Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5530#discussion_r28487021
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/impl/tree/treeParams.scala ---
@@ -0,0 +1,300 @@
+/*
+ * 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.impl.tree
+
+import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.ml.impl.estimator.PredictorParams
+import org.apache.spark.ml.param._
+import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo,
Strategy => OldStrategy}
+import org.apache.spark.mllib.tree.impurity.{Gini => OldGini, Entropy =>
OldEntropy,
+ Impurity => OldImpurity, Variance => OldVariance}
+
+
+/**
+ * :: DeveloperApi ::
+ * Parameters for Decision Tree-based algorithms.
+ * @tparam M Concrete class implementing this parameter trait
+ */
+@DeveloperApi
+private[ml] trait DecisionTreeParams[M] extends PredictorParams {
+
+ /**
+ * Maximum depth of the tree.
+ * E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2
leaf nodes.
+ * (default = 5)
+ * @group param
+ */
+ val maxDepth: IntParam =
+ new IntParam(this, "maxDepth", "Maximum depth of the tree." +
+ " E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2
leaf nodes.")
+
+ /**
+ * Maximum number of bins used for discretizing continuous features and
for choosing how to split
+ * on features at each node. More bins give higher granularity.
+ * Must be >= 2 and >= number of categories in any categorical feature.
+ * (default = 32)
+ * @group param
+ */
+ val maxBins: IntParam = new IntParam(this, "maxBins", "Max number of
bins for discretizing" +
+ " continuous features. Must be >=2 and >= number of categories for
any categorical feature.")
+
+ /**
+ * Minimum number of instances each child must have after split.
+ * If a split cause left or right child to have less than
minInstancesPerNode,
+ * this split will not be considered as a valid split.
+ * Should be >= 1.
+ * (default = 1)
+ * @group param
+ */
+ val minInstancesPerNode: IntParam = new IntParam(this,
"minInstancesPerNode", "Minimum number" +
+ " of instances each child must have after split. If a split cause
left or right child to" +
--- End diff --
`causes`
---
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]
