aboutsummaryrefslogtreecommitdiff
path: root/mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala
blob: 2ca386e4229caa0f5065bb4e43906575cbd1098e (plain) (blame)
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
/*
 * 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.clustering

import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.util.DefaultReadWriteTest
import org.apache.spark.mllib.clustering.{KMeans => MLlibKMeans}
import org.apache.spark.mllib.linalg.{Vector, Vectors}
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.sql.{DataFrame, Dataset, SQLContext}

private[clustering] case class TestRow(features: Vector)

class KMeansSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {

  final val k = 5
  @transient var dataset: Dataset[_] = _

  override def beforeAll(): Unit = {
    super.beforeAll()

    dataset = KMeansSuite.generateKMeansData(sqlContext, 50, 3, k)
  }

  test("default parameters") {
    val kmeans = new KMeans()

    assert(kmeans.getK === 2)
    assert(kmeans.getFeaturesCol === "features")
    assert(kmeans.getPredictionCol === "prediction")
    assert(kmeans.getMaxIter === 20)
    assert(kmeans.getInitMode === MLlibKMeans.K_MEANS_PARALLEL)
    assert(kmeans.getInitSteps === 5)
    assert(kmeans.getTol === 1e-4)
  }

  test("set parameters") {
    val kmeans = new KMeans()
      .setK(9)
      .setFeaturesCol("test_feature")
      .setPredictionCol("test_prediction")
      .setMaxIter(33)
      .setInitMode(MLlibKMeans.RANDOM)
      .setInitSteps(3)
      .setSeed(123)
      .setTol(1e-3)

    assert(kmeans.getK === 9)
    assert(kmeans.getFeaturesCol === "test_feature")
    assert(kmeans.getPredictionCol === "test_prediction")
    assert(kmeans.getMaxIter === 33)
    assert(kmeans.getInitMode === MLlibKMeans.RANDOM)
    assert(kmeans.getInitSteps === 3)
    assert(kmeans.getSeed === 123)
    assert(kmeans.getTol === 1e-3)
  }

  test("parameters validation") {
    intercept[IllegalArgumentException] {
      new KMeans().setK(1)
    }
    intercept[IllegalArgumentException] {
      new KMeans().setInitMode("no_such_a_mode")
    }
    intercept[IllegalArgumentException] {
      new KMeans().setInitSteps(0)
    }
  }

  test("fit, transform, and summary") {
    val predictionColName = "kmeans_prediction"
    val kmeans = new KMeans().setK(k).setPredictionCol(predictionColName).setSeed(1)
    val model = kmeans.fit(dataset)
    assert(model.clusterCenters.length === k)

    val transformed = model.transform(dataset)
    val expectedColumns = Array("features", predictionColName)
    expectedColumns.foreach { column =>
      assert(transformed.columns.contains(column))
    }
    val clusters =
      transformed.select(predictionColName).rdd.map(_.getInt(0)).distinct().collect().toSet
    assert(clusters.size === k)
    assert(clusters === Set(0, 1, 2, 3, 4))
    assert(model.computeCost(dataset) < 0.1)
    assert(model.hasParent)

    // Check validity of model summary
    val numRows = dataset.count()
    assert(model.hasSummary)
    val summary: KMeansSummary = model.summary
    assert(summary.predictionCol === predictionColName)
    assert(summary.featuresCol === "features")
    assert(summary.predictions.count() === numRows)
    for (c <- Array(predictionColName, "features")) {
      assert(summary.predictions.columns.contains(c))
    }
    assert(summary.cluster.columns === Array(predictionColName))
    val clusterSizes = summary.clusterSizes
    assert(clusterSizes.length === k)
    assert(clusterSizes.sum === numRows)
    assert(clusterSizes.forall(_ >= 0))
  }

  test("read/write") {
    def checkModelData(model: KMeansModel, model2: KMeansModel): Unit = {
      assert(model.clusterCenters === model2.clusterCenters)
    }
    val kmeans = new KMeans()
    testEstimatorAndModelReadWrite(kmeans, dataset, KMeansSuite.allParamSettings, checkModelData)
  }
}

object KMeansSuite {
  def generateKMeansData(sql: SQLContext, rows: Int, dim: Int, k: Int): DataFrame = {
    val sc = sql.sparkContext
    val rdd = sc.parallelize(1 to rows).map(i => Vectors.dense(Array.fill(dim)((i % k).toDouble)))
      .map(v => new TestRow(v))
    sql.createDataFrame(rdd)
  }

  /**
   * Mapping from all Params to valid settings which differ from the defaults.
   * This is useful for tests which need to exercise all Params, such as save/load.
   * This excludes input columns to simplify some tests.
   */
  val allParamSettings: Map[String, Any] = Map(
    "predictionCol" -> "myPrediction",
    "k" -> 3,
    "maxIter" -> 2,
    "tol" -> 0.01
  )
}