Package | Description |
---|---|
org.apache.ignite.ml.clustering.gmm |
Contains Gauss Mixture Model clustering algorithm (see
GmmModel ). |
org.apache.ignite.ml.clustering.kmeans |
Contains kMeans clustering algorithm.
|
org.apache.ignite.ml.composition |
Contains classes for ensemble of models implementation.
|
org.apache.ignite.ml.composition.bagging |
Contains bootstrap aggregation (bagging) trainer allowing to combine some other trainers and
return a bagged version of them.
|
org.apache.ignite.ml.composition.boosting |
Contains Gradient Boosting regression and classification abstract classes
allowing regressor type selecting in child classes.
|
org.apache.ignite.ml.composition.boosting.convergence |
Package contains implementation of convergency checking algorithms for gradient boosting.
|
org.apache.ignite.ml.composition.stacking |
Contains classes used for training with stacking technique.
|
org.apache.ignite.ml.dataset.feature.extractor |
Package for upstream object vectorizations.
|
org.apache.ignite.ml.dataset.feature.extractor.impl |
Package contains default implementations of
Vectorizer . |
org.apache.ignite.ml.dataset.impl.bootstrapping |
Base package for bootstrapped implementation of machine learning dataset.
|
org.apache.ignite.ml.environment.logging |
Package contains several logging strategy realisations.
|
org.apache.ignite.ml.inference |
Root package for model inference functionality.
|
org.apache.ignite.ml.knn |
Contains main APIs for kNN algorithms.
|
org.apache.ignite.ml.knn.ann |
Contains main APIs for ANN classification 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.knn.utils.indices |
Contains utils functionality for indices in kNN algorithms.
|
org.apache.ignite.ml.math |
Contains main APIs for matrix/vector algebra.
|
org.apache.ignite.ml.math.distances |
Contains main APIs for distances.
|
org.apache.ignite.ml.math.functions |
Contains serializable functions for distributed code algebra.
|
org.apache.ignite.ml.math.primitives.matrix |
Contains matrix related classes.
|
org.apache.ignite.ml.math.primitives.matrix.impl |
Contains several matrix implementations.
|
org.apache.ignite.ml.math.primitives.vector |
Contains vector related classes.
|
org.apache.ignite.ml.math.primitives.vector.impl |
Contains several vector implementations.
|
org.apache.ignite.ml.math.stat |
Contains utility classes for distributions.
|
org.apache.ignite.ml.math.util |
Some math utils.
|
org.apache.ignite.ml.multiclass |
Contains various multi-classifier models and trainers.
|
org.apache.ignite.ml.naivebayes.discrete |
Contains Bernoulli naive Bayes classifier.
|
org.apache.ignite.ml.naivebayes.gaussian |
Contains Gaussian naive Bayes classifier.
|
org.apache.ignite.ml.nn |
Contains neural networks and related classes.
|
org.apache.ignite.ml.nn.initializers |
Contains multilayer perceptron parameters initializers.
|
org.apache.ignite.ml.optimization |
Contains implementations of optimization algorithms and related classes.
|
org.apache.ignite.ml.optimization.updatecalculators |
Contains update calculators.
|
org.apache.ignite.ml.pipeline |
Contains Pipeline API.
|
org.apache.ignite.ml.preprocessing.imputing |
Contains Imputer preprocessor.
|
org.apache.ignite.ml.recommendation |
Contains recommendation system framework.
|
org.apache.ignite.ml.recommendation.util |
Contains util classes used in recommendation system framework.
|
org.apache.ignite.ml.regressions.linear |
Contains various linear regressions.
|
org.apache.ignite.ml.regressions.logistic |
Contains various logistic regressions.
|
org.apache.ignite.ml.selection.cv |
Root package for cross-validation algorithms.
|
org.apache.ignite.ml.selection.scoring.cursor |
Util classes used for score calculation.
|
org.apache.ignite.ml.selection.scoring.evaluator |
Package for model evaluator classes.
|
org.apache.ignite.ml.structures |
Contains some internal utility structures.
|
org.apache.ignite.ml.svm |
Contains main APIs for SVM(support vector machines) algorithms.
|
org.apache.ignite.ml.trainers |
Contains model trainers.
|
org.apache.ignite.ml.tree |
Root package for decision trees.
|
org.apache.ignite.ml.tree.boosting |
Contains implementation of gradient boosting on trees.
|
org.apache.ignite.ml.tree.impurity |
Root package for decision tree impurity measures and calculators.
|
org.apache.ignite.ml.tree.randomforest.data |
Package contains helper data structures for random forest implementation.
|
org.apache.ignite.ml.util |
Contains some utils for ML module.
|
org.apache.ignite.ml.util.generators |
Contains utility classes for data streams generation.
|
org.apache.ignite.ml.util.generators.primitives.scalar |
Contains generators of pseudo-random scalars in according to specific disctribution.
|
org.apache.ignite.ml.util.generators.primitives.vector |
Contains generators of pseudo-random vectors in according to specific disctribution.
|
org.apache.ignite.ml.util.generators.standard |
Contains classes for predefined data stream generators.
|
Modifier and Type | Method and Description |
---|---|
Vector |
NewComponentStatisticsAggregator.mean() |
Modifier and Type | Method and Description |
---|---|
Double |
GmmModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
GmmTrainer |
GmmTrainer.withInitialMeans(List<Vector> means)
Sets initial means.
|
Constructor and Description |
---|
GmmModel(Vector componentProbs,
List<MultivariateGaussianDistribution> distributions)
Creates an instance of GmmModel.
|
NewComponentStatisticsAggregator(long totalRowCount,
long rowCountForNewCluster,
Vector sumOfAnomalies)
Creates an instance of NewComponentStatisticsAggregator.
|
Modifier and Type | Method and Description |
---|---|
Vector[] |
KMeansModel.getCenters()
Get cluster centers.
|
Vector[] |
KMeansModelFormat.getCenters() |
Modifier and Type | Method and Description |
---|---|
Integer |
KMeansModel.predict(Vector vec)
Make a prediction for the specified input arguments.
|
Constructor and Description |
---|
KMeansModel(Vector[] centers,
DistanceMeasure distanceMeasure)
Construct KMeans model with given centers and distanceMeasure measure.
|
KMeansModelFormat(Vector[] centers,
DistanceMeasure distance) |
Modifier and Type | Method and Description |
---|---|
default Vector |
DatasetMapping.mapFeatures(Vector v)
Method used to map feature vectors.
|
Modifier and Type | Method and Description |
---|---|
static <K,V,L> IgniteBiFunction<K,V,Vector> |
CompositionUtils.asFeatureExtractor(FeatureLabelExtractor<K,V,L> extractor)
Create feature extractor from given mapping
(key, value) -> LabeledVector . |
IgniteModel<Vector,Double> |
ModelOnFeaturesSubspace.getMdl()
Returns model.
|
List<IgniteModel<Vector,Double>> |
ModelsComposition.getModels()
Returns containing models.
|
List<IgniteModel<Vector,Double>> |
ModelsCompositionFormat.models() |
Modifier and Type | Method and Description |
---|---|
default Vector |
DatasetMapping.mapFeatures(Vector v)
Method used to map feature vectors.
|
Double |
ModelOnFeaturesSubspace.predict(Vector features)
Projects features vector to subspace in according to mapping and apply model to it.
|
Double |
ModelsComposition.predict(Vector features)
Applies containing models to features and aggregate them to one prediction.
|
Modifier and Type | Method and Description |
---|---|
static <L> DatasetMapping<L,L> |
DatasetMapping.mappingFeatures(IgniteFunction<Vector,Vector> mapper)
Dataset mapping which maps features, leaving labels unaffected.
|
static <L> DatasetMapping<L,L> |
DatasetMapping.mappingFeatures(IgniteFunction<Vector,Vector> mapper)
Dataset mapping which maps features, leaving labels unaffected.
|
Constructor and Description |
---|
ModelsComposition(List<? extends IgniteModel<Vector,Double>> models,
PredictionsAggregator predictionsAggregator)
Constructs a new instance of composition of models.
