funs(gsub(",", "", .))) %>%
mutate_all(as.numeric)
)
table_01 <- table_01 %>%
mutate(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name,
everything())
prov_path <- paste0("./processed_forms/", unique(table_01$province_name), "/")
# create the appropriate province subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(prov_path)), dir.create(file.path(prov_path)), FALSE)
dist_path <- paste0(prov_path, paste0(district_number, " - ", district_name, "/"))
# create the appropriate district subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(dist_path)), dir.create(file.path(dist_path)), FALSE)
# write table data to a csv copy
write_csv(table_01, paste0(dist_path, "table_01.csv", na = ""))
# write table data to a national aggregate table
natl_table_01 <- rbind(natl_table_01, table_01)
} # end else
# Process Table 2, Urban Localities ---
if("02" %in% missing_tables){
missing_files <- rbind(missing_files,
tibble(district_number = district_number, district_name = district_name, missing_table = "02.pdf"))
} else {
# load the pdf file
target <- paste0("./district_tables_raw/", district_name, "/", district_number, "02.pdf")
pdf_import <- pdf_text(target)
pdf_text <- toString(pdf_import)
pdf_text <- read_lines(pdf_text)
pdf_text <- gsub("(?<=\\d)\\s(?=\\d)", " ", pdf_text, perl = T)
pdf_text <- gsub("KASHMORE", "KASHMOR", pdf_text)
pdf_text <- gsub("TURBAT MUNICIPAL CORPORATION KECH", "TURBAT MUNICIPAL CORPORATION KECH", pdf_text)
pdf_text <- gsub("100,000 - 199,999", "100,000 - 199,999", pdf_text)
if(d == 18){
pdf_text[10] <- "DADU DISTRICT"
}
if(d == 21){
pdf_text[19] <- "DERA ISMAIL KHAN CANTONMENT DERA ISMAIL KHAN TEHSIL 5,694 3,519 2,175 - 5,145 0.53 5.20"
pdf_text <- pdf_text[1:19]
}
if(d == 22){
pdf_text[16] <- ""
pdf_text[pdf_text != ""]
}
if(d == 38){
pdf_text[13] <- "ISLAMABAD METROPOLITAN CORPORATION ISLAMABAD TEHSIL 1,009,003 535,605 473,242 156 529,180 3.45 5.78"
pdf_text <- pdf_text [1:13]
}
if(d == 48){
pdf_text[9] <- "KARACHI CENTRAL DISTRICT"
}
if(d == 49){
pdf_text[8] <- "KARACHI EAST DISTRICT"
}
if(d == 50){
pdf_text[8] <- "KARACHI SOUTH DISTRICT"
}
if(d == 52){
pdf_text[8] <- "KARAK DISTRICT"
}
if(d == 59){
pdf_text[11] <- "KHUSHAB DISTRICT"
pdf_text <- gsub("RATE", "", pdf_text)
}
if(d == 69){
pdf_text[10] <- "LAHORE DISTRICT"
}
if(d == 71){
pdf_text[9] <- "LARKANA DISTRICT"
}
if(d == 86){
pdf_text[9] <- ""
}
if(d == 120){
pdf_text <- gsub("SUKKUR MUNICIPAL CORPORATION ", "SUKKUR MUNICIPAL CORPORATION ", pdf_text)
}
if(d == 133){
pdf_text[11] <- "WASHUK MC WASHUK SUB-TEHSIL 21,835 11,407 10,428 - - - 5.45"
}
if(d %in% c(28, 65)){
table_02 <- tibble(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name) %>%
mutate(
area_name = NA, locality_name = NA, locality_bucket = NA, pop_98 = NA, avg_annual_growth_98_17 = NA, avg_hh_size = NA, gender = NA, total_population = NA
)
natl_table_02 <- rbind(natl_table_02, table_02)
} else {
if(!(any(grepl(district_name, pdf_text)))){
table_02 <- tibble(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name) %>%
mutate(
