Entity Matching by Similarity Join
 
Loading...
Searching...
No Matches
OvlpSelfJoin Class Reference

#include <ovlpjoin.h>

Public Member Functions

void overlapjoin (int overlap_threshold, std::vector< std::pair< int, int > > &finalPairs)
 
void small_case (int L, int R, std::vector< std::pair< int, int > > &finalPairs)
 
 OvlpSelfJoin (const std::vector< std::vector< ui > > &sorted_records, const std::vector< double > &_recWeights, const std::vector< double > _wordwt, ui _maxHeapSize=0, bool _isWeightedComp=false)
 
bool comp_comb1 (const int a, const int b)
 
double weightedOverlapCoeff (int id1, int id2)
 
double overlapCoeff (int id1, int id2)
 
bool build_heap (const std::vector< std::pair< int, int > > &vec, const std::vector< std::vector< ui > > &dataset, int L, std::vector< int > &heap, std::vector< combination1 > &combs, int &heap_size)
 

Public Attributes

int n {0}
 
int c {0}
 
ui total_eles {0}
 
std::vector< std::vector< ui > > records
 
std::vector< std::vector< ui > > datasets
 
std::vector< double > recWeights
 
std::vector< double > wordwt
 
std::vector< std::pair< int, int > > idmap_records
 
std::vector< std::vector< std::pair< int, int > > > ele_lists
 
std::vector< std::pair< int, int > > result_pairs
 
std::vector< int > heap
 
std::vector< combination1combs
 
ui maxHeapSize {0}
 
bool isWeightedComp {false}
 
std::vector< WeightPairresult_pairs_
 
int isHeap {0}
 
int64_t candidate_num {0}
 
int64_t result_num {0}
 

Constructor & Destructor Documentation

◆ OvlpSelfJoin()

OvlpSelfJoin::OvlpSelfJoin ( const std::vector< std::vector< ui > > & sorted_records,
const std::vector< double > & _recWeights,
const std::vector< double > _wordwt,
ui _maxHeapSize = 0,
bool _isWeightedComp = false )
inline

Member Function Documentation

◆ build_heap()

bool OvlpSelfJoin::build_heap ( const std::vector< std::pair< int, int > > & vec,
const std::vector< std::vector< ui > > & dataset,
int L,
std::vector< int > & heap,
std::vector< combination1 > & combs,
int & heap_size )

◆ comp_comb1()

bool OvlpSelfJoin::comp_comb1 ( const int a,
const int b )
inline

◆ overlapCoeff()

double OvlpSelfJoin::overlapCoeff ( int id1,
int id2 )
inline

◆ overlapjoin()

void OvlpSelfJoin::overlapjoin ( int overlap_threshold,
std::vector< std::pair< int, int > > & finalPairs )

◆ small_case()

void OvlpSelfJoin::small_case ( int L,
int R,
std::vector< std::pair< int, int > > & finalPairs )

◆ weightedOverlapCoeff()

double OvlpSelfJoin::weightedOverlapCoeff ( int id1,
int id2 )
inline

Member Data Documentation

◆ c

int OvlpSelfJoin::c {0}

◆ candidate_num

int64_t OvlpSelfJoin::candidate_num {0}

◆ combs

std::vector<combination1> OvlpSelfJoin::combs

◆ datasets

std::vector<std::vector<ui> > OvlpSelfJoin::datasets

◆ ele_lists

std::vector<std::vector<std::pair<int, int> > > OvlpSelfJoin::ele_lists

◆ heap

std::vector<int> OvlpSelfJoin::heap

◆ idmap_records

std::vector<std::pair<int, int> > OvlpSelfJoin::idmap_records

◆ isHeap

int OvlpSelfJoin::isHeap {0}

◆ isWeightedComp

bool OvlpSelfJoin::isWeightedComp {false}

◆ maxHeapSize

ui OvlpSelfJoin::maxHeapSize {0}

◆ n

int OvlpSelfJoin::n {0}

◆ records

std::vector<std::vector<ui> > OvlpSelfJoin::records

◆ recWeights

std::vector<double> OvlpSelfJoin::recWeights

◆ result_num

int64_t OvlpSelfJoin::result_num {0}

◆ result_pairs

std::vector<std::pair<int, int> > OvlpSelfJoin::result_pairs

◆ result_pairs_

std::vector<WeightPair> OvlpSelfJoin::result_pairs_

◆ total_eles

ui OvlpSelfJoin::total_eles {0}

◆ wordwt

std::vector<double> OvlpSelfJoin::wordwt

The documentation for this class was generated from the following files: