rm(list=ls(all=t))filename <- "ehsection0_relabelled" # !!!Update filename
functions_vers <- "functions_1.7.R" # !!!Update helper functions filesource (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 # !!! No Direct PII# !!! No Direct PII-team!!!Include relevant variables, but check their population size first to confirm they are <100,000
dropvars <- c("dise")
mydata <- mydata[!names(mydata) %in% dropvars]
locvars <- c("a006_a_block_id", "a007_a_vill_id")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## a006_a_block_id. 006 Block ID
## 1 2 3 4 5 6 7 8 9
## 203 167 192 404 97 190 155 422 528
## [1] "Frequency table after encoding"
## a006_a_block_id. 006 Block ID
## 279 280 281 282 283 284 285 286 287
## 422 167 192 528 404 97 203 155 190
## [1] "Frequency table before encoding"
## a007_a_vill_id. 007 Village ID
## 1 2 3 4 5 6 7 8 9 10 11 12 13 15 16 17 18 19 20 21 22
## 16 16 16 15 20 30 28 14 15 15 17 24 24 15 18 21 16 17 18 30 22
## 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
## 18 17 32 27 26 18 15 15 24 26 22 16 29 19 17 21 27 16 16 18 16
## 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64
## 28 20 23 21 19 17 17 16 18 26 24 27 18 16 21 13 24 20 16 18 18
## 65 66 67 68 69 70 71 72 73 74 75 76 77 78 80 81 82 83 84 85 87
## 29 16 18 21 23 13 16 19 16 23 23 17 22 29 30 16 22 17 17 13 16
## 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
## 22 15 19 19 19 20 13 17 23 29 21 25 18 24 21 15 19 13 31 14 27
## 109 110 111 112 113 114 115 116 117 118 119 120 121 122
## 21 17 21 27 14 24 20 16 21 22 20 13 10 10
## [1] "Frequency table after encoding"
## a007_a_vill_id. 007 Village ID
## 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
## 18 30 14 22 15 16 16 16 17 17 19 25 23 30 17 10 31 15 22 16 21
## 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650
## 22 19 15 17 24 16 24 19 32 17 21 17 16 21 23 18 29 19 22 13 15
## 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
## 17 17 23 27 28 16 24 13 16 19 29 21 16 24 20 27 22 20 23 18 13
## 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
## 16 15 16 13 15 28 18 17 24 29 29 21 16 20 27 19 20 16 15 18 20
## 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
## 15 14 21 20 27 18 24 22 21 24 26 14 23 26 19 17 10 18 16 16 26
## 714 715 716 717 718 719 720 721 722 723 724 725 726 727
## 21 16 18 21 13 13 18 21 17 18 27 30 16 18# !!!No Indirect PII - Ordinal# !!!Include relevant variables in list below (Indirect PII - Categorical, and Ordinal if not processed yet)
indirect_PII <- c("a010_urban", "s1_relation")
capture_tables (indirect_PII)
# Recode those with very specific values. # Not enough variables for matching possible# !!! No open-ends# !!! No GPSAdds "_PU" (Public Use) to the end of the name
haven::write_dta(mydata, paste0(filename, "_PU.dta"))
haven::write_sav(mydata, paste0(filename, "_PU.sav"))
# Add report title dynamically
title_var <- paste0("DOL-ILAB SDC - ", filename)