area_name = NA, locality_name = NA, locality_bucket = NA, pop_98 = NA, avg_annual_growth_98_17 = NA, avg_hh_size = NA, gender = NA, total_population = NA
)
natl_table_02 <- rbind(natl_table_02, table_02)
} else {
# remove headers and footers from document
header_end <- as.integer(grep(district_name, pdf_text)) - 1
pdf_trimmed <- str_to_upper(pdf_text[- c(1:header_end)])
pdf_trimmed <- pdf_trimmed[pdf_trimmed != ""]
locality_sizes <- c("500,000 AND ABOVE", "200,000 - 499,999", "100,000 - 199,999", "100,000 - 199,999",
"50,000 - 99,999", "25,000 - 49,999", "10,000 - 24,999", "5,000 - 9,999", "BELOW 5,000")
gender_types <- c("ALL SEXES", "MALE", "FEMALE", "TRANSGENDER")
locality_buckets <- unlist(str_split(trimws(pdf_trimmed), "\\s{2,}"))[unlist(str_split(trimws(pdf_trimmed), "\\s{2,}")) %in% locality_sizes]
table_02 <- tibble()
for(k in 1:length(locality_buckets)){
total_out <- tibble()
bucket_start <- as.integer(grep(locality_buckets[k], pdf_trimmed)) + 1
bucket_end <- ifelse(k != length(locality_buckets), (as.integer(grep(locality_buckets[k+1], pdf_trimmed)-1)), length(pdf_trimmed))
bucket_extract <- pdf_trimmed[bucket_start:bucket_end]
bucket_split <- strsplit(trimws(bucket_extract), "\\s{2,}")
bucket_split <- bucket_split[lengths(bucket_split) > 0L]
for(c in 1:length(bucket_split)){
for(g in 1:length(gender_types)){
row_out <- tibble(
district_name = district_name,
area_name = bucket_split[[c]][2],
locality_name = bucket_split[[c]][1],
locality_bucket = locality_buckets[k],
pop_98 = ifelse(length(bucket_split[[c]]) == 7, NA, bucket_split[[c]][7]), # if 98 pop data is ommitted
avg_annual_growth_98_17 = ifelse(length(bucket_split[[c]]) == 7, NA, bucket_split[[c]][8]),
avg_hh_size = ifelse(length(bucket_split[[c]]) == 7, bucket_split[[c]][7], bucket_split[[c]][9]),
gender = gender_types[g],
total_population = bucket_split[[c]][g+2]
)
total_out <- rbind(total_out, row_out)
}
}
table_02 <- rbind(table_02, total_out)
}
# cleanup numerics
table_02 <- cbind(
table_02 %>% dplyr::select(1:4),
table_02 %>% dplyr::select(pop_98, avg_annual_growth_98_17, avg_hh_size) %>%
mutate_all(funs(gsub(",", "", .))) %>%
mutate_all(as.numeric),
table_02 %>% dplyr::select(gender),
table_02 %>% dplyr::select(c(total_population)) %>%
mutate_all(funs(gsub(",", "", .))) %>%
mutate_all(as.numeric)
)
# Convert NA values to 0 counts
table_02$total_population[is.na(table_02$total_population)] <- 0
table_02 <- table_02 %>%
mutate(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name,
everything())
if(d %in% c(48, 49, 50, 51, 67, 78)){
table_02$locality_name <- gsub("DISTRICT MUNICIPAL CORPORATION", paste0("DISTRICT MUNICIPAL CORPORATION ", district_name), table_02$locality_name)
}
table_02$locality_name <- gsub("LAHORE METROPOLITAN CORPORATIO", "LAHORE METROPOLITAN CORPORATION", table_02$locality_name)
prov_path <- paste0("./processed_forms/", unique(table_02$province_name), "/")
# create the appropriate province subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(prov_path)), dir.create(file.path(prov_path)), FALSE)
dist_path <- paste0(prov_path, paste0(district_number, " - ", district_name, "/"))
