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

Class GradientBoostingClassifier.Builder

java.lang.Object

com.workfusion.vds.sdk.ml.python.BasePythonClassifier.Builder<GradientBoostingClassifier.Builder,GradientBoostingClassifier>

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

Enclosing class:

GradientBoostingClassifier

public static class GradientBoostingClassifier.Builder
extends BasePythonClassifier.Builder<GradientBoostingClassifier.Builder,GradientBoostingClassifier>

The type Builder.

Field Summary

Fields inherited from class com.workfusion.vds.sdk.ml.python.BasePythonClassifier.Builder

modelName, workingDir

Constructor Summary

Constructors

Constructor and Description
Builder() Instantiates a new Builder.

Method Summary

Modifier and Type	Method and Description
GradientBoostingClassifier	build() Build classifier.
GradientBoostingClassifier.Builder	criterion(CriterionType criterion) Sets the function to measure the quality of a split.
GradientBoostingClassifier.Builder	estimators(int estimators) Sets the number of boosting stages to perform.
GradientBoostingClassifier.Builder	learningRate(double learningRate) Sets the learning rate.
GradientBoostingClassifier.Builder	lossFunction(LossFunctionType lossFunction) Sets the loss function to be optimized.
GradientBoostingClassifier.Builder	maxDepth(Integer maxDepth) Sets maximum depth of the individual regression estimators.
GradientBoostingClassifier.Builder	maxFeatures(double maxFeatures) Sets the fraction of features to consider when looking for the best split.
GradientBoostingClassifier.Builder	maxFeatures(int maxFeatures) Sets the maximum number of features to consider when looking for the best split.
GradientBoostingClassifier.Builder	maxFeatures(MaxFeaturesType maxFeatures) Sets the maximum number of features to consider when looking for the best split.
GradientBoostingClassifier.Builder	maxLeafNodes(Integer maxLeafNodes) Sets max leaf nodes.
GradientBoostingClassifier.Builder	minImpurityDecrease(double minImpurityDecrease) Sets min impurity decrease.
GradientBoostingClassifier.Builder	minSamplesLeaf(double minSamplesLeaf) Sets the minimum fraction of samples required to be at a leaf node.
GradientBoostingClassifier.Builder	minSamplesLeaf(int minSamplesLeaf) Sets the minimum number of samples required to be at a leaf node.
GradientBoostingClassifier.Builder	minSamplesSplit(double minSamplesSplit) Sets the minimum fraction of samples required to split an internal node.
GradientBoostingClassifier.Builder	minSamplesSplit(int minSamplesSplit) Sets the minimum number of samples required to split an internal node.
GradientBoostingClassifier.Builder	minWeightFractionLeaf(double minWeightFractionLeaf) Sets the minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.
GradientBoostingClassifier.Builder	modelName(String name) Set a model name.
GradientBoostingClassifier.Builder	presort(boolean presort) Sets whether to presort the data to speed up the finding of best splits in fitting.
GradientBoostingClassifier.Builder	presort(PresortType presort) Sets whether to presort the data to speed up the finding of best splits in fitting.
GradientBoostingClassifier.Builder	seed(Integer seed) Sets the seed used by the random number generator.
GradientBoostingClassifier.Builder	subsample(double subsample) Sets the fraction of samples to be used for fitting the individual base learners.
GradientBoostingClassifier.Builder	verbose(boolean verbose) Sets whether verbose mode is used.
GradientBoostingClassifier.Builder	warmStart(boolean warmStart) Sets whether warm start is used.

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

createDefaultClassifierBridge, workingDir

Methods inherited from class java.lang.Object

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

Constructor Detail

Builder

public Builder()

Instantiates a new Builder.

Method Detail

lossFunction

public GradientBoostingClassifier.Builder lossFunction(LossFunctionType lossFunction)

Sets the loss function to be optimized.

Parameters:

lossFunction - the loss functiton to set (LossFunctionType) (default: LossFunctionType.DEVIANCE)

Returns:

the builder

learningRate

public GradientBoostingClassifier.Builder learningRate(double learningRate)

Sets the learning rate. Learning rate shrinks the contribution of each classifier by learningRate. There is a trade-off between learningRate and estimators.

Parameters:

learningRate - the learning rate (default: 1.0)

Returns:

the builder

estimators

public GradientBoostingClassifier.Builder estimators(int estimators)

Sets the number of boosting stages to perform. Gradient boosting is fairly robust to over-fitting so a large number usually results in better performance.

Parameters:

estimators - the number of boosting stages (default: 100)

Returns:

the builder

maxDepth

public GradientBoostingClassifier.Builder maxDepth(Integer maxDepth)

Sets maximum depth of the individual regression estimators. The maximum depth limits the number of nodes in the tree. Tune this parameter for best performance; the best value depends on the interaction of the input variables.

