## 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))
# y1 <- list(c("Gujarat", "Dwarf"), c("Castle", "Cary"), c("Small", "Japan"),
# c("Big", "Japan"), c("Mani", "Blanco"), c("Uganda", "Erect"),
# c("Mota", "Company"))
# y2 <- c("Dark", "Light", "Small", "Improved", "Punjab", "SAM")
# y3 <- c("Local", "Bold", "Cary", "Mutant", "Runner", "Giant", "No.",
# "Bunch", "Peanut")
# GN[GNfields] <- lapply(GN[GNfields], function(x) MergeKW(x, y1, delim = c("space", "dash")))
# GN[GNfields] <- lapply(GN[GNfields], function(x) MergePrefix(x, y2, delim = c("space", "dash")))
# GN[GNfields] <- lapply(GN[GNfields], function(x) MergeSuffix(x, y3, delim = c("space", "dash")))
#
# # Generate KWIC index
# GNKWIC <- KWIC(GN, GNfields)
#
# # Specify the exceptions as a vector
# exep <- c("A", "B", "BIG", "BOLD", "BUNCH", "C", "COMPANY", "CULTURE",
# "DARK", "E", "EARLY", "EC", "ERECT", "EXOTIC", "FLESH", "GROUNDNUT",
# "GUTHUKAI", "IMPROVED", "K", "KUTHUKADAL", "KUTHUKAI", "LARGE",
# "LIGHT", "LOCAL", "OF", "OVERO", "P", "PEANUT", "PURPLE", "R",
# "RED", "RUNNER", "S1", "SAM", "SMALL", "SPANISH", "TAN", "TYPE",
# "U", "VALENCIA", "VIRGINIA", "WHITE")
#
# # Specify the synsets as a list
# syn <- list(c("CHANDRA", "AH114"), c("TG1", "VIKRAM"))
#
# # Fetch probable duplicate sets
# GNdup <- ProbDup(kwic1 = GNKWIC, method = "a", excep = exep, fuzzy = TRUE,
# phonetic = TRUE, encoding = "primary",
# semantic = TRUE, syn = syn)
# lapply(GNdup, dim)
#
# # Get disjoint probable duplicate sets of each kind
# disGNdup1 <- DisProbDup(GNdup, combine = NULL)
# lapply(disGNdup1, nrow)
#
# # Get disjoint probable duplicate sets combining all the kinds of sets
# disGNdup2 <- DisProbDup(GNdup, combine = c("F", "P", "S"))
# lapply(disGNdup2, nrow)
#
# ## End(Not run)
Run the code above in your browser using DataCamp Workspace