# create the appropriate district subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(dist_path)), dir.create(file.path(dist_path)), FALSE)
# write table data to a csv copy
write_csv(table_02, paste0(dist_path, "table_02.csv", na = ""))
# write table data to a national aggregate table
natl_table_02 <- rbind(natl_table_02, table_02)
}
} # end else
} # end else
# Process Table 3, Rural Localities ---
if("03" %in% missing_tables){
missing_files <- rbind(missing_files,
tibble(district_number = district_number, district_name = district_name, missing_table = "03.pdf"))
} else {
# load the pdf file
target <- paste0("./district_tables_raw/", district_name, "/", district_number, "03.pdf")
pdf_import <- pdf_text(target)
pdf_text <- toString(pdf_import)
pdf_text <- read_lines(pdf_text)
if(d == 65){
pdf_text[9] <- "KOHISTAN DISTRICT 1495 784711 424643 360055 13"
pdf_text[18] <- "DASSU SUB-DIVISION 318 223436 121177 102259 -"
pdf_text[27] <- "KANDIA SUB-DIVISION 194 83850 45597 38245 8"
pdf_text[36] <- "PALAS SUB-DIVISION 549 274923 149104 125814 5"
pdf_text[45] <- "PATTAN SUB-DIVISION 434 202502 108765 93737 0"
}
if(d == 113){
pdf_text[8] <- "SHERANI DISTRICT"
pdf_text[9] <- "5,000 AND ABOVE 181 152,952 84,390 68,561 1"
pdf_text[15] <- "SHERANI SUB-DIVISION"
pdf_text[16] <- "5,000 AND ABOVE 181 152,952 84,390 68,561 1"
pdf_text <- c(pdf_text[1:14], "UN-INHABITED 4 - - - -", pdf_text[15:22])
}
# for cases where there are no rural localities
if(!(any(grepl(district_name, pdf_text)))){
table_03 <- tibble(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name) %>%
mutate(
area_name = NA, locality_size = NA, locality_count = NA, gender = NA, total_population = NA
)
natl_table_03 <- rbind(natl_table_03, table_03)
} else {
# remove headers and footers from document
header_end <- as.integer(grep(district_name, pdf_text)) - 1
pdf_trimmed <- str_to_upper(pdf_text[- c(1:header_end)])
pdf_trimmed <- gsub("5000 AND ABOVE", "5,000 AND ABOVE", pdf_trimmed)
pdf_trimmed <- gsub("(?<=\\d)\\s(?=\\d)", " ", pdf_trimmed, perl = T)
pdf_trimmed <- pdf_trimmed[pdf_trimmed != ""]
# find the breaks for each administrative area
area_start <- as.integer(grep("5,000 AND ABOVE", pdf_trimmed) - 1)
area_end <- as.integer(grep("UN-INHABITED", pdf_trimmed))
locality_sizes <- c("TOTAL", "5,000 AND ABOVE", "2,000 - 4,999", "1,000 - 1,999", "500 - 999", "200 - 499", "LESS THAN 200", "UN-INHABITED")
gender_types <- c("ALL SEXES", "MALE", "FEMALE", "TRANSGENDER")
table_03 <- tibble()
for(k in 1:length(area_start)){
area_extract <- pdf_trimmed[area_start[k]:area_end[k]]
area_split <- strsplit(trimws(area_extract), "\\s{2,}")
total_out <- tibble()
for(c in 1:length(locality_sizes)){
for(g in 1:length(gender_types)){
row_out <- tibble(
area_name = area_split[[1]][1],
locality_size = ifelse(c == 1, "TOTAL", area_split[[c]][1]),
locality_count = area_split[[c]][2],
gender = gender_types[g],
total_population = area_split[[c]][g+2]
)
total_out <- rbind(total_out, row_out)
}
}
table_03 <- rbind(table_03, total_out)
}
# cleanup numerics
table_03 <- cbind(table_03 %>% dplyr::select(1:4),
table_03 %>% dplyr::select(total_population) %>%
mutate_all(funs(gsub(",", "", .))) %>%
