DOL-ILAB SDC - SAP20152016_Rural_NOPII
Pablo Diego-Rosell, PhD
2021-08-30
- Setup filenames
- Setup data, functions and create dictionary for dataset review
- Direct PII: variables to be removed
- Direct PII-team: Encode field team names
- Small locations: Encode locations with pop <100,000 using random large numbers
- Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
- Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
- Matching and crosstabulations: Run automated PII check
- Open-ends: review responses for any sensitive information, redact as necessary
- GPS data: Displace
- Save processed data in Stata and SPSS format
rm(list=ls(all=t))Setup filenames
filename <- "SAP20152016_Rural_NOPII" # !!!Update filename
functions_vers <- "functions_1.7.R" # !!!Update helper functions fileSetup data, functions and create dictionary for dataset review
source (functions_vers)Visually inspect variables in "dictionary.csv" and flag for risk, using the following flags:
# Direct PII: Respondent Names, Addresses, Identification Numbers, Phone Numbers
# Direct PII-team: Interviewer Names, other field team names
# Indirect PII-ordinal: Date of birth, Age, income, education, household composition.
# Indirect PII-categorical: Gender, education, ethnicity, nationality,
# occupation, employer, head of household, marital status
# GPS: Longitude, Latitude
# Small Location: Location (<100,000)
# Large Location (>100,000)
# Weight: weightVar
# Household ID: hhId,
# Open-ends: Review responses for any sensitive information, redact as necessary Direct PII: variables to be removed
# !!!Include any Direct PII variables
dropvars <- c("A_NOM",
"C_NOM",
"A_APEPAT",
"C_APEPAT",
"A_APEMAT",
"C_APEMAT",
"DNI_2015",
"FIRMA_2015",
"dni_2015",
"J_DNI",
"L_DNI",
"FIRMA_2016",
"dni_2016",
"ubigeo_2016",
"nombre_ie_2016")
mydata <- mydata[!names(mydata) %in% dropvars]Direct PII-team: Encode field team names
# !!!Replace vector in "variables" field below with relevant variable names
mydata <- encode_direct_PII_team (variables=c("ENCUES_2015", "ENCUES_2016"))## [1] "Frequency table before encoding"
## ENCUES_2015.
## 3 4 5 10 16 20 22 30 34 40 42 43 44 50 60 70 <NA>
## 52 136 33 523 1 722 1 648 1 492 3 16 15 682 257 270 1255
## [1] "Frequency table after encoding"
## ENCUES_2015.
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 <NA>
## 52 136 33 523 1 722 1 648 1 492 3 16 15 682 257 270 1255
## [1] "Frequency table before encoding"
## ENCUES_2016. C<f3>digo del Encuestador
## Missing-MINEDU No indica <NA>
## 3897 124 1086
## [1] "Frequency table after encoding"
## ENCUES_2016. C<f3>digo del Encuestador
## 1 <NA>
## 3897 1210mydata <- mydata[!names(mydata) %in% "DIGITA"] Small locations: Encode locations with pop <100,000 using random large numbers
# !!!Include relevant variables, but check their population size first to confirm they are <100,000
mydata <- mydata[!names(mydata) %in% "NOMESC"]
locvars <- c("CODLOC",
"CODMOD_2015",
"Escuela",
"cod_local_2016",
"codlocal_2016",
"Escuela_2016",
"COD_MOD_2015",
"COD_MOD_2016")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## CODLOC.
