org.apache.spark.ml.regression

Class RandomForestRegressionModel

java.lang.Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Transformer

org.apache.spark.ml.Model<M>

org.apache.spark.ml.PredictionModel<Vector,RandomForestRegressionModel>

org.apache.spark.ml.regression.RandomForestRegressionModel

All Implemented Interfaces:

java.io.Serializable, Params, Identifiable, MLWritable

public class RandomForestRegressionModel
extends PredictionModel<Vector,RandomForestRegressionModel>
implements MLWritable, scala.Serializable

:: Experimental :: Random Forest model for regression. It supports both continuous and categorical features.

param: _trees Decision trees in the ensemble. param: numFeatures Number of features used by this model

See Also:

Serialized Form

Method Summary

Methods

Modifier and Type	Method and Description
protected static <T> T	$(Param<T> param)
static BooleanParam	cacheNodeIds()
static IntParam	checkpointInterval()
static Params	clear(Param<?> param)
RandomForestRegressionModel	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
protected static <T extends Params> T	copyValues(T to, ParamMap extra)
protected static <T extends Params> ParamMap	copyValues$default$2()
protected static <T extends Params> T	defaultCopy(ParamMap extra)
static java.lang.String	explainParam(Param<?> param)
static java.lang.String	explainParams()
static ParamMap	extractParamMap()
static ParamMap	extractParamMap(ParamMap extra)
Vector	featureImportances() Estimate of the importance of each feature.
static Param<java.lang.String>	featuresCol()
Param<java.lang.String>	featuresCol() Param for features column name.
protected static DataType	featuresDataType()
static Param<java.lang.String>	featureSubsetStrategy()
static <T> scala.Option<T>	get(Param<T> param)
static boolean	getCacheNodeIds()
static int	getCheckpointInterval()
static <T> scala.Option<T>	getDefault(Param<T> param)
static java.lang.String	getFeaturesCol()
java.lang.String	getFeaturesCol()
static java.lang.String	getFeatureSubsetStrategy()
static java.lang.String	getImpurity()
static java.lang.String	getLabelCol()
java.lang.String	getLabelCol()
static int	getMaxBins()
static int	getMaxDepth()
static int	getMaxMemoryInMB()
static double	getMinInfoGain()
static int	getMinInstancesPerNode()
static int	getNumTrees()
static <T> T	getOrDefault(Param<T> param)
static Param<java.lang.Object>	getParam(java.lang.String paramName)
static java.lang.String	getPredictionCol()
java.lang.String	getPredictionCol()
static long	getSeed()
static double	getSubsamplingRate()
static <T> boolean	hasDefault(Param<T> param)
static boolean	hasParam(java.lang.String paramName)
static boolean	hasParent()
static Param<java.lang.String>	impurity()
protected static void	initializeLogIfNecessary(boolean isInterpreter)
static boolean	isDefined(Param<?> param)
static boolean	isSet(Param<?> param)
protected static boolean	isTraceEnabled()
static Param<java.lang.String>	labelCol()
Param<java.lang.String>	labelCol() Param for label column name.
static RandomForestRegressionModel	load(java.lang.String path)
protected static org.slf4j.Logger	log()
protected static void	logDebug(scala.Function0<java.lang.String> msg)
protected static void	logDebug(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logError(scala.Function0<java.lang.String> msg)
protected static void	logError(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logInfo(scala.Function0<java.lang.String> msg)
protected static void	logInfo(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static java.lang.String	logName()
protected static void	logTrace(scala.Function0<java.lang.String> msg)
protected static void	logTrace(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void	logWarning(scala.Function0<java.lang.String> msg)
protected static void	logWarning(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
static IntParam	maxBins()
static IntParam	maxDepth()
static IntParam	maxMemoryInMB()
static DoubleParam	minInfoGain()
static IntParam	minInstancesPerNode()
int	numFeatures() Returns the number of features the model was trained on.
int	numTrees() Deprecated. Use getNumTrees instead. This method will be removed in 2.1.0
static Param<?>[]	params()
static void	parent_$eq(Estimator<M> x$1)
static Estimator<M>	parent()
protected double	predict(Vector features) Predict label for the given features.
static Param<java.lang.String>	predictionCol()
Param<java.lang.String>	predictionCol() Param for prediction column name.
static MLReader<RandomForestRegressionModel>	read()
static void	save(java.lang.String path)
static LongParam	seed()
static <T> Params	set(Param<T> param, T value)
protected static Params	set(ParamPair<?> paramPair)
protected static Params	set(java.lang.String param, java.lang.Object value)
static org.apache.spark.ml.tree.DecisionTreeParams	setCacheNodeIds(boolean value)
static org.apache.spark.ml.tree.DecisionTreeParams	setCheckpointInterval(int value)
protected static <T> Params	setDefault(Param<T> param, T value)
protected static Params	setDefault(scala.collection.Seq<ParamPair<?>> paramPairs)
static M	setFeaturesCol(java.lang.String value)
static org.apache.spark.ml.tree.HasFeatureSubsetStrategy	setFeatureSubsetStrategy(java.lang.String value)
static org.apache.spark.ml.tree.TreeRegressorParams	setImpurity(java.lang.String value)
static org.apache.spark.ml.tree.DecisionTreeParams	setMaxBins(int value)
static org.apache.spark.ml.tree.DecisionTreeParams	setMaxDepth(int value)
static org.apache.spark.ml.tree.DecisionTreeParams	setMaxMemoryInMB(int value)
static org.apache.spark.ml.tree.DecisionTreeParams	setMinInfoGain(double value)
static org.apache.spark.ml.tree.DecisionTreeParams	setMinInstancesPerNode(int value)
static M	setParent(Estimator<M> parent)
static M	setPredictionCol(java.lang.String value)
static org.apache.spark.ml.tree.DecisionTreeParams	setSeed(long value)
static org.apache.spark.ml.tree.TreeEnsembleParams	setSubsamplingRate(double value)
static DoubleParam	subsamplingRate()
static java.lang.String	toDebugString()
java.lang.String	toString()
static int	totalNumNodes()
static Dataset<Row>	transform(Dataset<?> dataset)
static Dataset<Row>	transform(Dataset<?> dataset, ParamMap paramMap)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, ParamPair<?>... otherParamPairs)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, scala.collection.Seq<ParamPair<?>> otherParamPairs)
protected Dataset<Row>	transformImpl(Dataset<?> dataset)
static StructType	transformSchema(StructType schema)
protected static StructType	transformSchema(StructType schema, boolean logging)
DecisionTreeRegressionModel[]	trees()
double[]	treeWeights()
java.lang.String	uid() An immutable unique ID for the object and its derivatives.
protected static StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType)
StructType	validateAndTransformSchema(StructType schema, boolean fitting, DataType featuresDataType) Validates and transforms the input schema with the provided param map.
static void	validateParams()
MLWriter	write() Returns an MLWriter instance for this ML instance.