mutate_all(as.numeric)
)
# Convert NA values to 0 counts
table_03$total_population[is.na(table_03$total_population)] <- 0
table_03 <- table_03 %>%
mutate(
district_code = district_number,
district_name = district_name
) %>%
left_join(
all_codes
) %>%
dplyr::select(province_name, district_code, district_name,
everything())
prov_path <- paste0("./processed_forms/", unique(table_03$province_name), "/")
# create the appropriate province subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(prov_path)), dir.create(file.path(prov_path)), FALSE)
dist_path <- paste0(prov_path, paste0(district_number, " - ", district_name, "/"))
# create the appropriate district subdirectory if it doesn't already exist
ifelse(!dir.exists(file.path(dist_path)), dir.create(file.path(dist_path)), FALSE)
# write table data to a csv copy
write_csv(table_03, paste0(dist_path, "table_03.csv", na = ""))
# write table data to a national aggregate table
natl_table_03 <- rbind(natl_table_03, table_03)
}
} # end else
# Process Table 4, Age Distribution ---
if("04" %in% missing_tables){
missing_files <- rbind(missing_files,
tibble(district_number = district_number, district_name = district_name, missing_table = "04.pdf"))
} else {
# load the pdf file
target <- paste0("./district_tables_raw/", district_name, "/", district_number, "04.pdf")
pdf_import <- pdf_text(target)
pdf_text <- toString(pdf_import)
pdf_text <- read_lines(pdf_text)
if(d == 20){
pdf_text[102] <- "All Ages 212,652 - 103,213 10 212,652 109,429 103,213 10 - - - -"
pdf_text[109] <- "05 - 09 39,295 20,776 18,519 - 39,295 20,776 18,519 - - - - -"
}
if(d == 25){
pdf_text <- c(pdf_text[1:4], "FR KOHAT", pdf_text[5:192])
}
if(d == 65){
pdf_text <- gsub("ALL", "ALL AGES", pdf_text)
}
if(d == 88){
pdf_text[5] <- "MUSAKHEL DISTRICT"
}
if(d == 96){
pdf_text[6] <- "NUSHKI DISTRICT"
pdf_text[100] <- "All Ages 178,947 - - 3 - - - 3 46,396 24,281 22,115 -"
}
pdf_text <- gsub("KASHMORE", "KASHMOR", pdf_text)
# remove headers and footers from document
header_end <- as.integer(grep(district_name, pdf_text)) - 1
pdf_trimmed <- str_to_upper(pdf_text[- c(1:header_end)])
pdf_trimmed <- pdf_trimmed[pdf_trimmed != ""]
more_headers_starts <- grep("POPULATION BY SINGLE YEAR", pdf_trimmed)
if(length(more_headers_starts) == 0){
more_headers_starts <- grep("TOTAL\\s*RURAL\\s*URBAN", pdf_trimmed)}
if(length(more_headers_starts) > 0){
more_headers_ends <- grep("\\s{25,}12\\s{6,}13", pdf_trimmed)
if(length(more_headers_ends) == 0){
more_headers_ends <- grep("\\s*11\\s*12\\s*13", pdf_trimmed)
}
more_headers <- list()
for(j in 1:length(more_headers_starts)){
headers_out <- more_headers_starts[j]:more_headers_ends[j]
more_headers <- c(more_headers, headers_out)
}
more_headers <- unlist(more_headers)
pdf_trimmed <- pdf_trimmed[- more_headers]
} else {}
pdf_trimmed <- gsub("(?<=\\d)\\s(?=\\d)", " ", pdf_trimmed, perl = T)
# find the breaks for each administrative area
area_start <- as.integer(grep("ALL AGES", pdf_trimmed) - 1)
area_end <- as.integer(grep("75 & ABOVE", pdf_trimmed))
table_04 <- tibble()
# break down each administrative area
for(k in 1:length(area_start)){
