rm(list=ls(all=t))filename <- "ecsection6" # !!!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
#!!!Save flagged dictionary in .csv format, add "DatasetReview" to name and continue processing data with subset of flagged variables# !!! No Direct PII
## !!! No Direct PII-team
#dropvars <- c("dise")
mydata <- mydata[!names(mydata) %in% dropvars]
locvars <- c("q002_blckid", "q003_vill_id")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## q002_blckid. 002 Unique block ID
## 1 2 3 4 5 6 7 8 9
## 206 167 188 412 96 192 158 424 544
## [1] "Frequency table after encoding"
## q002_blckid. 002 Unique block ID
## 279 280 281 282 283 284 285 286 287
## 206 544 167 424 96 188 412 158 192
## [1] "Frequency table before encoding"
## q003_vill_id. 003 Village ID
## 1 2 3 4 5 6 7 8 9 10 11 12 13 15 16 17 18 19 20 21 22 23
## 17 16 17 16 20 29 29 16 15 13 17 26 24 14 18 21 18 18 20 30 23 18
## 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45
## 18 32 25 27 17 14 13 24 26 21 16 28 19 15 22 27 16 16 18 16 27 21
## 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
## 22 21 20 17 17 17 18 27 25 27 19 13 21 12 24 19 17 19 18 30 16 19
## 68 69 70 71 72 73 74 75 76 77 78 80 81 82 83 84 85 87 88 89 90 91
## 21 25 13 16 21 16 23 22 18 23 30 30 16 21 17 17 13 18 22 16 19 20
## 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113
## 18 20 14 20 24 28 21 26 17 25 20 15 19 16 31 13 28 22 17 21 27 15
## 114 115 116 117 118 119 120 121 122 <NA>
## 24 20 14 24 22 21 13 13 10 1
## [1] "Frequency table after encoding"
## q003_vill_id. 003 Village ID
## 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
## 18 16 24 20 21 16 27 13 20 18 19 17 23 17 10 21 19 18 24 24 16 27
## 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652
## 23 32 21 28 19 16 16 30 25 21 20 27 21 28 18 29 25 25 16 17 20 24
## 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
## 17 31 15 21 17 13 26 26 22 30 12 14 18 27 14 15 17 23 21 24 22 22
## 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
## 20 21 21 27 17 16 30 13 24 19 20 18 17 16 16 29 16 21 22 18 16 14
## 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
## 16 19 18 17 28 19 25 13 13 21 13 17 15 20 22 27 30 22 16 13 14 20
## 719 720 721 722 723 724 725 726 727 <NA>
## 26 17 19 18 18 15 18 17 13 1# !!! No Indirect PII - Ordinal variables
## !!! No Indirect PII - Categorical variables
##!!! Insufficient demographic information
## !!! No Open-ends variables
## !!! No GPS variables
#Adds "_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)