|
ModelsCompositionFormat(List<IgniteModel<Vector,Double>> models,
PredictionsAggregator predictionsAggregator)
Creates an instance of ModelsCompositionFormat.
|
Modifier and Type | Method and Description |
---|---|
Double |
BaggedModel.predict(Vector i)
Make a prediction for the specified input arguments.
|
Modifier and Type | Field and Description |
---|---|
protected IgniteSupplier<DatasetTrainer<? extends IgniteModel<Vector,Double>,Double>> |
GDBLearningStrategy.baseMdlTrainerBuilder
Base model trainer builder.
|
Modifier and Type | Method and Description |
---|---|
<K,V> List<IgniteModel<Vector,Double>> |
GDBLearningStrategy.learnModels(DatasetBuilder<K,V> datasetBuilder,
Preprocessor<K,V> preprocessor)
Implementation of gradient boosting iterations.
|
<K,V> List<IgniteModel<Vector,Double>> |
GDBLearningStrategy.update(GDBTrainer.GDBModel mdlToUpdate,
DatasetBuilder<K,V> datasetBuilder,
Preprocessor<K,V> preprocessor)
Gets state of model in arguments, compare it with training parameters of trainer and if they are fit then trainer
updates model in according to new data and return new model.
|
Modifier and Type | Method and Description |
---|---|
Double |
GDBTrainer.GDBModel.predict(Vector features)
Applies containing models to features and aggregate them to one prediction.
|
Modifier and Type | Method and Description |
---|---|
GDBLearningStrategy |
GDBLearningStrategy.withBaseModelTrainerBuilder(IgniteSupplier<DatasetTrainer<? extends IgniteModel<Vector,Double>,Double>> buildBaseMdlTrainer)
Sets base model builder.
|
Constructor and Description |
---|
GDBModel(List<? extends IgniteModel<Vector,Double>> models,
WeightedPredictionsAggregator predictionsAggregator,
IgniteFunction<Double,Double> internalToExternalLblMapping)
Creates an instance of GDBModel.
|
Modifier and Type | Method and Description |
---|---|
double |
ConvergenceChecker.computeError(Vector features,
Double answer,
ModelsComposition currMdl)
Compute error for the specific vector of dataset.
|
Modifier and Type | Class and Description |
---|---|
class |
StackedVectorDatasetTrainer<O,AM extends IgniteModel<Vector,O>,L>
StackedDatasetTrainer with Vector as submodels input and output. |
Modifier and Type | Method and Description |
---|---|
<M1 extends IgniteModel<Vector,Vector>> |
StackedVectorDatasetTrainer.addTrainer(DatasetTrainer<M1,L> trainer)
Adds submodel trainer along with converters needed on training and inference stages.
|
<M1 extends IgniteModel<Vector,Vector>> |
StackedVectorDatasetTrainer.addTrainer(DatasetTrainer<M1,L> trainer)
Adds submodel trainer along with converters needed on training and inference stages.
|
<M1 extends IgniteModel<Vector,Double>> |
StackedVectorDatasetTrainer.addTrainerWithDoubleOutput(DatasetTrainer<M1,L> trainer)
Shortcut for adding trainer
Vector -> Double where this trainer is treated as Vector -> Vector , where
output Vector is constructed by wrapping double value. |
Modifier and Type | Method and Description |
---|---|
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withAggregatorInputMerger(IgniteBinaryOperator<Vector> merger)
Specify binary operator used to merge submodels outputs to one.
|
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withOriginalFeaturesKept(IgniteFunction<Vector,Vector> submodelInput2AggregatingInputConverter)
Keep original features during training and propagate submodels input to aggregator during inference
using given function.
|
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withOriginalFeaturesKept(IgniteFunction<Vector,Vector> submodelInput2AggregatingInputConverter)
Keep original features during training and propagate submodels input to aggregator during inference
using given function.
|
StackedDatasetTrainer<IS,IA,O,AM,L> |
StackedDatasetTrainer.withSubmodelOutput2VectorConverter(IgniteFunction<IA,Vector> submodelOutput2VectorConverter)
Set function used for conversion of submodel output to
Vector . |
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withSubmodelOutput2VectorConverter(IgniteFunction<Vector,Vector> submodelOutput2VectorConverter)
Set function used for conversion of submodel output to
Vector . |
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withSubmodelOutput2VectorConverter(IgniteFunction<Vector,Vector> submodelOutput2VectorConverter)
Set function used for conversion of submodel output to
Vector . |
StackedDatasetTrainer<IS,IA,O,AM,L> |
StackedDatasetTrainer.withVector2SubmodelInputConverter(IgniteFunction<Vector,IS> vector2SubmodelInputConverter)
Set function used for conversion of
Vector to submodel input. |
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withVector2SubmodelInputConverter(IgniteFunction<Vector,Vector> vector2SubmodelInputConverter)
Set function used for conversion of
Vector to submodel input. |
StackedVectorDatasetTrainer<O,AM,L> |
StackedVectorDatasetTrainer.withVector2SubmodelInputConverter(IgniteFunction<Vector,Vector> vector2SubmodelInputConverter)
Set function used for conversion of
Vector to submodel input. |
Constructor and Description |
---|
SimpleStackedDatasetTrainer(DatasetTrainer<AM,L> aggregatingTrainer,
IgniteBinaryOperator<I> aggregatingInputMerger,
IgniteFunction<I,I> submodelInput2AggregatingInputConverter,
IgniteFunction<Vector,I> vector2SubmodelInputConverter,
IgniteFunction<I,Vector> submodelOutput2VectorConverter)
Construct instance of this class.
|
SimpleStackedDatasetTrainer(DatasetTrainer<AM,L> aggregatingTrainer,
IgniteBinaryOperator<I> aggregatingInputMerger,
IgniteFunction<I,I> submodelInput2AggregatingInputConverter,
IgniteFunction<Vector,I> vector2SubmodelInputConverter,
IgniteFunction<I,Vector> submodelOutput2VectorConverter)
Construct instance of this class.
|
StackedDatasetTrainer(DatasetTrainer<AM,L> aggregatorTrainer,
IgniteBinaryOperator<IA> aggregatingInputMerger,
IgniteFunction<IS,IA> submodelInput2AggregatingInputConverter,
List<DatasetTrainer<IgniteModel<IS,IA>,L>> submodelsTrainers,
IgniteFunction<Vector,IS> vector2SubmodelInputConverter,
IgniteFunction<IA,Vector> submodelOutput2VectorConverter)
Create instance of this class.
|
StackedDatasetTrainer(DatasetTrainer<AM,L> aggregatorTrainer,
IgniteBinaryOperator<IA> aggregatingInputMerger,
IgniteFunction<IS,IA> submodelInput2AggregatingInputConverter,
List<DatasetTrainer<IgniteModel<IS,IA>,L>> submodelsTrainers,
IgniteFunction<Vector,IS> vector2SubmodelInputConverter,
IgniteFunction<IA,Vector> submodelOutput2VectorConverter)
Create instance of this class.
|
Modifier and Type | Method and Description |
---|---|
protected Vector |
Vectorizer.createVector(int size)
Create an instance of vector.
|
Modifier and Type | Method and Description |
---|---|
protected Vector |
BinaryObjectVectorizer.createVector(int size)
Create an instance of vector.
|
Modifier and Type | Method and Description |
---|---|
protected Serializable |
DummyVectorizer.feature(Integer coord,
K key,
Vector value)
Extracts feature value by given coordinate.
|
protected int |
DummyVectorizer.sizeOf(K key,
Vector value)
Size of array-like structure of upstream object.
|
Constructor and Description |
---|
BootstrappedVector(Vector features,
double lb,
int[] counters)
Creates an instance of BootstrappedVector.
|
Modifier and Type | Method and Description |
---|---|
Vector |
CustomMLLogger.log(Vector vector)
Log vector.
|
Vector |
ConsoleLogger.log(Vector vector)
Log vector.
|
Vector |
NoOpLogger.log(Vector vector)
Log vector.