row_extract <- pdf_trimmed[area_start[k]:area_end[k]]
row_split <- strsplit(trimws(row_extract), "\\s{2,}")
total_out <- tibble(
area_name = row_split[[1]][1],
area_type = "TOTAL",
gender = c("ALL", "MALE", "FEMALE", "TRANSGENDER"),
group_all_ages = row_split[[2]][2:5],
group_00_04 = row_split[[3]][2:5],
age_below_1 = row_split[[4]][2:5],
age_01 = row_split[[5]][2:5],
age_02 = row_split[[6]][2:5],
age_03 = row_split[[7]][2:5],
age_04 = row_split[[8]][2:5],
group_05_09 = row_split[[9]][2:5],
age_05 = row_split[[10]][2:5],
age_06 = row_split[[11]][2:5],
age_07 = row_split[[12]][2:5],
age_08 = row_split[[13]][2:5],
age_09 = row_split[[14]][2:5],
group_10_14 = row_split[[15]][2:5],
age_10 = row_split[[16]][2:5],
age_11 = row_split[[17]][2:5],
age_12 = row_split[[18]][2:5],
age_13 = row_split[[19]][2:5],
age_14 = row_split[[20]][2:5],
group_15_19 = row_split[[21]][2:5],
age_15 = row_split[[22]][2:5],
age_16 = row_split[[23]][2:5],
age_17 = row_split[[24]][2:5],
age_18 = row_split[[25]][2:5],
age_19 = row_split[[26]][2:5],
group_20_24 = row_split[[27]][2:5],
age_20 = row_split[[28]][2:5],
age_21 = row_split[[29]][2:5],
age_22 = row_split[[30]][2:5],
age_23 = row_split[[31]][2:5],
age_24 = row_split[[32]][2:5],
group_25_29 = row_split[[33]][2:5],
age_25 = row_split[[34]][2:5],
age_26 = row_split[[35]][2:5],
age_27 = row_split[[36]][2:5],
age_28 = row_split[[37]][2:5],
age_29 = row_split[[38]][2:5],
group_30_34 = row_split[[39]][2:5],
age_30 = row_split[[40]][2:5],
age_31 = row_split[[41]][2:5],
age_32 = row_split[[42]][2:5],
age_33 = row_split[[43]][2:5],
age_34 = row_split[[44]][2:5],
group_35_39 = row_split[[45]][2:5],
age_35 = row_split[[46]][2:5],
age_36 = row_split[[47]][2:5],
age_37 = row_split[[48]][2:5],
age_38 = row_split[[49]][2:5],
age_39 = row_split[[50]][2:5],
group_40_44 = row_split[[51]][2:5],
age_40 = row_split[[52]][2:5],
age_41 = row_split[[53]][2:5],
age_42 = row_split[[54]][2:5],
age_43 = row_split[[55]][2:5],
age_44 = row_split[[56]][2:5],
group_45_49 = row_split[[57]][2:5],
age_45 = row_split[[58]][2:5],
age_46 = row_split[[59]][2:5],
age_47 = row_split[[60]][2:5],
age_48 = row_split[[61]][2:5],
age_49 = row_split[[62]][2:5],
group_50_54 = row_split[[63]][2:5],
age_50 = row_split[[64]][2:5],
age_51 = row_split[[65]][2:5],
age_52 = row_split[[66]][2:5],
age_53 = row_split[[67]][2:5],
age_54 = row_split[[68]][2:5],
group_55_59 = row_split[[69]][2:5],
age_55 = row_split[[70]][2:5],
age_56 = row_split[[71]][2:5],
age_57 = row_split[[72]][2:5],
age_58 = row_split[[73]][2:5],
age_59 = row_split[[74]][2:5],
group_60_64 = row_split[[75]][2:5],
age_60 = row_split[[76]][2:5],
age_61 = row_split[[77]][2:5],
age_62 = row_split[[78]][2:5],
age_63 = row_split[[79]][2:5],
age_64 = row_split[[80]][2:5],
group_65_69 = row_split[[81]][2:5],
age_65 = row_split[[82]][2:5],
age_66 = row_split[[83]][2:5],
age_67 = row_split[[84]][2:5],
age_68 = row_split[[85]][2:5],
age_69 = row_split[[86]][2:5],
group_70_74 = row_split[[87]][2:5],
age_70 = row_split[[88]][2:5],
age_71 = row_split[[89]][2:5],
age_72 = row_split[[90]][2:5],
age_73 = row_split[[91]][2:5],
