org.apache.ignite.ml.selection.cv

Class CrossValidation<M extends Model<Vector,L>,L,K,V>

java.lang.Object

org.apache.ignite.ml.selection.cv.CrossValidation<M,L,K,V>

Type Parameters:

M - Type of model.

L - Type of a label (truth or prediction).

K - Type of a key in upstream data.

V - Type of a value in upstream data.

public class CrossValidation<M extends Model<Vector,L>,L,K,V>
extends Object

Cross validation score calculator. Cross validation is an approach that allows to avoid overfitting that is made the following way: the training set is split into k smaller sets. The following procedure is followed for each of the k ?folds?:

• A model is trained using k-1 of the folds as training data;
• the resulting model is validated on the remaining part of the data (i.e., it is used as a test set to compute a performance measure such as accuracy).

Constructor Summary

Constructors

Constructor and Description
CrossValidation()

Method Summary

Modifier and Type	Method and Description
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Ignite ignite, IgniteCache<K,V> upstreamCache, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, int cv) Computes cross-validated metrics.
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Ignite ignite, IgniteCache<K,V> upstreamCache, IgniteBiPredicate<K,V> filter, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, int cv) Computes cross-validated metrics.
CrossValidationResult	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Ignite ignite, IgniteCache<K,V> upstreamCache, IgniteBiPredicate<K,V> filter, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, int cv, ParamGrid paramGrid) Computes cross-validated metrics with a passed parameter grid.
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Ignite ignite, IgniteCache<K,V> upstreamCache, IgniteBiPredicate<K,V> filter, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, UniformMapper<K,V> mapper, int cv) Computes cross-validated metrics.
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Map<K,V> upstreamMap, IgniteBiPredicate<K,V> filter, int parts, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, int cv) Computes cross-validated metrics.
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Map<K,V> upstreamMap, IgniteBiPredicate<K,V> filter, int parts, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, UniformMapper<K,V> mapper, int cv) Computes cross-validated metrics.
double[]	score(DatasetTrainer<M,L> trainer, Metric<L> scoreCalculator, Map<K,V> upstreamMap, int parts, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,L> lbExtractor, int cv) Computes cross-validated metrics.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CrossValidation

public CrossValidation()

Method Detail

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Ignite ignite,
                      IgniteCache<K,V> upstreamCache,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Score calculator.

ignite - Ignite instance.

upstreamCache - Ignite cache with upstream data.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Ignite ignite,
                      IgniteCache<K,V> upstreamCache,
                      IgniteBiPredicate<K,V> filter,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

ignite - Ignite instance.

upstreamCache - Ignite cache with upstream data.

filter - Base upstream data filter.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public CrossValidationResult score(DatasetTrainer<M,L> trainer,
                                   Metric<L> scoreCalculator,
                                   Ignite ignite,
                                   IgniteCache<K,V> upstreamCache,
                                   IgniteBiPredicate<K,V> filter,
                                   IgniteBiFunction<K,V,Vector> featureExtractor,
                                   IgniteBiFunction<K,V,L> lbExtractor,
                                   int cv,
                                   ParamGrid paramGrid)

Computes cross-validated metrics with a passed parameter grid. The real cross-validation training will be called each time for each parameter set.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

ignite - Ignite instance.

upstreamCache - Ignite cache with upstream data.

filter - Base upstream data filter.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

cv - Number of folds.

paramGrid - Parameter grid.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Ignite ignite,
                      IgniteCache<K,V> upstreamCache,
                      IgniteBiPredicate<K,V> filter,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      UniformMapper<K,V> mapper,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

ignite - Ignite instance.

upstreamCache - Ignite cache with upstream data.

filter - Base upstream data filter.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

mapper - Mapper used to map a key-value pair to a point on the segment (0, 1).

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Map<K,V> upstreamMap,
                      int parts,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

upstreamMap - Map with upstream data.

parts - Number of partitions.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Map<K,V> upstreamMap,
                      IgniteBiPredicate<K,V> filter,
                      int parts,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

upstreamMap - Map with upstream data.

filter - Base upstream data filter.

parts - Number of partitions.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.

score

public double[] score(DatasetTrainer<M,L> trainer,
                      Metric<L> scoreCalculator,
                      Map<K,V> upstreamMap,
                      IgniteBiPredicate<K,V> filter,
                      int parts,
                      IgniteBiFunction<K,V,Vector> featureExtractor,
                      IgniteBiFunction<K,V,L> lbExtractor,
                      UniformMapper<K,V> mapper,
                      int cv)

Computes cross-validated metrics.

Parameters:

trainer - Trainer of the model.

scoreCalculator - Base score calculator.

upstreamMap - Map with upstream data.

filter - Base upstream data filter.

parts - Number of partitions.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

mapper - Mapper used to map a key-value pair to a point on the segment (0, 1).

cv - Number of folds.

Returns:

Array of scores of the estimator for each run of the cross validation.