org.apache.spark.mllib.tree

Class DecisionTree

Object

org.apache.spark.mllib.tree.DecisionTree

All Implemented Interfaces:

java.io.Serializable, org.apache.spark.internal.Logging

public class DecisionTree
extends Object
implements scala.Serializable, org.apache.spark.internal.Logging

A class which implements a decision tree learning algorithm for classification and regression. It supports both continuous and categorical features.

param: strategy The configuration parameters for the tree algorithm which specify the type of decision tree (classification or regression), feature type (continuous, categorical), depth of the tree, quantile calculation strategy, etc. param: seed Random seed.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.spark.internal.Logging

org.apache.spark.internal.Logging.SparkShellLoggingFilter

Constructor Summary

Constructors

Constructor and Description
DecisionTree(Strategy strategy)

Method Summary

Modifier and Type	Method and Description
static void	org$apache$spark$internal$Logging$$log__$eq(org.slf4j.Logger x$1)
static org.slf4j.Logger	org$apache$spark$internal$Logging$$log_()
DecisionTreeModel	run(RDD<LabeledPoint> input) Method to train a decision tree model over an RDD
static DecisionTreeModel	train(RDD<LabeledPoint> input, scala.Enumeration.Value algo, Impurity impurity, int maxDepth) Method to train a decision tree model.
static DecisionTreeModel	train(RDD<LabeledPoint> input, scala.Enumeration.Value algo, Impurity impurity, int maxDepth, int numClasses) Method to train a decision tree model.
static DecisionTreeModel	train(RDD<LabeledPoint> input, scala.Enumeration.Value algo, Impurity impurity, int maxDepth, int numClasses, int maxBins, scala.Enumeration.Value quantileCalculationStrategy, scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo) Method to train a decision tree model.
static DecisionTreeModel	train(RDD<LabeledPoint> input, Strategy strategy) Method to train a decision tree model.
static DecisionTreeModel	trainClassifier(JavaRDD<LabeledPoint> input, int numClasses, java.util.Map<Integer,Integer> categoricalFeaturesInfo, String impurity, int maxDepth, int maxBins) Java-friendly API for org.apache.spark.mllib.tree.DecisionTree.trainClassifier
static DecisionTreeModel	trainClassifier(RDD<LabeledPoint> input, int numClasses, scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo, String impurity, int maxDepth, int maxBins) Method to train a decision tree model for binary or multiclass classification.
static DecisionTreeModel	trainRegressor(JavaRDD<LabeledPoint> input, java.util.Map<Integer,Integer> categoricalFeaturesInfo, String impurity, int maxDepth, int maxBins) Java-friendly API for org.apache.spark.mllib.tree.DecisionTree.trainRegressor
static DecisionTreeModel	trainRegressor(RDD<LabeledPoint> input, scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo, String impurity, int maxDepth, int maxBins) Method to train a decision tree model for regression.

Methods inherited from class Object

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

Methods inherited from interface org.apache.spark.internal.Logging

$init$, initializeForcefully, initializeLogIfNecessary, initializeLogIfNecessary, initializeLogIfNecessary$default$2, initLock, isTraceEnabled, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning, org$apache$spark$internal$Logging$$log__$eq, org$apache$spark$internal$Logging$$log_, uninitialize

Constructor Detail

DecisionTree

public DecisionTree(Strategy strategy)

Parameters:

strategy - The configuration parameters for the tree algorithm which specify the type of decision tree (classification or regression), feature type (continuous, categorical), depth of the tree, quantile calculation strategy, etc.

Method Detail

train

public static DecisionTreeModel train(RDD<LabeledPoint> input,
                                      Strategy strategy)

Method to train a decision tree model. The method supports binary and multiclass classification and regression.

Parameters:

input - Training dataset: RDD of LabeledPoint. For classification, labels should take values {0, 1, ..., numClasses-1}. For regression, labels are real numbers.

strategy - The configuration parameters for the tree algorithm which specify the type of decision tree (classification or regression), feature type (continuous, categorical), depth of the tree, quantile calculation strategy, etc.

Returns:

DecisionTreeModel that can be used for prediction.

Note:

Using org.apache.spark.mllib.tree.DecisionTree.trainClassifier and org.apache.spark.mllib.tree.DecisionTree.trainRegressor is recommended to clearly separate classification and regression.

train

public static DecisionTreeModel train(RDD<LabeledPoint> input,
                                      scala.Enumeration.Value algo,
                                      Impurity impurity,
                                      int maxDepth)

Method to train a decision tree model. The method supports binary and multiclass classification and regression.

Parameters:

input - Training dataset: RDD of LabeledPoint. For classification, labels should take values {0, 1, ..., numClasses-1}. For regression, labels are real numbers.

algo - Type of decision tree, either classification or regression.

impurity - Criterion used for information gain calculation.

maxDepth - Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes).

Returns:

DecisionTreeModel that can be used for prediction.

Note:

Using org.apache.spark.mllib.tree.DecisionTree.trainClassifier and org.apache.spark.mllib.tree.DecisionTree.trainRegressor is recommended to clearly separate classification and regression.

train

public static DecisionTreeModel train(RDD<LabeledPoint> input,
                                      scala.Enumeration.Value algo,
                                      Impurity impurity,
                                      int maxDepth,
                                      int numClasses)

Method to train a decision tree model. The method supports binary and multiclass classification and regression.

