org.apache.spark.examples.mllib.ChiSqSelectorExample.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of spark-examples_2.12 Show documentation
The newest version!
/*
 * 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.
 */

// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
// $example on$
import org.apache.spark.mllib.feature.ChiSqSelector
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
// $example off$

object ChiSqSelectorExample {

  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setAppName("ChiSqSelectorExample")
    val sc = new SparkContext(conf)

    // $example on$
    // Load some data in libsvm format
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
    // Discretize data in 16 equal bins since ChiSqSelector requires categorical features
    // Even though features are doubles, the ChiSqSelector treats each unique value as a category
    val discretizedData = data.map { lp =>
      LabeledPoint(lp.label, Vectors.dense(lp.features.toArray.map { x => (x / 16).floor }))
    }
    // Create ChiSqSelector that will select top 50 of 692 features
    val selector = new ChiSqSelector(50)
    // Create ChiSqSelector model (selecting features)
    val transformer = selector.fit(discretizedData)
    // Filter the top 50 features from each feature vector
    val filteredData = discretizedData.map { lp =>
      LabeledPoint(lp.label, transformer.transform(lp.features))
    }
    // $example off$

    println("filtered data: ")
    filteredData.collect.foreach(x => println(x))

    sc.stop()
  }
}
// scalastyle:on println