diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md
index 1166d9cd150c468814ceba45b0a0caac22bb70ec..12a6afbeea82995123a3779ced645e36344c1621 100644
--- a/docs/mllib-decision-tree.md
+++ b/docs/mllib-decision-tree.md
@@ -80,7 +80,7 @@ The ordered splits create "bins" and the maximum number of such
bins can be specified using the `maxBins` parameter.
Note that the number of bins cannot be greater than the number of instances `$N$` (a rare scenario
-since the default `maxBins` value is 100). The tree algorithm automatically reduces the number of
+since the default `maxBins` value is 32). The tree algorithm automatically reduces the number of
bins if the condition is not satisfied.
**Categorical features**
@@ -117,7 +117,7 @@ all nodes at each level of the tree. This could lead to high memory requirements
of the tree, potentially leading to memory overflow errors. To alleviate this problem, a `maxMemoryInMB`
training parameter specifies the maximum amount of memory at the workers (twice as much at the
master) to be allocated to the histogram computation. The default value is conservatively chosen to
-be 128 MB to allow the decision algorithm to work in most scenarios. Once the memory requirements
+be 256 MB to allow the decision algorithm to work in most scenarios. Once the memory requirements
for a level-wise computation cross the `maxMemoryInMB` threshold, the node training tasks at each
subsequent level are split into smaller tasks.
@@ -167,7 +167,7 @@ val numClasses = 2
val categoricalFeaturesInfo = Map[Int, Int]()
val impurity = "gini"
val maxDepth = 5
-val maxBins = 100
+val maxBins = 32
val model = DecisionTree.trainClassifier(data, numClasses, categoricalFeaturesInfo, impurity,
maxDepth, maxBins)
@@ -213,7 +213,7 @@ Integer numClasses = 2;
HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
String impurity = "gini";
Integer maxDepth = 5;
-Integer maxBins = 100;
+Integer maxBins = 32;
// Train a DecisionTree model for classification.
final DecisionTreeModel model = DecisionTree.trainClassifier(data, numClasses,
@@ -250,7 +250,7 @@ data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt').cache()
# Train a DecisionTree model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
model = DecisionTree.trainClassifier(data, numClasses=2, categoricalFeaturesInfo={},
- impurity='gini', maxDepth=5, maxBins=100)
+ impurity='gini', maxDepth=5, maxBins=32)
# Evaluate model on training instances and compute training error
predictions = model.predict(data.map(lambda x: x.features))
@@ -293,7 +293,7 @@ val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").cache
val categoricalFeaturesInfo = Map[Int, Int]()
val impurity = "variance"
val maxDepth = 5
-val maxBins = 100
+val maxBins = 32
val model = DecisionTree.trainRegressor(data, categoricalFeaturesInfo, impurity,
maxDepth, maxBins)
@@ -338,7 +338,7 @@ JavaSparkContext sc = new JavaSparkContext(sparkConf);
HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
String impurity = "variance";
Integer maxDepth = 5;
-Integer maxBins = 100;
+Integer maxBins = 32;
// Train a DecisionTree model.
final DecisionTreeModel model = DecisionTree.trainRegressor(data,
@@ -380,7 +380,7 @@ data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt').cache()
# Train a DecisionTree model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
model = DecisionTree.trainRegressor(data, categoricalFeaturesInfo={},
- impurity='variance', maxDepth=5, maxBins=100)
+ impurity='variance', maxDepth=5, maxBins=32)
# Evaluate model on training instances and compute training error
predictions = model.predict(data.map(lambda x: x.features))
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
index e4468e8bf17442193d8b4b67a3489843006f3d43..1f82e3f4cb18e381918f96f5065831a199c14ff8 100644
--- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
@@ -63,7 +63,7 @@ public final class JavaDecisionTree {
HashMap<Integer, Integer> categoricalFeaturesInfo = new HashMap<Integer, Integer>();
String impurity = "gini";
Integer maxDepth = 5;
- Integer maxBins = 100;
+ Integer maxBins = 32;
// Train a DecisionTree model for classification.
