-
Notifications
You must be signed in to change notification settings - Fork 47
/
util.html
485 lines (371 loc) · 56.6 KB
/
util.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
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
<!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.util</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.util</h1><div class="highlight"><pre>
<span></span><span class="c1"># Natural Language Toolkit: Classifier Utility Functions</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"># Steven Bird <stevenbird1@gmail.com> (minor additions)</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">Utility functions and classes for classifiers.</span>
<span class="sd">"""</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="c1"># from nltk.util import Deprecated</span>
<span class="kn">import</span> <span class="nn">nltk.classify.util</span> <span class="c1"># for accuracy & log_likelihood</span>
<span class="kn">from</span> <span class="nn">nltk.util</span> <span class="kn">import</span> <span class="n">LazyMap</span>
<span class="c1">######################################################################</span>
<span class="c1"># { Helper Functions</span>
<span class="c1">######################################################################</span>
<span class="c1"># alternative name possibility: 'map_featurefunc()'?</span>
<span class="c1"># alternative name possibility: 'detect_features()'?</span>
<span class="c1"># alternative name possibility: 'map_featuredetect()'?</span>
<span class="c1"># or.. just have users use LazyMap directly?</span>
<div class="viewcode-block" id="apply_features"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.apply_features">[docs]</a><span class="k">def</span> <span class="nf">apply_features</span><span class="p">(</span><span class="n">feature_func</span><span class="p">,</span> <span class="n">toks</span><span class="p">,</span> <span class="n">labeled</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Use the ``LazyMap`` class to construct a lazy list-like</span>
<span class="sd"> object that is analogous to ``map(feature_func, toks)``. In</span>
<span class="sd"> particular, if ``labeled=False``, then the returned list-like</span>
<span class="sd"> object's values are equal to::</span>
<span class="sd"> [feature_func(tok) for tok in toks]</span>
<span class="sd"> If ``labeled=True``, then the returned list-like object's values</span>
<span class="sd"> are equal to::</span>
<span class="sd"> [(feature_func(tok), label) for (tok, label) in toks]</span>
<span class="sd"> The primary purpose of this function is to avoid the memory</span>
<span class="sd"> overhead involved in storing all the featuresets for every token</span>
<span class="sd"> in a corpus. Instead, these featuresets are constructed lazily,</span>
<span class="sd"> as-needed. The reduction in memory overhead can be especially</span>
<span class="sd"> significant when the underlying list of tokens is itself lazy (as</span>
<span class="sd"> is the case with many corpus readers).</span>
<span class="sd"> :param feature_func: The function that will be applied to each</span>
<span class="sd"> token. It should return a featureset -- i.e., a dict</span>
<span class="sd"> mapping feature names to feature values.</span>
<span class="sd"> :param toks: The list of tokens to which ``feature_func`` should be</span>
<span class="sd"> applied. If ``labeled=True``, then the list elements will be</span>
<span class="sd"> passed directly to ``feature_func()``. If ``labeled=False``,</span>
<span class="sd"> then the list elements should be tuples ``(tok,label)``, and</span>
<span class="sd"> ``tok`` will be passed to ``feature_func()``.</span>
<span class="sd"> :param labeled: If true, then ``toks`` contains labeled tokens --</span>
<span class="sd"> i.e., tuples of the form ``(tok, label)``. (Default:</span>
<span class="sd"> auto-detect based on types.)</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">labeled</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">labeled</span> <span class="o">=</span> <span class="n">toks</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">toks</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">(</span><span class="nb">tuple</span><span class="p">,</span> <span class="nb">list</span><span class="p">))</span>
<span class="k">if</span> <span class="n">labeled</span><span class="p">:</span>
<span class="k">def</span> <span class="nf">lazy_func</span><span class="p">(</span><span class="n">labeled_token</span><span class="p">):</span>
<span class="k">return</span> <span class="p">(</span><span class="n">feature_func</span><span class="p">(</span><span class="n">labeled_token</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="n">labeled_token</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="k">return</span> <span class="n">LazyMap</span><span class="p">(</span><span class="n">lazy_func</span><span class="p">,</span> <span class="n">toks</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">LazyMap</span><span class="p">(</span><span class="n">feature_func</span><span class="p">,</span> <span class="n">toks</span><span class="p">)</span></div>