## 68518 68523 68599 68603 68655 68735 68900 68924 68938 68957 68962 68976
## 1 7 21 9 8 6 10 8 6 17 7 6
## 69103 69546 69551 69985 70007 70026 70031 70074 70088 70111 70149 71059
## 5 1 3 28 8 2 2 7 5 7 1 3
## 71115 71506 71733 71790 71926 71931 72087 73181 73195 73303 73322 73341
## 3 1 15 6 4 2 4 15 18 13 11 9
## 73398 73435 73440 73459 73510 73529 73548 73553 73567 73572 73591 73609
## 29 9 3 6 4 7 13 14 12 11 15 12
## 73685 73794 73888 130308 142655 147484 147709 147714 148520 150122 150136 150141
## 2 4 2 31 43 12 13 6 12 22 9 4
## 150202 150221 150259 150532 150551 150565 150570 150607 150612 150631 150754 150768
## 15 7 1 37 2 20 18 11 16 11 19 20
## 150773 150792 150834 150848 150966 150971 150985 151027 151188 151193 151206 151640
## 20 22 8 104 41 42 16 23 43 27 3 16
## 151664 152215 152239 152263 152588 152593 152606 152625 152734 152753 153818 153823
## 6 22 34 14 43 38 34 24 45 48 38 40
## 153837 153842 153861 153875 153880 153899 153903 153922 153941 154021 154035 154064
## 7 45 4 23 12 15 17 6 11 15 23 13
## 154078 154083 154097 154200 154238 155054 157010 157053 157072 157190 157227 157487
## 10 20 8 7 5 1 8 32 21 11 54 36
## 157492 157500 157538 157581 157595 157604 157618 157623 157656 157661 157680 157703
## 8 12 2 61 3 52 27 24 9 27 15 18
## 157736 157798 157802 157821 157835 157840 157864 157878 157915 157982 158057 158095
## 3 13 10 11 47 39 25 8 30 1 33 20
## 158104 158123 158161 158175 158180 158203 158217 158255 158340 158359 158364 158378
## 71 41 45 41 39 26 21 2 63 52 14 25
## 158383 158401 158415 158458 158482 158496 158509 158608 158627 158632 158646 158651
## 27 35 18 5 60 33 34 3 26 9 9 5
## 158665 158670 158707 158712 158745 158750 158934 159453 159491 159556 159702 159797
## 8 28 14 8 11 7 13 27 12 8 3 9
## 159815 164968 164987 165072 165086 165091 165185 165246 165326 165331 165345 165350
## 3 14 7 14 11 21 18 27 13 7 4 6
## 165468 165473 165543 165604 165680 165699 165703 165717 165736 165741 165784 165798
## 12 23 14 33 33 23 16 17 17 30 11 29
## 165802 165840 165915 165920 166076 166104 166118 166316 166590 166627 166632 166651
## 17 12 9 5 46 17 21 7 13 30 18 17
## 166774 166788 166830 166905 166948 166967 167170 167194 167207 167212 167226 167231
## 25 7 11 5 12 6 21 45 27 61 46 23
## 167269 167311 167349 167354 167368 167410 167537 167561 167575 167580 167599 167617
## 32 22 17 14 13 13 32 15 40 16 11 29
## 167636 167641 167679 169126 169150 170200 170219 170479 170484 170506 170610 170865
## 10 17 33 3 51 32 50 19 8 25 11 8
## 170907 171134 343357 505991 515508 517102 531928 536105 538208 538760 538779 563151
## 11 18 3 2 1 2 3 7 35 55 2 13
## 582376 601493 603468 603581 603717 603755 605066 605146 606061 609248 672305 <NA>
## 1 35 4 1 1 10 7 2 1 4 1 207
## [1] "Frequency table after encoding"
## CODLOC.
## 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877
## 41 4 29 11 6 9 11 71 9 21 32 1 46 16 12 1 28
## 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894
## 37 13 48 27 1 3 17 3 16 8 30 9 2 25 1 7 8
## 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911
## 104 2 10 16 25 11 14 4 35 43 6 34 12 6 18 1 33
## 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928
## 47 41 3 14 11 15 5 32 21 6 45 7 4 18 13 21 7
## 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945
## 63 8 1 1 35 33 23 9 4 15 15 27 7 7 30 15 14
## 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962
## 5 3 27 5 12 7 3 8 4 52 4 17 27 3 29 13 8
## 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979
## 1 1 17 1 11 39 34 60 2 9 5 38 20 52 20 7 2
## 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996
## 18 6 23 15 23 11 28 9 17 8 13 18 42 2 36 15 8
## 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
## 3 54 17 3 11 22 20 4 2 43 20 11 12 2 31 1 5
## 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
## 4 32 35 6 45 6 27 7 6 3 55 18 23 24 17 7 10
## 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
## 6 18 10 61 3 25 13 2 7 14 30 21 43 33 40 15 45
## 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
## 2 5 7 19 2 14 12 12 8 9 8 39 2 18 16 25 11
## 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081
## 29 7 10 13 17 34 22 11 12 33 20 1 22 9 7 7 8
## 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098
## 26 40 51 13 14 9 26 11 13 3 46 23 8 11 3 27 13
## 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115
## 14 17 21 8 15 24 12 22 7 10 41 13 33 3 50 23 5
## 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132
## 45 16 13 11 12 1 2 27 6 8 14 4 12 11 61 19 17
## 1133 1134 1135 <NA>
## 21 38 32 207
## [1] "Frequency table before encoding"
## CODMOD_2015.
## 204800 204875 204909 205005 205047 205112 205120 205153 205682 205690
## 19 13 7 18 11 18 17 40 21 18
## 205773 205781 205815 206334 216341 220285 226704 232207 232223 232231
## 22 5 10 5 11 7 24 15 31 40
## 232249 232264 232504 232512 232538 232546 232553 232561 232579 232587
## 7 22 13 45 4 16 12 15 10 17
## 232595 232603 232611 232645 232728 232777 233296 233361 233676 233718
## 10 20 7 5 13 27 6 7 5 21
## 233734 233825 233890 233908 233916 233924 233940 233957 233965 233973
## 16 57 56 7 56 31 3 29 8 50
## 233981 233999 234021 234062 234070 234096 234104 234112 234120 234138
## 26 24 33 20 71 41 32 14 25 26
## 234153 234161 234187 234195 234203 234211 234229 234237 234369 234377
## 24 31 26 9 9 5 8 28 50 13
## 234385 234401 234419 234427 234443 234450 234500 234583 234674 234682
## 10 11 39 35 22 8 30 7 25 11
## 234781 234831 234856 287409 287417 287425 287466 312090 312207 312215
## 8 15 18 17 2 10 5 5 1 8
## 312306 312421 312744 312868 313239 313296 313395 313460 313890 313908
## 20 10 3 8 4 1 15 2 14 18
## 313965 313981 314096 314187 314211 314237 314245 314252 314260 314278
## 13 29 4 11 9 8 13 13 12 10
## 314294 314310 405258 405498 405704 405738 405746 405753 405852 405886
## 14 2 12 10 7 21 9 4 32 2
## 405894 405902 405928 405936 406009 406041 406066 406082 406116 406124
## 19 18 39 24 41 104 16 21 11 16
## 406140 406215 406223 406264 406413 406595 406629 406645 406975 406983
## 3 32 16 6 32 41 38 44 21 34
## 407007 407049 408245 408278 408286 408294 408328 408344 408393 408468
## 24 48 13 13 7 4 42 12 14 33
## 408476 408484 408492 408526 408559 408567 408583 408609 408666 408732
## 23 16 13 7 11 19 6 14 15 14
## 408773 408823 408856 408922 408955 408971 409003 409011 409029 409193
## 11 9 16 28 13 13 44 27 57 7
## 409227 409235 409243 409284 409292 409300 409318 409326 409359 409441
## 38 15 11 22 28 17 34 22 29 25
## 409565 409896 410480 410514 410670 410738 410746 410779 410787 410803
## 47 3 31 8 50 55 11 17 8 23
## 473249 481283 486688 499863 502922 504142 517888 519496 519595 550392
## 41 43 17 13 3 35 17 11 17 17
## 551309 557587 585885 587147 592147 612291 612416 612689 612747 612804
## 11 26 10 8 5 26 4 5 2 8
## 615013 623017 623041 637215 647388 647412 647628 671628 672105 678904
## 14 10 3 3 28 11 13 11 8 2
## 678961 679829 680058 712562 712711 723023 723031 730655 731273 731596
## 3 7 21 6 6 1 7 12 25 6
## 735498 736116 775700 776039 783423 783597 796888 818674 818708 844159
## 6 4 9 12 18 2 5 11 11 7
## 844183 899351 930958 932434 932491 932848 1117944 1201870 1266428 1377209
## 6 7 29 6 11 26 4 31 7 33
## 1412634 <NA>
## 12 612
## [1] "Frequency table after encoding"
## CODMOD_2015.