|
Vector |
MLLogger.log(Vector vector)
Log vector.
|
Modifier and Type | Method and Description |
---|---|
Vector |
CustomMLLogger.log(Vector vector)
Log vector.
|
Vector |
ConsoleLogger.log(Vector vector)
Log vector.
|
Vector |
NoOpLogger.log(Vector vector)
Log vector.
|
Vector |
MLLogger.log(Vector vector)
Log vector.
|
Modifier and Type | Method and Description |
---|---|
static Model<Vector,Future<Double>> |
IgniteModelStorageUtil.getAsyncModel(Ignite ignite,
String name,
AsyncModelBuilder mdlBldr)
Retrieves Ignite model by name using asynchronous model builder.
|
Modifier and Type | Method and Description |
---|---|
List<LabeledVector<L>> |
KNNModel.findKClosest(int k,
Vector pnt)
Finds
k closest elements to the specified point. |
protected @NotNull TreeMap<Double,Set<Integer>> |
NNClassificationModel.getDistances(Vector v,
LabeledVectorSet<LabeledVector<Double>> trainingData)
Computes distances between given vector and each vector in training dataset.
|
Modifier and Type | Method and Description |
---|---|
Double |
ANNClassificationModel.predict(Vector v)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
Double |
KNNClassificationModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
Double |
KNNRegressionModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
static <L> void |
PointWithDistanceUtil.tryToAddIntoHeap(Queue<PointWithDistance<L>> heap,
int k,
Vector pnt,
List<LabeledVector<L>> dataPnts,
DistanceMeasure distanceMeasure)
Util method that adds data points into heap if they fits (if heap size is less than
k or a distance from
taget point to data point is less than a distance from target point to the most distant data point in heap). |
Modifier and Type | Method and Description |
---|---|
List<LabeledVector<L>> |
SpatialIndex.findKClosest(int k,
Vector pnt)
Finds
k closest elements to the specified point. |
List<LabeledVector<L>> |
KDTreeSpatialIndex.findKClosest(int k,
Vector pnt)
Finds
k closest elements to the specified point. |
List<LabeledVector<L>> |
BallTreeSpatialIndex.findKClosest(int k,
Vector pnt)
Finds
k closest elements to the specified point. |
List<LabeledVector<L>> |
ArraySpatialIndex.findKClosest(int k,
Vector pnt)
Finds
k closest elements to the specified point. |
Modifier and Type | Method and Description |
---|---|
static String |
Tracer.asAscii(Vector vec,
String fmt,
boolean showMeta) |
static void |
Blas.axpy(Double a,
Vector x,
Vector y)
Performs y += a * x
|
static void |
Blas.checkCardinality(Matrix a,
Vector v)
Checks if Matrix A can be multiplied by vector v, if not CardinalityException is thrown.
|
void |
Blas.copy(Vector x,
Vector y)
Copies Vector x into Vector y.
|
static Double |
Blas.dot(Vector x,
Vector y)
Returns dot product of vectors x and y.
|
static void |
Blas.gemv(double alpha,
Matrix a,
Vector x,
double beta,
Vector y)
y := alpha * A * x + beta * y.
|
static void |
Tracer.saveAsCsv(Vector vec,
String fmt,
String filePath)
Saves given vector as CSV file.
|
static void |
Blas.scal(Double a,
Vector x)
Performs in-place multiplication of vector x by a real scalar a.
|
static void |
Tracer.showAscii(Vector vec) |
static void |
Tracer.showAscii(Vector vec,
IgniteLogger log) |
static void |
Tracer.showAscii(Vector vec,
IgniteLogger log,
String fmt) |
static void |
Tracer.showAscii(Vector vec,
String fmt) |
static void |
Tracer.showHtml(Vector vec)
Shows given vector in the browser with D3-based visualization.
|
static void |
Tracer.showHtml(Vector vec,
boolean useAsciiFallback)
Shows given vector in the browser with D3-based visualization.
|
static void |
Tracer.showHtml(Vector vec,
Tracer.ColorMapper cm)
Shows given vector in the browser with D3-based visualization.
|
static void |
Tracer.showHtml(Vector vec,
Tracer.ColorMapper cm,
boolean useAsciiFallback)
Shows given vector in the browser with D3-based visualization.
|
Modifier and Type | Method and Description |
---|---|
double |
DistanceMeasure.compute(Vector a,
double[] b)
Compute the distance between n-dimensional vector and n-dimensional array.
|
double |
ManhattanDistance.compute(Vector a,
double[] b)
Compute the distance between n-dimensional vector and n-dimensional array.
|
double |
EuclideanDistance.compute(Vector a,
double[] b)
Compute the distance between n-dimensional vector and n-dimensional array.
|
double |
HammingDistance.compute(Vector a,
double[] b)
Compute the distance between n-dimensional vector and n-dimensional array.
|
double |
DistanceMeasure.compute(Vector a,
Vector b)
Compute the distance between two n-dimensional vectors.
|
double |
ManhattanDistance.compute(Vector a,
Vector b)
Compute the distance between two n-dimensional vectors.
|
double |
EuclideanDistance.compute(Vector a,
Vector b)
Compute the distance between two n-dimensional vectors.
|
double |
HammingDistance.compute(Vector a,
Vector b)
Compute the distance between two n-dimensional vectors.
|
Modifier and Type | Method and Description |
---|---|
Vector |
IgniteDifferentiableVectorToDoubleFunction.differential(Vector pnt)
Get function differential at a given point.
|
Modifier and Type | Method and Description |
---|---|
Vector |
IgniteDifferentiableVectorToDoubleFunction.differential(Vector pnt)
Get function differential at a given point.
|
Modifier and Type | Method and Description |
---|---|
Vector |
AbstractMatrix.foldColumns(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all columns in this matrix.
|
Vector |
Matrix.foldColumns(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all columns in this matrix.
|
Vector |
AbstractMatrix.foldRows(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all rows in this matrix.
|
Vector |
Matrix.foldRows(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all rows in this matrix.
|
Vector |
AbstractMatrix.getCol(int col)
Get a specific row from matrix.
|
Vector |
Matrix.getCol(int col)
Get a specific row from matrix.
|
Vector |
LUDecomposition.getPivot()
Returns the pivot permutation vector.
|
Vector |
AbstractMatrix.getRow(int row)
Get a specific row from matrix.
|
Vector |
Matrix.getRow(int row)
Get a specific row from matrix.
|
Vector |
Matrix.likeVector(int crd)
Creates new empty vector of compatible properties (similar or the same flavor) to this matrix.
|
Vector |
LUDecomposition.solve(Vector b) |
Vector |
AbstractMatrix.times(Vector vec)
Creates new matrix that is the product of multiplying this matrix and the argument vector.
|
Vector |
Matrix.times(Vector vec)
Creates new matrix that is the product of multiplying this matrix and the argument vector.
|
Vector |
AbstractMatrix.viewColumn(int col)
Creates new view into matrix column .
|
Vector |
Matrix.viewColumn(int col)
Creates new view into matrix column .
|
Vector |
AbstractMatrix.viewDiagonal()
Creates new view into matrix diagonal.
|
Vector |
Matrix.viewDiagonal()
Creates new view into matrix diagonal.
|
Vector |
AbstractMatrix.viewRow(int row)
Creates new view into matrix row.
|
Vector |
Matrix.viewRow(int row)
Creates new view into matrix row.
|
Modifier and Type | Method and Description |
---|---|
Matrix |
AbstractMatrix.assignColumn(int col,
Vector vec)
Assigns values from given vector to the specified column in this matrix.
|
Matrix |
Matrix.assignColumn(int col,
Vector vec)
Assigns values from given vector to the specified column in this matrix.
|
Matrix |
AbstractMatrix.assignRow(int row,
Vector vec)
Assigns values from given vector to the specified row in this matrix.
|
Matrix |
Matrix.assignRow(int row,
Vector vec)
Assigns values from given vector to the specified row in this matrix.
|
Vector |
LUDecomposition.solve(Vector b) |
Vector |
AbstractMatrix.times(Vector vec)
Creates new matrix that is the product of multiplying this matrix and the argument vector.
