org.apache.spark.examples.ml.SimpleParamsExample.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.
 */

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

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.mllib.linalg.{Vector, Vectors}
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.sql.{Row, SQLContext}

/**
 * A simple example demonstrating ways to specify parameters for Estimators and Transformers.
 * Run with
 * {{{
 * bin/run-example ml.SimpleParamsExample
 * }}}
 */
object SimpleParamsExample {

  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("SimpleParamsExample")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    import sqlContext.implicits._

    // Prepare training data.
    // We use LabeledPoint, which is a case class.  Spark SQL can convert RDDs of case classes
    // into DataFrames, where it uses the case class metadata to infer the schema.
    val training = sc.parallelize(Seq(
      LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)),
      LabeledPoint(0.0, Vectors.dense(2.0, 1.0, -1.0)),
      LabeledPoint(0.0, Vectors.dense(2.0, 1.3, 1.0)),
      LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5))))

    // Create a LogisticRegression instance.  This instance is an Estimator.
    val lr = new LogisticRegression()
    // Print out the parameters, documentation, and any default values.
    println("LogisticRegression parameters:\n" + lr.explainParams() + "\n")

    // We may set parameters using setter methods.
    lr.setMaxIter(10)
      .setRegParam(0.01)

    // Learn a LogisticRegression model.  This uses the parameters stored in lr.
    val model1 = lr.fit(training.toDF())
    // Since model1 is a Model (i.e., a Transformer produced by an Estimator),
    // we can view the parameters it used during fit().
    // This prints the parameter (name: value) pairs, where names are unique IDs for this
    // LogisticRegression instance.
    println("Model 1 was fit using parameters: " + model1.parent.extractParamMap())

    // We may alternatively specify parameters using a ParamMap,
    // which supports several methods for specifying parameters.
    val paramMap = ParamMap(lr.maxIter -> 20)
    paramMap.put(lr.maxIter, 30) // Specify 1 Param.  This overwrites the original maxIter.
    paramMap.put(lr.regParam -> 0.1, lr.thresholds -> Array(0.45, 0.55)) // Specify multiple Params.

    // One can also combine ParamMaps.
    val paramMap2 = ParamMap(lr.probabilityCol -> "myProbability") // Change output column name
    val paramMapCombined = paramMap ++ paramMap2

    // Now learn a new model using the paramMapCombined parameters.
    // paramMapCombined overrides all parameters set earlier via lr.set* methods.
    val model2 = lr.fit(training.toDF(), paramMapCombined)
    println("Model 2 was fit using parameters: " + model2.parent.extractParamMap())

    // Prepare test data.
    val test = sc.parallelize(Seq(
      LabeledPoint(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
      LabeledPoint(0.0, Vectors.dense(3.0, 2.0, -0.1)),
      LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5))))

    // Make predictions on test data using the Transformer.transform() method.
    // LogisticRegressionModel.transform will only use the 'features' column.
    // Note that model2.transform() outputs a 'myProbability' column instead of the usual
    // 'probability' column since we renamed the lr.probabilityCol parameter previously.
    model2.transform(test.toDF())
      .select("features", "label", "myProbability", "prediction")
      .collect()
      .foreach { case Row(features: Vector, label: Double, prob: Vector, prediction: Double) =>
        println(s"($features, $label) -> prob=$prob, prediction=$prediction")
      }

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