Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/15770#discussion_r178987751
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala
---
@@ -0,0 +1,216 @@
+/*
+ * 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, Since}
+import org.apache.spark.ml.Transformer
+import org.apache.spark.ml.linalg.Vector
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.clustering.{PowerIterationClustering =>
MLlibPowerIterationClustering}
+import
org.apache.spark.mllib.clustering.PowerIterationClustering.Assignment
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+import org.apache.spark.sql.functions.col
+import org.apache.spark.sql.types.{IntegerType, LongType, StructField,
StructType}
+
+/**
+ * Common params for PowerIterationClustering
+ */
+private[clustering] trait PowerIterationClusteringParams extends Params
with HasMaxIter
+ with HasFeaturesCol with HasPredictionCol with HasWeightCol {
+
+ /**
+ * The number of clusters to create (k). Must be > 1. Default: 2.
+ * @group param
+ */
+ @Since("2.3.0")
+ final val k = new IntParam(this, "k", "The number of clusters to create.
" +
+ "Must be > 1.", ParamValidators.gt(1))
+
+ /** @group getParam */
+ @Since("2.3.0")
+ def getK: Int = $(k)
+
+ /**
+ * Param for the initialization algorithm. This can be either "random"
to use a random vector
+ * as vertex properties, or "degree" to use normalized sum similarities.
Default: random.
+ */
+ @Since("2.3.0")
+ final val initMode = {
+ val allowedParams = ParamValidators.inArray(Array("random", "degree"))
+ new Param[String](this, "initMode", "The initialization algorithm. " +
+ "Supported options: 'random' and 'degree'.", allowedParams)
+ }
+
+ /** @group expertGetParam */
+ @Since("2.3.0")
+ def getInitMode: String = $(initMode)
+
+ /**
+ * Param for the column name for ids returned by
PowerIterationClustering.transform().
+ * Default: "id"
+ * @group param
+ */
+ @Since("2.3.0")
+ val idCol = new Param[String](this, "id", "column name for ids.")
+
+ /** @group getParam */
+ @Since("2.3.0")
+ def getIdCol: String = $(idCol)
+
+ /**
+ * Param for the column name for neighbors required by
PowerIterationClustering.transform().
+ * Default: "neighbor"
+ * @group param
+ */
+ @Since("2.3.0")
+ val neighborCol = new Param[String](this, "neighbor", "column name for
neighbors.")
+
+ /** @group getParam */
+ @Since("2.3.0")
+ def getNeighborCol: String = $(neighborCol)
+
+ /**
+ * Validates the input schema
--- End diff --
nit: No need for doc like this which is explained by the method title
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