## 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
## 15 9 11 33 15 6 1 8 13 21 44 14 24 31 41 28 8
## 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469
## 38 7 15 39 7 6 7 32 5 2 9 57 23 3 11 16 24
## 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
## 17 3 41 11 17 13 21 10 14 7 11 44 16 33 4 1 18
## 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503
## 6 25 7 6 10 13 28 2 19 11 9 11 14 12 11 19 5
## 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520
## 14 26 13 9 35 2 42 12 38 7 23 21 57 12 24 41 2
## 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537
## 25 14 8 18 20 56 34 11 33 10 8 29 26 16 13 29 31
## 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554
## 8 6 9 6 4 16 13 26 11 30 11 21 3 40 55 8 43
## 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571
## 14 8 17 2 10 8 22 10 20 28 12 26 7 5 50 11 7
## 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588
## 18 10 8 9 24 14 10 24 45 3 8 4 31 22 13 11 13
## 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
## 5 32 12 32 29 4 25 22 12 7 2 3 7 4 13 16 17
## 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
## 48 4 22 13 11 13 11 27 13 10 27 26 18 50 22 18 13
## 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639
## 7 8 31 10 17 39 11 6 19 18 5 3 56 6 7 32 15
## 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
## 5 17 7 4 104 35 5 7 50 40 17 3 12 18 25 16 3
## 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673
## 1 5 26 11 5 29 8 4 15 28 47 34 2 13 5 6 16
## 674 675 676 677 678 679 680 681 682 683 684 685 686 <NA>
## 21 15 21 17 20 71 11 10 17 7 41 31 7 612
## [1] "Frequency table before encoding"
## Escuela.
## 204800 204875 204909 205005 205047 205112 205120 205153 205682 205690
## 19 13 7 18 11 18 17 40 21 18
## 205773 205781 205815 206334 216341 220285 226704 232207 232223 232231
## 22 5 10 5 11 7 24 15 31 40
## 232249 232264 232504 232512 232538 232546 232553 232561 232579 232587
## 7 22 13 45 4 16 12 15 10 17
## 232595 232603 232611 232645 232728 232777 233296 233361 233676 233718
## 10 20 7 5 13 27 6 7 5 21
## 233734 233825 233890 233908 233916 233924 233940 233957 233965 233973
## 16 57 56 7 56 31 3 29 8 50
## 233981 233999 234021 234062 234070 234096 234104 234112 234120 234138
## 26 24 33 20 71 41 32 14 25 26
## 234153 234161 234187 234195 234203 234211 234229 234237 234369 234377
## 24 31 26 9 9 5 8 28 50 13
## 234385 234401 234419 234427 234443 234450 234500 234583 234674 234682
## 10 11 39 35 22 8 30 7 25 11
## 234781 234831 234856 287409 287417 287425 287466 312090 312207 312215
## 8 15 18 17 2 10 5 5 1 8
## 312306 312421 312744 312868 313239 313296 313395 313460 313890 313908
## 20 10 3 8 4 1 15 2 14 18
## 313965 313981 314096 314187 314211 314237 314245 314252 314260 314278
## 13 29 4 11 9 8 13 13 12 10
## 314294 314310 405258 405498 405704 405738 405746 405753 405852 405886
## 14 2 12 10 7 21 9 4 32 2
## 405894 405902 405928 405936 406009 406041 406066 406082 406116 406124
## 19 18 39 24 41 104 16 21 11 16
## 406140 406215 406223 406264 406413 406595 406629 406645 406975 406983
## 3 32 16 6 32 41 38 44 21 34
## 407007 407049 408245 408278 408286 408294 408328 408344 408393 408468
## 24 48 13 13 7 4 42 12 14 33
## 408476 408484 408492 408526 408559 408567 408583 408609 408666 408732
## 23 16 13 7 11 19 6 14 15 14
## 408773 408823 408856 408922 408955 408971 409003 409011 409029 409193
## 11 9 16 28 13 13 44 27 57 7
## 409227 409235 409243 409284 409292 409300 409318 409326 409359 409441
## 38 15 11 22 28 17 34 22 29 25
## 409565 409896 410480 410514 410670 410738 410746 410779 410787 410803
## 47 3 31 8 50 55 11 17 8 23
## 473249 481283 486688 499863 502922 504142 517888 519496 519595 550392
## 41 43 17 13 3 35 17 11 17 17
## 551309 557587 585885 587147 592147 612291 612416 612689 612747 612804
## 11 26 10 8 5 26 4 5 2 8
## 615013 623017 623041 637215 647388 647412 647628 671628 672105 678904
## 14 10 3 3 28 11 13 11 8 2
## 678961 679829 680058 712562 712711 723023 723031 730655 731273 731596
## 3 7 21 6 6 1 7 12 25 6
## 735498 736116 775700 776039 783423 783597 796888 818674 818708 844159
## 6 4 9 12 18 2 5 11 11 7
## 844183 899351 930958 932434 932491 932848 1117944 1201870 1266428 1377209
## 6 7 29 6 11 26 4 31 7 33
## 1412634 <NA>
## 12 612
## [1] "Frequency table after encoding"
## Escuela.
## 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171
## 11 7 22 18 1 3 56 26 31 25 12 17 21 16 26 5 57
## 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188
## 22 21 13 4 7 3 11 56 2 11 22 50 24 35 12 11 11
## 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
## 25 6 6 10 7 4 13 14 6 11 13 10 7 12 8 13 8
## 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
## 4 27 41 9 4 55 31 18 5 12 11 44 18 32 11 16 4
## 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
## 11 33 19 24 26 7 13 3 8 35 39 3 17 9 5 50 7
## 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
## 41 25 1 10 10 50 28 40 28 17 39 13 38 7 13 18 10
## 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273
## 8 11 30 34 17 18 19 6 47 8 27 12 4 43 23 24 20
## 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
## 17 11 2 9 13 6 57 32 11 2 71 7 7 11 33 6 9
## 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
## 3 14 45 6 32 20 33 29 31 12 16 8 41 17 29 44 10
## 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324
## 26 9 26 8 41 4 10 15 104 11 16 8 8 31 42 7 16
## 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
## 21 3 2 32 1 2 14 2 15 17 29 5 15 13 7 48 2
## 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
## 5 24 34 14 14 10 23 12 8 15 21 7 3 15 25 38 6
## 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375
## 7 17 10 8 5 26 24 28 10 4 7 5 16 28 9 21 13
## 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392
## 19 3 29 7 6 13 5 18 14 13 22 18 8 16 22 13 11
## 393 394 395 396 397 398 399 400 401 402 403 404 405 <NA>
## 14 13 15 5 11 7 31 11 5 17 21 20 40 612
## [1] "Frequency table before encoding"
## cod_local_2016. Código local - Escuela
## 55610 58185 59420 59509 59665 60433 62922 63530 64068 65421 66736 67161
## 1 1 1 1 1 2 1 1 1 2 1 1
## 68599 68603 68655 68679 68735 68900 68924 68938 68943 68957 68962 68976
## 16 5 5 2 2 3 2 4 2 8 3 4
## 68981 69103 69235 69551 69706 69810 69985 70007 70074 70088 70111 70149
## 8 2 2 2 4 1 24 2 4 2 3 6
## 71115 71733 71752 71766 71790 71931 73044 73119 73162 73181 73195 73280
## 2 14 4 2 1 1 4 11 10 4 7 2
## 73303 73322 73341 73398 73435 73529 73534 