|
Vector |
Matrix.times(Vector vec)
Creates new matrix that is the product of multiplying this matrix and the argument vector.
|
Modifier and Type | Method and Description |
---|---|
Vector |
AbstractMatrix.foldColumns(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all columns in this matrix.
|
Vector |
Matrix.foldColumns(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all columns in this matrix.
|
Vector |
AbstractMatrix.foldRows(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all rows in this matrix.
|
Vector |
Matrix.foldRows(IgniteFunction<Vector,Double> fun)
Collects the results of applying a given function to all rows in this matrix.
|
Modifier and Type | Method and Description |
---|---|
Vector |
ViewMatrix.likeVector(int crd)
Creates new empty vector of compatible properties (similar or the same flavor) to this matrix.
|
Vector |
DenseMatrix.likeVector(int crd)
Creates new empty vector of compatible properties (similar or the same flavor) to this matrix.
|
Vector |
SparseMatrix.likeVector(int crd)
Creates new empty vector of compatible properties (similar or the same flavor) to this matrix.
|
Modifier and Type | Interface and Description |
---|---|
interface |
NamedVector
A named vector interface based on
Vector . |
Modifier and Type | Class and Description |
---|---|
class |
AbstractVector
This class provides a helper implementation of the
Vector
interface to minimize the effort required to implement it. |
Modifier and Type | Method and Description |
---|---|
Vector |
Vector.assign(double val)
Assigns given value to all elements of this vector.
|
Vector |
AbstractVector.assign(double val)
Assigns given value to all elements of this vector.
|
Vector |
Vector.assign(double[] vals)
Assigns values from given array to this vector.
|
Vector |
AbstractVector.assign(double[] vals)
Assigns values from given array to this vector.
|
Vector |
Vector.assign(IntToDoubleFunction fun)
Assigns each vector element to the value generated by given function.
|
Vector |
AbstractVector.assign(IntToDoubleFunction fun)
Assigns each vector element to the value generated by given function.
|
Vector |
Vector.assign(Vector vec)
Copies values from the argument vector to this one.
|
Vector |
AbstractVector.assign(Vector vec)
Copies values from the argument vector to this one.
|
static Vector |
VectorUtils.concat(Vector... vs)
Concatenates given vectors.
|
static Vector |
VectorUtils.concat(Vector v1,
Vector... vs)
Concatenates given vectors.
|
static Vector |
VectorUtils.concat(Vector v1,
Vector v2)
Concatenates two given vectors.
|
Vector |
Vector.copy()
Creates new copy of this vector.
|
Vector |
AbstractVector.copy()
Creates new copy of this vector.
|
Vector |
Vector.copyOfRange(int from,
int to)
Copies the specified range of the vector into a new vector.
|
Vector |
AbstractVector.copyOfRange(int from,
int to)
Copies the specified range of the vector into a new vector.
|
static Vector |
VectorUtils.copyPart(Vector v,
int off,
int len)
Get copy of part of given length of given vector starting from given offset.
|
Vector |
Vector.divide(double x)
Creates new vector containing values from this vector divided by the argument.
|
Vector |
AbstractVector.divide(double x)
Creates new vector containing values from this vector divided by the argument.
|
static Vector |
VectorUtils.elementWiseMinus(Vector vec1,
Vector vec2)
Performs in-place vector subtraction.
|
static Vector |
VectorUtils.elementWiseTimes(Vector vec1,
Vector vec2)
Performs in-place vector multiplication.
|
Vector |
Vector.increment(int idx,
double val)
Increments value at given index.
|
Vector |
AbstractVector.increment(int idx,
double val)
Increments value at given index.
|
Vector |
Vector.incrementX(int idx,
double val)
Increments value at given index without checking for index boundaries.
|
Vector |
AbstractVector.incrementX(int idx,
double val)
Increments value at given index without checking for index boundaries.
|
Vector |
Vector.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
Vector.logNormalize()
Creates new vector containing the
log(1 + entry) / L_2 norm values of this vector. |
Vector |
AbstractVector.logNormalize()
Creates new vector containing the
log(1 + entry) / L_2 norm values of this vector. |
Vector |
Vector.logNormalize(double power)
Creates new vector with a normalized value calculated as
log_power(1 + entry) / L_power norm . |
Vector |
AbstractVector.logNormalize(double power)
Creates new vector with a normalized value calculated as
log_power(1 + entry) / L_power norm . |
Vector |
Vector.map(IgniteBiFunction<Double,Double,Double> fun,
double y)
Maps all elements of this vector by applying given function to each element with a constant
second parameter
y . |
Vector |
AbstractVector.map(IgniteBiFunction<Double,Double,Double> fun,
double y)
Maps all elements of this vector by applying given function to each element with a constant
second parameter
y . |
Vector |
Vector.map(IgniteDoubleFunction<Double> fun)
Maps all values in this vector through a given function.
|
Vector |
AbstractVector.map(IgniteDoubleFunction<Double> fun)
Maps all values in this vector through a given function.
|
Vector |
Vector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
AbstractVector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
Vector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
AbstractVector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
Vector.normalize()
Creates new vector containing the normalized (L_2 norm) values of this vector.
|
Vector |
AbstractVector.normalize()
Creates new vector containing the normalized (L_2 norm) values of this vector.
|
Vector |
Vector.normalize(double power)
Creates new vector containing the normalized (L_power norm) values of this vector.
|
Vector |
AbstractVector.normalize(double power)
Creates new vector containing the normalized (L_power norm) values of this vector.
|
static Vector |
VectorUtils.num2Vec(double val)
Wrap specified value into vector.
|
static Vector |
VectorUtils.of(double... values)
Creates dense local on heap vector based on array of doubles.
|
static Vector |
VectorUtils.of(Double[] values)
Creates vector based on array of Doubles.
|
static Vector |
VectorUtils.oneHot(int num,
int vecSize)
Turn number into a local Vector of given size with one-hot encoding.
|
static Vector |
VectorUtils.oneHot(int num,
int vecSize,
boolean isDistributed)
Turn number into Vector of given size with one-hot encoding.
|
Vector |
Vector.plus(double x)
Creates new vector containing sum of each element in this vector and argument.
|
Vector |
AbstractVector.plus(double x)
Creates new vector containing sum of each element in this vector and argument.
|
Vector |
Vector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
AbstractVector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
Vector.set(int idx,
double val)
Sets value.
|
Vector |
AbstractVector.set(int idx,
double val)
Sets value.
|
Vector |
Vector.setRaw(int idx,
Serializable val)
Sets value.
|
Vector |
AbstractVector.setRaw(int idx,
Serializable val)
Sets value.
|
Vector |
Vector.setRawX(int idx,
Serializable val)
Sets value without checking for index boundaries.
|
Vector |
AbstractVector.setRawX(int idx,
Serializable val)
Sets value without checking for index boundaries.
|
Vector |
Vector.setX(int idx,
double val)
Sets value without checking for index boundaries.
|
Vector |
AbstractVector.setX(int idx,
double val)
Sets value without checking for index boundaries.
|
Vector |
Vector.sort()
Sorts this vector in ascending order.
|
Vector |
AbstractVector.sort()
Sorts this vector in ascending order.
|
Vector |
Vector.times(double x)
Gets a new vector that contains product of each element and the argument.
|
Vector |
AbstractVector.times(double x)
Gets a new vector that contains product of each element and the argument.
|
Vector |
Vector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
Vector |
AbstractVector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
Vector |
Vector.viewPart(int off,
int len) |
Vector |
AbstractVector.viewPart(int off,
int len) |
static Vector |
VectorUtils.zeroesLike(Vector v)
Create new vector like given vector initialized by zeroes.
|
static Vector |
VectorUtils.zipWith(Vector v1,
Vector v2,
IgniteBiFunction<Double,Double,Double> f)
Zip two vectors with given binary function
(i.e. apply binary function to both vector elementwise and construct vector from results).
