com.workfusion.vds.sdk.ml.sklearn.gradientboosting

Class GradientBoostingClassifier

java.lang.Object

com.workfusion.vds.sdk.ml.python.BasePythonClassifier

com.workfusion.vds.sdk.ml.sklearn.gradientboosting.GradientBoostingClassifier

All Implemented Interfaces:

Classifier, PythonClassifier, AutoCloseable

public class GradientBoostingClassifier
extends BasePythonClassifier

The type Random forest classifier.

Since:

10.0

Author:

Konstantin Kovalev

See Also:

GradientBoostingClassifier

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	GradientBoostingClassifier.Builder The type Builder.

Method Summary

Modifier and Type	Method and Description
static GradientBoostingClassifier.Builder	builder() Construct new builder instance.
CriterionType	getCriterion() Gets criterion.
int	getEstimators() Gets the number of boosting stages.
double	getLearningRate() Gets the learning rate.
LossFunctionType	getLossFunction() Gets loss function type (LossFunctionType).
Integer	getMaxDepth() Gets the maximum depth of the tree.
Object	getMaxFeatures() Gets number of features to consider when looking for the best split.
Integer	getMaxLeafNodes() Gets max leaf nodes.
double	getMinImpurityDecrease() Gets min impurity decrease.
Object	getMinSamplesLeaf() Gets the minimum number of samples required to be at a leaf node.
Object	getMinSamplesSplit() Gets the minimum number of samples required to split an internal node.
double	getMinWeightFractionLeaf() Gets the minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.
Object	getPresort() Whether presort is used.
Integer	getSeed() Gets the seed used by the random number generator.
double	getSubsample() Gets the fraction of samples to be used for fitting the individual base learners.
boolean	isVerbose() Whether the verbosity of the tree building process are used.
boolean	isWarmStart() Whether warm start is used.

Methods inherited from class com.workfusion.vds.sdk.ml.python.BasePythonClassifier

close, fit, getModelName, getSerializableModel, getWorkingDir, init, predict

Methods inherited from class java.lang.Object

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

Method Detail

getLossFunction

public LossFunctionType getLossFunction()

Gets loss function type (LossFunctionType).

Returns:

the loss funtion type

getLearningRate

public double getLearningRate()

Gets the learning rate. Learning rate shrinks the contribution of each classifier by learning_rate.

Returns:

the learning rate

getEstimators

public int getEstimators()

Gets the number of boosting stages.

Returns:

the estimators

getMaxDepth

public Integer getMaxDepth()

Gets the maximum depth of the tree.

Returns:

the max depth

getCriterion

public CriterionType getCriterion()

Gets criterion. The function to measure the quality of a split.

Returns:

the criterion

getMinSamplesSplit

public Object getMinSamplesSplit()

Gets the minimum number of samples required to split an internal node.

Returns:

the min samples split

getMinSamplesLeaf

public Object getMinSamplesLeaf()

Gets the minimum number of samples required to be at a leaf node.

Returns:

the min samples leaf

getMinWeightFractionLeaf

public double getMinWeightFractionLeaf()

Gets the minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.

Returns:

the min weight fraction leaf

getSubsample

public double getSubsample()

Gets the fraction of samples to be used for fitting the individual base learners.

Returns:

the subsample fraction

getMaxFeatures

public Object getMaxFeatures()

Gets number of features to consider when looking for the best split.

Returns:

the max features

getMaxLeafNodes

public Integer getMaxLeafNodes()

Gets max leaf nodes. Grow trees with maxLeafNodes in best-first fashion. Best nodes are defined as relative reduction in impurity.

Returns:

the max leaf nodes

getMinImpurityDecrease

public double getMinImpurityDecrease()

Gets min impurity decrease. A node will be split if this split induces a decrease of the impurity greater than or equal to this value.

Returns:

the min impurity decrease

isVerbose

public boolean isVerbose()

Whether the verbosity of the tree building process are used.

Returns:

the verbose flag

isWarmStart

public boolean isWarmStart()

Whether warm start is used.

Returns:

the warm start flag

getSeed

public Integer getSeed()

Gets the seed used by the random number generator.

Returns:

the seed

getPresort

public Object getPresort()

Whether presort is used.

Returns:

the presort

builder

public static GradientBoostingClassifier.Builder builder()

Construct new builder instance.

Returns:

new builder instance