Package | Description |
---|---|
org.apache.ignite.ml.composition.boosting.convergence |
Package contains implementation of convergency checking algorithms for gradient boosting.
|
org.apache.ignite.ml.composition.boosting.convergence.mean |
Contains implementation of convergence checking computer by mean of absolute value of errors in dataset.
|
org.apache.ignite.ml.composition.boosting.convergence.median |
Contains implementation of convergence checking computer by median of medians of errors in dataset.
|
org.apache.ignite.ml.composition.boosting.convergence.simple |
Contains implementation of Stub for convergence checking.
|
org.apache.ignite.ml.dataset |
Base package for machine learning dataset classes.
|
org.apache.ignite.ml.dataset.impl.cache |
Base package for cache based implementation of machine learning dataset.
|
org.apache.ignite.ml.dataset.impl.local |
Base package for local implementation of machine learning dataset.
|
org.apache.ignite.ml.dataset.primitive |
Package that contains basic primitives build on top of
Dataset . |
org.apache.ignite.ml.knn |
Contains main APIs for kNN algorithms.
|
org.apache.ignite.ml.knn.classification |
Contains main APIs for kNN classification algorithms.
|
org.apache.ignite.ml.knn.regression |
Contains helper classes for kNN regression algorithms.
|
org.apache.ignite.ml.knn.utils |
Contains util functionality for kNN algorithms.
|
org.apache.ignite.ml.nn |
Contains neural networks and related classes.
|
org.apache.ignite.ml.tree |
Root package for decision trees.
|
org.apache.ignite.ml.tree.leaf |
Root package for decision trees leaf builders.
|
org.apache.ignite.ml.tree.randomforest |
Contains random forest implementation classes.
|
org.apache.ignite.ml.tree.randomforest.data.impurity |
Contains implementation of impurity computers based on histograms.
|
org.apache.ignite.ml.tree.randomforest.data.statistics |
Contains implementation of statistics computers for Random Forest.
|
Modifier and Type | Method and Description |
---|---|
abstract Double |
ConvergenceChecker.computeMeanErrorOnDataset(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition mdl)
Compute error for given model on learning dataset.
|
boolean |
ConvergenceChecker.isConverged(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition currMdl)
Checks convergency on dataset.
|
Modifier and Type | Method and Description |
---|---|
Double |
MeanAbsValueConvergenceChecker.computeMeanErrorOnDataset(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition mdl)
Compute error for given model on learning dataset.
|
Modifier and Type | Method and Description |
---|---|
Double |
MedianOfMedianConvergenceChecker.computeMeanErrorOnDataset(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition mdl)
Compute error for given model on learning dataset.
|
Modifier and Type | Method and Description |
---|---|
Double |
ConvergenceCheckerStub.computeMeanErrorOnDataset(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition mdl)
Compute error for given model on learning dataset.
|
boolean |
ConvergenceCheckerStub.isConverged(Dataset<EmptyContext,? extends FeatureMatrixWithLabelsOnHeapData> dataset,
ModelsComposition currMdl)
Checks convergency on dataset.
