Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5626#discussion_r29024762
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala
---
@@ -0,0 +1,165 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import org.scalatest.FunSuite
+
+import org.apache.spark.ml.impl.TreeTests
+import org.apache.spark.mllib.linalg.Vectors
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.tree.{EnsembleTestHelper, RandomForest =>
OldRandomForest}
+import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo}
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.DataFrame
+
+
+/**
+ * Test suite for [[RandomForestClassifier]].
+ */
+class RandomForestClassifierSuite extends FunSuite with
MLlibTestSparkContext {
+
+ import RandomForestClassifierSuite.compareAPIs
+
+ private var orderedLabeledPoints50_1000: RDD[LabeledPoint] = _
+ private var orderedLabeledPoints5_20: RDD[LabeledPoint] = _
+
+ override def beforeAll() {
+ super.beforeAll()
+ orderedLabeledPoints50_1000 =
+
sc.parallelize(EnsembleTestHelper.generateOrderedLabeledPoints(numFeatures =
50, 1000))
+ orderedLabeledPoints5_20 =
+
sc.parallelize(EnsembleTestHelper.generateOrderedLabeledPoints(numFeatures = 5,
20))
+ }
+
+
/////////////////////////////////////////////////////////////////////////////
+ // Tests calling train()
+
/////////////////////////////////////////////////////////////////////////////
+
+ def binaryClassificationTestWithContinuousFeatures(rf:
RandomForestClassifier) {
+ val categoricalFeatures = Map.empty[Int, Int]
+ val numClasses = 2
+ val newRF = rf
+ .setImpurity("Gini")
+ .setMaxDepth(2)
+ .setNumTrees(1)
+ .setFeatureSubsetStrategy("auto")
+ .setSeed(123)
+ compareAPIs(orderedLabeledPoints50_1000, newRF, categoricalFeatures,
numClasses)
+ }
+
+ test("Binary classification with continuous features:" +
+ " comparing DecisionTree vs. RandomForest(numTrees = 1)") {
+ val rf = new RandomForestClassifier()
+ binaryClassificationTestWithContinuousFeatures(rf)
+ }
+
+ test("Binary classification with continuous features and node Id cache:"
+
+ " comparing DecisionTree vs. RandomForest(numTrees = 1)") {
+ val rf = new RandomForestClassifier()
+ .setCacheNodeIds(true)
+ binaryClassificationTestWithContinuousFeatures(rf)
+ }
+
+ test("alternating categorical and continuous features with multiclass
labels to test indexing") {
+ val arr = new Array[LabeledPoint](4)
--- End diff --
~~~scala
val arr = Array(
LabeledPoint(0.0, Vectors.dense(1.0, 0.0, 0.0, 3.0, 1.0)),
...)
~~~
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
