singlepp::TrainSingleOptions Struct Reference

Options for train_single() and friends. More...

#include <train_single.hpp>

Public Attributes
int	top = -1
int	num_threads = 1

Detailed Description

Options for train_single() and friends.

Member Data Documentation

num_threads

int singlepp::TrainSingleOptions::num_threads = 1

Number of threads to use. The parallelization scheme is determined by tatami::parallelize().

top

int singlepp::TrainSingleOptions::top = -1

Number of top markers to use from each pairwise comparison between labels. Larger values improve the stability of the correlations at the cost of increasing noise and computational work.

When the test and reference datasets do not have the same features, the specified number of top markers is taken from the intersection of features. This avoids that some markers will be selected even if not all genes in markers are present in the test dataset.

Setting this to a negative value will instruct train_single() to use all supplied markers. This is useful in situations where the supplied markers have already been curated.

---

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

• singlepp/train_single.hpp