73548 73553 73567 73572 73591
## 6 4 4 29 5 3 14 3 6 7 7 6
## 73609 73789 130308 142655 146154 147484 147686 147709 147714 148520 148600 148997
## 8 12 18 18 5 6 4 9 3 7 8 3
## 150122 150136 150202 150221 150259 150513 150532 150565 150570 150607 150612 150631
## 8 5 13 5 14 7 43 11 10 6 5 3
## 150645 150650 150754 150768 150773 150792 150834 150848 150966 150971 150985 151027
## 20 7 13 17 21 22 5 36 26 34 4 14
## 151070 151107 151188 151193 151206 151254 151598 151640 151664 151678 152060 152215
## 3 10 31 15 3 11 1 10 4 1 1 19
## 152239 152263 152282 152574 152588 152593 152606 152625 152668 152673 152734 152753
## 32 8 5 6 22 19 23 8 21 10 40 27
## 152786 153540 153818 153823 153837 153842 153861 153875 153880 153899 153903 153922
## 25 2 40 15 2 21 3 29 5 4 7 1
## 153941 153955 154021 154035 154064 154078 154083 154097 154120 154200 154238 154262
## 4 19 16 11 3 3 9 4 29 3 1 6
## 154549 155054 157010 157053 157072 157190 157213 157227 157345 157350 157374 157393
## 2 1 3 19 5 7 1 33 9 1 39 10
## 157406 157487 157492 157500 157538 157543 157581 157595 157604 157618 157623 157656
## 9 31 3 8 1 5 29 3 51 20 12 6
## 157661 157680 157703 157717 157722 157736 157760 157779 157798 157802 157821 157835
## 16 7 8 22 24 14 1 5 5 8 7 39
## 157840 157864 157878 157915 157982 158024 158057 158095 158104 158123 158161 158175
## 36 10 3 14 14 4 15 8 35 17 39 27
## 158180 158203 158217 158236 158241 158255 158335 158340 158359 158364 158378 158383
## 21 16 11 26 15 10 1 51 35 4 10 23
## 158401 158415 158444 158458 158482 158496 158509 158547 158590 158608 158627 158632
## 36 7 1 17 49 30 30 4 15 3 10 2
## 158646 158665 158670 158707 158712 158745 158750 158788 158905 158934 159453 159491
## 2 4 13 4 3 4 6 24 1 5 6 6
## 159556 159702 159797 159815 160121 164930 164968 165029 165072 165086 165091 165185
## 15 2 5 20 1 1 8 8 5 2 20 11
## 165190 165246 165326 165331 165345 165473 165543 165604 165637 165680 165699 165703
## 9 13 5 5 2 16 5 12 18 18 12 6
## 165717 165736 165741 165798 165802 165840 165864 165915 165920 166038 166076 166104
## 10 9 40 15 6 5 12 3 2 1 44 7
## 166118 166316 166533 166590 166627 166632 166651 166774 166788 166830 166905 166948
## 16 2 1 6 15 8 10 16 2 7 4 7
## 167014 167170 167189 167194 167207 167212 167226 167231 167269 167311 167349 167354
## 21 41 4 24 16 57 45 30 13 9 6 4
## 167368 167410 167537 167561 167575 167580 167599 167603 167617 167636 167641 167679
## 6 4 38 7 37 9 5 15 17 6 12 9
## 167684 169150 170196 170200 170304 170318 170375 170479 170484 170506 170610 170709
## 29 41 1 14 7 19 1 16 5 25 4 1
## 170832 170865 170907 170931 171134 343357 462430 462543 505991 508447 515508 517084
## 5 5 7 2 8 21 10 2 17 4 9 1
## 517102 520915 526465 526470 531928 534658 535506 536105 538208 538227 538779 555306
## 15 1 14 16 24 7 3 6 24 1 29 7
## 556042 560162 562439 563151 571844 582376 585308 601493 602242 603468 603581 603699
## 1 2 1 8 7 6 1 33 6 24 7 22
## 603717 603755 605066 605132 605146 606061 609248 611760 672305 748169 <NA>
## 1 4 5 3 13 1 37 1 5 1 1096
## [1] "Frequency table after encoding"
## cod_local_2016. Código local - Escuela
## 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727
## 15 6 5 8 2 8 10 1 4 45 24 6 10 2 7 20 57
## 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744
## 3 5 1 40 13 4 4 3 5 40 4 13 5 20 8 3 14
## 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761
## 7 6 9 10 2 2 2 24 8 4 7 4 3 6 29 12 8
## 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778
## 24 33 1 36 3 4 1 15 2 9 3 20 10 8 8 30 35
## 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
## 5 22 11 1 13 39 5 14 6 7 9 27 27 3 1 6 5
## 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
## 1 1 12 6 3 9 36 6 10 11 30 3 7 6 18 21 3
## 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829
## 6 3 51 4 17 4 1 6 4 8 5 1 6 21 3 1 18
## 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
## 2 4 1 22 6 15 21 6 5 24 7 4 1 12 43 8 1
## 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863
## 37 29 1 4 2 3 7 4 10 6 6 5 15 9 12 4 1
## 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880
## 32 6 2 2 2 7 1 1 12 6 2 14 4 18 10 14 39
## 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
## 14 2 3 8 1 16 3 15 37 3 2 3 1 1 7 19 26
## 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914
## 1 7 1 16 10 16 16 2 5 21 7 13 19 2 14 23 15
## 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931
## 5 15 16 16 13 5 1 2 7 2 10 5 5 24 5 1 9
## 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
## 23 19 21 33 2 39 2 14 1 5 51 8 5 2 12 1 11
## 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965
## 19 1 7 4 4 24 3 6 1 49 1 15 1 10 5 7 3
## 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982
## 21 8 9 7 8 44 15 16 4 19 7 4 35 24 29 5 15
## 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999
## 22 5 9 29 8 2 20 4 17 11 38 6 25 16 1 2 10
## 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016
## 17 1 1 36 1 41 14 10 11 7 5 1 14 3 31 4 2
## 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
## 3 5 29 4 29 7 5 1 1 4 4 16 1 5 18 40 8
## 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
## 31 6 8 17 16 4 9 34 1 41 9 10 25 26 3 1 2
## 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067
## 2 17 22 7 5 5 11 30 2 3 1 4 7 4 13 2 7
## 1068 <NA>
## 1 1096
## [1] "Frequency table before encoding"
## codlocal_2016.
## 68523 68599 68603 68655 68735 68900 68924 68938 68957 68962 68976 69103
## 1 15 4 7 2 7 2 5 15 7 5 2
## 69546 69551 69985 70007 70026 70074 70088 70111 71059 71115 71733 71790
## 1 3 21 6 2 3 2 1 1 2 13 5
## 71931 72087 73181 73195 73303 73322 73341 73398 73435 73440 73459 73510
## 1 1 9 12 10 4 9 28 7 2 4 2
## 73529 73548 73553 73567 73572 73591 73609 73794 73888 130308 142655 147484
## 5 6 10 11 6 12 9 4 2 14 17 9
## 147709 147714 148520 150122 150136 150141 150202 150221 150532 150565 150570 150607
## 11 4 9 14 9 2 10 7 30 15 19 11
## 150612 150631 150754 150768 150773 150792 150834 150848 150966 150971 150985 151027
## 10 9 15 15 16 20 7 38 27 24 11 16
## 151188 151193 151206 151640 151664 152215 152239 152263 152588 152593 152606 152625
## 31 20 3 16 5 18 30 10 34 29 32 19
## 152734 152753 153818 153823 153837 153842 153861 153875 153880 153899 153903 153922
## 39 45 24 32 7 40 4 16 12 12 15 6
## 153941 154021 154035 154064 154078 154083 154097 154200 154238 157010 157053 157072
## 8 15 18 10 10 19 7 6 4 2 10 10
## 157190 157227 157487 157492 157500 157538 157581 157604 157618 157623 157656 157661
## 12 47 24 7 10 1 47 45 21 20 7 24
## 157680 157703 157798 157802 157821 157835 157840 157864 157878 157915 158057 158095
## 15 14 13 10 9 31 27 8 8 25 27 16
## 158104 158123 158161 158175 158180 158203 158217 158340 158359 158364 158378 158383
## 15 30 40 28 18 25 15 48 15 12 24 23
## 158401 158415 158482 158496 158509 158608 158627 158632 158646 158651 158665 158670
## 27 17 47 28 22 2 25 9 9 4 7 27
## 158707 158712 158745 158750 158934 159453 159491 159556 159702 159797 164968 164987
## 12 6 9 7 11 14 1 12 3 11 12 5
## 165072 165086 165091 165185 165246 165326 165331 165345 165350 165468 165473 165543
## 14 6 17 12 20 8 7 3 3 9 14 13
## 165604 165680 165699 165703 165717 165736 165741 165784 165798 165802 165840 165915
## 11 32 22 12 12 14 16 1 26 5 11 9
## 165920 166076 166104 166118 166316 166590 166627 166632 166651 166774 166788 166830
## 5 40 16 18 3 12 24 17 17 20 7 9
## 166905 166948 166967 167194 167207 167212 167226 167231 167269 167311 167349 167354
## 4 10 4 38 23 52 24 19 24 16 14 12
## 167368 167410 167537 167561 167575 167580 167599 167617 167636 167641 167679 169126
## 13 6 24 13 35 13 10 16 9 11 26 1
## 169150 170200 170219 170479 170484 170506 170610 170865 170907 171134 536105 538208
## 37 22 16 17 7 22 10 8 10 12 7 30
## 538760 563151 601493 603755 605066 <NA>
## 28 12 28 8 6 1544
## [1] "Frequency table after encoding"
## codlocal_2016.
