Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/2868#discussion_r19508975
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala ---
@@ -0,0 +1,189 @@
+/*
+ * 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.mllib.tree.impl
+
+import scala.collection.mutable
+
+import org.apache.spark.rdd.RDD
+import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.mllib.tree.configuration.FeatureType._
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.mllib.tree.model.{Bin, Node, Split}
+
+import org.apache.hadoop.fs.{Path, FileSystem}
+
+/**
+ * :: DeveloperApi ::
+ * This is used by the node id cache to find the child id that a data
point would belong to.
+ * @param split Split information.
+ * @param nodeIndex The current node index of a data point that this will
update.
+ */
+@DeveloperApi
+private[tree] case class NodeIndexUpdater(
+ split: Split,
+ nodeIndex: Int) {
+ /**
+ * Determine a child node index based on the feature value and the split.
+ * @param binnedFeatures Binned feature values.
+ * @param bins Bin information to convert the bin indices to approximate
feature values.
+ * @return Child node index to update to.
+ */
+ def updateNodeIndex(binnedFeatures: Array[Int], bins:
Array[Array[Bin]]): Int = {
+ if (split.featureType == Continuous) {
+ val featureIndex = split.feature
+ val binIndex = binnedFeatures(featureIndex)
+ val featureValueUpperBound =
bins(featureIndex)(binIndex).highSplit.threshold
--- End diff --
Since you now know `split` available, can you replace
`bins(featureIndex)(binIndex).highSplit.threshold` with `split.threshold` and
then eliminate the `bins` argument?
---
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]
