rm(list=ls(all=t))

Setup filenames

filename <- "Section_5" # !!!Update filename
functions_vers <-  "functions_1.8.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 

Direct PII: variables to be removed

# !!!Include any Direct PII variables
# !!!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

# !!!Include relevant variables, but check their population size first to confirm they are <100,000
# !!!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

# !!!No Indirect PII - Categorical


# Recode those with very specific values. 

Matching and crosstabulations: Run automated PII check

# !!!Insufficient demographic data

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

# !!! Identify open-end variables here: 
open_ends <- c("c_s5q1noresponse", "c_mother_noresponse", "c_father_noresponse")

report_open (list_open_ends = open_ends)

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



mydata$c_mother_noresponse[334] <- "[Tagalog]"
mydata$c_mother_noresponse[335] <- "[Tagalog]"
mydata$c_father_noresponse[334] <- "[Tagalog]"
mydata$c_father_noresponse[1556] <- "His father left them [date redacted] in 2012"
mydata$c_father_noresponse[2114] <- "[name redacted] His father was already died."
mydata$c_father_noresponse[2116] <- "[name redacted] His father was already died."
mydata$c_father_noresponse[4130] <- "The father is deceased [date redacted] in 2014"

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)