org.apache.spark.examples.ml.TrainValidationSplitExample.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_2.10 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 1.6.2-6

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.
 */

package org.apache.spark.examples.ml

import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}

/**
 * A simple example demonstrating model selection using TrainValidationSplit.
 *
 * The example is based on [[SimpleParamsExample]] using linear regression.
 * Run with
 * {{{
 * bin/run-example ml.TrainValidationSplitExample
 * }}}
 */
object TrainValidationSplitExample {

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

    // Prepare training and test data.
    val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
    val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345)

    val lr = new LinearRegression()

    // We use a ParamGridBuilder to construct a grid of parameters to search over.
    // TrainValidationSplit will try all combinations of values and determine best model using
    // the evaluator.
    val paramGrid = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .addGrid(lr.fitIntercept, Array(true, false))
      .addGrid(lr.elasticNetParam, Array(0.0, 0.5, 1.0))
      .build()

    // In this case the estimator is simply the linear regression.
    // A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
    val trainValidationSplit = new TrainValidationSplit()
      .setEstimator(lr)
      .setEvaluator(new RegressionEvaluator)
      .setEstimatorParamMaps(paramGrid)

    // 80% of the data will be used for training and the remaining 20% for validation.
    trainValidationSplit.setTrainRatio(0.8)

    // Run train validation split, and choose the best set of parameters.
    val model = trainValidationSplit.fit(training)

    // Make predictions on test data. model is the model with combination of parameters
    // that performed best.
    model.transform(test)
      .select("features", "label", "prediction")
      .show()

    sc.stop()
  }
}