PGRdup (version 0.2.3.9)

AddProbDup: Add probable duplicate sets fields to the PGR passport database

Description

AddProbDup adds the fuzzy, phonetic and semantic probable duplicates sets data fields from an object of class ProbDup to the original PGR passport database.

Usage

AddProbDup(pdup, db, addto = c("I", "II"), max.count = 30)

Value

A data frame of the PGR passport database with the probable duplicate sets fields added.

Arguments

pdup

An object of class ProbDup.

db

A data frame of the PGR passport database.

addto

Either "I" or "II" indicating the database to which the data.fields are to be added (see Details).

max.count

The maximum count of probable duplicate sets whose information is to be retrieved.

Details

This function helps to add information associated with identified fuzzy, phonetic and semantic probable duplicate sets using the ProbDup function to the original PGR passport database. Associated data fields such as SET_NO, ID and IDKW are added based on the PRIM_ID field(column).

In case more than one KWIC index was used to generate the object of class ProbDup, the argument addto can be used to specify to which database the data fields are to be added. The default "I" indicates the database from which the first KWIC index was created and "II" indicates the database from which the second index was created.

See Also

DataClean, KWIC, ProbDup

Examples

# \dontshow{
threads_dt <- data.table::getDTthreads()
threads_OMP <- Sys.getenv("OMP_THREAD_LIMIT")
data.table::setDTthreads(2)

data.table::setDTthreads(2)
Sys.setenv(`OMP_THREAD_LIMIT` = 2)
# }

if (FALSE) {

#' # 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)

# Add the duplicates sets to the original database                 
GNwithdup <-  AddProbDup(pdup = GNdup, db = GN1000, addto = "I")                  

}

# \dontshow{
data.table::setDTthreads(threads_dt)
Sys.setenv(`OMP_THREAD_LIMIT` = threads_OMP)
# }