Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/6756#discussion_r33084351
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -0,0 +1,209 @@
+/*
+ * 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.clustering
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.ml.param.shared.{HasFeaturesCol, HasMaxIter,
HasPredictionCol, HasSeed}
+import org.apache.spark.ml.param.{Param, ParamMap, Params}
+import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.mllib
+import org.apache.spark.mllib.clustering.KMeans
+import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types._
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.util.Utils
+
+
+/**
+ * Common params for KMeans and KMeansModel
+ */
+private[clustering] trait KMeansParams
+ extends Params with HasMaxIter with HasFeaturesCol with HasSeed with
HasPredictionCol {
+ /**
+ * Param for the column name for the number of clusters to create.
+ * @group param
+ */
+ val k = new Param[Int](this, "k", "number of clusters to create")
+
+ /** @group getParam */
+ def getK: Int = $(k)
+
+ /**
+ * Param for the column name for the number of runs of the algorithm to
execute in parallel.
+ * @group param
+ */
+ val runs = new Param[Int](this, "runs", "number of runs of the algorithm
to execute in parallel")
+
+ /** @group getParam */
+ def getRuns: Int = $(runs)
+
+ /**
+ * Param for the column name for the distance threshold
+ * within which we've consider centers to have converged.
+ * @group param
+ */
+ val epsilon = new Param[Double](this, "epsilon", "distance threshold")
+
+ /** @group getParam */
+ def getEpsilon: Double = $(epsilon)
+
+ /**
+ * Param for the initialization algorithm.
+ * @group param
+ */
+ val initializationMode = new Param[String](this, "initializationMode",
"initialization algorithm")
+
+ /** @group getParam */
+ def getInitializationMode: String = $(initializationMode)
+
+ /**
+ * Param for the number of steps for k-means initialization mode.
+ * @group param
+ */
+ val initializationSteps =
--- End diff --
Ditto: "initSteps"
---
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]