<div class="viewcode-block" id="attested_labels"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.attested_labels">[docs]</a><span class="k">def</span> <span class="nf">attested_labels</span><span class="p">(</span><span class="n">tokens</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> :return: A list of all labels that are attested in the given list</span>
<span class="sd"> of tokens.</span>
<span class="sd"> :rtype: list of (immutable)</span>
<span class="sd"> :param tokens: The list of classified tokens from which to extract</span>
<span class="sd"> labels. A classified token has the form ``(token, label)``.</span>
<span class="sd"> :type tokens: list</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="nb">tuple</span><span class="p">({</span><span class="n">label</span> <span class="k">for</span> <span class="p">(</span><span class="n">tok</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">})</span></div>
<div class="viewcode-block" id="log_likelihood"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.log_likelihood">[docs]</a><span class="k">def</span> <span class="nf">log_likelihood</span><span class="p">(</span><span class="n">classifier</span><span class="p">,</span> <span class="n">gold</span><span class="p">):</span>
<span class="n">results</span> <span class="o">=</span> <span class="n">classifier</span><span class="o">.</span><span class="n">prob_classify_many</span><span class="p">([</span><span class="n">fs</span> <span class="k">for</span> <span class="p">(</span><span class="n">fs</span><span class="p">,</span> <span class="n">l</span><span class="p">)</span> <span class="ow">in</span> <span class="n">gold</span><span class="p">])</span>
<span class="n">ll</span> <span class="o">=</span> <span class="p">[</span><span class="n">pdist</span><span class="o">.</span><span class="n">prob</span><span class="p">(</span><span class="n">l</span><span class="p">)</span> <span class="k">for</span> <span class="p">((</span><span class="n">fs</span><span class="p">,</span> <span class="n">l</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">gold</span><span class="p">,</span> <span class="n">results</span><span class="p">)]</span>
<span class="k">return</span> <span class="n">math</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">ll</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">ll</span><span class="p">))</span></div>
<div class="viewcode-block" id="accuracy"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.accuracy">[docs]</a><span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="n">classifier</span><span class="p">,</span> <span class="n">gold</span><span class="p">):</span>
<span class="n">results</span> <span class="o">=</span> <span class="n">classifier</span><span class="o">.</span><span class="n">classify_many</span><span class="p">([</span><span class="n">fs</span> <span class="k">for</span> <span class="p">(</span><span class="n">fs</span><span class="p">,</span> <span class="n">l</span><span class="p">)</span> <span class="ow">in</span> <span class="n">gold</span><span class="p">])</span>
<span class="n">correct</span> <span class="o">=</span> <span class="p">[</span><span class="n">l</span> <span class="o">==</span> <span class="n">r</span> <span class="k">for</span> <span class="p">((</span><span class="n">fs</span><span class="p">,</span> <span class="n">l</span><span class="p">),</span> <span class="n">r</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">gold</span><span class="p">,</span> <span class="n">results</span><span class="p">)]</span>
<span class="k">if</span> <span class="n">correct</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">correct</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">correct</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">0</span></div>
<div class="viewcode-block" id="CutoffChecker"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.CutoffChecker">[docs]</a><span class="k">class</span> <span class="nc">CutoffChecker</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> A helper class that implements cutoff checks based on number of</span>
<span class="sd"> iterations and log likelihood.</span>
<span class="sd"> Accuracy cutoffs are also implemented, but they're almost never</span>
<span class="sd"> a good idea to use.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="CutoffChecker.__init__"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.CutoffChecker.__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">cutoffs</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cutoffs</span> <span class="o">=</span> <span class="n">cutoffs</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="k">if</span> <span class="s2">"min_ll"</span> <span class="ow">in</span> <span class="n">cutoffs</span><span class="p">:</span>
<span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_ll"</span><span class="p">]</span> <span class="o">=</span> <span class="o">-</span><span class="nb">abs</span><span class="p">(</span><span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_ll"</span><span class="p">])</span>
<span class="k">if</span> <span class="s2">"min_lldelta"</span> <span class="ow">in</span> <span class="n">cutoffs</span><span class="p">:</span>
