\name{internals} \alias{begin} \alias{begin-methods} \alias{begin,RLBigData-method} \alias{nextPairs} \alias{nextPairs-methods} \alias{nextPairs,RLBigData-method} \alias{clear} \alias{clear-methods} \alias{clear,RLBigData-method} \alias{blockfldfun} \alias{getSQLStatement} \alias{getSQLStatement-methods} \alias{getSQLStatement,RLBigData-method} \alias{init_sqlite_extensions} \alias{.allows_extensions} \alias{.lib_path} \alias{getPatternCounts} \alias{getPatternCounts-methods} \alias{getPatternCounts,RLBigData-method} \alias{getMatchCount} \alias{getMatchCount-methods} \alias{getMatchCount,RLBigData-method} \alias{getNonMatchCount} \alias{getNonMatchCount-methods} \alias{getNonMatchCount,RLBigData-method} \alias{getNACount} \alias{getNACount-methods} \alias{getNACount,RLBigData-method} \alias{getColumnNames} \alias{getColumnNames-methods} \alias{getColumnNames,RLBigDataDedup-method} \alias{getColumnNames,RLBigDataLinkage-method} \alias{getThresholds} \alias{countpattern} \alias{hasWeights} \alias{hasWeights-methods} \alias{hasWeights,RecLinkData-method} \alias{hasWeights,RLBigData-method} \title{ Internal functions and methods } \description{ These functions and methods are used internally and should usually not be called from outside the package. } \usage{ begin(x, ...) nextPairs(x, n = 10000, ...) clear(x, ...) blockfldfun(blockfld, phoneticFld, phoneticFun, coln) getSQLStatement(data1, data2 = data1, con, type, blockFld, excludeFld, strcmpFld, strcmpFun, phoneticFld, phoneticFun) init_sqlite_extensions(db) .allows_extensions(db) .lib_path() getPatternCounts(x, n=10000, cutoff=1, withProgressBar = (sink.number()==0)) getMatchCount(object) getNonMatchCount(object) getNACount(object) getColumnNames(object, withExcluded = FALSE) getThresholds(W, M, U, my, ny) countpattern(x, matching = FALSE) hasWeights(object) } \arguments{ \item{x, object}{Depends on the function, usually a \code{"\linkS4class{RecLinkData}"}, \code{"\linkS4class{RLBigData}"} or \code{"\linkS4class{RLResult}"}. A matrix of binary observations for \code{countpattern}.} \item{n}{Maximum number of comparison patterns to fetch.} \item{blockfld}{Blocking definition as in \code{\link[=RLBigDataDedup]{RLBigData*}}.} \item{phoneticFld}{Indices of attributes for which phonetic code should be used.} \item{phoneticFun}{Name of phonetic function as in \code{\link[=RLBigDataDedup]{RLBigData*}}.} \item{data1, data2}{Data frame with records.} \item{type}{"linkage" or "deduplication", the type of linkage.} \item{excludeFld}{Indices or names of fields to exclude from comparison.} \item{strcmpFld}{Indices of attributes for which string comparison should be used.} \item{strcmpFun}{Name of string comparison function as in \code{\link[=RLBigDataDedup]{RLBigData*}}.} \item{con}{A SQLite database connection.} \item{coln}{Column names of records.} \item{db}{Database connection.} \item{cutoff}{Threshold from which string comparison values are rounded to 1.} \item{withProgressBar}{Whether to display a progress bar.} \item{withExcluded}{Logical. Wether to output names of excluded columns} \item{W,M,U}{Linkage weights, m- and u-probabilites. See \code{\link{emWeights}} for details.} \item{W,M,U}{Error bounds. See \code{\link{emClassify}} for details.} \item{\dots}{Optional arguments.} \item{matching}{If TRUE an additional vector is returned which stores which row belongs to which pattern.} } \details{ \describe{ \item{\code{begin}}{Sends a query to the database of an \code{"RLBigData"} object which creates comparison patterns.} \item{\code{nextPairs}}{Retreives the next \code{n} comparison patterns.} \item{\code{clear}}{Closes the result set opened by \code{begin}.} \item{\code{blockfldfun}}{Constructs the part of SQL statement which implements blocking.} \item{\code{blockfldfun}}{Constructs the part of SQL statement which implements blocking.} \item{\code{getSQLStatement}}{Constructs SQL statement for retreiving comparison patterns.} \item{\code{init_sqlite_extensions}}{Load string comparison and phonetic functions into database.} \item{\code{.allows_extensions}}{Tests wether SQLite engine supports extension functions.} \item{\code{.lib_path}}{Gets path of shared library of package.} \item{\code{getPatternCounts}}{Counts binary patterns, implemented through \code{\link{countpattern}}.} \item{\code{getMatchCount}}{Gets number of matches from a \code{"\linkS4class{RLBigData}"} object.} \item{\code{getNACount}}{Gets number of pairs with unknown matching status from a \code{"\linkS4class{RLBigData}"} object.} \item{\code{getDbFile}}{Returns path of database file for a data or result object.} \item{\code{getColumnNames}}{Returns column names of a \code{"\linkS4class{RLBigData}"} object as a character vector.} \item{\code{getThresholds}}{Calculates upper and lower classification based on error bounds.} \item{\code{countpattern}}{Modified version of \code{\link[e1071]{countpattern}} in package e1071.} \item{\code{hasWeights}}{Determines whether a data object has weights.} } } \author{ Andreas Borg, Murat Sariyar } \keyword{internal}