PGRdup (version 0.2.3.9)

ViewProbDup: Visualize the probable duplicate sets retrieved in a ProbDup object

Description

ViewProbDup plots summary visualizations of accessions within the probable duplicate sets retrieved in a ProbDup object according to a grouping factor field(column) in the original database(s).

Usage

ViewProbDup(
  pdup,
  db1,
  db2 = NULL,
  factor.db1,
  factor.db2 = NULL,
  max.count = 30,
  select,
  order = "type",
  main = NULL
)

Value

A list containing the following objects:

Summary1	The summary data.frame of number of accessions per factor level.
Summary2	The summary data.frame of number of accessions and sets per each type of sets classified according to factor levels.
SummaryGrob	A grid graphical object (Grob) of the summary visualization plot. Can be plotted using the grid.arrange function

Arguments

pdup

An object of class ProbDup.

db1

A data frame of the PGR passport database.

db2

A data frame of the PGR passport database. Required when pdup was created using more than one KWIC Index.

factor.db1

The db1 column to be considered for grouping the accessions. Should be of class character or factor.

factor.db2

The db2 column to be considered for grouping the accessions. Should be of class character or factor. retrieved.

max.count

The maximum count of probable duplicate sets whose information is to be plotted (see Note).

select

A character vector of factor names in factor.db1 and/or factor.db2 to be considered for grouping accessions (see Note).

order

The order of the type of sets retrieved in the plot. The default is "type" (see Details).

main

The title of the plot.

See Also

ProbDup, DisProbDup, DataClean, ggplot, gridExtra-package

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) {

# Method "b and c"
#=================

# Load PGR passport databases
GN1 <- GN1000[!grepl("^ICG", GN1000$DonorID), ]
GN1$DonorID <- NULL
GN2 <- GN1000[grepl("^ICG", GN1000$DonorID), ]
GN2 <- GN2[!grepl("S", GN2$DonorID), ]
GN2$NationalID <- NULL

GN1$SourceCountry <- toupper(GN1$SourceCountry)
GN2$SourceCountry <- toupper(GN2$SourceCountry)

GN1$SourceCountry <- gsub("UNITED STATES OF AMERICA", "USA", GN1$SourceCountry)
GN2$SourceCountry <- gsub("UNITED STATES OF AMERICA", "USA", GN2$SourceCountry)

# Specify as a vector the database fields to be used
GN1fields <- c("NationalID", "CollNo", "OtherID1", "OtherID2")
GN2fields <- c("DonorID", "CollNo", "OtherID1", "OtherID2")

# Clean the data
GN1[GN1fields] <- lapply(GN1[GN1fields], function(x) DataClean(x))
GN2[GN2fields] <- lapply(GN2[GN2fields], 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")
GN1[GN1fields] <- lapply(GN1[GN1fields], function(x) MergeKW(x, y1, delim = c("space", "dash")))
GN1[GN1fields] <- lapply(GN1[GN1fields], function(x) MergePrefix(x, y2, delim = c("space", "dash")))
GN1[GN1fields] <- lapply(GN1[GN1fields], function(x) MergeSuffix(x, y3, delim = c("space", "dash")))
GN2[GN2fields] <- lapply(GN2[GN2fields], function(x) MergeKW(x, y1, delim = c("space", "dash")))
GN2[GN2fields] <- lapply(GN2[GN2fields], function(x) MergePrefix(x, y2, delim = c("space", "dash")))
GN2[GN2fields] <- lapply(GN2[GN2fields], function(x) MergeSuffix(x, y3, delim = c("space", "dash")))

# Remove duplicated DonorID records in GN2
GN2 <- GN2[!duplicated(GN2$DonorID), ]

# Generate KWIC index
GN1KWIC <- KWIC(GN1, GN1fields)
GN2KWIC <- KWIC(GN2, GN2fields)

# 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"))

GNdupc <- ProbDup(kwic1 = GN1KWIC, kwic2 = GN2KWIC, method = "c",
                  excep = exep, fuzzy = TRUE, phonetic = TRUE,
                  encoding = "primary", semantic = TRUE, syn = syn)

GNdupcView <- ViewProbDup(GNdupc, GN1, GN2, "SourceCountry", "SourceCountry",
                         max.count = 30, select = c("INDIA", "USA"), order = "type",
                         main = "Groundnut Probable Duplicates")

library(gridExtra)                                                    
grid.arrange(GNdupcView$SummaryGrob)                          

}   

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