<span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_lldelta"</span><span class="p">]</span> <span class="o">=</span> <span class="nb">abs</span><span class="p">(</span><span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_lldelta"</span><span class="p">])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ll</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">acc</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">iter</span> <span class="o">=</span> <span class="mi">1</span></div>
<div class="viewcode-block" id="CutoffChecker.check"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.CutoffChecker.check">[docs]</a> <span class="k">def</span> <span class="nf">check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">classifier</span><span class="p">,</span> <span class="n">train_toks</span><span class="p">):</span>
<span class="n">cutoffs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cutoffs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">iter</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">if</span> <span class="s2">"max_iter"</span> <span class="ow">in</span> <span class="n">cutoffs</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">iter</span> <span class="o">>=</span> <span class="n">cutoffs</span><span class="p">[</span><span class="s2">"max_iter"</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span> <span class="c1"># iteration cutoff.</span>
<span class="n">new_ll</span> <span class="o">=</span> <span class="n">nltk</span><span class="o">.</span><span class="n">classify</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">log_likelihood</span><span class="p">(</span><span class="n">classifier</span><span class="p">,</span> <span class="n">train_toks</span><span class="p">)</span>
<span class="k">if</span> <span class="n">math</span><span class="o">.</span><span class="n">isnan</span><span class="p">(</span><span class="n">new_ll</span><span class="p">):</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">if</span> <span class="s2">"min_ll"</span> <span class="ow">in</span> <span class="n">cutoffs</span> <span class="ow">or</span> <span class="s2">"min_lldelta"</span> <span class="ow">in</span> <span class="n">cutoffs</span><span class="p">:</span>
<span class="k">if</span> <span class="s2">"min_ll"</span> <span class="ow">in</span> <span class="n">cutoffs</span> <span class="ow">and</span> <span class="n">new_ll</span> <span class="o">>=</span> <span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_ll"</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span> <span class="c1"># log likelihood cutoff</span>
<span class="k">if</span> <span class="p">(</span>
<span class="s2">"min_lldelta"</span> <span class="ow">in</span> <span class="n">cutoffs</span>
<span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">ll</span>
<span class="ow">and</span> <span class="p">((</span><span class="n">new_ll</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">ll</span><span class="p">)</span> <span class="o"><=</span> <span class="nb">abs</span><span class="p">(</span><span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_lldelta"</span><span class="p">]))</span>
<span class="p">):</span>
<span class="k">return</span> <span class="kc">True</span> <span class="c1"># log likelihood delta cutoff</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ll</span> <span class="o">=</span> <span class="n">new_ll</span>
<span class="k">if</span> <span class="s2">"max_acc"</span> <span class="ow">in</span> <span class="n">cutoffs</span> <span class="ow">or</span> <span class="s2">"min_accdelta"</span> <span class="ow">in</span> <span class="n">cutoffs</span><span class="p">:</span>
<span class="n">new_acc</span> <span class="o">=</span> <span class="n">nltk</span><span class="o">.</span><span class="n">classify</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">log_likelihood</span><span class="p">(</span><span class="n">classifier</span><span class="p">,</span> <span class="n">train_toks</span><span class="p">)</span>
<span class="k">if</span> <span class="s2">"max_acc"</span> <span class="ow">in</span> <span class="n">cutoffs</span> <span class="ow">and</span> <span class="n">new_acc</span> <span class="o">>=</span> <span class="n">cutoffs</span><span class="p">[</span><span class="s2">"max_acc"</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span> <span class="c1"># log likelihood cutoff</span>
<span class="k">if</span> <span class="p">(</span>
<span class="s2">"min_accdelta"</span> <span class="ow">in</span> <span class="n">cutoffs</span>
<span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">acc</span>
<span class="ow">and</span> <span class="p">((</span><span class="n">new_acc</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">acc</span><span class="p">)</span> <span class="o"><=</span> <span class="nb">abs</span><span class="p">(</span><span class="n">cutoffs</span><span class="p">[</span><span class="s2">"min_accdelta"</span><span class="p">]))</span>
<span class="p">):</span>
<span class="k">return</span> <span class="kc">True</span> <span class="c1"># log likelihood delta cutoff</span>
<span class="bp">self</span><span class="o">.</span><span class="n">acc</span> <span class="o">=</span> <span class="n">new_acc</span>
<span class="k">return</span> <span class="kc">False</span> <span class="c1"># no cutoff reached.</span></div></div>
