Github user wangmiao1981 commented on a diff in the pull request:
https://github.com/apache/spark/pull/15770#discussion_r102330772
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala
---
@@ -0,0 +1,182 @@
+/*
+ * 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 {
+
+ /**
+ * The number of clusters to create (k). Must be > 1. Default: 2.
+ * @group param
+ */
+ @Since("2.2.0")
+ final val k = new IntParam(this, "k", "The number of clusters to create.
" +
+ "Must be > 1.", ParamValidators.gt(1))
+
+ /** @group getParam */
+ @Since("2.2.0")
+ 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("2.2.0")
+ final val initMode = new Param[String](this, "initMode", "The
initialization algorithm. " +
+ "Supported options: 'random' and 'degree'.",
+ (value: String) => validateInitMode(value))
+
+ private[spark] def validateInitMode(initMode: String): Boolean = {
+ initMode match {
+ case "random" => true
+ case "degree" => true
+ case _ => false
+ }
+ }
+
+ /** @group expertGetParam */
+ @Since("2.2.0")
+ def getInitMode: String = $(initMode)
+
+ /**
+ * Param for the column name for ids returned by
[[PowerIterationClustering.transform()]].
+ * Default: "id"
+ * @group param
+ */
+ val idCol = new Param[String](this, "idCol", "column name for ids.")
--- End diff --
PIC is different compared with K-Means. K-Means `transform` applies
`predict` method to each row of the input (i.e., each data point). While PIC
`run` is applying the K-Means to the pseudo-eigenvector from `powerIter`
method. This is not one-to-one map from Input dataset to result. Please also
see the comments below.
---
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]
