Github user vlad17 commented on a diff in the pull request:
https://github.com/apache/spark/pull/14547#discussion_r78484182
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/tree/impurity/ApproxBernoulliImpurity.scala
---
@@ -0,0 +1,162 @@
+/*
+ * 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.tree.impurity
+
+import org.apache.spark.annotation.{DeveloperApi, Since}
+import org.apache.spark.mllib.tree.impurity._
+
+/**
+ * [[ApproxBernoulliImpurity]] currently uses variance as a (proxy)
impurity measure
+ * during tree construction. The main purpose of the class is to have an
alternative
+ * leaf prediction calculation.
+ *
+ * Only data with examples each of weight 1.0 is supported.
+ *
+ * Class for calculating variance during regression.
+ */
+@Since("2.1")
+object ApproxBernoulliImpurity extends Impurity {
+
+ /**
+ * :: DeveloperApi ::
+ * information calculation for multiclass classification
+ * @param counts Array[Double] with counts for each label
+ * @param totalCount sum of counts for all labels
+ * @return information value, or 0 if totalCount = 0
+ */
+ @Since("2.1")
+ @DeveloperApi
+ override def calculate(counts: Array[Double], totalCount: Double):
Double =
+ throw new
UnsupportedOperationException("ApproxBernoulliImpurity.calculate")
+
+ /**
+ * :: DeveloperApi ::
+ * variance calculation
+ * @param count number of instances
+ * @param sum sum of labels
+ * @param sumSquares summation of squares of the labels
+ * @return information value, or 0 if count = 0
+ */
+ @Since("2.1")
+ @DeveloperApi
+ override def calculate(count: Double, sum: Double, sumSquares: Double):
Double = {
+ Variance.calculate(count, sum, sumSquares)
+ }
+
+ /**
+ * Get this impurity instance.
+ * This is useful for passing impurity parameters to a Strategy in Java.
+ */
+ @Since("2.1")
+ def instance: this.type = this
--- End diff --
done
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