## 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458
## 14 3 2 7 15 15 12 6 31 2 1 10 34 12 47 13 30
## 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475
## 5 18 10 25 47 9 25 30 12 7 14 15 6 6 10 13 48
## 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492
## 7 19 9 4 10 39 45 9 30 3 7 11 10 6 8 10 6
## 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509
## 37 15 9 31 12 24 9 20 11 4 1 29 22 12 7 21 22
## 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
## 12 28 5 4 2 20 18 6 4 9 35 5 52 12 3 2 15
## 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543
## 16 15 11 10 19 7 18 17 24 28 1 2 9 24 47 7 6
## 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560
## 10 17 1 24 27 26 10 2 15 14 4 20 15 25 7 4 2
## 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577
## 45 19 7 12 12 3 12 11 9 28 16 4 17 14 7 10 1
## 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594
## 6 9 9 16 15 17 2 14 2 10 9 8 17 24 24 3 18
## 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
## 4 23 7 15 9 10 13 5 9 30 24 11 7 3 5 7 13
## 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
## 6 23 1 11 16 27 9 7 4 16 1 1 14 16 12 5 16
## 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
## 11 16 20 26 32 24 27 38 10 28 19 10 14 27 2 13 12
## 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662
## 12 2 2 40 11 8 12 38 21 4 13 3 8 10 24 27 14
## 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679
## 11 28 15 1 12 32 20 40 32 8 9 22 17 5 7 22 16
## 680 681 682 683 684 685 686 <NA>
## 1 12 5 7 16 8 40 1544
## [1] "Frequency table before encoding"
## Escuela_2016.
## 204800 204875 204909 205005 205047 205112 205120 205153 205682 205690
## 11 5 2 8 6 9 13 18 9 8
## 205773 205781 205815 206334 207373 207407 216341 219741 220285 226704
## 9 2 7 3 1 1 7 4 3 9
## 232207 232223 232231 232249 232264 232504 232512 232538 232546 232553
## 9 17 15 2 11 3 21 3 7 5
## 232561 232579 232587 232595 232603 232611 232645 232728 232777 233130
## 4 3 7 4 9 3 1 3 6 4
## 233296 233361 233676 233718 233734 233825 233882 233890 233908 233916
## 6 4 3 11 5 29 1 29 6 34
## 233924 233932 233940 233957 233965 233973 233981 233999 234021 234062
## 19 3 3 15 3 22 9 12 15 8
## 234096 234104 234112 234120 234138 234153 234161 234187 234195 234203
## 17 16 4 10 12 12 15 10 2 4
## 234229 234237 234351 234369 234377 234385 234401 234419 234427 234443
## 4 14 1 33 5 8 7 21 18 10
## 234450 234500 234583 234674 234682 234781 234831 234856 236158 236349
## 3 14 6 16 8 4 7 7 7 5
## 236422 236448 236463 236471 236489 236653 236661 236927 287409 287425
## 20 6 8 1 7 2 38 19 8 8
## 287466 309294 309377 309435 309567 310441 312090 312215 312306 312421
## 3 11 1 1 4 1 2 5 12 3
## 312744 312868 313395 313460 313890 313908 313965 313981 314070 314187
## 2 2 7 1 4 7 6 12 3 3
## 314211 314237 314245 314252 314260 314278 314294 405258 405498 405704
## 4 5 3 6 7 7 6 7 13 5
## 405738 405746 405837 405852 405894 405902 405928 405936 406009 406066
## 8 5 1 18 11 11 15 15 6 10
## 406082 406116 406124 406140 406215 406223 406264 406413 406595 406629
## 11 6 5 3 17 4 4 17 22 19
## 406645 406975 406983 407007 407049 408211 408245 408278 408286 408294
## 22 9 23 8 27 1 8 5 5 3
## 408328 408336 408393 408468 408476 408484 408492 408559 408567 408609
## 20 1 5 18 12 6 10 2 13 11
## 408666 408732 408773 408823 408856 408922 408955 408971 409003 409011
## 16 5 5 3 9 11 6 7 24 16
## 409029 409193 409227 409235 409243 409284 409292 409300 409318 409326
## 37 2 20 9 5 17 15 10 17 8
## 409359 409441 409565 410464 410480 410514 410613 410746 410779 410787
## 13 16 23 1 14 5 1 7 10 5
## 410803 473249 481283 486688 486928 489120 495069 495325 498782 499863
## 10 19 24 15 2 11 14 16 1 4
## 502922 504142 517581 517888 518084 518472 519496 519595 519678 525923
## 2 17 30 8 21 10 12 6 6 26
## 550392 551309 557587 579268 579276 579284 579292 579300 585885 587055
## 7 3 16 9 1 1 25 41 6 19
## 587147 589200 589747 589804 591255 591602 592147 612051 612119 612291
## 3 1 1 6 31 36 4 2 2 5
## 612507 612689 612804 615013 616110 617787 617829 621391 623017 623041
## 9 2 5 4 6 20 5 14 4 3
## 637272 639542 647388 647446 647628 655746 671628 672105 679829 680058
## 8 4 16 17 6 1 8 5 3 11
## 680124 699603 712562 712778 723031 730655 731273 735498 736116 775700
## 22 12 1 2 2 7 12 4 2 5
## 776039 783423 783597 783621 783696 783704 783720 783787 783795 791319
## 4 16 1 1 15 1 24 10 14 21
## 791574 794438 796888 818674 818708 844159 844183 891408 891812 895482
## 5 2 4 6 4 3 4 14 1 1
## 927871 930958 931055 931063 931436 932236 932434 932491 932608 932848
## 18 9 25 23 1 21 1 4 17 13
## 933226 933283 933291 933317 933531 933598 933846 1031574 1117704 1120005
## 16 14 1 10 1 3 9 4 15 1
## 1201649 1201870 1260942 1266428 1271840 1273655 1314376 1320647 1321322 1321330
## 17 14 2 5 1 2 2 11 7 17
## 1321355 1321421 1327279 1327287 1336072 1343573 1343581 1344639 1345024 1347269
## 20 21 2 10 4 15 18 17 9 1
## 1347293 1347301 1347434 1347459 1347921 1347939 1347970 1352269 1364868 1369248
## 19 14 1 15 27 20 15 1 7 24
## 1372507 1374438 1377209 1377233 1377415 1379361 1379544 1380021 1380120 1386226
## 7 3 24 1 29 1 5 28 4 8
## 1388610 1388644 1388651 1389261 1389279 1390095 1390467 1390517 1390582 1390665
## 1 8 11 10 6 2 24 7 1 23
## 1390673 1392083 1392091 1392109 1392117 1392125 1392141 1392174 1392216 1392224
## 22 19 5 18 8 14 36 21 2 9
## 1392240 1392257 1396191 1396209 1396225 1396852 1396878 1396886 1398783 1398932
## 3 12 30 24 37 22 4 17 1 1
## 1401934 1401942 1401959 1402536 1408426 1412634 1412873 1415983 1418615 1423003
## 18 8 29 7 2 8 4 1 5 22
## 1442185 1458348 1459791 1459809 1523802 1523810 1523828 1540988 1540996 1541192
## 6 10 10 19 17 11 15 11 16 15
## 1625532 1625557 1625573 1630631 1637263 1659101 1666130 1718626 1719210 1723469
## 7 8 9 3 4 13 1 4 6 3
## <NA>
## 1086
## [1] "Frequency table after encoding"
## Escuela_2016.