Methods inherited from class org.apache.spark.ml.PredictionModel

featuresDataType, setFeaturesCol, setPredictionCol, transform, transformSchema

Methods inherited from class org.apache.spark.ml.Model

hasParent, parent, setParent

Methods inherited from class org.apache.spark.ml.Transformer

transform, transform, transform

Methods inherited from class org.apache.spark.ml.PipelineStage

transformSchema

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.spark.ml.util.MLWritable

save

Methods inherited from interface org.apache.spark.ml.param.Params

clear, copyValues, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, paramMap, params, set, set, set, setDefault, setDefault, shouldOwn, validateParams

Method Detail

read

public static MLReader<RandomForestRegressionModel> read()

load

public static RandomForestRegressionModel load(java.lang.String path)

params

public static Param<?>[] params()

validateParams

public static void validateParams()

explainParam

public static java.lang.String explainParam(Param<?> param)

explainParams

public static java.lang.String explainParams()

isSet

public static final boolean isSet(Param<?> param)

isDefined

public static final boolean isDefined(Param<?> param)

hasParam

public static boolean hasParam(java.lang.String paramName)

getParam

public static Param<java.lang.Object> getParam(java.lang.String paramName)

set

public static final <T> Params set(Param<T> param,
             T value)

set

protected static final Params set(java.lang.String param,
         java.lang.Object value)

set

protected static final Params set(ParamPair<?> paramPair)

get

public static final <T> scala.Option<T> get(Param<T> param)

clear

public static final Params clear(Param<?> param)

getOrDefault

public static final <T> T getOrDefault(Param<T> param)

