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
|
package de.lmu.ifi.dbs.elki.datasource.parser;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2012
Ludwig-Maximilians-Universität München
Lehr- und Forschungseinheit für Datenbanksysteme
ELKI Development Team
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
import gnu.trove.iterator.TIntFloatIterator;
import gnu.trove.map.hash.TIntFloatHashMap;
import java.util.BitSet;
import java.util.HashMap;
import java.util.List;
import java.util.regex.Pattern;
import de.lmu.ifi.dbs.elki.data.LabelList;
import de.lmu.ifi.dbs.elki.data.SparseFloatVector;
import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation;
import de.lmu.ifi.dbs.elki.data.type.VectorFieldTypeInformation;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.Flag;
/**
* A parser to load term frequency data, which essentially are sparse vectors
* with text keys.
*
* @author Erich Schubert
*
* @apiviz.has SparseFloatVector
*/
@Title("Term frequency parser")
@Description("Parse a file containing term frequencies. The expected format is 'label term1 <freq> term2 <freq> ...'. Terms must not contain the separator character!")
public class TermFrequencyParser extends NumberVectorLabelParser<SparseFloatVector> {
/**
* Class logger
*/
private static final Logging logger = Logging.getLogger(TermFrequencyParser.class);
/**
* Maximum dimension used
*/
int maxdim;
/**
* Map
*/
HashMap<String, Integer> keymap;
/**
* Normalize
*/
boolean normalize;
/**
* Constructor.
*
* @param normalize Normalize
* @param colSep
* @param quoteChar
* @param labelIndices
*/
public TermFrequencyParser(boolean normalize, Pattern colSep, char quoteChar, BitSet labelIndices) {
super(colSep, quoteChar, labelIndices, SparseFloatVector.STATIC);
this.normalize = normalize;
this.maxdim = 0;
this.keymap = new HashMap<String, Integer>();
}
@Override
protected void parseLineInternal(String line) {
List<String> entries = tokenize(line);
double len = 0;
TIntFloatHashMap values = new TIntFloatHashMap();
LabelList labels = null;
String curterm = null;
for(int i = 0; i < entries.size(); i++) {
if(curterm == null) {
curterm = entries.get(i);
}
else {
try {
float attribute = Float.valueOf(entries.get(i));
Integer curdim = keymap.get(curterm);
if(curdim == null) {
curdim = maxdim + 1;
keymap.put(curterm, curdim);
maxdim += 1;
}
values.put(curdim, attribute);
len += attribute;
curterm = null;
}
catch(NumberFormatException e) {
if(curterm != null) {
if(labels == null) {
labels = new LabelList(1);
}
labels.add(curterm);
}
curterm = entries.get(i);
}
}
}
if(curterm != null) {
if(labels == null) {
labels = new LabelList(1);
}
labels.add(curterm);
}
if(normalize) {
if(Math.abs(len - 1.0) > 1E-10 && len > 1E-10) {
for(TIntFloatIterator iter = values.iterator(); iter.hasNext();) {
iter.advance();
iter.setValue((float) (iter.value() / len));
}
}
}
curvec = new SparseFloatVector(values, maxdim);
curlbl = labels;
}
@Override
protected SimpleTypeInformation<SparseFloatVector> getTypeInformation(int dimensionality) {
if(dimensionality > 0) {
return new VectorFieldTypeInformation<SparseFloatVector>(SparseFloatVector.class, dimensionality, new SparseFloatVector(SparseFloatVector.EMPTYMAP, dimensionality));
}
if(dimensionality == DIMENSIONALITY_VARIABLE) {
return new SimpleTypeInformation<SparseFloatVector>(SparseFloatVector.class);
}
throw new AbortException("No vectors were read from the input file - cannot determine vector data type.");
}
@Override
protected Logging getLogger() {
return logger;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends NumberVectorLabelParser.Parameterizer<SparseFloatVector> {
/**
* Option ID for normalization
*/
public static final OptionID NORMALIZE_FLAG = OptionID.getOrCreateOptionID("tf.normalize", "Normalize vectors to manhattan length 1 (convert term counts to term frequencies)");
/**
* Normalization flag
*/
boolean normalize = false;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
Flag normF = new Flag(NORMALIZE_FLAG);
if(config.grab(normF)) {
normalize = normF.getValue();
}
}
@Override
protected TermFrequencyParser makeInstance() {
return new TermFrequencyParser(normalize, colSep, quoteChar, labelIndices);
}
}
}
|