|
Modifier and Type | Method and Description |
---|---|
static IgniteFunction<Vector,Vector> |
VectorUtils.getProjector(int[] mapping)
Get projector from index mapping.
|
static IgniteFunction<Vector,Vector> |
VectorUtils.getProjector(int[] mapping)
Get projector from index mapping.
|
Modifier and Type | Method and Description |
---|---|
Vector |
Vector.assign(Vector vec)
Copies values from the argument vector to this one.
|
Vector |
AbstractVector.assign(Vector vec)
Copies values from the argument vector to this one.
|
protected void |
AbstractVector.checkCardinality(Vector vec) |
static Vector |
VectorUtils.concat(Vector... vs)
Concatenates given vectors.
|
static Vector |
VectorUtils.concat(Vector v1,
Vector... vs)
Concatenates given vectors.
|
static Vector |
VectorUtils.concat(Vector v1,
Vector... vs)
Concatenates given vectors.
|
static Vector |
VectorUtils.concat(Vector v1,
Vector v2)
Concatenates two given vectors.
|
static Vector |
VectorUtils.copyPart(Vector v,
int off,
int len)
Get copy of part of given length of given vector starting from given offset.
|
Matrix |
Vector.cross(Vector vec)
Gets the cross product of this vector and the other vector.
|
Matrix |
AbstractVector.cross(Vector vec)
Gets the cross product of this vector and the other vector.
|
double |
Vector.dot(Vector vec)
Gets dot product of two vectors.
|
double |
AbstractVector.dot(Vector vec)
Gets dot product of two vectors.
|
static Vector |
VectorUtils.elementWiseMinus(Vector vec1,
Vector vec2)
Performs in-place vector subtraction.
|
static Vector |
VectorUtils.elementWiseTimes(Vector vec1,
Vector vec2)
Performs in-place vector multiplication.
|
<T> T |
Vector.foldMap(Vector vec,
IgniteBiFunction<T,Double,T> foldFun,
IgniteBiFunction<Double,Double,Double> combFun,
T zeroVal)
Combines & maps two vector and folds them into a single value.
|
<T> T |
AbstractVector.foldMap(Vector vec,
IgniteBiFunction<T,Double,T> foldFun,
IgniteBiFunction<Double,Double,Double> combFun,
T zeroVal)
Combines & maps two vector and folds them into a single value.
|
double |
Vector.getDistanceSquared(Vector vec)
Get the square of the distance between this vector and the argument vector.
|
double |
AbstractVector.getDistanceSquared(Vector vec)
Get the square of the distance between this vector and the argument vector.
|
Vector |
Vector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
AbstractVector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
Vector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
AbstractVector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
Vector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
AbstractVector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
Vector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
Vector |
AbstractVector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
static double |
VectorUtils.vec2Num(Vector vec)
Turn Vector into number by looking at index of maximal element in vector.
|
static Vector |
VectorUtils.zeroesLike(Vector v)
Create new vector like given vector initialized by zeroes.
|
static Vector |
VectorUtils.zipWith(Vector v1,
Vector v2,
IgniteBiFunction<Double,Double,Double> f)
Zip two vectors with given binary function
(i.e. apply binary function to both vector elementwise and construct vector from results).
|
Modifier and Type | Class and Description |
---|---|
class |
DelegatingNamedVector
Delegating named vector that delegates all operations to underlying vector and adds implementation of
NamedVector functionality using embedded map that maps string index on real integer index. |
class |
DelegatingVector
Convenient class that can be used to add decorations to an existing vector.
|
class |
DenseVector
Basic implementation for vector.
|
class |
SparseVector
Local on-heap sparse vector based on hash map storage.
|
class |
VectorizedViewMatrix
Row or column vector view off the matrix.
|
class |
VectorView
Implements the partial view into the parent
Vector . |
Modifier and Type | Method and Description |
---|---|
Vector |
DelegatingVector.assign(double val)
Assigns given value to all elements of this vector.
|
Vector |
DelegatingVector.assign(double[] vals)
Assigns values from given array to this vector.
|
Vector |
DelegatingVector.assign(IntToDoubleFunction fun)
Assigns each vector element to the value generated by given function.
|
Vector |
DelegatingVector.assign(Vector vec)
Copies values from the argument vector to this one.
|
Vector |
VectorView.copy()
Creates new copy of this vector.
|
Vector |
VectorizedViewMatrix.copy()
Creates new copy of this vector.
|
Vector |
DelegatingVector.copy()
Creates new copy of this vector.
|
Vector |
DelegatingVector.copyOfRange(int from,
int to)
Copies the specified range of the vector into a new vector.
|
Vector |
DelegatingVector.divide(double x)
Creates new vector containing values from this vector divided by the argument.
|
Vector |
DelegatingVector.getVector()
Get the delegating vector
|
Vector |
DelegatingVector.increment(int idx,
double val)
Increments value at given index.
|
Vector |
DelegatingVector.incrementX(int idx,
double val)
Increments value at given index without checking for index boundaries.
|
Vector |
DenseVector.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
VectorView.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
SparseVector.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
VectorizedViewMatrix.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
DelegatingVector.like(int crd)
Creates new empty vector of the same underlying class but of different cardinality.
|
Vector |
DelegatingVector.logNormalize()
Creates new vector containing the
log(1 + entry) / L_2 norm values of this vector. |
Vector |
DelegatingVector.logNormalize(double power)
Creates new vector with a normalized value calculated as
log_power(1 + entry) / L_power norm . |
Vector |
DelegatingVector.map(IgniteBiFunction<Double,Double,Double> fun,
double y)
Maps all elements of this vector by applying given function to each element with a constant
second parameter
y . |
Vector |
DelegatingVector.map(IgniteDoubleFunction<Double> fun)
Maps all values in this vector through a given function.
|
Vector |
DelegatingVector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
DelegatingVector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
DelegatingVector.normalize()
Creates new vector containing the normalized (L_2 norm) values of this vector.
|
Vector |
DelegatingVector.normalize(double power)
Creates new vector containing the normalized (L_power norm) values of this vector.
|
Vector |
DelegatingVector.plus(double x)
Creates new vector containing sum of each element in this vector and argument.
|
Vector |
DelegatingVector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
DelegatingVector.set(int idx,
double val)
Sets value.
|
Vector |
DelegatingVector.setRaw(int idx,
Serializable val)
Sets value.
|
Vector |
DelegatingVector.setRawX(int idx,
Serializable val)
Sets value without checking for index boundaries.
|
Vector |
DelegatingVector.setX(int idx,
double val)
Sets value without checking for index boundaries.
|
Vector |
DelegatingVector.sort()
Sorts this vector in ascending order.
|
Vector |
SparseVector.times(double x)
Gets a new vector that contains product of each element and the argument.
|
Vector |
DelegatingVector.times(double x)
Gets a new vector that contains product of each element and the argument.
|
Vector |
DelegatingVector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
Vector |
DelegatingVector.viewPart(int off,
int len) |
Modifier and Type | Method and Description |
---|---|
Vector |
DelegatingVector.assign(Vector vec)
Copies values from the argument vector to this one.
|
Matrix |
DelegatingVector.cross(Vector vec)
Gets the cross product of this vector and the other vector.
|
double |
DelegatingVector.dot(Vector vec)
Gets dot product of two vectors.
|
<T> T |
DelegatingVector.foldMap(Vector vec,
IgniteBiFunction<T,Double,T> foldFun,
IgniteBiFunction<Double,Double,Double> combFun,
T zeroVal)
Combines & maps two vector and folds them into a single value.
|
double |
DelegatingVector.getDistanceSquared(Vector vec)
Get the square of the distance between this vector and the argument vector.
|
Vector |
DelegatingVector.map(Vector vec,
IgniteBiFunction<Double,Double,Double> fun)
Maps all values in this vector through a given function.
|
Vector |
DelegatingVector.minus(Vector vec)
Creates new vector containing element by element difference between this vector and the argument one.
|
Vector |
DelegatingVector.plus(Vector vec)
Creates new vector containing element by element sum from both vectors.
|
Vector |
DelegatingVector.times(Vector vec)
Gets a new vector that is an element-wie product of this vector and the argument.
