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
|
/*
* 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.regression
import org.apache.spark.annotation.AlphaComponent
import org.apache.spark.ml.param.{Params, ParamMap, HasMaxIter, HasRegParam}
import org.apache.spark.mllib.linalg.{BLAS, Vector}
import org.apache.spark.mllib.regression.LinearRegressionWithSGD
import org.apache.spark.sql.DataFrame
import org.apache.spark.storage.StorageLevel
/**
* Params for linear regression.
*/
private[regression] trait LinearRegressionParams extends RegressorParams
with HasRegParam with HasMaxIter
/**
* :: AlphaComponent ::
*
* Linear regression.
*/
@AlphaComponent
class LinearRegression extends Regressor[Vector, LinearRegression, LinearRegressionModel]
with LinearRegressionParams {
setRegParam(0.1)
setMaxIter(100)
def setRegParam(value: Double): this.type = set(regParam, value)
def setMaxIter(value: Int): this.type = set(maxIter, value)
override protected def train(dataset: DataFrame, paramMap: ParamMap): LinearRegressionModel = {
// Extract columns from data. If dataset is persisted, do not persist oldDataset.
val oldDataset = extractLabeledPoints(dataset, paramMap)
val handlePersistence = dataset.rdd.getStorageLevel == StorageLevel.NONE
if (handlePersistence) {
oldDataset.persist(StorageLevel.MEMORY_AND_DISK)
}
// Train model
val lr = new LinearRegressionWithSGD()
lr.optimizer
.setRegParam(paramMap(regParam))
.setNumIterations(paramMap(maxIter))
val model = lr.run(oldDataset)
val lrm = new LinearRegressionModel(this, paramMap, model.weights, model.intercept)
if (handlePersistence) {
oldDataset.unpersist()
}
lrm
}
}
/**
* :: AlphaComponent ::
*
* Model produced by [[LinearRegression]].
*/
@AlphaComponent
class LinearRegressionModel private[ml] (
override val parent: LinearRegression,
override val fittingParamMap: ParamMap,
val weights: Vector,
val intercept: Double)
extends RegressionModel[Vector, LinearRegressionModel]
with LinearRegressionParams {
override protected def predict(features: Vector): Double = {
BLAS.dot(features, weights) + intercept
}
override protected def copy(): LinearRegressionModel = {
val m = new LinearRegressionModel(parent, fittingParamMap, weights, intercept)
Params.inheritValues(this.paramMap, this, m)
m
}
}
|