Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/2847#discussion_r23273448
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala ---
@@ -0,0 +1,208 @@
+/*
+ * 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.fpm
+
+import org.apache.spark.Logging
+import org.apache.spark.SparkContext._
+import org.apache.spark.broadcast._
+import org.apache.spark.rdd.RDD
+
+import scala.collection.mutable.{ArrayBuffer, Map}
+
+/**
+ * This class implements Parallel FPGrowth algorithm to do frequent
pattern matching on input data.
+ * Parallel FPGrowth (PFP) partitions computation in such a way that each
machine executes an
+ * independent group of mining tasks. More detail of this algorithm can be
found at
+ * http://infolab.stanford.edu/~echang/recsys08-69.pdf
+ */
+class FPGrowth private(private var minSupport: Double) extends Logging
with Serializable {
+
+ /**
+ * Constructs a FPGrowth instance with default parameters:
+ * {minSupport: 0.5}
+ */
+ def this() = this(0.5)
+
+ /**
+ * set the minimal support level, default is 0.5
+ * @param minSupport minimal support level
+ */
+ def setMinSupport(minSupport: Double): this.type = {
+ this.minSupport = minSupport
+ this
+ }
+
+ /**
+ * Compute a FPGrowth Model that contains frequent pattern result.
+ * @param data input data set
+ * @return FPGrowth Model
+ */
+ def run(data: RDD[Array[String]]): FPGrowthModel = {
+ val model = runAlgorithm(data)
+ model
+ }
+
+ /**
+ * Implementation of PFP.
+ */
+ private def runAlgorithm(data: RDD[Array[String]]): FPGrowthModel = {
+ val count = data.count()
+ val minCount = minSupport * count
+ val single = generateSingleItem(data, minCount)
+ val combinations = generateCombinations(data, minCount, single)
+ new FPGrowthModel(single ++ combinations)
+ }
+
+ /**
+ * Generate single item pattern by filtering the input data using
minimal support level
+ */
+ private def generateSingleItem(
+ data: RDD[Array[String]],
+ minCount: Double): Array[(String, Int)] = {
+ data.flatMap(v => v)
+ .map(v => (v, 1))
+ .reduceByKey(_ + _)
+ .filter(_._2 >= minCount)
+ .collect()
+ .distinct
+ .sortWith(_._2 > _._2)
+ }
+
+ /**
+ * Generate combination of items by computing on FPTree,
+ * the computation is done on each FPTree partitions.
+ */
+ private def generateCombinations(
+ data: RDD[Array[String]],
+ minCount: Double,
+ singleItem: Array[(String, Int)]): Array[(String, Int)] = {
+ val single = data.context.broadcast(singleItem)
+ data.flatMap(basket => createFPTree(basket, single))
+ .groupByKey()
+ .flatMap(partition => runFPTree(partition, minCount))
+ .collect()
+ }
+
+ /**
+ * Create FP-Tree partition for the giving basket
+ */
+ private def createFPTree(
+ basket: Array[String],
+ singleItem: Broadcast[Array[(String, Int)]]): Array[(String,
Array[String])] = {
+ var output = ArrayBuffer[(String, Array[String])]()
+ var combination = ArrayBuffer[String]()
+ val single = singleItem.value
+ var items = ArrayBuffer[(String, Int)]()
+
+ // Filter the basket by single item pattern
+ val iterator = basket.iterator
+ while (iterator.hasNext){
+ val item = iterator.next
+ val opt = single.find(_._1.equals(item))
--- End diff --
If we need to test membership, should we make `single` a map?
---
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]
