-
Notifications
You must be signed in to change notification settings - Fork 47
/
rte_classify.html
320 lines (245 loc) · 29.8 KB
/
rte_classify.html
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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
<!DOCTYPE html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta name="theme-color" content="#2D2D2D" />
<title>NLTK :: nltk.classify.rte_classify</title>
<link rel="stylesheet" href="../../../_static/css/nltk_theme.css"/>
<link rel="stylesheet" href="../../../_static/css/custom.css"/>
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script src="https://email.tl.fortawesome.com/c/eJxNjUEOgyAQAF8jR7Kw6wIHDh7sP1Cw2mgxgmn6-3JsMqc5zEQfE8dkxOY1KKMUOI3ACFKRJpSW2AAp7ontYIaxI6i7XPJVwyeVfCQ550Os3jLrGSNOLgbdAy6s0PBk2TFNjEbsfq31LB0OnX407pJa5v2faRadwSW63mn5KuLyR9j2tgx3zecanl-55R_-jjPs"></script>
</head>
<body>
<div id="nltk-theme-container">
<header>
<div id="logo-container">
<h1>
<a href="../../../index.html">NLTK</a>
</h1>
</div>
<div id="project-container">
<h1>Documentation</h1>
</div>
<a id="menu-toggle" class="fa fa-bars" aria-hidden="true"></a>
<script type="text/javascript">
$("#menu-toggle").click(function() {
$("#menu-toggle").toggleClass("toggled");
$("#side-menu-container").slideToggle(300);
});
</script>
</header>
<div id="content-container">
<div id="side-menu-container">
<div id="search" role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
<div id="side-menu" role="navigation">
<p class="caption" role="heading"><span class="caption-text">NLTK Documentation</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../api/nltk.html">API Reference</a></li>
<li class="toctree-l1"><a class="reference external" href="http://www.nltk.org/howto">Example Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../py-modindex.html">Module Index</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/nltk/nltk/wiki">Wiki</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/nltk/nltk/wiki/FAQ">FAQ</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../install.html">Installing NLTK</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../data.html">Installing NLTK Data</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">More</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../news.html">Release Notes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../contribute.html">Contributing to NLTK</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../team.html">NLTK Team</a></li>
</ul>
</div>
</div>
<div id="main-content-container">
<div id="main-content" role="main">
<h1>Source code for nltk.classify.rte_classify</h1><div class="highlight"><pre>
<span></span><span class="c1"># Natural Language Toolkit: RTE Classifier</span>
<span class="c1">#</span>
<span class="c1"># Copyright (C) 2001-2021 NLTK Project</span>
<span class="c1"># Author: Ewan Klein <ewan@inf.ed.ac.uk></span>
<span class="c1"># URL: <http://nltk.org/></span>
<span class="c1"># For license information, see LICENSE.TXT</span>
<span class="sd">"""</span>
<span class="sd">Simple classifier for RTE corpus.</span>
<span class="sd">It calculates the overlap in words and named entities between text and</span>
<span class="sd">hypothesis, and also whether there are words / named entities in the</span>
<span class="sd">hypothesis which fail to occur in the text, since this is an indicator that</span>
<span class="sd">the hypothesis is more informative than (i.e not entailed by) the text.</span>
<span class="sd">TO DO: better Named Entity classification</span>
<span class="sd">TO DO: add lemmatization</span>
<span class="sd">"""</span>
<span class="kn">from</span> <span class="nn">nltk.classify.maxent</span> <span class="kn">import</span> <span class="n">MaxentClassifier</span>
<span class="kn">from</span> <span class="nn">nltk.classify.util</span> <span class="kn">import</span> <span class="n">accuracy</span><span class="p">,</span> <span class="n">check_megam_config</span>
<span class="kn">from</span> <span class="nn">nltk.tokenize</span> <span class="kn">import</span> <span class="n">RegexpTokenizer</span>
<div class="viewcode-block" id="RTEFeatureExtractor"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.RTEFeatureExtractor">[docs]</a><span class="k">class</span> <span class="nc">RTEFeatureExtractor</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This builds a bag of words for both the text and the hypothesis after</span>
<span class="sd"> throwing away some stopwords, then calculates overlap and difference.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="RTEFeatureExtractor.__init__"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.RTEFeatureExtractor.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rtepair</span><span class="p">,</span> <span class="n">stop</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">use_lemmatize</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> :param rtepair: a ``RTEPair`` from which features should be extracted</span>
<span class="sd"> :param stop: if ``True``, stopwords are thrown away.</span>
<span class="sd"> :type stop: bool</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stop</span> <span class="o">=</span> <span class="n">stop</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stopwords</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">"a"</span><span class="p">,</span>
