Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5267#discussion_r27682172
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/HierarchicalClustering.scala
---
@@ -0,0 +1,610 @@
+/*
+ * 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.clustering
+
+import breeze.linalg.{DenseVector => BDV, SparseVector => BSV, Vector =>
BV, norm => breezeNorm}
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.util.random.XORShiftRandom
+import org.apache.spark.{Logging, SparkException}
+
+import scala.collection.{Map, mutable}
+
+
+/**
+ * Top-level methods for calling the hierarchical clustering algorithm
+ */
+object HierarchicalClustering extends Logging {
--- End diff --
Those static train() methods used to be added everywhere, but at some
point, we realized that they require a lot of duplicated code (since Java does
not recognize default arguments). We're trying to just add builder methods
from now on, but we have to keep the old static train() methods for API
stability.
You're right about consistency. I've been thinking about whether we should
start deprecating the old static train() methods.
---
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]