## 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
## 16 4 17 10 8 12 8 2 1 18 11 23 6 10 11 3 15
## 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
## 34 3 6 8 1 4 5 15 3 5 1 8 27 1 19 15 15
## 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
## 18 21 8 21 33 4 1 12 5 21 3 5 11 5 11 5 5
## 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651
## 6 3 11 1 1 2 30 10 20 10 1 10 3 30 8 20 9
## 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
## 10 8 7 6 5 9 4 7 8 36 1 6 3 13 1 24 10
## 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685
## 15 12 19 2 3 2 3 5 12 6 8 18 1 10 1 19 4
## 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
## 22 4 6 22 9 5 4 1 4 2 23 9 3 5 7 8 4
## 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
## 5 4 6 1 2 26 4 10 3 10 9 9 10 2 11 7 1
## 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736
## 13 7 18 15 24 22 2 14 14 3 17 16 13 4 10 2 3
## 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
## 1 5 3 4 6 36 4 4 1 5 21 4 6 1 8 15 12
## 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
## 1 3 22 31 2 17 1 1 8 9 6 2 5 24 4 4 25
## 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787
## 6 1 8 9 18 8 3 7 8 20 14 4 5 7 27 2 4
## 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804
## 22 5 9 1 15 1 17 15 1 11 3 6 6 12 28 24 4
## 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821
## 4 14 1 14 17 1 37 15 7 3 13 5 17 6 20 19 16
## 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
## 3 6 5 1 7 12 2 29 5 8 9 5 16 5 19 1 7
## 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855
## 2 3 23 17 14 15 1 14 8 41 8 4 5 16 17 14 5
## 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
## 13 4 9 17 14 9 17 1 3 13 12 9 1 1 2 1 7
## 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889
## 6 1 2 8 4 4 5 6 1 21 5 19 16 3 29 16 15
## 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906
## 21 15 6 3 4 2 38 7 7 12 7 17 11 18 2 9 4
## 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923
## 2 18 16 1 1 11 20 11 7 29 8 3 2 3 19 37 4
## 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
## 14 6 2 22 7 21 25 10 9 5 6 17 22 7 11 1 3
## 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957
## 14 3 4 2 7 15 11 18 1 16 2 3 7 4 1 2 17
## 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974
## 1 10 11 7 3 9 19 12 2 2 6 11 6 7 5 7 11
## 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
## 16 1 20 10 9 7 24 15 17 29 16 1 24 23 24 4 7
## 992 993 <NA>
## 3 8 1086
## [1] "Frequency table before encoding"
## COD_MOD_2015.
## 204800 204875 204909 205005 205047 205112 205120 205153 205682 205690
## 19 13 7 18 11 18 18 57 21 18
## 205773 205781 205815 206334 216341 220285 226704 232207 232223 232231
## 38 5 10 5 12 7 24 15 31 40
## 232249 232264 232504 232512 232538 232546 232553 232561 232579 232587
## 7 22 13 45 4 17 12 15 10 17
## 232595 232603 232611 232645 232728 232777 233296 233361 233676 233718
## 10 20 7 5 24 41 7 19 5 21
## 233734 233825 233890 233908 233916 233924 233940 233957 233965 233973
## 17 57 56 7 56 31 3 30 8 50
## 233981 233999 234021 234062 234070 234096 234104 234112 234120 234138
## 26 25 33 36 86 42 32 14 25 26
## 234153 234161 234187 234195 234203 234211 234229 234237 234369 234377
## 24 31 26 9 9 5 8 28 50 13
## 234385 234401 234419 234427 234443 234450 234500 234583 234674 234682
## 10 11 40 35 22 8 30 7 25 11
## 234781 234831 234856 287409 287417 287425 287466 312090 312207 312215
## 8 15 18 17 2 10 6 5 1 8
## 312306 312421 312744 312868 313239 313296 313395 313460 313890 313908
## 20 10 5 14 4 1 16 3 14 18
## 313965 313981 314096 314187 314211 314237 314245 314252 314260 314278
## 13 29 4 11 9 8 13 13 12 10
## 314294 314310 405258 405498 405704 405738 405746 405753 405852 405886
## 14 2 13 10 7 21 9 4 32 2
## 405894 405902 405928 405936 406009 406041 406066 406082 406116 406124
## 19 19 39 24 41 104 16 21 11 16
## 406140 406215 406223 406264 406413 406595 406629 406645 406975 406983
## 3 32 16 6 32 42 38 44 21 34
## 407007 407049 408245 408278 408286 408294 408328 408344 408393 408468
## 24 48 13 13 7 4 42 18 14 34
## 408476 408484 408492 408526 408559 408567 408583 408609 408666 408732
## 23 16 13 7 11 19 6 14 15 14
## 408773 408823 408856 408922 408955 408971 409003 409011 409029 409193
## 11 9 16 28 13 13 44 27 57 7
## 409227 409235 409243 409284 409292 409300 409318 409326 409359 409441
## 38 15 11 22 28 17 35 22 30 25
## 409565 409896 410480 410514 410670 410738 410746 410779 410787 410803
## 48 3 31 8 50 55 11 18 8 23
## 473249 481283 486688 499863 502922 504142 517888 519496 519595 550392
## 41 43 17 13 3 35 17 11 17 17
## 551309 557587 585885 587147 592147 612291 612416 612689 612747 612804
## 11 26 10 8 5 40 5 5 2 8
## 615013 623017 623041 637215 647388 647412 647628 671628 672105 678904
## 14 10 3 4 28 11 13 11 8 2
## 678961 679829 680058 712562 712711 723023 723031 730655 731273 731596
## 3 7 36 11 6 1 7 13 36 6
## 735498 736116 775700 776039 783423 783597 796888 818674 818708 844159
## 6 6 20 12 18 2 5 11 11 7
## 844183 899351 930958 932434 932491 932848 1117944 1201870 1266428 1377209
## 6 7 29 7 11 26 4 32 7 33
## 1412634 <NA>
## 12 414
## [1] "Frequency table after encoding"
## COD_MOD_2015.
## 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
## 17 2 35 39 11 38 9 10 19 7 24 9 22 6 14 11 8
## 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
## 36 7 26 18 5 31 8 7 11 10 14 18 48 4 29 40 13
## 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
## 11 8 7 16 17 19 42 13 6 11 12 10 21 11 7 4 4
## 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
## 13 8 41 23 8 5 24 14 5 5 12 42 10 9 12 5 17
## 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
## 16 8 7 7 86 2 55 3 17 57 28 8 15 4 104 7 7
## 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
## 13 19 13 12 3 21 25 6 25 22 32 33 6 41 19 10 1
## 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338
## 35 14 18 29 17 11 15 50 44 13 5 45 15 28 17 13 13
## 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
## 12 7 42 23 36 40 40 24 22 31 34 7 14 5 21 6 36
## 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
## 32 11 3 41 11 2 5 32 24 11 10 11 5 50 20 43 18
## 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
## 10 18 5 13 13 1 6 30 22 2 4 13 11 26 4 35 4
## 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406
## 28 13 57 17 13 8 9 6 9 30 11 16 6 7 18 13 17
## 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
## 8 26 25 20 18 16 21 14 28 7 16 2 19 33 11 7 8
## 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
## 20 27 17 31 15 11 15 10 56 11 1 13 14 30 7 5 38
## 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457
## 16 10 7 21 56 34 24 11 57 3 48 32 38 44 7 18 8
## 458 459 460 461 462 463 464 465 466 467 468 469 470 <NA>
## 31 3 50 3 25 3 10 26 32 18 2 14 26 414
## [1] "Frequency table before encoding"
## COD_MOD_2016.
