spark ModelSelectionViaTrainValidationSplitExample 源码

spark ModelSelectionViaTrainValidationSplitExample 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaTrainValidationSplitExample.scala

/*
 * 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

// $example on$
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
// $example off$
import org.apache.spark.sql.SparkSession

/**
 * A simple example demonstrating model selection using TrainValidationSplit.
 *
 * Run with
 * {{{
 * bin/run-example ml.ModelSelectionViaTrainValidationSplitExample
 * }}}
 */
object ModelSelectionViaTrainValidationSplitExample {

  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("ModelSelectionViaTrainValidationSplitExample")
      .getOrCreate()

    // $example on$
    // Prepare training and test data.
    val data = spark.read.format("libsvm").load("data/mllib/sample_linear_regression_data.txt")
    val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345)

    val lr = new LinearRegression()
        .setMaxIter(10)

    // 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)
      .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.
      .setTrainRatio(0.8)
      // Evaluate up to 2 parameter settings in parallel
      .setParallelism(2)

    // 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()
    // $example off$

    spark.stop()
  }
}

相关信息

spark 源码目录

相关文章

spark AFTSurvivalRegressionExample 源码

spark ALSExample 源码

spark BinarizerExample 源码

spark BisectingKMeansExample 源码

spark BucketedRandomProjectionLSHExample 源码

spark BucketizerExample 源码

spark ChiSqSelectorExample 源码

spark ChiSquareTestExample 源码

spark CorrelationExample 源码

spark CountVectorizerExample 源码