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
|
/*
* 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.evaluation
import org.apache.spark.annotation.{Experimental, Since}
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.util.{DefaultParamsReadable, DefaultParamsWritable, Identifiable, SchemaUtils}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.sql.types.DoubleType
/**
* :: Experimental ::
* Evaluator for binary classification, which expects two input columns: rawPrediction and label.
* The rawPrediction column can be of type double (binary 0/1 prediction, or probability of label 1)
* or of type vector (length-2 vector of raw predictions, scores, or label probabilities).
*/
@Since("1.2.0")
@Experimental
class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override val uid: String)
extends Evaluator with HasRawPredictionCol with HasLabelCol with DefaultParamsWritable {
@Since("1.2.0")
def this() = this(Identifiable.randomUID("binEval"))
/**
* param for metric name in evaluation (supports `"areaUnderROC"` (default), `"areaUnderPR"`)
* @group param
*/
@Since("1.2.0")
val metricName: Param[String] = {
val allowedParams = ParamValidators.inArray(Array("areaUnderROC", "areaUnderPR"))
new Param(
this, "metricName", "metric name in evaluation (areaUnderROC|areaUnderPR)", allowedParams)
}
/** @group getParam */
@Since("1.2.0")
def getMetricName: String = $(metricName)
/** @group setParam */
@Since("1.2.0")
def setMetricName(value: String): this.type = set(metricName, value)
/** @group setParam */
@Since("1.5.0")
def setRawPredictionCol(value: String): this.type = set(rawPredictionCol, value)
/**
* @group setParam
* @deprecated use [[setRawPredictionCol()]] instead
*/
@deprecated("use setRawPredictionCol instead", "1.5.0")
@Since("1.2.0")
def setScoreCol(value: String): this.type = set(rawPredictionCol, value)
/** @group setParam */
@Since("1.2.0")
def setLabelCol(value: String): this.type = set(labelCol, value)
setDefault(metricName -> "areaUnderROC")
@Since("1.2.0")
override def evaluate(dataset: DataFrame): Double = {
val schema = dataset.schema
SchemaUtils.checkColumnTypes(schema, $(rawPredictionCol), Seq(DoubleType, new VectorUDT))
SchemaUtils.checkColumnType(schema, $(labelCol), DoubleType)
// TODO: When dataset metadata has been implemented, check rawPredictionCol vector length = 2.
val scoreAndLabels = dataset.select($(rawPredictionCol), $(labelCol)).rdd.map {
case Row(rawPrediction: Vector, label: Double) => (rawPrediction(1), label)
case Row(rawPrediction: Double, label: Double) => (rawPrediction, label)
}
val metrics = new BinaryClassificationMetrics(scoreAndLabels)
val metric = $(metricName) match {
case "areaUnderROC" => metrics.areaUnderROC()
case "areaUnderPR" => metrics.areaUnderPR()
}
metrics.unpersist()
metric
}
@Since("1.5.0")
override def isLargerBetter: Boolean = $(metricName) match {
case "areaUnderROC" => true
case "areaUnderPR" => true
}
@Since("1.4.1")
override def copy(extra: ParamMap): BinaryClassificationEvaluator = defaultCopy(extra)
}
@Since("1.6.0")
object BinaryClassificationEvaluator extends DefaultParamsReadable[BinaryClassificationEvaluator] {
@Since("1.6.0")
override def load(path: String): BinaryClassificationEvaluator = super.load(path)
}
|