1 | // Copyright 2015 Georg-August-Universität Göttingen, Germany
|
---|
2 | //
|
---|
3 | // Licensed under the Apache License, Version 2.0 (the "License");
|
---|
4 | // you may not use this file except in compliance with the License.
|
---|
5 | // You may obtain a copy of the License at
|
---|
6 | //
|
---|
7 | // http://www.apache.org/licenses/LICENSE-2.0
|
---|
8 | //
|
---|
9 | // Unless required by applicable law or agreed to in writing, software
|
---|
10 | // distributed under the License is distributed on an "AS IS" BASIS,
|
---|
11 | // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
---|
12 | // See the License for the specific language governing permissions and
|
---|
13 | // limitations under the License.
|
---|
14 |
|
---|
15 | package de.ugoe.cs.cpdp.dataprocessing;
|
---|
16 |
|
---|
17 | import org.apache.commons.collections4.list.SetUniqueList;
|
---|
18 |
|
---|
19 | import weka.core.Attribute;
|
---|
20 | import weka.core.Instance;
|
---|
21 | import weka.core.Instances;
|
---|
22 | import weka.experiment.Stats;
|
---|
23 |
|
---|
24 | /**
|
---|
25 | * Normalizes each attribute of each data set separately.
|
---|
26 | *
|
---|
27 | * @author Steffen Herbold
|
---|
28 | */
|
---|
29 | public class Normalization implements ISetWiseProcessingStrategy, IProcessesingStrategy {
|
---|
30 |
|
---|
31 | /**
|
---|
32 | * @see de.ugoe.cs.cpdp.dataprocessing.SetWiseProcessingStrategy#apply(weka.core.Instances,
|
---|
33 | * org.apache.commons.collections4.list.SetUniqueList)
|
---|
34 | */
|
---|
35 | @Override
|
---|
36 | public void apply(Instances testdata, SetUniqueList<Instances> traindataSet) {
|
---|
37 | final Attribute classAtt = testdata.classAttribute();
|
---|
38 |
|
---|
39 | for (int i = 0; i < testdata.numAttributes(); i++) {
|
---|
40 | if (!testdata.attribute(i).equals(classAtt)) {
|
---|
41 | Stats teststats = testdata.attributeStats(i).numericStats;
|
---|
42 |
|
---|
43 | double minVal = teststats.min;
|
---|
44 | double maxVal = teststats.max;
|
---|
45 |
|
---|
46 | for (Instances traindata : traindataSet) {
|
---|
47 | Stats trainstats = traindata.attributeStats(i).numericStats;
|
---|
48 | if (minVal > trainstats.min) {
|
---|
49 | minVal = trainstats.min;
|
---|
50 | }
|
---|
51 | if (maxVal < trainstats.max) {
|
---|
52 | maxVal = trainstats.max;
|
---|
53 | }
|
---|
54 | }
|
---|
55 |
|
---|
56 | for (int j = 0; j < testdata.numInstances(); j++) {
|
---|
57 | Instance inst = testdata.instance(j);
|
---|
58 | double newValue = (inst.value(i) - minVal) / (maxVal - minVal);
|
---|
59 | inst.setValue(i, newValue);
|
---|
60 | }
|
---|
61 |
|
---|
62 | for (Instances traindata : traindataSet) {
|
---|
63 | for (int j = 0; j < traindata.numInstances(); j++) {
|
---|
64 | Instance inst = traindata.instance(j);
|
---|
65 | double newValue = (inst.value(i) - minVal) / (maxVal - minVal);
|
---|
66 | inst.setValue(i, newValue);
|
---|
67 | }
|
---|
68 | }
|
---|
69 | }
|
---|
70 | }
|
---|
71 |
|
---|
72 | }
|
---|
73 |
|
---|
74 | /**
|
---|
75 | * @see de.ugoe.cs.cpdp.dataprocessing.ProcessesingStrategy#apply(weka.core.Instances,
|
---|
76 | * weka.core.Instances)
|
---|
77 | */
|
---|
78 | @Override
|
---|
79 | public void apply(Instances testdata, Instances traindata) {
|
---|
80 | final Attribute classAtt = testdata.classAttribute();
|
---|
81 |
|
---|
82 | for (int i = 0; i < testdata.numAttributes(); i++) {
|
---|
83 | if (!testdata.attribute(i).equals(classAtt)) {
|
---|
84 | Stats teststats = testdata.attributeStats(i).numericStats;
|
---|
85 |
|
---|
86 | double minVal = teststats.min;
|
---|
87 | double maxVal = teststats.max;
|
---|
88 |
|
---|
89 | Stats trainstats = traindata.attributeStats(i).numericStats;
|
---|
90 | if (minVal > trainstats.min) {
|
---|
91 | minVal = trainstats.min;
|
---|
92 | }
|
---|
93 | if (maxVal < trainstats.max) {
|
---|
94 | maxVal = trainstats.max;
|
---|
95 | }
|
---|
96 |
|
---|
97 | for (int j = 0; j < testdata.numInstances(); j++) {
|
---|
98 | Instance inst = testdata.instance(j);
|
---|
99 | double newValue = (inst.value(i) - minVal) / (maxVal - minVal);
|
---|
100 | inst.setValue(i, newValue);
|
---|
101 | }
|
---|
102 |
|
---|
103 | for (int j = 0; j < traindata.numInstances(); j++) {
|
---|
104 | Instance inst = traindata.instance(j);
|
---|
105 | double newValue = (inst.value(i) - minVal) / (maxVal - minVal);
|
---|
106 | inst.setValue(i, newValue);
|
---|
107 | }
|
---|
108 | }
|
---|
109 | }
|
---|
110 | }
|
---|
111 |
|
---|
112 | /**
|
---|
113 | * Does not have parameters. String is ignored.
|
---|
114 | *
|
---|
115 | * @param parameters
|
---|
116 | * ignored
|
---|
117 | */
|
---|
118 | @Override
|
---|
119 | public void setParameter(String parameters) {
|
---|
120 | // no parameters
|
---|
121 | }
|
---|
122 | }
|
---|