Entity Matching by Similarity Join
 
Loading...
Searching...
No Matches
group.h File Reference
#include "common/tokenizer.h"
#include <sstream>
#include <string>
#include <vector>
#include <unordered_map>

Go to the source code of this file.

Classes

class  GroupInterchangeable
 

Namespaces

namespace  feature_utils
 

Typedefs

using Groups = std::vector<std::unordered_map<int, std::vector<std::string>>>
 
using GroupTokens = std::vector<std::unordered_map<int, std::vector<std::vector<std::string>>>>
 
using Clusters = std::vector<std::unordered_map<std::string, int>>
 

Functions

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

Typedef Documentation

◆ Clusters

using Clusters = std::vector<std::unordered_map<std::string, int>>

◆ Groups

using Groups = std::vector<std::unordered_map<int, std::vector<std::string>>>

◆ GroupTokens

using GroupTokens = std::vector<std::unordered_map<int, std::vector<std::vector<std::string>>>>