## 201467 201889 204800 204859 204875 204909 205005 205013 205047 205112
## 1 1 11 1 5 2 9 1 4 9
## 205120 205153 205682 205690 205773 205781 205815 206128 206243 206334
## 10 28 9 8 20 2 6 1 1 2
## 207373 207407 207449 216341 219683 219741 220111 220285 226704 226753
## 1 2 1 7 1 4 1 5 10 1
## 226860 232207 232223 232231 232249 232264 232504 232512 232538 232546
## 1 9 18 19 2 12 4 21 3 5
## 232553 232561 232579 232587 232595 232603 232611 232645 232728 232777
## 5 4 3 7 4 10 3 1 5 16
## 233114 233130 233296 233361 233676 233718 233734 233825 233841 233882
## 1 4 5 4 3 11 5 29 1 1
## 233890 233908 233916 233924 233932 233940 233957 233965 233973 233981
## 28 2 37 19 1 4 14 3 25 8
## 233999 234021 234047 234062 234070 234096 234104 234112 234120 234138
## 15 15 1 13 36 22 16 4 10 11
## 234153 234161 234187 234195 234203 234211 234229 234237 234351 234369
## 10 14 11 2 2 1 4 13 1 29
## 234377 234385 234401 234419 234427 234443 234450 234500 234583 234674
## 5 8 7 20 17 9 3 16 4 15
## 234682 234781 234831 234856 236109 236158 236281 236349 236364 236422
## 7 4 7 7 1 8 4 9 3 19
## 236430 236448 236463 236471 236489 236646 236653 236661 236901 236927
## 1 7 8 2 7 1 2 42 3 20
## 245332 287409 287425 287466 306365 309187 309237 309286 309294 309377
## 1 8 6 2 1 1 1 2 13 1
## 309419 309435 309492 309567 309641 309682 310433 310441 312058 312090
## 3 1 1 5 1 1 3 1 1 2
## 312215 312306 312421 312561 312629 312744 312868 313080 313239 313387
## 5 13 3 1 1 3 5 1 2 1
## 313395 313460 313866 313890 313908 313965 313981 314013 314070 314187
## 8 2 1 4 10 7 13 1 3 6
## 314211 314237 314245 314252 314260 314278 314294 314310 322891 340281
## 4 5 5 6 7 7 5 1 1 1
## 405258 405498 405704 405738 405746 405753 405811 405829 405837 405852
## 8 8 5 9 5 2 1 1 2 13
## 405894 405902 405928 405936 406009 406041 406066 406082 406116 406124
## 10 10 15 15 18 60 10 11 6 6
## 406140 406215 406223 406264 406405 406413 406595 406629 406645 406975
## 3 15 4 4 1 17 22 21 23 9
## 406983 407007 407049 407718 408211 408245 408278 408286 408294 408328
## 23 9 28 1 1 7 5 5 2 19
## 408336 408344 408369 408393 408468 408476 408484 408492 408526 408559
## 1 3 1 5 18 12 6 6 1 3
## 408567 408609 408666 408732 408773 408823 408856 408922 408930 408955
## 12 7 8 5 4 3 8 11 1 6
## 408971 409003 409011 409029 409193 409227 409235 409243 409276 409284
## 5 25 16 38 2 19 8 5 1 13
## 409292 409300 409318 409326 409359 409441 409565 409896 410449 410464
## 15 10 17 8 13 17 23 1 1 1
## 410480 410506 410514 410613 410670 410738 410746 410779 410787 410803
## 15 1 5 1 23 18 7 10 5 10
## 411025 433276 434498 436683 473249 481283 486688 486928 489096 489120
## 1 1 1 1 22 23 8 3 1 10
## 495069 495325 496661 497537 498782 499863 502922 504142 517581 517888
## 14 16 2 1 1 4 2 15 30 9
## 517995 518084 518191 518472 519173 519496 519595 519678 525923 550392
## 2 22 1 11 2 6 6 6 35 7
## 551309 557587 570010 579268 579276 579284 579292 579300 579649 585885
## 3 17 1 11 1 2 27 22 1 6
## 587055 587147 587204 589200 589747 589804 591131 591164 591255 591602
## 20 3 14 1 2 10 1 1 33 40
## 591875 592147 594119 612051 612119 612291 612507 612689 612747 612804
## 6 5 1 2 2 16 10 1 1 4
## 614933 615013 615070 616110 617233 617647 617787 617829 621276 621391
## 1 6 1 7 1 1 40 7 1 16
## 623017 623041 636019 637272 639542 639617 647388 647412 647446 647628
## 4 2 1 13 6 1 15 7 25 6
## 655746 659599 664292 671628 672105 678755 679829 679969 680058 680124
## 1 1 1 6 5 1 6 1 21 22
## 693630 695130 699603 699900 712562 712711 712778 723031 730515 730655
## 1 1 12 1 2 2 2 2 1 8
## 731273 731596 735035 735498 736116 755926 775700 776039 779041 780320
## 10 2 4 4 3 1 8 4 1 1
## 783423 783597 783621 783696 783704 783720 783787 783795 785097 791319
## 13 1 1 21 1 27 11 15 1 25
## 791483 791574 794438 796888 818005 818674 818708 820803 844159 844183
## 1 5 3 2 1 5 4 1 3 4
## 844316 876409 891408 891812 892273 895482 895813 897884 899336 899351
## 1 1 15 1 1 1 1 1 1 1
## 927871 928440 929638 930859 930958 931055 931063 931329 931436 931469
## 19 1 1 1 7 30 23 1 1 1
## 932236 932434 932491 932608 932848 933226 933283 933291 933317 933531
## 26 1 5 12 13 14 12 1 10 1
## 933598 933846 934422 1010040 1031574 1117704 1117944 1120005 1145127 1194380
## 3 10 1 1 8 11 1 1 1 1
## 1200906 1201649 1201870 1237106 1253905 1259381 1260942 1266428 1269109 1271840
## 2 16 15 1 2 1 3 5 1 1
## 1273655 1314376 1320571 1320647 1321322 1321330 1321355 1321421 1327279 1327287
## 2 2 1 19 7 16 20 31 2 10
## 1327824 1336072 1341585 1343573 1343581 1344639 1345024 1347269 1347293 1347434
## 1 6 1 14 21 17 9 1 18 2
## 1347459 1347921 1347939 1347970 1352269 1355361 1361773 1364868 1364900 1369248
## 16 27 20 16 1 1 2 7 1 21
## 1370477 1371095 1372499 1372507 1374438 1377209 1377233 1377415 1379361 1379544
## 1 2 1 7 5 23 1 34 1 7
## 1380021 1380120 1386226 1386432 1387315 1388511 1388602 1388610 1388644 1388651
## 28 5 13 2 1 1 1 2 9 11
## 1389261 1389279 1389303 1390095 1390467 1390517 1390582 1390665 1390673 1392083
## 10 7 2 2 21 8 1 17 26 16
## 1392091 1392109 1392117 1392125 1392141 1392174 1392216 1392224 1392232 1392240
## 5 11 14 14 52 21 3 10 1 4
## 1392257 1393099 1394907 1395367 1396191 1396209 1396225 1396852 1396878 1396886
## 12 1 1 1 37 23 35 24 4 18
## 1396894 1398783 1398791 1398932 1401926 1401934 1401942 1401959 1402536 1408426
## 2 1 1 2 1 22 8 28 7 2
## 1412634 1412873 1415983 1418615 1423003 1434927 1442185 1452705 1458348 1459809
## 7 7 5 5 21 1 4 8 11 18
## 1501741 1523802 1523810 1523828 1527001 1540988 1540996 1541192 1569433 1573930
## 1 15 12 17 1 12 15 14 1 1
## 1579325 1625532 1625557 1625565 1625573 1630631 1632868 1637263 1639103 1645191
## 1 8 8 1 10 4 1 16 1 1
## 1653591 1659101 1666007 <NA>
## 1 21 1 566
## [1] "Frequency table after encoding"
## COD_MOD_2016.
## 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784
## 1 15 7 4 1 16 1 21 26 25 14 1 1 12 1 7 5
## 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801
## 1 9 5 1 1 35 23 3 4 15 2 40 10 6 3 2 6
## 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818
## 52 16 9 1 1 18 10 3 1 1 15 7 1 22 28 7 1
## 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
## 4 6 3 12 11 10 6 7 7 1 4 11 31 4 14 2 1
## 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852
## 22 3 2 7 1 3 3 7 12 18 3 1 1 1 9 11 1
## 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869
## 19 1 23 20 9 8 17 8 1 1 2 1 6 27 13 4 2
## 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
## 1 1 1 9 2 1 14 5 10 1 15 1 4 8 21 8 3
## 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903
## 4 10 1 15 13 11 13 1 2 1 11 2 3 5 20 4 5
## 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920
## 1 23 2 1 1 10 12 3 28 16 3 5 1 16 2 11 5
## 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
## 1 1 1 8 7 9 3 1 25 16 1 7 16 24 29 1 2
## 