Entity Matching by Similarity Join
 
Loading...
Searching...
No Matches
Functions
feature_utils Namespace Reference

Functions

int overlap (const std::vector< std::string > &v1, const std::vector< std::string > &v2)
 
int tripletMin (int a, int b, int c)
 
double levDist (const std::string &v1, const std::string &v2)
 
double jaccard (const std::vector< std::string > &v1, const std::vector< std::string > &v2)
 
double cosine (const std::vector< std::string > &v1, const std::vector< std::string > &v2)
 
double dice (const std::vector< std::string > &v1, const std::vector< std::string > &v2)
 
double exactMatch (const std::string &s1, const std::string &s2)
 
double absoluteNorm (const std::string &s1, const std::string &s2)
 
void stringSplit (std::string str, char delim, std::vector< std::string > &res)
 
void tokenize (const std::string &str, const std::string &type, std::vector< std::string > &tokens, const std::string &delims)
 

Function Documentation

◆ absoluteNorm()

double feature_utils::absoluteNorm ( const std::string & s1,
const std::string & s2 )
inline

◆ cosine()

double feature_utils::cosine ( const std::vector< std::string > & v1,
const std::vector< std::string > & v2 )
inline

◆ dice()

double feature_utils::dice ( const std::vector< std::string > & v1,
const std::vector< std::string > & v2 )
inline

◆ exactMatch()

double feature_utils::exactMatch ( const std::string & s1,
const std::string & s2 )
inline

◆ jaccard()

double feature_utils::jaccard ( const std::vector< std::string > & v1,
const std::vector< std::string > & v2 )
inline

◆ levDist()

double feature_utils::levDist ( const std::string & v1,
const std::string & v2 )
inline

◆ overlap()

int feature_utils::overlap ( const std::vector< std::string > & v1,
const std::vector< std::string > & v2 )
inline

◆ stringSplit()

void feature_utils::stringSplit ( std::string str,
char delim,
std::vector< std::string > & res )
inline

◆ tokenize()

void feature_utils::tokenize ( const std::string & str,
const std::string & type,
std::vector< std::string > & tokens,
const std::string & delims )
inline

◆ tripletMin()

int feature_utils::tripletMin ( int a,
int b,
int c )
inline