pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::Hubness Struct Reference

How unevenly points appear in each other's neighbor lists. More...

#include <nearest_neighbors.hpp>

Public Attributes

std::vector< int64_t > occurrences
 How many neighbor lists each point appears in (its "k-occurrence"). The mean is k.
 
double skewness = 0
 The skewness of occurrences. Near 0 when points appear about equally often; well above 1 means a few hubs dominate (Radovanović et al., JMLR 2010).
 
int64_t max_occurrence = 0
 The most lists any one point is in, and its fraction of all queries.
 
double max_fraction = 0
 
double never_a_neighbor = 0
 The fraction of points in nobody's list.
 

Detailed Description

How unevenly points appear in each other's neighbor lists.

Member Data Documentation

◆ max_fraction

double pulsatrix::Hubness::max_fraction = 0

◆ max_occurrence

int64_t pulsatrix::Hubness::max_occurrence = 0

The most lists any one point is in, and its fraction of all queries.

◆ never_a_neighbor

double pulsatrix::Hubness::never_a_neighbor = 0

The fraction of points in nobody's list.

◆ occurrences

std::vector<int64_t> pulsatrix::Hubness::occurrences

How many neighbor lists each point appears in (its "k-occurrence"). The mean is k.

◆ skewness

double pulsatrix::Hubness::skewness = 0

The skewness of occurrences. Near 0 when points appear about equally often; well above 1 means a few hubs dominate (Radovanović et al., JMLR 2010).


The documentation for this struct was generated from the following file: