/
Transformer.scala
123 lines (106 loc) · 4.04 KB
/
Transformer.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
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
/*
* 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
import scala.annotation.varargs
import org.apache.spark.Logging
import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
/**
* :: DeveloperApi ::
* Abstract class for transformers that transform one dataset into another.
*/
@DeveloperApi
abstract class Transformer extends PipelineStage {
/**
* Transforms the dataset with optional parameters
* @param dataset input dataset
* @param firstParamPair the first param pair, overwrite embedded params
* @param otherParamPairs other param pairs, overwrite embedded params
* @return transformed dataset
*/
@varargs
def transform(
dataset: DataFrame,
firstParamPair: ParamPair[_],
otherParamPairs: ParamPair[_]*): DataFrame = {
val map = new ParamMap()
.put(firstParamPair)
.put(otherParamPairs: _*)
transform(dataset, map)
}
/**
* Transforms the dataset with provided parameter map as additional parameters.
* @param dataset input dataset
* @param paramMap additional parameters, overwrite embedded params
* @return transformed dataset
*/
def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame = {
this.copy(paramMap).transform(dataset)
}
/**
* Transforms the input dataset.
*/
def transform(dataset: DataFrame): DataFrame
override def copy(extra: ParamMap): Transformer
}
/**
* :: DeveloperApi ::
* Abstract class for transformers that take one input column, apply transformation, and output the
* result as a new column.
*/
@DeveloperApi
abstract class UnaryTransformer[IN, OUT, T <: UnaryTransformer[IN, OUT, T]]
extends Transformer with HasInputCol with HasOutputCol with Logging {
/** @group setParam */
def setInputCol(value: String): T = set(inputCol, value).asInstanceOf[T]
/** @group setParam */
def setOutputCol(value: String): T = set(outputCol, value).asInstanceOf[T]
/**
* Creates the transform function using the given param map. The input param map already takes
* account of the embedded param map. So the param values should be determined solely by the input
* param map.
*/
protected def createTransformFunc: IN => OUT
/**
* Returns the data type of the output column.
*/
protected def outputDataType: DataType
/**
* Validates the input type. Throw an exception if it is invalid.
*/
protected def validateInputType(inputType: DataType): Unit = {}
override def transformSchema(schema: StructType): StructType = {
val inputType = schema($(inputCol)).dataType
validateInputType(inputType)
if (schema.fieldNames.contains($(outputCol))) {
throw new IllegalArgumentException(s"Output column ${$(outputCol)} already exists.")
}
val outputFields = schema.fields :+
StructField($(outputCol), outputDataType, nullable = false)
StructType(outputFields)
}
override def transform(dataset: DataFrame): DataFrame = {
transformSchema(dataset.schema, logging = true)
dataset.withColumn($(outputCol),
callUDF(this.createTransformFunc, outputDataType, dataset($(inputCol))))
}
override def copy(extra: ParamMap): T = defaultCopy(extra)
}