<span class="s2">"the"</span><span class="p">,</span>
<span class="s2">"it"</span><span class="p">,</span>
<span class="s2">"they"</span><span class="p">,</span>
<span class="s2">"of"</span><span class="p">,</span>
<span class="s2">"in"</span><span class="p">,</span>
<span class="s2">"to"</span><span class="p">,</span>
<span class="s2">"is"</span><span class="p">,</span>
<span class="s2">"have"</span><span class="p">,</span>
<span class="s2">"are"</span><span class="p">,</span>
<span class="s2">"were"</span><span class="p">,</span>
<span class="s2">"and"</span><span class="p">,</span>
<span class="s2">"very"</span><span class="p">,</span>
<span class="s2">"."</span><span class="p">,</span>
<span class="s2">","</span><span class="p">,</span>
<span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">negwords</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"no"</span><span class="p">,</span> <span class="s2">"not"</span><span class="p">,</span> <span class="s2">"never"</span><span class="p">,</span> <span class="s2">"failed"</span><span class="p">,</span> <span class="s2">"rejected"</span><span class="p">,</span> <span class="s2">"denied"</span><span class="p">}</span>
<span class="c1"># Try to tokenize so that abbreviations, monetary amounts, email</span>
<span class="c1"># addresses, URLs are single tokens.</span>
<span class="n">tokenizer</span> <span class="o">=</span> <span class="n">RegexpTokenizer</span><span class="p">(</span><span class="sa">r</span><span class="s2">"[\w.@:/]+|\w+|\$[\d.]+"</span><span class="p">)</span>
<span class="c1"># Get the set of word types for text and hypothesis</span>
<span class="bp">self</span><span class="o">.</span><span class="n">text_tokens</span> <span class="o">=</span> <span class="n">tokenizer</span><span class="o">.</span><span class="n">tokenize</span><span class="p">(</span><span class="n">rtepair</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hyp_tokens</span> <span class="o">=</span> <span class="n">tokenizer</span><span class="o">.</span><span class="n">tokenize</span><span class="p">(</span><span class="n">rtepair</span><span class="o">.</span><span class="n">hyp</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">text_words</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">text_tokens</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hyp_tokens</span><span class="p">)</span>
<span class="k">if</span> <span class="n">use_lemmatize</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">text_words</span> <span class="o">=</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">_lemmatize</span><span class="p">(</span><span class="n">token</span><span class="p">)</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_tokens</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">=</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">_lemmatize</span><span class="p">(</span><span class="n">token</span><span class="p">)</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyp_tokens</span><span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">stop</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">text_words</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_words</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopwords</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopwords</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_overlap</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">&</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_words</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_hyp_extra</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_words</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_txt_extra</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_words</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyp_words</span></div>
<div class="viewcode-block" id="RTEFeatureExtractor.overlap"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.RTEFeatureExtractor.overlap">[docs]</a> <span class="k">def</span> <span class="nf">overlap</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">toktype</span><span class="p">,</span> <span class="n">debug</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Compute the overlap between text and hypothesis.</span>
<span class="sd"> :param toktype: distinguish Named Entities from ordinary words</span>
<span class="sd"> :type toktype: 'ne' or 'word'</span>
<span class="sd"> """</span>
<span class="n">ne_overlap</span> <span class="o">=</span> <span class="p">{</span><span class="n">token</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_overlap</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ne</span><span class="p">(</span><span class="n">token</span><span class="p">)}</span>
<span class="k">if</span> <span class="n">toktype</span> <span class="o">==</span> <span class="s2">"ne"</span><span class="p">:</span>
<span class="k">if</span> <span class="n">debug</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"ne overlap"</span><span class="p">,</span> <span class="n">ne_overlap</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ne_overlap</span>
<span class="k">elif</span> <span class="n">toktype</span> <span class="o">==</span> <span class="s2">"word"</span><span class="p">:</span>
