# NOT RUN {
# Load PGR passport database
GN <- GN1000
# Specify as a vector the database fields to be used
GNfields <- c("NationalID", "CollNo", "DonorID", "OtherID1", "OtherID2")
# Clean the data
GN[GNfields] <- lapply(GN[GNfields], function(x) DataClean(x))
# }
# NOT RUN {
# Generate KWIC index
GNKWIC <- KWIC(GN, GNfields)
GNKWIC
# Retrieve the KWIC index from the KWIC object
KWIC <- GNKWIC[[1]]
# Retrieve the keyword frequencies from the KWIC object
KeywordFreq <- GNKWIC[[2]]
# Show error in case of duplicates and NULL values
# in the primary key/ID field "NationalID"
GN[1001:1005,] <- GN[1:5,]
GN[1001,3] <- ""
GNKWIC <- KWIC(GN, GNfields)
# }
Run the code above in your browser using DataLab