<span class="c1">######################################################################</span>
<span class="c1"># { Demos</span>
<span class="c1">######################################################################</span>
<div class="viewcode-block" id="names_demo_features"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.names_demo_features">[docs]</a><span class="k">def</span> <span class="nf">names_demo_features</span><span class="p">(</span><span class="n">name</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">"startswith"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"endswith"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">for</span> <span class="n">letter</span> <span class="ow">in</span> <span class="s2">"abcdefghijklmnopqrstuvwxyz"</span><span class="p">:</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"count(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">letter</span><span class="p">)</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"has(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">letter</span> <span class="ow">in</span> <span class="n">name</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">return</span> <span class="n">features</span></div>
<div class="viewcode-block" id="binary_names_demo_features"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.binary_names_demo_features">[docs]</a><span class="k">def</span> <span class="nf">binary_names_demo_features</span><span class="p">(</span><span class="n">name</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">"startswith(vowel)"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">in</span> <span class="s2">"aeiouy"</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"endswith(vowel)"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">in</span> <span class="s2">"aeiouy"</span>
<span class="k">for</span> <span class="n">letter</span> <span class="ow">in</span> <span class="s2">"abcdefghijklmnopqrstuvwxyz"</span><span class="p">:</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"count(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">letter</span><span class="p">)</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"has(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">letter</span> <span class="ow">in</span> <span class="n">name</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"startswith(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">letter</span> <span class="o">==</span> <span class="n">name</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="n">features</span><span class="p">[</span><span class="s2">"endswith(</span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="n">letter</span><span class="p">]</span> <span class="o">=</span> <span class="n">letter</span> <span class="o">==</span> <span class="n">name</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">return</span> <span class="n">features</span></div>
<div class="viewcode-block" id="names_demo"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.names_demo">[docs]</a><span class="k">def</span> <span class="nf">names_demo</span><span class="p">(</span><span class="n">trainer</span><span class="p">,</span> <span class="n">features</span><span class="o">=</span><span class="n">names_demo_features</span><span class="p">):</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">from</span> <span class="nn">nltk.corpus</span> <span class="kn">import</span> <span class="n">names</span>
<span class="c1"># Construct a list of classified names, using the names corpus.</span>
<span class="n">namelist</span> <span class="o">=</span> <span class="p">[(</span><span class="n">name</span><span class="p">,</span> <span class="s2">"male"</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">names</span><span class="o">.</span><span class="n">words</span><span class="p">(</span><span class="s2">"male.txt"</span><span class="p">)]</span> <span class="o">+</span> <span class="p">[</span>
<span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="s2">"female"</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">names</span><span class="o">.</span><span class="n">words</span><span class="p">(</span><span class="s2">"female.txt"</span><span class="p">)</span>
<span class="p">]</span>
<span class="c1"># Randomly split the names into a test & train set.</span>
<span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">123456</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">namelist</span><span class="p">)</span>
<span class="n">train</span> <span class="o">=</span> <span class="n">namelist</span><span class="p">[:</span><span class="mi">5000</span><span class="p">]</span>
<span class="n">test</span> <span class="o">=</span> <span class="n">namelist</span><span class="p">[</span><span class="mi">5000</span><span class="p">:</span><span class="mi">5500</span><span class="p">]</span>
<span class="c1"># Train up a classifier.</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Training classifier..."</span><span class="p">)</span>
<span class="n">classifier</span> <span class="o">=</span> <span class="n">trainer</span><span class="p">([(</span><span class="n">features</span><span class="p">(</span><span class="n">n</span><span class="p">),</span> <span class="n">g</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">g</span><span class="p">)</span> <span class="ow">in</span> <span class="n">train</span><span class="p">])</span>
