-
Notifications
You must be signed in to change notification settings - Fork 47
/
megam.html
323 lines (243 loc) · 23.6 KB
/
megam.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
321
322
323
<!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.megam</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.megam</h1><div class="highlight"><pre>
<span></span><span class="c1"># Natural Language Toolkit: Interface to Megam Classifier</span>
<span class="c1">#</span>
<span class="c1"># Copyright (C) 2001-2021 NLTK Project</span>
<span class="c1"># Author: Edward Loper <edloper@gmail.com></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">A set of functions used to interface with the external megam_ maxent</span>
<span class="sd">optimization package. Before megam can be used, you should tell NLTK where it</span>
<span class="sd">can find the megam binary, using the ``config_megam()`` function. Typical</span>
<span class="sd">usage:</span>
<span class="sd"> >>> from nltk.classify import megam</span>
<span class="sd"> >>> megam.config_megam() # pass path to megam if not found in PATH # doctest: +SKIP</span>
<span class="sd"> [Found megam: ...]</span>
<span class="sd">Use with MaxentClassifier. Example below, see MaxentClassifier documentation</span>
<span class="sd">for details.</span>
<span class="sd"> nltk.classify.MaxentClassifier.train(corpus, 'megam')</span>
<span class="sd">.. _megam: http://www.umiacs.umd.edu/~hal/megam/index.html</span>
<span class="sd">"""</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">from</span> <span class="nn">nltk.internals</span> <span class="kn">import</span> <span class="n">find_binary</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">numpy</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="n">numpy</span> <span class="o">=</span> <span class="kc">None</span>
<span class="c1">######################################################################</span>
<span class="c1"># { Configuration</span>
<span class="c1">######################################################################</span>
<span class="n">_megam_bin</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="config_megam"><a class="viewcode-back" href="../../../api/nltk.classify.megam.html#nltk.classify.megam.config_megam">[docs]</a><span class="k">def</span> <span class="nf">config_megam</span><span class="p">(</span><span class="nb">bin</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Configure NLTK's interface to the ``megam`` maxent optimization</span>
<span class="sd"> package.</span>
<span class="sd"> :param bin: The full path to the ``megam`` binary. If not specified,</span>
<span class="sd"> then nltk will search the system for a ``megam`` binary; and if</span>
<span class="sd"> one is not found, it will raise a ``LookupError`` exception.</span>
<span class="sd"> :type bin: str</span>
<span class="sd"> """</span>
<span class="k">global</span> <span class="n">_megam_bin</span>
<span class="n">_megam_bin</span> <span class="o">=</span> <span class="n">find_binary</span><span class="p">(</span>
<span class="s2">"megam"</span><span class="p">,</span>
<span class="nb">bin</span><span class="p">,</span>
<span class="n">env_vars</span><span class="o">=</span><span class="p">[</span><span class="s2">"MEGAM"</span><span class="p">],</span>
<span class="n">binary_names</span><span class="o">=</span><span class="p">[</span><span class="s2">"megam.opt"</span><span class="p">,</span> <span class="s2">"megam"</span><span class="p">,</span> <span class="s2">"megam_686"</span><span class="p">,</span> <span class="s2">"megam_i686.opt"</span><span class="p">],</span>
<span class="n">url</span><span class="o">=</span><span class="s2">"http://www.umiacs.umd.edu/~hal/megam/index.html"</span><span class="p">,</span>
<span class="p">)</span></div>
<span class="c1">######################################################################</span>
<span class="c1"># { Megam Interface Functions</span>
<span class="c1">######################################################################</span>
<div class="viewcode-block" id="write_megam_file"><a class="viewcode-back" href="../../../api/nltk.classify.megam.html#nltk.classify.megam.write_megam_file">[docs]</a><span class="k">def</span> <span class="nf">write_megam_file</span><span class="p">(</span><span class="n">train_toks</span><span class="p">,</span> <span class="n">encoding</span><span class="p">,</span> <span class="n">stream</span><span class="p">,</span> <span class="n">bernoulli</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">explicit</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generate an input file for ``megam`` based on the given corpus of</span>
<span class="sd"> classified tokens.</span>
<span class="sd"> :type train_toks: list(tuple(dict, str))</span>
<span class="sd"> :param train_toks: Training data, represented as a list of</span>
<span class="sd"> pairs, the first member of which is a feature dictionary,</span>
<span class="sd"> and the second of which is a classification label.</span>
<span class="sd"> :type encoding: MaxentFeatureEncodingI</span>
<span class="sd"> :param encoding: A feature encoding, used to convert featuresets</span>
<span class="sd"> into feature vectors. May optionally implement a cost() method</span>
<span class="sd"> in order to assign different costs to different class predictions.</span>
<span class="sd"> :type stream: stream</span>
<span class="sd"> :param stream: The stream to which the megam input file should be</span>
<span class="sd"> written.</span>
<span class="sd"> :param bernoulli: If true, then use the 'bernoulli' format. I.e.,</span>
<span class="sd"> all joint features have binary values, and are listed iff they</span>
<span class="sd"> are true. Otherwise, list feature values explicitly. If</span>
<span class="sd"> ``bernoulli=False``, then you must call ``megam`` with the</span>
<span class="sd"> ``-fvals`` option.</span>
<span class="sd"> :param explicit: If true, then use the 'explicit' format. I.e.,</span>
<span class="sd"> list the features that would fire for any of the possible</span>
<span class="sd"> labels, for each token. If ``explicit=True``, then you must</span>
<span class="sd"> call ``megam`` with the ``-explicit`` option.</span>
<span class="sd"> """</span>
<span class="c1"># Look up the set of labels.</span>
<span class="n">labels</span> <span class="o">=</span> <span class="n">encoding</span><span class="o">.</span><span class="n">labels</span><span class="p">()</span>
<span class="n">labelnum</span> <span class="o">=</span> <span class="p">{</span><span class="n">label</span><span class="p">:</span> <span class="n">i</span> <span class="k">for</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">labels</span><span class="p">)}</span>
<span class="c1"># Write the file, which contains one line per instance.</span>
<span class="k">for</span> <span class="n">featureset</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">train_toks</span><span class="p">:</span>
