[GitHub] spark pull request: [SPARK-1303] [MLLIB] Added discretization capa...

[avulanov <gi...@git.apache.org>]

Github user avulanov commented on a diff in the pull request:

    https://github.com/apache/spark/pull/216#discussion_r16053704
  
    --- Diff: mllib/src/main/scala/org/apache/spark/mllib/discretization/EntropyMinimizationDiscretizer.scala ---
    @@ -0,0 +1,276 @@
    +/*
    + * 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.discretization
    +
    +import scala.collection.mutable
    +import org.apache.spark.SparkContext._
    +import org.apache.spark.rdd.RDD
    +import org.apache.spark.storage.StorageLevel
    +import org.apache.spark.mllib.regression.LabeledPoint
    +
    +/**
    + * This class contains methods to calculate thresholds to discretize continuous values with the
    + * method proposed by Fayyad and Irani in Multi-Interval Discretization of Continuous-Valued
    + * Attributes (1993).
    + *
    + * @param continuousFeaturesIndexes Indexes of features to be discretized.
    + * @param elementsPerPartition Maximum number of thresholds to treat in each RDD partition.
    + * @param maxBins Maximum number of bins for each discretized feature.
    + */
    +class EntropyMinimizationDiscretizer private (
    +    val continuousFeaturesIndexes: Seq[Int],
    +    val elementsPerPartition: Int,
    +    val maxBins: Int)
    +  extends Serializable {
    +
    +  private val partitions = { x: Long => math.ceil(x.toDouble / elementsPerPartition).toInt }
    +  private val log2 = { x: Double => math.log(x) / math.log(2) }
    +
    +  /**
    +   * Run the algorithm with the configured parameters on an input.
    +   * @param data RDD of LabeledPoint's.
    +   * @return A EntropyMinimizationDiscretizerModel with the thresholds to discretize.
    +   */
    +  def run(data: RDD[LabeledPoint]) = {
    +    val labels2Int = data.context.broadcast(data.map(_.label).distinct.collect.zipWithIndex.toMap)
    +    val nLabels = labels2Int.value.size
    +
    +    var thresholds = Map.empty[Int, Seq[Double]]
    +    for (i <- continuousFeaturesIndexes) {
    +      val featureValues = data.map({
    +        case LabeledPoint(label, values) => (values(i), labels2Int.value(label))
    --- End diff --
    
    values(i) -->> values.toArray(i)


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org