/
TokenRatioPerDocument.java
87 lines (75 loc) · 3.21 KB
/
TokenRatioPerDocument.java
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
/*******************************************************************************
* Copyright 2018
* Ubiquitous Knowledge Processing (UKP) Lab
* Technische Universität Darmstadt
*
* Licensed 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.dkpro.tc.features.maxnormalization;
import java.util.Arrays;
import java.util.Collection;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.uima.fit.descriptor.TypeCapability;
import org.apache.uima.fit.util.JCasUtil;
import org.apache.uima.jcas.JCas;
import org.apache.uima.resource.ResourceInitializationException;
import org.dkpro.tc.api.exception.TextClassificationException;
import org.dkpro.tc.api.features.Feature;
import org.dkpro.tc.api.features.FeatureType;
import org.dkpro.tc.api.features.meta.MetaCollectorConfiguration;
import org.dkpro.tc.api.type.TextClassificationTarget;
import org.dkpro.tc.features.ngram.meta.base.MaximumNormalizationExtractorBase;
import org.dkpro.tc.features.ngram.meta.maxnormalization.MaxNrOfTokensOverAllDocumentsMC;
import de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Token;
/**
* Ratio of the number of characters in a document with respect to the longest document in the
* training data
*/
@TypeCapability(inputs = { "de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence" })
public class TokenRatioPerDocument
extends MaximumNormalizationExtractorBase
{
public static final String FEATURE_NAME = "TokenRatioPerTarget";
@Override
public Set<Feature> extract(JCas jcas, TextClassificationTarget aTarget)
throws TextClassificationException
{
long maxLen = getMax();
Collection<Token> tokens = JCasUtil.selectCovered(jcas, Token.class, aTarget);
double ratio = getRatio(tokens.size(), maxLen);
return new Feature(FEATURE_NAME, ratio, FeatureType.NUMERIC).asSet();
}
@Override
public List<MetaCollectorConfiguration> getMetaCollectorClasses(
Map<String, Object> parameterSettings)
throws ResourceInitializationException
{
return Arrays.asList(new MetaCollectorConfiguration(MaxNrOfTokensOverAllDocumentsMC.class,
parameterSettings).addStorageMapping(
MaxNrOfTokensOverAllDocumentsMC.PARAM_TARGET_LOCATION,
TokenRatioPerDocument.PARAM_SOURCE_LOCATION,
MaxNrOfTokensOverAllDocumentsMC.LUCENE_DIR));
}
@Override
protected String getFieldName()
{
return MaxNrOfTokensOverAllDocumentsMC.LUCENE_FIELD + featureExtractorName;
}
@Override
protected String getFeaturePrefix()
{
return getClass().getSimpleName();
}
}