final DecisionTreeModel model = DecisionTree.trainClassifier(data, numClasses,
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala
index cf3d2cca81ff6200129b7b64ffd559501a3ebfc0..72c3ab475b61f28d2010365812732cae6533b5d0 100644
--- a/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala
@@ -52,9 +52,9 @@ object DecisionTreeRunner {
input: String = null,
dataFormat: String = "libsvm",
algo: Algo = Classification,
- maxDepth: Int = 4,
+ maxDepth: Int = 5,
impurity: ImpurityType = Gini,
- maxBins: Int = 100,
+ maxBins: Int = 32,
fracTest: Double = 0.2)
def main(args: Array[String]) {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
index dd766c12d28a46f6dd96cbaab4eb3d73610ece65..d1309b2b20f546173a84ba5370ce1663bb7d5f74 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
@@ -330,9 +330,9 @@ object DecisionTree extends Serializable with Logging {
* Supported values: "gini" (recommended) or "entropy".
* @param 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: 4)
+ * (suggested value: 5)
* @param maxBins maximum number of bins used for splitting features
- * (suggested value: 100)
+ * (suggested value: 32)
* @return DecisionTreeModel that can be used for prediction
*/
def trainClassifier(
@@ -374,9 +374,9 @@ object DecisionTree extends Serializable with Logging {
* Supported values: "variance".
* @param 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: 4)
+ * (suggested value: 5)
* @param maxBins maximum number of bins used for splitting features
- * (suggested value: 100)
+ * (suggested value: 32)
* @return DecisionTreeModel that can be used for prediction
*/
def trainRegressor(
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
index cfc8192a85abd47d25324b1905605d4d8c6ab3c6..23f74d5360fe54fa6737234b6b1015a1f97b1ad4 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
@@ -50,7 +50,7 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
* 1, 2, ... , k-1. It's important to note that features are
* zero-indexed.
* @param maxMemoryInMB Maximum memory in MB allocated to histogram aggregation. Default value is
- * 128 MB.
+ * 256 MB.
*/
@Experimental
class Strategy (
@@ -58,10 +58,10 @@ class Strategy (
val impurity: Impurity,
val maxDepth: Int,
val numClassesForClassification: Int = 2,
- val maxBins: Int = 100,
+ val maxBins: Int = 32,
val quantileCalculationStrategy: QuantileStrategy = Sort,
val categoricalFeaturesInfo: Map[Int, Int] = Map[Int, Int](),
- val maxMemoryInMB: Int = 128) extends Serializable {
+ val maxMemoryInMB: Int = 256) extends Serializable {
if (algo == Classification) {
require(numClassesForClassification >= 2)
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala
index 8e556c917b2e71147f9630caa910db7c6cabea0b..69482f2acbb40b64ba19923bfccd8c523e2de1f2 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala
@@ -31,7 +31,6 @@ import org.apache.spark.mllib.tree.impurity.{Entropy, Gini, Variance}
import org.apache.spark.mllib.tree.model.{DecisionTreeModel, Node}
import org.apache.spark.mllib.util.LocalSparkContext
-
class DecisionTreeSuite extends FunSuite with LocalSparkContext {
def validateClassifier(
@@ -353,8 +352,6 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
assert(splits(0).length === 99)
assert(bins.length === 2)
assert(bins(0).length === 100)
- assert(splits(0).length === 99)
- assert(bins(0).length === 100)
val treeInput = TreePoint.convertToTreeRDD(rdd, bins, metadata)
val bestSplits = DecisionTree.findBestSplits(treeInput, new Array(8), metadata, 0,
@@ -381,8 +378,6 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
assert(splits(0).length === 99)
assert(bins.length === 2)
assert(bins(0).length === 100)
- assert(splits(0).length === 99)