age_74 = row_split[[92]][2:5],
group_75_and_up = row_split[[93]][2:5]
)
rural_out <- tibble(
area_name = row_split[[1]][1],
area_type = "RURAL",
gender = c("ALL", "MALE", "FEMALE", "TRANSGENDER"),
group_all_ages = row_split[[2]][6:9],
group_00_04 = row_split[[3]][6:9],
age_below_1 = row_split[[4]][6:9],
age_01 = row_split[[5]][6:9],
age_02 = row_split[[6]][6:9],
age_03 = row_split[[7]][6:9],
age_04 = row_split[[8]][6:9],
group_05_09 = row_split[[9]][6:9],
age_05 = row_split[[10]][6:9],
age_06 = row_split[[11]][6:9],
age_07 = row_split[[12]][6:9],
age_08 = row_split[[13]][6:9],
age_09 = row_split[[14]][6:9],
group_10_14 = row_split[[15]][6:9],
age_10 = row_split[[16]][6:9],
age_11 = row_split[[17]][6:9],
age_12 = row_split[[18]][6:9],
age_13 = row_split[[19]][6:9],
age_14 = row_split[[20]][6:9],
group_15_19 = row_split[[21]][6:9],
age_15 = row_split[[22]][6:9],
age_16 = row_split[[23]][6:9],
age_17 = row_split[[24]][6:9],
age_18 = row_split[[25]][6:9],
age_19 = row_split[[26]][6:9],
group_20_24 = row_split[[27]][6:9],
age_20 = row_split[[28]][6:9],
age_21 = row_split[[29]][6:9],
age_22 = row_split[[30]][6:9],
age_23 = row_split[[31]][6:9],
age_24 = row_split[[32]][6:9],
group_25_29 = row_split[[33]][6:9],
age_25 = row_split[[34]][6:9],
age_26 = row_split[[35]][6:9],
age_27 = row_split[[36]][6:9],
age_28 = row_split[[37]][6:9],
age_29 = row_split[[38]][6:9],
group_30_34 = row_split[[39]][6:9],
age_30 = row_split[[40]][6:9],
age_31 = row_split[[41]][6:9],
age_32 = row_split[[42]][6:9],
age_33 = row_split[[43]][6:9],
age_34 = row_split[[44]][6:9],
group_35_39 = row_split[[45]][6:9],
age_35 = row_split[[46]][6:9],
age_36 = row_split[[47]][6:9],
age_37 = row_split[[48]][6:9],
age_38 = row_split[[49]][6:9],
age_39 = row_split[[50]][6:9],
group_40_44 = row_split[[51]][6:9],
age_40 = row_split[[52]][6:9],
age_41 = row_split[[53]][6:9],
age_42 = row_split[[54]][6:9],
age_43 = row_split[[55]][6:9],
age_44 = row_split[[56]][6:9],
group_45_49 = row_split[[57]][6:9],
age_45 = row_split[[58]][6:9],
age_46 = row_split[[59]][6:9],
age_47 = row_split[[60]][6:9],
age_48 = row_split[[61]][6:9],
age_49 = row_split[[62]][6:9],
group_50_54 = row_split[[63]][6:9],
age_50 = row_split[[64]][6:9],
age_51 = row_split[[65]][6:9],
age_52 = row_split[[66]][6:9],
age_53 = row_split[[67]][6:9],
age_54 = row_split[[68]][6:9],
group_55_59 = row_split[[69]][6:9],
age_55 = row_split[[70]][6:9],
age_56 = row_split[[71]][6:9],
age_57 = row_split[[72]][6:9],
age_58 = row_split[[73]][6:9],
age_59 = row_split[[74]][6:9],
group_60_64 = row_split[[75]][6:9],
age_60 = row_split[[76]][6:9],
age_61 = row_split[[77]][6:9],
age_62 = row_split[[78]][6:9],
age_63 = row_split[[79]][6:9],
age_64 = row_split[[80]][6:9],
group_65_69 = row_split[[81]][6:9],
age_65 = row_split[[82]][6:9],
age_66 = row_split[[83]][6:9],
age_67 = row_split[[84]][6:9],
age_68 = row_split[[85]][6:9],
age_69 = row_split[[86]][6:9],
group_70_74 = row_split[[87]][6:9],
age_70 = row_split[[88]][6:9],
age_71 = row_split[[89]][6:9],
age_72 = row_split[[90]][6:9],
age_73 = row_split[[91]][6:9],
age_74 = row_split[[92]][6:9],