<span class="k">if</span> <span class="n">debug</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"word overlap"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_overlap</span> <span class="o">-</span> <span class="n">ne_overlap</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_overlap</span> <span class="o">-</span> <span class="n">ne_overlap</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Type not recognized:'</span><span class="si">%s</span><span class="s2">'"</span> <span class="o">%</span> <span class="n">toktype</span><span class="p">)</span></div>
<div class="viewcode-block" id="RTEFeatureExtractor.hyp_extra"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.RTEFeatureExtractor.hyp_extra">[docs]</a> <span class="k">def</span> <span class="nf">hyp_extra</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">toktype</span><span class="p">,</span> <span class="n">debug</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Compute the extraneous material in the hypothesis.</span>
<span class="sd"> :param toktype: distinguish Named Entities from ordinary words</span>
<span class="sd"> :type toktype: 'ne' or 'word'</span>
<span class="sd"> """</span>
<span class="n">ne_extra</span> <span class="o">=</span> <span class="p">{</span><span class="n">token</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hyp_extra</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ne</span><span class="p">(</span><span class="n">token</span><span class="p">)}</span>
<span class="k">if</span> <span class="n">toktype</span> <span class="o">==</span> <span class="s2">"ne"</span><span class="p">:</span>
<span class="k">return</span> <span class="n">ne_extra</span>
<span class="k">elif</span> <span class="n">toktype</span> <span class="o">==</span> <span class="s2">"word"</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hyp_extra</span> <span class="o">-</span> <span class="n">ne_extra</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Type not recognized: '</span><span class="si">%s</span><span class="s2">'"</span> <span class="o">%</span> <span class="n">toktype</span><span class="p">)</span></div>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_ne</span><span class="p">(</span><span class="n">token</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This just assumes that words in all caps or titles are</span>
<span class="sd"> named entities.</span>
<span class="sd"> :type token: str</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">token</span><span class="o">.</span><span class="n">istitle</span><span class="p">()</span> <span class="ow">or</span> <span class="n">token</span><span class="o">.</span><span class="n">isupper</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_lemmatize</span><span class="p">(</span><span class="n">word</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Use morphy from WordNet to find the base form of verbs.</span>
<span class="sd"> """</span>
<span class="n">lemma</span> <span class="o">=</span> <span class="n">nltk</span><span class="o">.</span><span class="n">corpus</span><span class="o">.</span><span class="n">wordnet</span><span class="o">.</span><span class="n">morphy</span><span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="n">pos</span><span class="o">=</span><span class="n">nltk</span><span class="o">.</span><span class="n">corpus</span><span class="o">.</span><span class="n">wordnet</span><span class="o">.</span><span class="n">VERB</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lemma</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="n">lemma</span>
<span class="k">return</span> <span class="n">word</span></div>
<div class="viewcode-block" id="rte_features"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.rte_features">[docs]</a><span class="k">def</span> <span class="nf">rte_features</span><span class="p">(</span><span class="n">rtepair</span><span class="p">):</span>
<span class="n">extractor</span> <span class="o">=</span> <span class="n">RTEFeatureExtractor</span><span class="p">(</span><span class="n">rtepair</span><span class="p">)</span>
<span class="n">features</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"alwayson"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"word_overlap"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">overlap</span><span class="p">(</span><span class="s2">"word"</span><span class="p">))</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"word_hyp_extra"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">hyp_extra</span><span class="p">(</span><span class="s2">"word"</span><span class="p">))</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"ne_overlap"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">overlap</span><span class="p">(</span><span class="s2">"ne"</span><span class="p">))</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"ne_hyp_extra"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">hyp_extra</span><span class="p">(</span><span class="s2">"ne"</span><span class="p">))</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"neg_txt"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">negwords</span> <span class="o">&</span> <span class="n">extractor</span><span class="o">.</span><span class="n">text_words</span><span class="p">)</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"neg_hyp"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">extractor</span><span class="o">.</span><span class="n">negwords</span> <span class="o">&</span> <span class="n">extractor</span><span class="o">.</span><span class="n">hyp_words</span><span class="p">)</span>
