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

Go to download

Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 2.1.3.2

Show 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, SparkContext}
// $example on$
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.LinearRegressionWithSGD
// $example off$

@deprecated("Use ml.regression.LinearRegression or LBFGS", "2.0.0")
object LinearRegressionWithSGDExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("LinearRegressionWithSGDExample")
    val sc = new SparkContext(conf)

    // $example on$
    // Load and parse the data
    val data = sc.textFile("data/mllib/ridge-data/lpsa.data")
    val parsedData = data.map { line =>
      val parts = line.split(',')
      LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble)))
    }.cache()

    // Building the model
    val numIterations = 100
    val stepSize = 0.00000001
    val model = LinearRegressionWithSGD.train(parsedData, numIterations, stepSize)

    // Evaluate model on training examples and compute training error
    val valuesAndPreds = parsedData.map { point =>
      val prediction = model.predict(point.features)
      (point.label, prediction)
    }
    val MSE = valuesAndPreds.map{ case(v, p) => math.pow((v - p), 2) }.mean()
    println("training Mean Squared Error = " + MSE)

    // Save and load model
    model.save(sc, "target/tmp/scalaLinearRegressionWithSGDModel")
    val sameModel = LinearRegressionModel.load(sc, "target/tmp/scalaLinearRegressionWithSGDModel")
    // $example off$

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