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954
## 5 4 2 12 27 9 22 6 1 9 15 1 6 4 5 1 11
## 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971
## 1 2 4 10 9 1 2 1 5 8 23 1 8 5 1 6 18
## 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988
## 19 2 10 19 2 7 1 13 4 1 13 2 1 7 3 1 7
## 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005
## 17 1 19 1 26 11 1 12 6 4 2 21 38 8 2 10 12
## 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022
## 21 1 37 1 1 1 13 17 2 1 4 1 5 5 1 1 14
## 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039
## 8 1 7 10 1 5 1 1 2 22 1 1 6 4 1 23 8
## 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
## 23 1 1 21 17 10 1 19 4 1 15 2 13 1 1 1 1
## 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
## 7 40 1 2 2 3 3 22 10 5 5 16 1 1 15 6 1
## 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090
## 4 5 22 2 16 8 1 13 1 6 1 2 1 1 21 36 16
## 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
## 2 18 7 2 6 1 20 1 5 18 1 10 60 4 10 3 1
## 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
## 11 27 7 2 2 9 6 14 10 13 1 5 10 1 1 1 8
## 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141
## 5 1 1 5 1 2 15 1 14 1 4 21 3 1 1 8 8
## 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158
## 15 3 22 5 18 4 17 15 1 1 42 11 30 28 7 8 25
## 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175
## 1 6 15 23 30 1 1 15 7 1 2 2 1 1 10 2 13
## 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
## 1 25 5 11 2 3 2 2 10 2 5 5 1 5 16 4 6
## 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209
## 1 6 28 1 10 2 1 18 1 1 9 29 2 1 15 1 6
## 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
## 1 5 4 7 16 1 1 1 1 4 11 1 1 1 12 19 1
## 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243
## 20 7 1 7 17 37 6 4 8 2 2 1 21 5 13 1 1
## 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
## 12 14 1 1 8 21 10 3 19 5 1 34 15 5 2 20 1
## 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
## 7 1 7 1 1 4 4 13 4 5 1 1 2 6 17 16 14
## 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294
## 1 28 14 1 5 33 8 20 7 1 10 21 8 2 7 1 4
## 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
## 16 4 23 2 11 8 1 5 1 1 1 8 1 3 8 5 3
## 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
## 3 1 2 3 1 3 7 1 9 1 1 5 35 1 1 2 10
## 1329 1330 <NA>
## 1 17 566Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Focus on variables with a "Lowest Freq" in dictionary of 30 or less.
dropvars <- c("D_DD",
"D_MM",
"F_DD",
"F_MM",
"fecha_nacimiento_2016")
mydata <- mydata[!names(mydata) %in% dropvars]Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
# !!!Include relevant variables in list below (Indirect PII - Categorical, and Ordinal if not processed yet)
indirect_PII <- c("TURNO",
"idioma1_2015",
"I_SEXO",
"area")
capture_tables (indirect_PII)
# Recode those with very specific values.
break_language <- c(-9,-8,-7,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16)
labels_language <- c("No indica"=1,
"No se puede leer"=2,
"Error"=3,
"Castellano \xf3 Espa\xf1ol"=4,
"Quechua"=5,
"Aymara"=6,
"Otro"=7,
"Ingl\xe9s"=8,
"Portugues"=9,
"Franc\xe9s"=10,
"Italiano"=11,
"Shipibo"=12,
"Aguaruna"=13,
"Machiguenga"=14,
"Alem\xe1n"=15,
"Catal\xe1n"=16,
"Hindu"=17,
"Coreano"=18,
"Chino"=19)
mydata <- ordinal_recode (variable="idioma1_2015", break_points=break_language, missing=999999, value_labels=labels_language)
## [1] "Frequency table before encoding"
## idioma1_2015. P2. Cual fue el idioma con el que aprendiste a hablar? 1
## Castellano <f3> Espa<f1>ol Quechua Aymara
## 1421 3004 31
## Japon<e9>s <NA>
## 4 647
## recoded
## [-9,-8) [-8,-7) [-7,1) [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,8) [8,9) [9,10)
## 1 0 0 0 1421 0 0 0 0 0 0 0 0
## 2 0 0 0 0 3004 0 0 0 0 0 0 0
## 3 0 0 0 0 0 31 0 0 0 0 0 0
## 4 0 0 0 0 0 0 4 0 0 0 0 0
## recoded
## [10,11) [11,12) [12,13) [13,14) [14,15) [15,16) [16,1e+06)
## 1 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 0
## 4 0 0 0 0 0 0 0
## [1] "Frequency table after encoding"
## idioma1_2015. P2. Cual fue el idioma con el que aprendiste a hablar? 1
## Castellano ó Español Quechua Aymara Otro
## 1421 3004 31 4
## <NA>
## 647
## [1] "Inspect value labels and relabel as necessary"
## No indica No se puede leer Error Castellano ó Español
## 1 2 3 4
## Quechua Aymara Otro Inglés
## 5 6 7 8
## Portugues Francés Italiano Shipibo
## 9 10 11 12
## Aguaruna Machiguenga Alemán Catalán
## 13 14 15 16
## Hindu Coreano Chino
## 17 18 19Matching and crosstabulations: Run automated PII check
# selected categorical key variables: gender, occupation/education and age
selectedKeyVars = c('sexo', 'grado11') ##!!! Replace with candidate categorical demo vars
# creating the sdcMicro object with the assigned variables
sdcInitial <- createSdcObj(dat = mydata, keyVars = selectedKeyVars)
sdcInitial## The input dataset consists of 5107 rows and 392 variables.
## --> Categorical key variables: sexo, grado11
## ----------------------------------------------------------------------## Information on categorical key variables:
##
## Reported is the number, mean size and size of the smallest category >0 for recoded variables.
## In parenthesis, the same statistics are shown for the unmodified data.
## Note: NA (missings) are counted as seperate categories!## Key Variable Number of categories Mean size Size of smallest (>0)
## sexo 3 (3) 2347.000 (2347.000) 2256
## grado11 3 (3) 2548.500 (2548.500) 2547
##
## (2256)
## (2547)## ----------------------------------------------------------------------## Infos on 2/3-Anonymity:
##
## Number of observations violating
## - 2-anonymity: 0 (0.000%)
## - 3-anonymity: 0 (0.000%)
## - 5-anonymity: 0 (0.000%)
##
## ----------------------------------------------------------------------Show values of key variable of records that violate k-anonymity
mydata <- labelDataset(mydata)
notAnon <- sdcInitial@risk$individual[,2] < 2 # for 2-anonymity
mydata[notAnon,selectedKeyVars]## # A tibble: 0 x 2
## # ... with 2 variables: sexo <dbl>, grado11 <dbl>sdcFinal <- localSuppression(sdcInitial)Open-ends: review responses for any sensitive information, redact as necessary
# !!! Identify open-end variables here:
open_ends <- c("name_schship_2015",
"name_schship_2016")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
# !!!Removed, as they contain a lot of sensitive information and they are in Spanish.
mydata <- mydata[!names(mydata) %in% "name_schship_2015"]
mydata <- mydata[!names(mydata) %in% "name_schship_2016"]GPS data: Displace
# !!!No GPS dataSave processed data in Stata and SPSS format
haven::write_dta(mydata, paste0(filename, "_PU.dta"))
colnames(mydata) <- gsub('^_', '', colnames(mydata))
mydata [is.na(mydata)] <- NA
haven::write_sav(mydata, paste0(filename, "_PU.sav"))
# Add report title dynamically
title_var <- paste0("DOL-ILAB SDC - ", filename)