<span class="k">return</span> <span class="n">features</span></div>
<div class="viewcode-block" id="rte_featurize"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.rte_featurize">[docs]</a><span class="k">def</span> <span class="nf">rte_featurize</span><span class="p">(</span><span class="n">rte_pairs</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[(</span><span class="n">rte_features</span><span class="p">(</span><span class="n">pair</span><span class="p">),</span> <span class="n">pair</span><span class="o">.</span><span class="n">value</span><span class="p">)</span> <span class="k">for</span> <span class="n">pair</span> <span class="ow">in</span> <span class="n">rte_pairs</span><span class="p">]</span></div>
<div class="viewcode-block" id="rte_classifier"><a class="viewcode-back" href="../../../api/nltk.classify.rte_classify.html#nltk.classify.rte_classify.rte_classifier">[docs]</a><span class="k">def</span> <span class="nf">rte_classifier</span><span class="p">(</span><span class="n">algorithm</span><span class="p">,</span> <span class="n">sample_N</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="kn">from</span> <span class="nn">nltk.corpus</span> <span class="kn">import</span> <span class="n">rte</span> <span class="k">as</span> <span class="n">rte_corpus</span>
<span class="n">train_set</span> <span class="o">=</span> <span class="n">rte_corpus</span><span class="o">.</span><span class="n">pairs</span><span class="p">([</span><span class="s2">"rte1_dev.xml"</span><span class="p">,</span> <span class="s2">"rte2_dev.xml"</span><span class="p">,</span> <span class="s2">"rte3_dev.xml"</span><span class="p">])</span>
<span class="n">test_set</span> <span class="o">=</span> <span class="n">rte_corpus</span><span class="o">.</span><span class="n">pairs</span><span class="p">([</span><span class="s2">"rte1_test.xml"</span><span class="p">,</span> <span class="s2">"rte2_test.xml"</span><span class="p">,</span> <span class="s2">"rte3_test.xml"</span><span class="p">])</span>
<span class="k">if</span> <span class="n">sample_N</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">train_set</span> <span class="o">=</span> <span class="n">train_set</span><span class="p">[:</span><span class="n">sample_N</span><span class="p">]</span>
<span class="n">test_set</span> <span class="o">=</span> <span class="n">test_set</span><span class="p">[:</span><span class="n">sample_N</span><span class="p">]</span>
<span class="n">featurized_train_set</span> <span class="o">=</span> <span class="n">rte_featurize</span><span class="p">(</span><span class="n">train_set</span><span class="p">)</span>
<span class="n">featurized_test_set</span> <span class="o">=</span> <span class="n">rte_featurize</span><span class="p">(</span><span class="n">test_set</span><span class="p">)</span>
<span class="c1"># Train the classifier</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Training classifier..."</span><span class="p">)</span>
<span class="k">if</span> <span class="n">algorithm</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"megam"</span><span class="p">]:</span> <span class="c1"># MEGAM based algorithms.</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">MaxentClassifier</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">featurized_train_set</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">algorithm</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"GIS"</span><span class="p">,</span> <span class="s2">"IIS"</span><span class="p">]:</span> <span class="c1"># Use default GIS/IIS MaxEnt algorithm</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">MaxentClassifier</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">featurized_train_set</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">err_msg</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span>
<span class="s2">"RTEClassifier only supports these algorithms:</span><span class="se">\n</span><span class="s2"> "</span>
<span class="s2">"'megam', 'GIS', 'IIS'.</span><span class="se">\n</span><span class="s2">"</span>
<span class="p">)</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="n">err_msg</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Testing classifier..."</span><span class="p">)</span>
<span class="n">acc</span> <span class="o">=</span> <span class="n">accuracy</span><span class="p">(</span><span class="n">clf</span><span class="p">,</span> <span class="n">featurized_test_set</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Accuracy: </span><span class="si">%6.4f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">acc</span><span class="p">)</span>
<span class="k">return</span> <span class="n">clf</span></div>
</pre></div>
</div>
</div>
</div>
<footer>
<div id="footer-info">
<ul id="build-details">
<li class="footer-element">
<a href="https://github.com/nltk/nltk/tree/3.6.5">3.6.5</a>
</li>
<li class="footer-element">
Oct 11, 2021
</li>
</ul>
<div id="copyright">
© 2021, NLTK Project
</div>
<div id="credit">
created with <a href="http://sphinx-doc.org/">Sphinx</a> and <a href="https://github.com/tomaarsen/nltk_theme">NLTK Theme</a>
</div>
</div>
</footer>
</div>
</body>
</html>