|
Constructor and Description |
---|
DelegatingNamedVector(Vector vector,
Map<String,Integer> map)
Constructs a new instance of delegating named vector.
|
DelegatingVector(Vector dlg) |
VectorView(Vector parent,
int off,
int len) |
Modifier and Type | Method and Description |
---|---|
Vector |
DistributionMixture.componentsProbs() |
Vector |
DistributionMixture.likelihood(Vector x) |
Vector |
MultivariateGaussianDistribution.mean() |
Modifier and Type | Method and Description |
---|---|
Vector |
DistributionMixture.likelihood(Vector x) |
double |
Distribution.prob(Vector x) |
double |
DistributionMixture.prob(Vector x) |
double |
MultivariateGaussianDistribution.prob(Vector x) |
Constructor and Description |
---|
DistributionMixture(Vector componentProbs,
List<C> distributions)
Creates an instance of DistributionMixture.
|
MultivariateGaussianDistribution(Vector mean,
Matrix covariance)
Constructs an instance of MultivariateGaussianDistribution.
|
Modifier and Type | Method and Description |
---|---|
static Vector |
MatrixUtil.likeVector(Matrix matrix)
Create the like vector with read-only matrices support.
|
static Vector |
MatrixUtil.likeVector(Matrix matrix,
int crd)
Create the like vector with read-only matrices support.
|
static Vector |
MatrixUtil.zipFoldByColumns(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by column-by-column with specified function.
|
static Vector |
MatrixUtil.zipFoldByRows(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by row-by-row with specified function.
|
static Vector |
MatrixUtil.zipWith(Vector v1,
Vector v2,
IgniteTriFunction<Double,Double,Integer,Double> f)
Zip two vectors with given tri-function taking as third argument position in vector (i.e. apply binary function
to both vector elementwise and construct vector from results).
|
Modifier and Type | Method and Description |
---|---|
static DenseVector |
MatrixUtil.localCopyOf(Vector vec)
TODO: IGNITE-5723, rewrite in a more optimal way.
|
static Vector |
MatrixUtil.zipWith(Vector v1,
Vector v2,
IgniteTriFunction<Double,Double,Integer,Double> f)
Zip two vectors with given tri-function taking as third argument position in vector (i.e. apply binary function
to both vector elementwise and construct vector from results).
|
Modifier and Type | Method and Description |
---|---|
static DenseMatrix |
MatrixUtil.fromList(List<Vector> vecs,
boolean entriesAreRows) |
static Vector |
MatrixUtil.zipFoldByColumns(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by column-by-column with specified function.
|
static Vector |
MatrixUtil.zipFoldByColumns(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by column-by-column with specified function.
|
static Vector |
MatrixUtil.zipFoldByRows(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by row-by-row with specified function.
|
static Vector |
MatrixUtil.zipFoldByRows(Matrix mtx1,
Matrix mtx2,
IgniteBiFunction<Vector,Vector,Double> fun)
Zips two matrices by row-by-row with specified function.
|
Modifier and Type | Class and Description |
---|---|
class |
MultiClassModel<M extends IgniteModel<Vector,Double>>
Base class for multi-classification model for set of classifiers.
|
class |
OneVsRestTrainer<M extends IgniteModel<Vector,Double>>
This is a common heuristic trainer for multi-class labeled models.
|
Modifier and Type | Method and Description |
---|---|
Double |
MultiClassModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
Double |
DiscreteNaiveBayesModel.predict(Vector vector) |
Modifier and Type | Method and Description |
---|---|
Double |
GaussianNaiveBayesModel.predict(Vector vector)
Returns a number of class to which the input belongs.
|
Modifier and Type | Field and Description |
---|---|
protected Vector |
MLPLayer.biases
Biases vector.
|
Modifier and Type | Method and Description |
---|---|
Vector |
MultilayerPerceptron.biases(int layerIdx)
Get biases of layer with given index.
|
Vector |
MultilayerPerceptron.differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
Matrix inputsBatch,
Matrix truthBatch)
Compose function in the following way: feed output of this model as input to second argument to loss function.
|
Vector |
MultilayerPerceptron.parameters()
Get parameters vector.
|
protected Vector |
MultilayerPerceptron.paramsAsVector(List<MLPLayer> layersParams)
Flatten this MLP parameters as vector.
|
Modifier and Type | Method and Description |
---|---|
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
MLPTrainer.getLoss()
Get the loss function to be minimized during the training.
|
Modifier and Type | Method and Description |
---|---|
MultilayerPerceptron |
MultilayerPerceptron.setBiases(int layerIdx,
Vector bias)
Sets the biases of layer with a given index.
|
MultilayerPerceptron |
MultilayerPerceptron.setParameters(Vector vector)
Set parameters.
|
Modifier and Type | Method and Description |
---|---|
Vector |
MultilayerPerceptron.differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
Matrix inputsBatch,
Matrix truthBatch)
Compose function in the following way: feed output of this model as input to second argument to loss function.
|
MLPTrainer<P> |
MLPTrainer.withLoss(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Set up the loss function to be minimized during the training.
|
Constructor and Description |
---|
MLPLayer(Matrix weights,
Vector biases)
Construct MLPLayer from weights and biases.
|
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.
|
MLPTrainer(MLPArchitecture arch,
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 |
---|---|
void |
RandomInitializer.initBiases(Vector biases)
In-place change values of vector representing vectors.
|
void |
MLPInitializer.initBiases(Vector biases)
In-place change values of vector representing vectors.
|
Modifier and Type | Field and Description |
---|---|
static IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
LossFunctions.HINGE
Hinge loss function.
|
static IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
LossFunctions.L1
L1 loss function.
|
static IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
LossFunctions.L2
L2 loss function.
|
static IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
LossFunctions.LOG
Log loss function.
|
static IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
LossFunctions.MSE
Mean squared error loss function.
|
Modifier and Type | Method and Description |
---|---|
Vector |
SmoothParametrized.differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
Matrix inputsBatch,
Matrix truthBatch)
Compose function in the following way: feed output of this model as input to second argument to loss function.
|
Modifier and Type | Method and Description |
---|---|
Vector |
SmoothParametrized.differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
Matrix inputsBatch,
Matrix truthBatch)
Compose function in the following way: feed output of this model as input to second argument to loss function.
|
Modifier and Type | Field and Description |
---|---|
protected Vector |
RPropParameterUpdate.deltas
Previous iteration parameters deltas.
|
protected Vector |
RPropParameterUpdate.prevIterationGradient
Previous iteration model partial derivatives by parameters.
|
protected Vector |
NesterovParameterUpdate.prevIterationUpdates
Previous step weights updates.
|
protected Vector |
RPropParameterUpdate.prevIterationUpdates
Previous iteration parameters updates.
|
protected Vector |
RPropParameterUpdate.updatesMask
Updates mask (values by which updateCache is multiplied).
|
Modifier and Type | Field and Description |
---|---|
protected IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
RPropUpdateCalculator.loss
Loss function.
|
protected IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> |
SimpleGDUpdateCalculator.loss
Loss function.
|
Modifier and Type | Method and Description |
---|---|
Vector |
SimpleGDParameterUpdate.gradient()
Get gradient.
|
Vector |
NesterovParameterUpdate.prevIterationUpdates()
Get previous step parameters updates.
|
Vector |
RPropParameterUpdate.updatesMask()
Get updates mask (values by which updateCache is multiplied).
|
Modifier and Type | Method and Description |
---|---|
RPropParameterUpdate |
RPropParameterUpdate.setDeltas(Vector deltas)
Set previous iteration deltas.
|
NesterovParameterUpdate |
NesterovParameterUpdate.setPreviousUpdates(Vector updates)
Set previous step parameters updates.
|
RPropParameterUpdate |
RPropParameterUpdate.setUpdatesMask(Vector updatesMask)
Set updates mask (values by which updateCache is multiplied).
|
Modifier and Type | Method and Description |
---|---|
P |
ParameterUpdateCalculator.init(M mdl,
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Initializes the update calculator.