Parameters:

input - Training dataset: RDD of LabeledPoint. For classification, labels should take values {0, 1, ..., numClasses-1}. For regression, labels are real numbers.

algo - Type of decision tree, either classification or regression.

impurity - Criterion used for information gain calculation.

maxDepth - Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes).

numClasses - Number of classes for classification. Default value of 2.

Returns:

DecisionTreeModel that can be used for prediction.

Note:

Using org.apache.spark.mllib.tree.DecisionTree.trainClassifier and org.apache.spark.mllib.tree.DecisionTree.trainRegressor is recommended to clearly separate classification and regression.

train

public static DecisionTreeModel train(RDD<LabeledPoint> input,
                                      scala.Enumeration.Value algo,
                                      Impurity impurity,
                                      int maxDepth,
                                      int numClasses,
                                      int maxBins,
                                      scala.Enumeration.Value quantileCalculationStrategy,
                                      scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo)

Method to train a decision tree model. The method supports binary and multiclass classification and regression.

Parameters:

input - Training dataset: RDD of LabeledPoint. For classification, labels should take values {0, 1, ..., numClasses-1}. For regression, labels are real numbers.

algo - Type of decision tree, either classification or regression.

impurity - Criterion used for information gain calculation.

maxDepth - Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes).

numClasses - Number of classes for classification. Default value of 2.

maxBins - Maximum number of bins used for splitting features.

quantileCalculationStrategy - Algorithm for calculating quantiles.

categoricalFeaturesInfo - Map storing arity of categorical features. An entry (n to k) indicates that feature n is categorical with k categories indexed from 0: {0, 1, ..., k-1}.

Returns:

DecisionTreeModel that can be used for prediction.

Note:

Using org.apache.spark.mllib.tree.DecisionTree.trainClassifier and org.apache.spark.mllib.tree.DecisionTree.trainRegressor is recommended to clearly separate classification and regression.

trainClassifier

public static DecisionTreeModel trainClassifier(RDD<LabeledPoint> input,
                                                int numClasses,
                                                scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo,
                                                String impurity,
                                                int maxDepth,
                                                int maxBins)

Method to train a decision tree model for binary or multiclass classification.

Parameters:

input - Training dataset: RDD of LabeledPoint. Labels should take values {0, 1, ..., numClasses-1}.

numClasses - Number of classes for classification.

categoricalFeaturesInfo - Map storing arity of categorical features. An entry (n to k) indicates that feature n is categorical with k categories indexed from 0: {0, 1, ..., k-1}.

impurity - Criterion used for information gain calculation. Supported values: "gini" (recommended) or "entropy".

maxDepth - Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes). (suggested value: 5)

maxBins - Maximum number of bins used for splitting features. (suggested value: 32)

Returns:

DecisionTreeModel that can be used for prediction.

trainClassifier

public static DecisionTreeModel trainClassifier(JavaRDD<LabeledPoint> input,
                                                int numClasses,
                                                java.util.Map<Integer,Integer> categoricalFeaturesInfo,
                                                String impurity,
                                                int maxDepth,
                                                int maxBins)

Java-friendly API for org.apache.spark.mllib.tree.DecisionTree.trainClassifier

Parameters:

input - (undocumented)

numClasses - (undocumented)

categoricalFeaturesInfo - (undocumented)

impurity - (undocumented)

maxDepth - (undocumented)

maxBins - (undocumented)

Returns:

(undocumented)

trainRegressor

public static DecisionTreeModel trainRegressor(RDD<LabeledPoint> input,
                                               scala.collection.immutable.Map<Object,Object> categoricalFeaturesInfo,
                                               String impurity,
                                               int maxDepth,
                                               int maxBins)

Method to train a decision tree model for regression.

Parameters:

input - Training dataset: RDD of LabeledPoint. Labels are real numbers.

categoricalFeaturesInfo - Map storing arity of categorical features. An entry (n to k) indicates that feature n is categorical with k categories indexed from 0: {0, 1, ..., k-1}.

impurity - Criterion used for information gain calculation. The only supported value for regression is "variance".

maxDepth - Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes). (suggested value: 5)

maxBins - Maximum number of bins used for splitting features. (suggested value: 32)

Returns:

DecisionTreeModel that can be used for prediction.

trainRegressor

public static DecisionTreeModel trainRegressor(JavaRDD<LabeledPoint> input,
                                               java.util.Map<Integer,Integer> categoricalFeaturesInfo,
                                               String impurity,
                                               int maxDepth,
                                               int maxBins)

Java-friendly API for org.apache.spark.mllib.tree.DecisionTree.trainRegressor

Parameters:

input - (undocumented)

categoricalFeaturesInfo - (undocumented)

impurity - (undocumented)

maxDepth - (undocumented)

maxBins - (undocumented)

Returns:

(undocumented)

org$apache$spark$internal$Logging$$log_

public static org.slf4j.Logger org$apache$spark$internal$Logging$$log_()

org$apache$spark$internal$Logging$$log__$eq

public static void org$apache$spark$internal$Logging$$log__$eq(org.slf4j.Logger x$1)

run

public DecisionTreeModel run(RDD<LabeledPoint> input)

Method to train a decision tree model over an RDD

Parameters:

input - Training data: RDD of LabeledPoint.

Returns:

DecisionTreeModel that can be used for prediction.