mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56

/*
 * 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.ml.tuning

import org.scalatest.FunSuite

import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.mllib.classification.LogisticRegressionSuite.generateLogisticInput
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.sql.{SQLContext, SchemaRDD}

class CrossValidatorSuite extends FunSuite with MLlibTestSparkContext {

  @transient var dataset: SchemaRDD = _

  override def beforeAll(): Unit = {
    super.beforeAll()
    val sqlContext = new SQLContext(sc)
    dataset = sqlContext.createSchemaRDD(
      sc.parallelize(generateLogisticInput(1.0, 1.0, 100, 42), 2))
  }

  test("cross validation with logistic regression") {
    val lr = new LogisticRegression
    val lrParamMaps = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.001, 1000.0))
      .addGrid(lr.maxIter, Array(0, 10))
      .build()
    val eval = new BinaryClassificationEvaluator
    val cv = new CrossValidator()
      .setEstimator(lr)
      .setEstimatorParamMaps(lrParamMaps)
      .setEvaluator(eval)
      .setNumFolds(3)
    val cvModel = cv.fit(dataset)
    val bestParamMap = cvModel.bestModel.fittingParamMap
    assert(bestParamMap(lr.regParam) === 0.001)
    assert(bestParamMap(lr.maxIter) === 10)
  }
}