$

protected static final <T> T $(Param<T> param)

setDefault

protected static final <T> Params setDefault(Param<T> param,
                    T value)

setDefault

protected static final Params setDefault(scala.collection.Seq<ParamPair<?>> paramPairs)

getDefault

public static final <T> scala.Option<T> getDefault(Param<T> param)

hasDefault

public static final <T> boolean hasDefault(Param<T> param)

defaultCopy

protected static final <T extends Params> T defaultCopy(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap()

copyValues

protected static <T extends Params> T copyValues(T to,
                              ParamMap extra)

copyValues$default$2

protected static <T extends Params> ParamMap copyValues$default$2()

logName

protected static java.lang.String logName()

log

protected static org.slf4j.Logger log()

logInfo

protected static void logInfo(scala.Function0<java.lang.String> msg)

logDebug

protected static void logDebug(scala.Function0<java.lang.String> msg)

logTrace

protected static void logTrace(scala.Function0<java.lang.String> msg)

logWarning

protected static void logWarning(scala.Function0<java.lang.String> msg)

logError

protected static void logError(scala.Function0<java.lang.String> msg)

logInfo

protected static void logInfo(scala.Function0<java.lang.String> msg,
           java.lang.Throwable throwable)

logDebug

protected static void logDebug(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

logTrace

protected static void logTrace(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

logWarning

protected static void logWarning(scala.Function0<java.lang.String> msg,
              java.lang.Throwable throwable)

logError

protected static void logError(scala.Function0<java.lang.String> msg,
            java.lang.Throwable throwable)

isTraceEnabled

protected static boolean isTraceEnabled()

initializeLogIfNecessary

protected static void initializeLogIfNecessary(boolean isInterpreter)

transformSchema

protected static StructType transformSchema(StructType schema,
                         boolean logging)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                     ParamPair<?> firstParamPair,
                     scala.collection.Seq<ParamPair<?>> otherParamPairs)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                     ParamMap paramMap)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                     ParamPair<?> firstParamPair,
                     ParamPair<?>... otherParamPairs)

parent

public static Estimator<M> parent()

parent_$eq

public static void parent_$eq(Estimator<M> x$1)

setParent

public static M setParent(Estimator<M> parent)

hasParent

public static boolean hasParent()

labelCol

public static final Param<java.lang.String> labelCol()

getLabelCol

public static final java.lang.String getLabelCol()

featuresCol

public static final Param<java.lang.String> featuresCol()

getFeaturesCol

public static final java.lang.String getFeaturesCol()

predictionCol

public static final Param<java.lang.String> predictionCol()

getPredictionCol

public static final java.lang.String getPredictionCol()

validateAndTransformSchema

protected static StructType validateAndTransformSchema(StructType schema,
                                    boolean fitting,
                                    DataType featuresDataType)

setFeaturesCol

public static M setFeaturesCol(java.lang.String value)

setPredictionCol

public static M setPredictionCol(java.lang.String value)

featuresDataType

protected static DataType featuresDataType()

transformSchema

public static StructType transformSchema(StructType schema)

transform

public static Dataset<Row> transform(Dataset<?> dataset)

checkpointInterval

public static final IntParam checkpointInterval()

getCheckpointInterval

public static final int getCheckpointInterval()

seed

public static final LongParam seed()

getSeed

public static final long getSeed()

maxDepth

public static final IntParam maxDepth()

maxBins

public static final IntParam maxBins()

minInstancesPerNode

public static final IntParam minInstancesPerNode()

minInfoGain

public static final DoubleParam minInfoGain()

maxMemoryInMB

public static final IntParam maxMemoryInMB()

cacheNodeIds

public static final BooleanParam cacheNodeIds()

setMaxDepth

public static org.apache.spark.ml.tree.DecisionTreeParams setMaxDepth(int value)

getMaxDepth

public static final int getMaxDepth()

setMaxBins

public static org.apache.spark.ml.tree.DecisionTreeParams setMaxBins(int value)

getMaxBins

public static final int getMaxBins()

setMinInstancesPerNode

public static org.apache.spark.ml.tree.DecisionTreeParams setMinInstancesPerNode(int value)

getMinInstancesPerNode

public static final int getMinInstancesPerNode()

setMinInfoGain

public static org.apache.spark.ml.tree.DecisionTreeParams setMinInfoGain(double value)

getMinInfoGain

public static final double getMinInfoGain()

setSeed

public static org.apache.spark.ml.tree.DecisionTreeParams setSeed(long value)

setMaxMemoryInMB

public static org.apache.spark.ml.tree.DecisionTreeParams setMaxMemoryInMB(int value)

getMaxMemoryInMB

public static final int getMaxMemoryInMB()

setCacheNodeIds

public static org.apache.spark.ml.tree.DecisionTreeParams setCacheNodeIds(boolean value)

