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
|
/*
* 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.apache.spark.SparkFunSuite
import org.apache.spark.ml.{Estimator, Model}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.{BinaryClassificationEvaluator, Evaluator, RegressionEvaluator}
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.param.shared.HasInputCol
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.mllib.classification.LogisticRegressionSuite.generateLogisticInput
import org.apache.spark.mllib.util.{LinearDataGenerator, MLlibTestSparkContext}
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.types.StructType
class TrainValidationSplitSuite extends SparkFunSuite with MLlibTestSparkContext {
test("train validation with logistic regression") {
val dataset = sqlContext.createDataFrame(
sc.parallelize(generateLogisticInput(1.0, 1.0, 100, 42), 2))
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 TrainValidationSplit()
.setEstimator(lr)
.setEstimatorParamMaps(lrParamMaps)
.setEvaluator(eval)
.setTrainRatio(0.5)
val cvModel = cv.fit(dataset)
val parent = cvModel.bestModel.parent.asInstanceOf[LogisticRegression]
assert(cv.getTrainRatio === 0.5)
assert(parent.getRegParam === 0.001)
assert(parent.getMaxIter === 10)
assert(cvModel.validationMetrics.length === lrParamMaps.length)
}
test("train validation with linear regression") {
val dataset = sqlContext.createDataFrame(
sc.parallelize(LinearDataGenerator.generateLinearInput(
6.3, Array(4.7, 7.2), Array(0.9, -1.3), Array(0.7, 1.2), 100, 42, 0.1), 2))
val trainer = new LinearRegression().setSolver("l-bfgs")
val lrParamMaps = new ParamGridBuilder()
.addGrid(trainer.regParam, Array(1000.0, 0.001))
.addGrid(trainer.maxIter, Array(0, 10))
.build()
val eval = new RegressionEvaluator()
val cv = new TrainValidationSplit()
.setEstimator(trainer)
.setEstimatorParamMaps(lrParamMaps)
.setEvaluator(eval)
.setTrainRatio(0.5)
val cvModel = cv.fit(dataset)
val parent = cvModel.bestModel.parent.asInstanceOf[LinearRegression]
assert(parent.getRegParam === 0.001)
assert(parent.getMaxIter === 10)
assert(cvModel.validationMetrics.length === lrParamMaps.length)
eval.setMetricName("r2")
val cvModel2 = cv.fit(dataset)
val parent2 = cvModel2.bestModel.parent.asInstanceOf[LinearRegression]
assert(parent2.getRegParam === 0.001)
assert(parent2.getMaxIter === 10)
assert(cvModel2.validationMetrics.length === lrParamMaps.length)
}
test("transformSchema should check estimatorParamMaps") {
import TrainValidationSplitSuite._
val est = new MyEstimator("est")
val eval = new MyEvaluator
val paramMaps = new ParamGridBuilder()
.addGrid(est.inputCol, Array("input1", "input2"))
.build()
val cv = new TrainValidationSplit()
.setEstimator(est)
.setEstimatorParamMaps(paramMaps)
.setEvaluator(eval)
.setTrainRatio(0.5)
cv.transformSchema(new StructType()) // This should pass.
val invalidParamMaps = paramMaps :+ ParamMap(est.inputCol -> "")
cv.setEstimatorParamMaps(invalidParamMaps)
intercept[IllegalArgumentException] {
cv.transformSchema(new StructType())
}
}
}
object TrainValidationSplitSuite {
abstract class MyModel extends Model[MyModel]
class MyEstimator(override val uid: String) extends Estimator[MyModel] with HasInputCol {
override def fit(dataset: DataFrame): MyModel = {
throw new UnsupportedOperationException
}
override def transformSchema(schema: StructType): StructType = {
require($(inputCol).nonEmpty)
schema
}
override def copy(extra: ParamMap): MyEstimator = defaultCopy(extra)
}
class MyEvaluator extends Evaluator {
override def evaluate(dataset: DataFrame): Double = {
throw new UnsupportedOperationException
}
override def isLargerBetter: Boolean = true
override val uid: String = "eval"
override def copy(extra: ParamMap): MyEvaluator = defaultCopy(extra)
}
}
|
