rm(list=ls(all=t))

Setup filenames

filename <- "C_t1_work_relabelled" # !!!Update filename
functions_vers <-  "functions_1.7.R" # !!!Update helper functions file

Setup 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 

#!!!Save flagged dictionary in .csv format, add "DatasetReview" to name and continue processing data with subset of flagged variables

Direct PII: variables to be removed

# !!!No Direct PII

Direct PII-team: Encode field team names

# !!!No Direct PII-team

Small locations: Encode locations with pop <100,000 using random large numbers

# !!!No small locations

Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values

# !!!No Indirect PII - Ordinal

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("t1_c1_work_own_farm",
                  "t1_c2_help_farm_7days",
                  "t1_c4_income_farm_7days",
                  "t1_c5_work_own_nonfarm",
                  "t1_c6_help_nonfarm_7days",
                  "t1_c8_income_nonfarm_7days",
                  "t1_c9_work_nonfamily",
                  "t1_c11_income_nonfamily_7days",
                  "t1_c13_work_type")

capture_tables (indirect_PII)

Matching and crosstabulations: Run automated PII check

#!!! Insufficient demographic information

Open-ends: review responses for any sensitive information, redact as necessary

# !!! Identify open-end variables here: 
open_ends <- c("t1_c13_work_type_specify")
report_open (list_open_ends = open_ends)

# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number 

dropvars <- c("t1_c13_work_type_specify") 
mydata <- mydata[!names(mydata) %in% dropvars] # Drop as actually verbatim data in Indi

GPS data: Displace

# !!!No GPS data

Save processed data in Stata and SPSS format

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)