getCacheNodeIds

public static final boolean getCacheNodeIds()

setCheckpointInterval

public static org.apache.spark.ml.tree.DecisionTreeParams setCheckpointInterval(int value)

subsamplingRate

public static final DoubleParam subsamplingRate()

setSubsamplingRate

public static org.apache.spark.ml.tree.TreeEnsembleParams setSubsamplingRate(double value)

getSubsamplingRate

public static final double getSubsamplingRate()

featureSubsetStrategy

public static final Param<java.lang.String> featureSubsetStrategy()

setFeatureSubsetStrategy

public static org.apache.spark.ml.tree.HasFeatureSubsetStrategy setFeatureSubsetStrategy(java.lang.String value)

getFeatureSubsetStrategy

public static final java.lang.String getFeatureSubsetStrategy()

impurity

public static final Param<java.lang.String> impurity()

setImpurity

public static org.apache.spark.ml.tree.TreeRegressorParams setImpurity(java.lang.String value)

getImpurity

public static final java.lang.String getImpurity()

getNumTrees

public static int getNumTrees()

toDebugString

public static java.lang.String toDebugString()

totalNumNodes

public static int totalNumNodes()

save

public static void save(java.lang.String path)
                 throws java.io.IOException

Throws:

java.io.IOException

uid

public java.lang.String uid()

Description copied from interface: Identifiable

An immutable unique ID for the object and its derivatives.

Specified by:

uid in interface Identifiable

Returns:

(undocumented)

numFeatures

public int numFeatures()

Description copied from class: PredictionModel

Returns the number of features the model was trained on. If unknown, returns -1

Overrides:

numFeatures in class PredictionModel<Vector,RandomForestRegressionModel>

trees

public DecisionTreeRegressionModel[] trees()

treeWeights

public double[] treeWeights()

transformImpl

protected Dataset<Row> transformImpl(Dataset<?> dataset)

Overrides:

transformImpl in class PredictionModel<Vector,RandomForestRegressionModel>

predict

protected double predict(Vector features)

Description copied from class: PredictionModel

Predict label for the given features. This internal method is used to implement transform() and output predictionCol.

Specified by:

predict in class PredictionModel<Vector,RandomForestRegressionModel>

Parameters:

features - (undocumented)

Returns:

(undocumented)

numTrees

public int numTrees()

Deprecated. Use getNumTrees instead. This method will be removed in 2.1.0

Number of trees in ensemble

Returns:

(undocumented)

copy

public RandomForestRegressionModel copy(ParamMap extra)

Description copied from interface: Params

Creates a copy of this instance with the same UID and some extra params. Subclasses should implement this method and set the return type properly.

Specified by:

copy in interface Params

Specified by:

copy in class Model<RandomForestRegressionModel>

Parameters:

extra - (undocumented)

Returns:

(undocumented)

See Also:

defaultCopy()

toString

public java.lang.String toString()

Specified by:

toString in interface Identifiable

Overrides:

toString in class java.lang.Object

featureImportances

public Vector featureImportances()

Estimate of the importance of each feature.

Each feature's importance is the average of its importance across all trees in the ensemble The importance vector is normalized to sum to 1. This method is suggested by Hastie et al. (Hastie, Tibshirani, Friedman. "The Elements of Statistical Learning, 2nd Edition." 2001.) and follows the implementation from scikit-learn.

Returns:

(undocumented)

See Also:

DecisionTreeRegressionModel.featureImportances

write

public MLWriter write()

Description copied from interface: MLWritable

Returns an MLWriter instance for this ML instance.

Specified by:

write in interface MLWritable

Returns:

(undocumented)

validateAndTransformSchema

public StructType validateAndTransformSchema(StructType schema,
                                    boolean fitting,
                                    DataType featuresDataType)

Validates and transforms the input schema with the provided param map.

Parameters:

schema - input schema

fitting - whether this is in fitting

featuresDataType - SQL DataType for FeaturesType. E.g., VectorUDT for vector features.

Returns:

output schema

labelCol

public Param<java.lang.String> labelCol()

Param for label column name.

Returns:

(undocumented)

getLabelCol

public java.lang.String getLabelCol()

featuresCol

public Param<java.lang.String> featuresCol()

Param for features column name.

Returns:

(undocumented)

getFeaturesCol

public java.lang.String getFeaturesCol()

predictionCol

public Param<java.lang.String> predictionCol()

Param for prediction column name.

Returns:

(undocumented)

getPredictionCol

public java.lang.String getPredictionCol()