|
NesterovParameterUpdate |
NesterovUpdateCalculator.init(M mdl,
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Initializes the update calculator.
|
RPropParameterUpdate |
RPropUpdateCalculator.init(SmoothParametrized mdl,
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Initializes the update calculator.
|
SimpleGDParameterUpdate |
SimpleGDUpdateCalculator.init(SmoothParametrized mdl,
IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss)
Initializes the update calculator.
|
Constructor and Description |
---|
NesterovParameterUpdate(Vector prevIterationUpdates)
Construct NesterovParameterUpdate.
|
RPropParameterUpdate(Vector prevIterationUpdates,
Vector prevIterationGradient,
Vector deltas,
Vector updatesMask)
Construct instance of this class by given parameters.
|
SimpleGDParameterUpdate(Vector gradient)
Construct instance of this class.
|
Modifier and Type | Method and Description |
---|---|
IgniteModel<Vector,Double> |
PipelineMdl.getInternalMdl() |
Modifier and Type | Method and Description |
---|---|
Double |
PipelineMdl.predict(Vector vector) |
Modifier and Type | Method and Description |
---|---|
PipelineMdl<K,V> |
PipelineMdl.withInternalMdl(IgniteModel<Vector,Double> internalMdl) |
Constructor and Description |
---|
ImputerPreprocessor(Vector imputingValues,
Preprocessor<K,V> basePreprocessor)
Constructs a new instance of imputing preprocessor.
|
Constructor and Description |
---|
RecommendationModel(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix)
Constructs a new instance of recommendation model.
|
RecommendationModel(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix)
Constructs a new instance of recommendation model.
|
Modifier and Type | Method and Description |
---|---|
Map<O,Vector> |
MatrixFactorizationGradient.getObjGrad()
Returns gradient of object of recommendation matrix (unmodifiable).
|
Map<S,Vector> |
MatrixFactorizationGradient.getSubjGrad()
Returns gradient of subject of recommendation function (unmodifiable).
|
Modifier and Type | Method and Description |
---|---|
void |
MatrixFactorizationGradient.applyGradient(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix)
Applies given gradient to recommendation model (object matrix and subject matrix) and updates this model
correspondingly.
|
void |
MatrixFactorizationGradient.applyGradient(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix)
Applies given gradient to recommendation model (object matrix and subject matrix) and updates this model
correspondingly.
|
MatrixFactorizationGradient<O,S> |
RecommendationDatasetData.calculateGradient(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix,
int batchSize,
int seed,
double regParam,
double learningRate)
Calculates gradient of the loss function of recommendation system SGD training.
|
MatrixFactorizationGradient<O,S> |
RecommendationDatasetData.calculateGradient(Map<O,Vector> objMatrix,
Map<S,Vector> subjMatrix,
int batchSize,
int seed,
double regParam,
double learningRate)
Calculates gradient of the loss function of recommendation system SGD training.
|
Constructor and Description |
---|
MatrixFactorizationGradient(Map<O,Vector> objGrad,
Map<S,Vector> subjGrad,
int rows)
Constructs a new instance of matrix factorization gradient.
|
MatrixFactorizationGradient(Map<O,Vector> objGrad,
Map<S,Vector> subjGrad,
int rows)
Constructs a new instance of matrix factorization gradient.
|
Modifier and Type | Method and Description |
---|---|
Vector |
LinearRegressionModel.getWeights() |
Modifier and Type | Method and Description |
---|---|
Double |
LinearRegressionModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
Constructor and Description |
---|
LinearRegressionModel(Vector weights,
double intercept) |
Modifier and Type | Method and Description |
---|---|
Vector |
LogisticRegressionModel.weights()
Gets the weights.
|
Modifier and Type | Method and Description |
---|---|
Double |
LogisticRegressionModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
LogisticRegressionModel |
LogisticRegressionModel.withWeights(Vector weights)
Set up the weights.
|
Constructor and Description |
---|
LogisticRegressionModel(Vector weights,
double intercept) |
Modifier and Type | Class and Description |
---|---|
class |
AbstractCrossValidation<M extends IgniteModel<Vector,L>,L,K,V>
Cross validation score calculator.
|
class |
CrossValidation<M extends IgniteModel<Vector,L>,L,K,V>
Cross validation score calculator.
|
class |
DebugCrossValidation<M extends IgniteModel<Vector,L>,L,K,V>
Cross validation score calculator.
|
Constructor and Description |
---|
CacheBasedLabelPairCursor(IgniteCache<K,V> upstreamCache,
IgniteBiPredicate<K,V> filter,
Preprocessor<K,V> preprocessor,
IgniteModel<Vector,L> mdl)
Constructs a new instance of cache based truth with prediction cursor.
|
CacheBasedLabelPairCursor(IgniteCache<K,V> upstreamCache,
Preprocessor<K,V> preprocessor,
IgniteModel<Vector,L> mdl)
Constructs a new instance of cache based truth with prediction cursor.
|
LocalLabelPairCursor(Map<K,V> upstreamMap,
IgniteBiPredicate<K,V> filter,
Preprocessor<K,V> preprocessor,
IgniteModel<Vector,L> mdl)
Constructs a new instance of local truth with prediction cursor.
|
Modifier and Type | Method and Description |
---|---|
static <K,V> BinaryClassificationMetricValues |
Evaluator.evaluate(IgniteCache<K,V> dataCache,
IgniteBiPredicate<K,V> filter,
IgniteModel<Vector,Double> mdl,
Preprocessor<K,V> preprocessor)
Computes the given metrics on the given cache.
|
static <L,K,V> double |
Evaluator.evaluate(IgniteCache<K,V> dataCache,
IgniteBiPredicate<K,V> filter,
IgniteModel<Vector,L> mdl,
Preprocessor<K,V> preprocessor,
Metric<L> metric)
Computes the given metric on the given cache.
|
static <K,V> BinaryClassificationMetricValues |
Evaluator.evaluate(IgniteCache<K,V> dataCache,
IgniteModel<Vector,Double> mdl,
Preprocessor<K,V> preprocessor)
Computes the given metrics on the given cache.
|
static <L,K,V> double |
Evaluator.evaluate(IgniteCache<K,V> dataCache,
IgniteModel<Vector,L> mdl,
Preprocessor<K,V> preprocessor,
Metric<L> metric)
Computes the given metric on the given cache.
|
static <K,V> BinaryClassificationMetricValues |
Evaluator.evaluate(Map<K,V> dataCache,
IgniteBiPredicate<K,V> filter,
IgniteModel<Vector,Double> mdl,
Preprocessor<K,V> preprocessor)
Computes the given metrics on the given cache.
|
static <L,K,V> double |
Evaluator.evaluate(Map<K,V> dataCache,
IgniteBiPredicate<K,V> filter,
IgniteModel<Vector,L> mdl,
Preprocessor<K,V> preprocessor,
Metric<L> metric)
Computes the given metric on the given cache.
|
static <K,V> BinaryClassificationMetricValues |
Evaluator.evaluate(Map<K,V> dataCache,
IgniteModel<Vector,Double> mdl,
Preprocessor<K,V> preprocessor)
Computes the given metrics on the given cache.
|
static <L,K,V> double |
Evaluator.evaluate(Map<K,V> dataCache,
IgniteModel<Vector,L> mdl,
Preprocessor<K,V> preprocessor,
Metric<L> metric)
Computes the given metric on the given cache.
|
static <K,V> RegressionMetricValues |
Evaluator.evaluateRegression(IgniteCache<K,V> dataCache,
IgniteBiPredicate<K,V> filter,
IgniteModel<Vector,Double> mdl,
Preprocessor<K,V> preprocessor)
Computes the regression metrics on the given cache.
|
Modifier and Type | Class and Description |
---|---|
class |
DatasetRow<V extends Vector>
Class to keep one observation in dataset.
|
Modifier and Type | Field and Description |
---|---|
protected V |
DatasetRow.vector
Vector.
