diff options
author | Xiangrui Meng <meng@databricks.com> | 2014-09-08 18:59:57 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2014-09-08 18:59:57 -0700 |
commit | 50a4fa774a0e8a17d7743b33ce8941bf4041144d (patch) | |
tree | 18089ba49e1450cf1b76238c9b435883f7003474 /mllib/src/main | |
parent | 7db53391f1b349d1f49844197b34f94806f5e336 (diff) | |
download | spark-50a4fa774a0e8a17d7743b33ce8941bf4041144d.tar.gz spark-50a4fa774a0e8a17d7743b33ce8941bf4041144d.tar.bz2 spark-50a4fa774a0e8a17d7743b33ce8941bf4041144d.zip |
[SPARK-3443][MLLIB] update default values of tree:
Adjust the default values of decision tree, based on the memory requirement discussed in https://github.com/apache/spark/pull/2125 :
1. maxMemoryInMB: 128 -> 256
2. maxBins: 100 -> 32
3. maxDepth: 4 -> 5 (in some example code)
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes #2322 from mengxr/tree-defaults and squashes the following commits:
cda453a [Xiangrui Meng] fix tests
5900445 [Xiangrui Meng] update comments
8c81831 [Xiangrui Meng] update default values of tree:
Diffstat (limited to 'mllib/src/main')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala | 8 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala | 6 |
2 files changed, 7 insertions, 7 deletions
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 dd766c12d2..d1309b2b20 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 cfc8192a85..23f74d5360 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) |