|
Modifier and Type | Method and Description |
---|---|
default <I extends Dataset<C,D>> |
Dataset.wrap(IgniteFunction<Dataset<C,D>,I> wrapper)
Wraps this dataset into the specified wrapper to introduce new functionality based on
compute and
computeWithCtx methods. |
Modifier and Type | Method and Description |
---|---|
<C extends Serializable,D extends AutoCloseable> |
DatasetBuilder.build(LearningEnvironmentBuilder envBuilder,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder,
LearningEnvironment localLearningEnv)
Constructs a new instance of
Dataset that includes allocation required data structures and
initialization of context part of partitions. |
static <K,V,C extends Serializable,D extends AutoCloseable> |
DatasetFactory.create(DatasetBuilder<K,V> datasetBuilder,
LearningEnvironmentBuilder envBuilder,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder,
LearningEnvironment environment)
Creates a new instance of distributed dataset using the specified
partCtxBuilder and partDataBuilder . |
static <K,V,C extends Serializable,D extends AutoCloseable> |
DatasetFactory.create(DatasetBuilder<K,V> datasetBuilder,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder)
Creates a new instance of distributed dataset using the specified
partCtxBuilder and partDataBuilder . |
static <K,V,C extends Serializable,D extends AutoCloseable> |
DatasetFactory.create(Ignite ignite,
IgniteCache<K,V> upstreamCache,
LearningEnvironmentBuilder envBuilder,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder,
LearningEnvironment environment)
Creates a new instance of distributed dataset using the specified
partCtxBuilder and partDataBuilder . |
static <K,V,C extends Serializable,D extends AutoCloseable> |
DatasetFactory.create(Ignite ignite,
IgniteCache<K,V> upstreamCache,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder)
Creates a new instance of distributed dataset using the specified
partCtxBuilder and partDataBuilder . |
static <K,V,C extends Serializable,D extends AutoCloseable> |
DatasetFactory.create(Map<K,V> upstreamMap,
LearningEnvironmentBuilder envBuilder,
int partitions,
PartitionContextBuilder<K,V,C> partCtxBuilder,
PartitionDataBuilder<K,V,C,D> partDataBuilder,
LearningEnvironment environment)
Creates a new instance of local dataset using the specified
partCtxBuilder and partDataBuilder . |
Modifier and Type | Method and Description |
---|---|
default <I extends Dataset<C,D>> |
Dataset.wrap(IgniteFunction<Dataset<C,D>,I> wrapper)
Wraps this dataset into the specified wrapper to introduce new functionality based on
compute and
computeWithCtx methods. |
Modifier and Type | Class and Description |
---|---|
class |
CacheBasedDataset<K,V,C extends Serializable,D extends AutoCloseable>
An implementation of dataset based on Ignite Cache, which is used as
upstream and as reliable storage for
partition context as well. |
Modifier and Type | Class and Description |
---|---|
class |
LocalDataset<C extends Serializable,D extends AutoCloseable>
An implementation of dataset based on local data structures such as
Map and List and doesn't require
Ignite environment. |
Modifier and Type | Class and Description |
---|---|
class |
DatasetWrapper<C extends Serializable,D extends AutoCloseable>
A dataset wrapper that allows to introduce new functionality based on common
compute methods. |
class |
SimpleDataset<C extends Serializable>
A simple dataset introduces additional methods based on a matrix of features.
|
class |
SimpleLabeledDataset<C extends Serializable>
A simple labeled dataset introduces additional methods based on a matrix of features and labels vector.
|
Modifier and Type | Field and Description |
---|---|
protected Dataset<C,D> |
DatasetWrapper.delegate
Delegate that performs
compute actions. |
Constructor and Description |
---|
DatasetWrapper(Dataset<C,D> delegate)
Constructs a new instance of dataset wrapper that delegates
compute actions to the actual delegate. |
SimpleDataset(Dataset<C,SimpleDatasetData> delegate)
Creates a new instance of simple dataset that introduces additional methods based on a matrix of features.
|
SimpleLabeledDataset(Dataset<C,SimpleLabeledDatasetData> delegate)
Creates a new instance of simple labeled dataset that introduces additional methods based on a matrix of features
and labels vector.
|
Modifier and Type | Method and Description |
---|---|
protected abstract M |
KNNTrainer.convertDatasetIntoModel(Dataset<EmptyContext,SpatialIndex<Double>> dataset)
Convers given dataset into KNN model (classification or regression depends on implementation).
|
Constructor and Description |
---|
KNNModel(Dataset<EmptyContext,SpatialIndex<L>> dataset,
DistanceMeasure distanceMeasure,
int k,
boolean weighted)
Constructs a new instance of KNN model.
|
Modifier and Type | Method and Description |
---|---|
protected KNNClassificationModel |
KNNClassificationTrainer.convertDatasetIntoModel(Dataset<EmptyContext,SpatialIndex<Double>> dataset)
Convers given dataset into KNN model (classification or regression depends on implementation).
|
Modifier and Type | Method and Description |
---|---|
protected KNNRegressionModel |
KNNRegressionTrainer.convertDatasetIntoModel(Dataset<EmptyContext,SpatialIndex<Double>> dataset)
Convers given dataset into KNN model (classification or regression depends on implementation).
|
Modifier and Type | Method and Description |
---|---|
static <K,V,C extends Serializable> |
KNNUtils.buildDataset(LearningEnvironmentBuilder envBuilder,
DatasetBuilder<K,V> datasetBuilder,
Preprocessor<K,V> vectorizer)
Builds dataset.