|
Modifier and Type | Method and Description |
---|---|
static Vector |
LabeledVectorSet.emptyVector(int size,
boolean isDistributed) |
Vector |
Dataset.features(int idx)
Get the features.
|
Constructor and Description |
---|
LabeledVector(Vector vector,
L lb)
Construct labeled vector.
|
Modifier and Type | Method and Description |
---|---|
Vector |
SVMLinearClassificationModel.weights()
Gets the weights.
|
Modifier and Type | Method and Description |
---|---|
Double |
SVMLinearClassificationModel.predict(Vector input)
Make a prediction for the specified input arguments.
|
SVMLinearClassificationModel |
SVMLinearClassificationModel.withWeights(Vector weights)
Set up the weights.
|
Constructor and Description |
---|
SVMLinearClassificationModel(Vector weights,
double intercept) |
Modifier and Type | Method and Description |
---|---|
static <M extends IgniteModel<Vector,Double>,L> |
TrainerTransformers.makeBagged(DatasetTrainer<M,L> trainer,
int ensembleSize,
double subsampleRatio,
int featureVectorSize,
int featuresSubspaceDim,
PredictionsAggregator aggregator)
Add bagging logic to a given trainer.
|
Modifier and Type | Method and Description |
---|---|
default Vector |
FeatureLabelExtractor.extractFeatures(K key,
V val)
Extract features from key and value.
|
Modifier and Type | Method and Description |
---|---|
AdaptableDatasetTrainer<I,O,IW,OW,M,L> |
AdaptableDatasetTrainer.afterFeatureExtractor(IgniteFunction<Vector,Vector> after)
Specify function which will be applied after feature extractor.
|
AdaptableDatasetTrainer<I,O,IW,OW,M,L> |
AdaptableDatasetTrainer.afterFeatureExtractor(IgniteFunction<Vector,Vector> after)
Specify function which will be applied after feature extractor.
|
Modifier and Type | Method and Description |
---|---|
Double |
DecisionTreeConditionalNode.predict(Vector features)
Make a prediction for the specified input arguments.
|
Double |
DecisionTreeLeafNode.predict(Vector doubles)
Make a prediction for the specified input arguments.
|
Modifier and Type | Method and Description |
---|---|
<K,V> List<IgniteModel<Vector,Double>> |
GDBOnTreesLearningStrategy.update(GDBTrainer.GDBModel mdlToUpdate,
DatasetBuilder<K,V> datasetBuilder,
Preprocessor<K,V> vectorizer)
Gets state of model in arguments, compare it with training parameters of trainer and if they are fit then trainer
updates model in according to new data and return new model.
|
Modifier and Type | Method and Description |
---|---|
protected Vector |
ImpurityMeasureCalculator.getFeatureValues(DecisionTreeData data,
TreeDataIndex idx,
int featureId,
int k)
Returns feature value in according to kth order statistic.
|
Modifier and Type | Method and Description |
---|---|
Double |
TreeNode.predict(Vector features)
Make a prediction for the specified input arguments.
|
Double |
TreeRoot.predict(Vector vector)
Make a prediction for the specified input arguments.
|
NodeId |
TreeNode.predictNextNodeKey(Vector features)
Returns leaf node for feature vector in according to decision tree.
|
Modifier and Type | Method and Description |
---|---|
IgniteCache<Integer,Vector> |
SandboxMLCache.fillCacheWith(MLSandboxDatasets dataset)
Fills cache with data and returns it.
|
Modifier and Type | Method and Description |
---|---|
default DatasetBuilder<Vector,Double> |
DataStreamGenerator.asDatasetBuilder(int datasetSize,
IgniteBiPredicate<Vector,Double> filter,
int partitions)
Convert first N values from stream to
DatasetBuilder . |
default DatasetBuilder<Vector,Double> |
DataStreamGenerator.asDatasetBuilder(int datasetSize,
IgniteBiPredicate<Vector,Double> filter,
int partitions,
UpstreamTransformerBuilder upstreamTransformerBuilder)
Convert first N values from stream to
DatasetBuilder . |
default DatasetBuilder<Vector,Double> |
DataStreamGenerator.asDatasetBuilder(int datasetSize,
int partitions)
Convert first N values from stream to
DatasetBuilder . |
default Map<Vector,Double> |
DataStreamGenerator.asMap(int datasetSize)
Convert first N values from stream to map.
|
default Stream<Vector> |
DataStreamGenerator.unlabeled() |
Modifier and Type | Method and Description |
---|---|
default DatasetBuilder<Vector,Double> |
DataStreamGenerator.asDatasetBuilder(int datasetSize,
IgniteBiPredicate<Vector,Double> filter,
int partitions)
Convert first N values from stream to
DatasetBuilder . |
default DatasetBuilder<Vector,Double> |
DataStreamGenerator.asDatasetBuilder(int datasetSize,
IgniteBiPredicate<Vector,Double> filter,
int partitions,
UpstreamTransformerBuilder upstreamTransformerBuilder)
Convert first N values from stream to
DatasetBuilder . |
default Stream<LabeledVector<Double>> |
DataStreamGenerator.labeled(IgniteFunction<Vector,Double> classifier) |
default DataStreamGenerator |
DataStreamGenerator.mapVectors(IgniteFunction<Vector,Vector> f)
Apply user defined mapper to vectors stream without labels hiding.
|
default DataStreamGenerator |
DataStreamGenerator.mapVectors(IgniteFunction<Vector,Vector> f)
Apply user defined mapper to vectors stream without labels hiding.
|
Modifier and Type | Method and Description |
---|---|
default Vector |
RandomProducer.noizify(Vector vector)
Adds values generated by random producer to each vector value.
|
Modifier and Type | Method and Description |
---|---|
default Vector |
RandomProducer.noizify(Vector vector)
Adds values generated by random producer to each vector value.
|
Modifier and Type | Method and Description |
---|---|
Vector |
ParametricVectorGenerator.get() |
Vector |
VectorGeneratorsFamily.get() |
Vector |
VectorGeneratorsFamily.VectorWithDistributionId.vector() |
Modifier and Type | Method and Description |
---|---|
static VectorGenerator |
VectorGeneratorPrimitives.constant(Vector v) |
static VectorGenerator |
VectorGeneratorPrimitives.gauss(Vector means,
Vector variances)
Returns vector generator of vectors from multidimension gauss distribution.
|
static VectorGenerator |
VectorGeneratorPrimitives.gauss(Vector means,
Vector variances,
Long seed)
Returns vector generator of vectors from multidimension gauss distribution.
|
default VectorGenerator |
VectorGenerator.move(Vector v)
Moves all vectors to other position by summing with input vector.
|
static VectorGenerator |
VectorGeneratorPrimitives.parallelogram(Vector bounds)
Returns vector generator of vectors from multidimension uniform distribution around zero.
|
static VectorGenerator |
VectorGeneratorPrimitives.parallelogram(Vector bounds,
long seed)
Returns vector generator of vectors from multidimension uniform distribution around zero.
|
Modifier and Type | Method and Description |
---|---|
default VectorGenerator |
VectorGenerator.filter(IgnitePredicate<Vector> predicate)
Filters values of vector generator using predicate.
|
default VectorGenerator |
VectorGenerator.map(IgniteFunction<Vector,Vector> mapper)
Maps values of vector generator using mapper.
|
default VectorGenerator |
VectorGenerator.map(IgniteFunction<Vector,Vector> mapper)
Maps values of vector generator using mapper.
|
Constructor and Description |
---|
VectorWithDistributionId(Vector vector,
int distributionId)
Creates an instance of VectorWithDistributionId.
|
Modifier and Type | Method and Description |
---|---|
GaussianMixtureDataStream.Builder |
GaussianMixtureDataStream.Builder.add(Vector mean,
Vector variance)
Adds multidimentional gaussian component.
|
Constructor and Description |
---|
RegressionDataStream(int vectorSize,
IgniteFunction<Vector,Double> function,
double minXVal,
double maxXVal)
Creates an instance of RegressionDataStream.
|
GridGain In-Memory Computing Platform : ver. 8.9.4 Release Date : April 16 2024