Parameters:

maxDepth - the max depth (default: 3)

Returns:

the builder

criterion

public GradientBoostingClassifier.Builder criterion(CriterionType criterion)

Sets the function to measure the quality of a split.

Parameters:

criterion - the criterion (CriterionType) (default: CriterionType.FRIEDMAN_MSE)

Returns:

the builder

minSamplesSplit

public GradientBoostingClassifier.Builder minSamplesSplit(double minSamplesSplit)

Sets the minimum fraction of samples required to split an internal node.

Parameters:

minSamplesSplit - the min samples split

Returns:

the builder

minSamplesSplit

public GradientBoostingClassifier.Builder minSamplesSplit(int minSamplesSplit)

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

Parameters:

minSamplesSplit - the min samples split (default: 2)

Returns:

the builder

minSamplesLeaf

public GradientBoostingClassifier.Builder minSamplesLeaf(int minSamplesLeaf)

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

Parameters:

minSamplesLeaf - the min samples leaf (default: 1)

Returns:

the builder

minSamplesLeaf

public GradientBoostingClassifier.Builder minSamplesLeaf(double minSamplesLeaf)

Sets the minimum fraction of samples required to be at a leaf node.

Parameters:

minSamplesLeaf - the min samples leaf

Returns:

the builder

minWeightFractionLeaf

public GradientBoostingClassifier.Builder minWeightFractionLeaf(double minWeightFractionLeaf)

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

Parameters:

minWeightFractionLeaf - the min weight fraction leaf (default: 0.0)

Returns:

the builder

subsample

public GradientBoostingClassifier.Builder subsample(double subsample)

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

Parameters:

subsample - the fraction of samples (default: 1.0)

Returns:

the builder

maxFeatures

public GradientBoostingClassifier.Builder maxFeatures(MaxFeaturesType maxFeatures)

Sets the maximum number of features to consider when looking for the best split. If null then maxFeatures=n_features.

Parameters:

maxFeatures - the max features (MaxFeaturesType) (default: MaxFeaturesType.AUTO)

Returns:

the builder

maxFeatures

public GradientBoostingClassifier.Builder maxFeatures(int maxFeatures)

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

Parameters:

maxFeatures - the max features

Returns:

the builder

maxFeatures

public GradientBoostingClassifier.Builder maxFeatures(double maxFeatures)

Sets the fraction of features to consider when looking for the best split.

Parameters:

maxFeatures - the max features

Returns:

the builder

maxLeafNodes

public GradientBoostingClassifier.Builder maxLeafNodes(Integer maxLeafNodes)

Sets max leaf nodes. Grow trees with maxLeafNodes in best-first fashion. Best nodes are defined as relative reduction in impurity. If null then unlimited number of leaf nodes.

Parameters:

maxLeafNodes - the max leaf nodes (default: null)

Returns:

the builder

minImpurityDecrease

public GradientBoostingClassifier.Builder minImpurityDecrease(double minImpurityDecrease)

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

Parameters:

minImpurityDecrease - the min impurity decrease (default: 0.0)

Returns:

the builder

verbose

public GradientBoostingClassifier.Builder verbose(boolean verbose)

Sets whether verbose mode is used.

Parameters:

verbose - the verbose mode (default: false)

Returns:

the builder

warmStart

public GradientBoostingClassifier.Builder warmStart(boolean warmStart)

Sets whether warm start is used.

Parameters:

warmStart - the warm start (default: false)

Returns:

the builder

seed

public GradientBoostingClassifier.Builder seed(Integer seed)

Sets the seed used by the random number generator. If null then default random number generator is used (np.random).

Parameters:

seed - the seed (default: null)

Returns:

the builder

presort

public GradientBoostingClassifier.Builder presort(PresortType presort)

Sets whether to presort the data to speed up the finding of best splits in fitting. Auto mode by default will use presorting on dense data and default to normal sorting on sparse data.

Parameters:

presort - the verbose mode (PresortType) (default: PresortType.AUTO)

Returns:

the builder

presort

public GradientBoostingClassifier.Builder presort(boolean presort)

Sets whether to presort the data to speed up the finding of best splits in fitting. Setting presort to true on sparse data will raise an error.

Parameters:

presort - the verbose mode

Returns:

the builder

modelName

public GradientBoostingClassifier.Builder modelName(String name)

Description copied from class: BasePythonClassifier.Builder

Set a model name.

Overrides:

modelName in class BasePythonClassifier.Builder<GradientBoostingClassifier.Builder,GradientBoostingClassifier>

Parameters:

name - the model name (String)

Returns:

the builder

build

public GradientBoostingClassifier build()

Description copied from class: BasePythonClassifier.Builder

Build classifier.

Specified by:

build in class BasePythonClassifier.Builder<GradientBoostingClassifier.Builder,GradientBoostingClassifier>

Returns:

the classifier instance