|
Modifier and Type | Method and Description |
---|---|
IgniteFunction<Dataset<EmptyContext,SimpleLabeledDatasetData>,MLPArchitecture> |
MLPTrainer.getArchSupplier()
Get the multilayer perceptron architecture supplier that defines layers and activators.
|
Modifier and Type | Method and Description |
---|---|
MLPTrainer<P> |
MLPTrainer.withArchSupplier(IgniteFunction<Dataset<EmptyContext,SimpleLabeledDatasetData>,MLPArchitecture> archSupplier)
Set up the multilayer perceptron architecture supplier that defines layers and activators.
|
Constructor and Description |
---|
MLPTrainer(IgniteFunction<Dataset<EmptyContext,SimpleLabeledDatasetData>,MLPArchitecture> archSupplier,
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
UpdatesStrategy<? super MultilayerPerceptron,P> updatesStgy,
int maxIterations,
int batchSize,
int locIterations,
long seed)
Constructs a new instance of multilayer perceptron trainer.
|
Modifier and Type | Method and Description |
---|---|
<K,V> DecisionTreeNode |
DecisionTree.fit(Dataset<EmptyContext,DecisionTreeData> dataset) |
protected abstract ImpurityMeasureCalculator<T> |
DecisionTree.getImpurityMeasureCalculator(Dataset<EmptyContext,DecisionTreeData> dataset)
Returns impurity measure calculator.
|
protected ImpurityMeasureCalculator<GiniImpurityMeasure> |
DecisionTreeClassificationTrainer.getImpurityMeasureCalculator(Dataset<EmptyContext,DecisionTreeData> dataset)
Returns impurity measure calculator.
|
protected ImpurityMeasureCalculator<MSEImpurityMeasure> |
DecisionTreeRegressionTrainer.getImpurityMeasureCalculator(Dataset<EmptyContext,DecisionTreeData> dataset)
Returns impurity measure calculator.
|
Modifier and Type | Method and Description |
---|---|
DecisionTreeLeafNode |
MeanDecisionTreeLeafBuilder.createLeafNode(Dataset<EmptyContext,DecisionTreeData> dataset,
TreeFilter pred)
Creates new leaf node for given dataset and node predicate.
|
DecisionTreeLeafNode |
MostCommonDecisionTreeLeafBuilder.createLeafNode(Dataset<EmptyContext,DecisionTreeData> dataset,
TreeFilter pred)
Creates new leaf node for given dataset and node predicate.
|
DecisionTreeLeafNode |
DecisionTreeLeafBuilder.createLeafNode(Dataset<EmptyContext,DecisionTreeData> dataset,
TreeFilter pred)
Creates new leaf node for given dataset and node predicate.
|
Modifier and Type | Method and Description |
---|---|
protected boolean |
RandomForestClassifierTrainer.init(Dataset<EmptyContext,BootstrappedDatasetPartition> dataset)
Aggregates all unique labels from dataset and assigns integer id value for each label.
|
protected boolean |
RandomForestTrainer.init(Dataset<EmptyContext,BootstrappedDatasetPartition> dataset)
Init-step before learning.
|
Modifier and Type | Method and Description |
---|---|
Map<NodeId,ImpurityHistogramsComputer.NodeImpurityHistograms<S>> |
ImpurityHistogramsComputer.aggregateImpurityStatistics(ArrayList<TreeRoot> roots,
Map<Integer,BucketMeta> histMeta,
Map<NodeId,TreeNode> nodesToLearn,
Dataset<EmptyContext,BootstrappedDatasetPartition> dataset)
Computes histograms for each feature.
|
Modifier and Type | Method and Description |
---|---|
List<NormalDistributionStatistics> |
NormalDistributionStatisticsComputer.computeStatistics(List<FeatureMeta> meta,
Dataset<EmptyContext,BootstrappedDatasetPartition> dataset)
Computes statistics of normal distribution on features in dataset.
|
void |
LeafValuesComputer.setValuesForLeaves(ArrayList<TreeRoot> roots,
Dataset<EmptyContext,BootstrappedDatasetPartition> dataset)
Takes a list of all built trees and in one map-reduceImpurityStatistics step collect statistics for evaluating
leaf-values for each tree and sets values for leaves.
|
GridGain In-Memory Computing Platform : ver. 8.9.14 Release Date : November 5 2024