<span class="c1"># First, the instance number (or, in the weighted multiclass case, the cost of each label).</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">encoding</span><span class="p">,</span> <span class="s2">"cost"</span><span class="p">):</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span>
<span class="s2">":"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">encoding</span><span class="o">.</span><span class="n">cost</span><span class="p">(</span><span class="n">featureset</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">l</span><span class="p">))</span> <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="n">labels</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">labelnum</span><span class="p">[</span><span class="n">label</span><span class="p">])</span>
<span class="c1"># For implicit file formats, just list the features that fire</span>
<span class="c1"># for this instance's actual label.</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">explicit</span><span class="p">:</span>
<span class="n">_write_megam_features</span><span class="p">(</span><span class="n">encoding</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">featureset</span><span class="p">,</span> <span class="n">label</span><span class="p">),</span> <span class="n">stream</span><span class="p">,</span> <span class="n">bernoulli</span><span class="p">)</span>
<span class="c1"># For explicit formats, list the features that would fire for</span>
<span class="c1"># any of the possible labels.</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="n">labels</span><span class="p">:</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">" #"</span><span class="p">)</span>
<span class="n">_write_megam_features</span><span class="p">(</span><span class="n">encoding</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">featureset</span><span class="p">,</span> <span class="n">l</span><span class="p">),</span> <span class="n">stream</span><span class="p">,</span> <span class="n">bernoulli</span><span class="p">)</span>
<span class="c1"># End of the instance.</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span></div>
<div class="viewcode-block" id="parse_megam_weights"><a class="viewcode-back" href="../../../api/nltk.classify.megam.html#nltk.classify.megam.parse_megam_weights">[docs]</a><span class="k">def</span> <span class="nf">parse_megam_weights</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">features_count</span><span class="p">,</span> <span class="n">explicit</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Given the stdout output generated by ``megam`` when training a</span>
<span class="sd"> model, return a ``numpy`` array containing the corresponding weight</span>
<span class="sd"> vector. This function does not currently handle bias features.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">numpy</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"This function requires that numpy be installed"</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">explicit</span><span class="p">,</span> <span class="s2">"non-explicit not supported yet"</span>
<span class="n">lines</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">features_count</span><span class="p">,</span> <span class="s2">"d"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">lines</span><span class="p">:</span>
<span class="k">if</span> <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">():</span>
<span class="n">fid</span><span class="p">,</span> <span class="n">weight</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
<span class="n">weights</span><span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">fid</span><span class="p">)]</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">weight</span><span class="p">)</span>
<span class="k">return</span> <span class="n">weights</span></div>
<span class="k">def</span> <span class="nf">_write_megam_features</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">stream</span><span class="p">,</span> <span class="n">bernoulli</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">vector</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"MEGAM classifier requires the use of an "</span> <span class="s2">"always-on feature."</span>
<span class="p">)</span>
<span class="k">for</span> <span class="p">(</span><span class="n">fid</span><span class="p">,</span> <span class="n">fval</span><span class="p">)</span> <span class="ow">in</span> <span class="n">vector</span><span class="p">:</span>
<span class="k">if</span> <span class="n">bernoulli</span><span class="p">:</span>
<span class="k">if</span> <span class="n">fval</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">" </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">fid</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">fval</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"If bernoulli=True, then all"</span> <span class="s2">"features must be binary."</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">f</span><span class="s2">" </span><span class="si">{</span><span class="n">fid</span><span class="si">}</span><span class="s2"> </span><span class="si">{</span><span class="n">fval</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<div class="viewcode-block" id="call_megam"><a class="viewcode-back" href="../../../api/nltk.classify.megam.html#nltk.classify.megam.call_megam">[docs]</a><span class="k">def</span> <span class="nf">call_megam</span><span class="p">(</span><span class="n">args</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Call the ``megam`` binary with the given arguments.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">args</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"args should be a list of strings"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">_megam_bin</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">config_megam</span><span class="p">()</span>
<span class="c1"># Call megam via a subprocess</span>
<span class="n">cmd</span> <span class="o">=</span> <span class="p">[</span><span class="n">_megam_bin</span><span class="p">]</span> <span class="o">+</span> <span class="n">args</span>
<span class="n">p</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">)</span>
<span class="p">(</span><span class="n">stdout</span><span class="p">,</span> <span class="n">stderr</span><span class="p">)</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">communicate</span><span class="p">()</span>
<span class="c1"># Check the return code.</span>
<span class="k">if</span> <span class="n">p</span><span class="o">.</span><span class="n">returncode</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="n">stderr</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">OSError</span><span class="p">(</span><span class="s2">"megam command failed!"</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">stdout</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">return</span> <span class="n">stdout</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">stdout</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">)</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>