org.apache.spark.examples.ml.ModelSelectionViaCrossValidationExample.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.ml

// $example on$
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.ml.linalg.Vector
import org.apache.spark.ml.tuning.{CrossValidator, ParamGridBuilder}
import org.apache.spark.sql.Row
// $example off$
import org.apache.spark.sql.SparkSession

/**
 * A simple example demonstrating model selection using CrossValidator.
 * This example also demonstrates how Pipelines are Estimators.
 *
 * Run with
 * {{{
 * bin/run-example ml.ModelSelectionViaCrossValidationExample
 * }}}
 */
object ModelSelectionViaCrossValidationExample {

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

    // $example on$
    // Prepare training data from a list of (id, text, label) tuples.
    val training = spark.createDataFrame(Seq(
      (0L, "a b c d e spark", 1.0),
      (1L, "b d", 0.0),
      (2L, "spark f g h", 1.0),
      (3L, "hadoop mapreduce", 0.0),
      (4L, "b spark who", 1.0),
      (5L, "g d a y", 0.0),
      (6L, "spark fly", 1.0),
      (7L, "was mapreduce", 0.0),
      (8L, "e spark program", 1.0),
      (9L, "a e c l", 0.0),
      (10L, "spark compile", 1.0),
      (11L, "hadoop software", 0.0)
    )).toDF("id", "text", "label")

    // Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
    val tokenizer = new Tokenizer()
      .setInputCol("text")
      .setOutputCol("words")
    val hashingTF = new HashingTF()
      .setInputCol(tokenizer.getOutputCol)
      .setOutputCol("features")
    val lr = new LogisticRegression()
      .setMaxIter(10)
    val pipeline = new Pipeline()
      .setStages(Array(tokenizer, hashingTF, lr))

    // We use a ParamGridBuilder to construct a grid of parameters to search over.
    // With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
    // this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
    val paramGrid = new ParamGridBuilder()
      .addGrid(hashingTF.numFeatures, Array(10, 100, 1000))
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .build()

    // We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
    // This will allow us to jointly choose parameters for all Pipeline stages.
    // A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
    // Note that the evaluator here is a BinaryClassificationEvaluator and its default metric
    // is areaUnderROC.
    val cv = new CrossValidator()
      .setEstimator(pipeline)
      .setEvaluator(new BinaryClassificationEvaluator)
      .setEstimatorParamMaps(paramGrid)
      .setNumFolds(2)  // Use 3+ in practice

    // Run cross-validation, and choose the best set of parameters.
    val cvModel = cv.fit(training)

    // Prepare test documents, which are unlabeled (id, text) tuples.
    val test = spark.createDataFrame(Seq(
      (4L, "spark i j k"),
      (5L, "l m n"),
      (6L, "mapreduce spark"),
      (7L, "apache hadoop")
    )).toDF("id", "text")

    // Make predictions on test documents. cvModel uses the best model found (lrModel).
    cvModel.transform(test)
      .select("id", "text", "probability", "prediction")
      .collect()
      .foreach { case Row(id: Long, text: String, prob: Vector, prediction: Double) =>
        println(s"($id, $text) --> prob=$prob, prediction=$prediction")
      }
    // $example off$

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