Classifier trained from a single reference. More...

#include <train_single.hpp>

Public Member Functions
const Markers< Index_ > &	get_markers () const

const std::vector< Index_ > &	get_subset () const

size_t	num_labels () const

size_t	num_profiles () const

Detailed Description

template<typename Index_, typename Float_>
class singlepp::TrainedSingle< Index_, Float_ >

Classifier trained from a single reference.

Instances of this class should not be directly constructed, but instead returned by calling train_single() on a reference dataset. Each instance can be used in classify_single() with a test dataset that has the same number and order of genes as the reference dataset.

Template Parameters

Index_	Integer type for the row/column indices of the matrix.
Float_	Floating-point type for the correlations and scores.

Member Function Documentation

◆ get_markers()

template<typename Index_ , typename Float_ >

const Markers< Index_ > & singlepp::TrainedSingle< Index_, Float_ >::get_markers ( ) const

inline

Returns: A vector of vectors of vectors of ranked marker genes to be used in the classification. In the innermost vectors, each value is an index into the subset vector (see get_subset()), e.g., get_subset()[get_markers()[2][1].front()] is the row index of the first marker of the third label over the first label. The set of marker genes is a subset of the input markers used in train_single().