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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
|
/*
* 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.feature
import org.apache.hadoop.fs.Path
import org.apache.spark.annotation.{Experimental, Since}
import org.apache.spark.ml._
import org.apache.spark.ml.linalg.{Vector, VectorUDT}
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.util._
import org.apache.spark.mllib.feature
import org.apache.spark.mllib.linalg.{Vector => OldVector, Vectors => OldVectors}
import org.apache.spark.mllib.linalg.VectorImplicits._
import org.apache.spark.rdd.RDD
import org.apache.spark.sql._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{StructField, StructType}
/**
* Params for [[StandardScaler]] and [[StandardScalerModel]].
*/
private[feature] trait StandardScalerParams extends Params with HasInputCol with HasOutputCol {
/**
* Whether to center the data with mean before scaling.
* It will build a dense output, so this does not work on sparse input
* and will raise an exception.
* Default: false
* @group param
*/
val withMean: BooleanParam = new BooleanParam(this, "withMean",
"Whether to center data with mean")
/** @group getParam */
def getWithMean: Boolean = $(withMean)
/**
* Whether to scale the data to unit standard deviation.
* Default: true
* @group param
*/
val withStd: BooleanParam = new BooleanParam(this, "withStd",
"Whether to scale the data to unit standard deviation")
/** @group getParam */
def getWithStd: Boolean = $(withStd)
/** Validates and transforms the input schema. */
protected def validateAndTransformSchema(schema: StructType): StructType = {
SchemaUtils.checkColumnType(schema, $(inputCol), new VectorUDT)
require(!schema.fieldNames.contains($(outputCol)),
s"Output column ${$(outputCol)} already exists.")
val outputFields = schema.fields :+ StructField($(outputCol), new VectorUDT, false)
StructType(outputFields)
}
setDefault(withMean -> false, withStd -> true)
}
/**
* :: Experimental ::
* Standardizes features by removing the mean and scaling to unit variance using column summary
* statistics on the samples in the training set.
*
* The "unit std" is computed using the
* [[https://en.wikipedia.org/wiki/Standard_deviation#Corrected_sample_standard_deviation
* corrected sample standard deviation]],
* which is computed as the square root of the unbiased sample variance.
*/
@Experimental
@Since("1.2.0")
class StandardScaler @Since("1.4.0") (
@Since("1.4.0") override val uid: String)
extends Estimator[StandardScalerModel] with StandardScalerParams with DefaultParamsWritable {
@Since("1.2.0")
def this() = this(Identifiable.randomUID("stdScal"))
/** @group setParam */
@Since("1.2.0")
def setInputCol(value: String): this.type = set(inputCol, value)
/** @group setParam */
@Since("1.2.0")
def setOutputCol(value: String): this.type = set(outputCol, value)
/** @group setParam */
@Since("1.4.0")
def setWithMean(value: Boolean): this.type = set(withMean, value)
/** @group setParam */
@Since("1.4.0")
def setWithStd(value: Boolean): this.type = set(withStd, value)
@Since("2.0.0")
override def fit(dataset: Dataset[_]): StandardScalerModel = {
transformSchema(dataset.schema, logging = true)
val input: RDD[OldVector] = dataset.select($(inputCol)).rdd.map {
case Row(v: Vector) => OldVectors.fromML(v)
}
val scaler = new feature.StandardScaler(withMean = $(withMean), withStd = $(withStd))
val scalerModel = scaler.fit(input)
copyValues(new StandardScalerModel(uid, scalerModel.std, scalerModel.mean).setParent(this))
}
@Since("1.4.0")
override def transformSchema(schema: StructType): StructType = {
validateAndTransformSchema(schema)
}
@Since("1.4.1")
override def copy(extra: ParamMap): StandardScaler = defaultCopy(extra)
}
@Since("1.6.0")
object StandardScaler extends DefaultParamsReadable[StandardScaler] {
@Since("1.6.0")
override def load(path: String): StandardScaler = super.load(path)
}
/**
* :: Experimental ::
* Model fitted by [[StandardScaler]].
*
* @param std Standard deviation of the StandardScalerModel
* @param mean Mean of the StandardScalerModel
*/
@Experimental
@Since("1.2.0")
class StandardScalerModel private[ml] (
@Since("1.4.0") override val uid: String,
@Since("2.0.0") val std: Vector,
@Since("2.0.0") val mean: Vector)
extends Model[StandardScalerModel] with StandardScalerParams with MLWritable {
import StandardScalerModel._
/** @group setParam */
@Since("1.2.0")
def setInputCol(value: String): this.type = set(inputCol, value)
/** @group setParam */
@Since("1.2.0")
def setOutputCol(value: String): this.type = set(outputCol, value)
@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
transformSchema(dataset.schema, logging = true)
val scaler = new feature.StandardScalerModel(std, mean, $(withStd), $(withMean))
// TODO: Make the transformer natively in ml framework to avoid extra conversion.
val transformer: Vector => Vector = v => scaler.transform(OldVectors.fromML(v)).asML
val scale = udf(transformer)
dataset.withColumn($(outputCol), scale(col($(inputCol))))
}
@Since("1.4.0")
override def transformSchema(schema: StructType): StructType = {
validateAndTransformSchema(schema)
}
@Since("1.4.1")
override def copy(extra: ParamMap): StandardScalerModel = {
val copied = new StandardScalerModel(uid, std, mean)
copyValues(copied, extra).setParent(parent)
}
@Since("1.6.0")
override def write: MLWriter = new StandardScalerModelWriter(this)
}
@Since("1.6.0")
object StandardScalerModel extends MLReadable[StandardScalerModel] {
private[StandardScalerModel]
class StandardScalerModelWriter(instance: StandardScalerModel) extends MLWriter {
private case class Data(std: Vector, mean: Vector)
override protected def saveImpl(path: String): Unit = {
DefaultParamsWriter.saveMetadata(instance, path, sc)
val data = Data(instance.std, instance.mean)
val dataPath = new Path(path, "data").toString
sparkSession.createDataFrame(Seq(data)).repartition(1).write.parquet(dataPath)
}
}
private class StandardScalerModelReader extends MLReader[StandardScalerModel] {
private val className = classOf[StandardScalerModel].getName
override def load(path: String): StandardScalerModel = {
val metadata = DefaultParamsReader.loadMetadata(path, sc, className)
val dataPath = new Path(path, "data").toString
val Row(std: Vector, mean: Vector) = sparkSession.read.parquet(dataPath)
.select("std", "mean")
.head()
val model = new StandardScalerModel(metadata.uid, std, mean)
DefaultParamsReader.getAndSetParams(model, metadata)
model
}
}
@Since("1.6.0")
override def read: MLReader[StandardScalerModel] = new StandardScalerModelReader
@Since("1.6.0")
override def load(path: String): StandardScalerModel = super.load(path)
}
|