- assert(bins(0).length === 100)
val treeInput = TreePoint.convertToTreeRDD(rdd, bins, metadata)
val bestSplits = DecisionTree.findBestSplits(treeInput, new Array(2), metadata, 0,
@@ -410,8 +405,6 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
assert(splits(0).length === 99)
assert(bins.length === 2)
assert(bins(0).length === 100)
- assert(splits(0).length === 99)
- assert(bins(0).length === 100)
val treeInput = TreePoint.convertToTreeRDD(rdd, bins, metadata)
val bestSplits = DecisionTree.findBestSplits(treeInput, new Array(2), metadata, 0,
@@ -439,8 +432,6 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
assert(splits(0).length === 99)
assert(bins.length === 2)
assert(bins(0).length === 100)
- assert(splits(0).length === 99)
- assert(bins(0).length === 100)
val treeInput = TreePoint.convertToTreeRDD(rdd, bins, metadata)
val bestSplits = DecisionTree.findBestSplits(treeInput, new Array(2), metadata, 0,
@@ -464,8 +455,6 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
assert(splits(0).length === 99)
assert(bins.length === 2)
assert(bins(0).length === 100)
- assert(splits(0).length === 99)
- assert(bins(0).length === 100)
// Train a 1-node model
val strategyOneNode = new Strategy(Classification, Entropy, 1, 2, 100)
@@ -600,7 +589,7 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
val arr = DecisionTreeSuite.generateContinuousDataPointsForMulticlass()
val rdd = sc.parallelize(arr)
val strategy = new Strategy(algo = Classification, impurity = Gini, maxDepth = 4,
- numClassesForClassification = 3)
+ numClassesForClassification = 3, maxBins = 100)
assert(strategy.isMulticlassClassification)
val metadata = DecisionTreeMetadata.buildMetadata(rdd, strategy)
@@ -626,7 +615,7 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
val arr = DecisionTreeSuite.generateContinuousDataPointsForMulticlass()
val rdd = sc.parallelize(arr)
val strategy = new Strategy(algo = Classification, impurity = Gini, maxDepth = 4,
- numClassesForClassification = 3, categoricalFeaturesInfo = Map(0 -> 3))
+ numClassesForClassification = 3, maxBins = 100, categoricalFeaturesInfo = Map(0 -> 3))
assert(strategy.isMulticlassClassification)
val metadata = DecisionTreeMetadata.buildMetadata(rdd, strategy)
assert(metadata.isUnordered(featureIndex = 0))
@@ -652,7 +641,8 @@ class DecisionTreeSuite extends FunSuite with LocalSparkContext {
val arr = DecisionTreeSuite.generateCategoricalDataPointsForMulticlassForOrderedFeatures()
val rdd = sc.parallelize(arr)
val strategy = new Strategy(algo = Classification, impurity = Gini, maxDepth = 4,
- numClassesForClassification = 3, categoricalFeaturesInfo = Map(0 -> 10, 1 -> 10))
+ numClassesForClassification = 3, maxBins = 100,
+ categoricalFeaturesInfo = Map(0 -> 10, 1 -> 10))
assert(strategy.isMulticlassClassification)
val metadata = DecisionTreeMetadata.buildMetadata(rdd, strategy)
assert(!metadata.isUnordered(featureIndex = 0))
diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py
index a2fade61e9a71d41bb9cfafc1a5eae48873cf260..ccc000ac70ba64ef7e38e3bbb06126cd5a5b427b 100644
--- a/python/pyspark/mllib/tree.py
+++ b/python/pyspark/mllib/tree.py
@@ -138,7 +138,7 @@ class DecisionTree(object):
@staticmethod
def trainClassifier(data, numClasses, categoricalFeaturesInfo,
- impurity="gini", maxDepth=4, maxBins=100):
+ impurity="gini", maxDepth=5, maxBins=32):
"""
Train a DecisionTreeModel for classification.
@@ -170,7 +170,7 @@ class DecisionTree(object):
@staticmethod
def trainRegressor(data, categoricalFeaturesInfo,
- impurity="variance", maxDepth=4, maxBins=100):
+ impurity="variance", maxDepth=5, maxBins=32):
"""
Train a DecisionTreeModel for regression.