pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::ClusterSampler Class Reference

Cluster-weighted sampling, as ESM-2 drew UniRef50: a cluster uniformly, then one of its members uniformly, so large families don't dominate. With every sequence its own cluster, it is uniform sampling with replacement. More...

#include <protein_training.hpp>

Public Member Functions

 ClusterSampler (const std::vector< std::string > &cluster_of, uint64_t seed=0)
 
int64_t next ()
 The next sequence's index.
 
int64_t num_clusters () const
 

Detailed Description

Cluster-weighted sampling, as ESM-2 drew UniRef50: a cluster uniformly, then one of its members uniformly, so large families don't dominate. With every sequence its own cluster, it is uniform sampling with replacement.

Constructor & Destructor Documentation

◆ ClusterSampler()

pulsatrix::ClusterSampler::ClusterSampler ( const std::vector< std::string > &  cluster_of,
uint64_t  seed = 0 
)
Parameters
cluster_ofEach sequence's cluster, any ids.
Exceptions
std::invalid_argumentif empty.

Member Function Documentation

◆ next()

int64_t pulsatrix::ClusterSampler::next ( )

The next sequence's index.

◆ num_clusters()

int64_t pulsatrix::ClusterSampler::num_clusters ( ) const
inline

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