<span class="c1"># Run the classifier on the test data.</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">classifier</span><span class="p">,</span> <span class="p">[(</span><span class="n">features</span><span class="p">(</span><span class="n">n</span><span class="p">),</span> <span class="n">g</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">g</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</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="c1"># For classifiers that can find probabilities, show the log</span>
<span class="c1"># likelihood and some sample probability distributions.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">test_featuresets</span> <span class="o">=</span> <span class="p">[</span><span class="n">features</span><span class="p">(</span><span class="n">n</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">g</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</span><span class="p">]</span>
<span class="n">pdists</span> <span class="o">=</span> <span class="n">classifier</span><span class="o">.</span><span class="n">prob_classify_many</span><span class="p">(</span><span class="n">test_featuresets</span><span class="p">)</span>
<span class="n">ll</span> <span class="o">=</span> <span class="p">[</span><span class="n">pdist</span><span class="o">.</span><span class="n">logprob</span><span class="p">(</span><span class="n">gold</span><span class="p">)</span> <span class="k">for</span> <span class="p">((</span><span class="n">name</span><span class="p">,</span> <span class="n">gold</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">pdists</span><span class="p">)]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Avg. log likelihood: </span><span class="si">%6.4f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">ll</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">test</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="s2">"Unseen Names P(Male) P(Female)</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">*</span> <span class="mi">40</span><span class="p">)</span>
<span class="k">for</span> <span class="p">((</span><span class="n">name</span><span class="p">,</span> <span class="n">gender</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">pdists</span><span class="p">))[:</span><span class="mi">5</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">gender</span> <span class="o">==</span> <span class="s2">"male"</span><span class="p">:</span>
<span class="n">fmt</span> <span class="o">=</span> <span class="s2">" </span><span class="si">%-15s</span><span class="s2"> *</span><span class="si">%6.4f</span><span class="s2"> </span><span class="si">%6.4f</span><span class="s2">"</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">fmt</span> <span class="o">=</span> <span class="s2">" </span><span class="si">%-15s</span><span class="s2"> </span><span class="si">%6.4f</span><span class="s2"> *</span><span class="si">%6.4f</span><span class="s2">"</span>
<span class="nb">print</span><span class="p">(</span><span class="n">fmt</span> <span class="o">%</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">pdist</span><span class="o">.</span><span class="n">prob</span><span class="p">(</span><span class="s2">"male"</span><span class="p">),</span> <span class="n">pdist</span><span class="o">.</span><span class="n">prob</span><span class="p">(</span><span class="s2">"female"</span><span class="p">)))</span>
<span class="k">except</span> <span class="ne">NotImplementedError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="c1"># Return the classifier</span>
<span class="k">return</span> <span class="n">classifier</span></div>
<div class="viewcode-block" id="partial_names_demo"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.partial_names_demo">[docs]</a><span class="k">def</span> <span class="nf">partial_names_demo</span><span class="p">(</span><span class="n">trainer</span><span class="p">,</span> <span class="n">features</span><span class="o">=</span><span class="n">names_demo_features</span><span class="p">):</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">from</span> <span class="nn">nltk.corpus</span> <span class="kn">import</span> <span class="n">names</span>
<span class="n">male_names</span> <span class="o">=</span> <span class="n">names</span><span class="o">.</span><span class="n">words</span><span class="p">(</span><span class="s2">"male.txt"</span><span class="p">)</span>
<span class="n">female_names</span> <span class="o">=</span> <span class="n">names</span><span class="o">.</span><span class="n">words</span><span class="p">(</span><span class="s2">"female.txt"</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">654321</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">male_names</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">female_names</span><span class="p">)</span>
<span class="c1"># Create a list of male names to be used as positive-labeled examples for training</span>
<span class="n">positive</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">male_names</span><span class="p">[:</span><span class="mi">2000</span><span class="p">])</span>
<span class="c1"># Create a list of male and female names to be used as unlabeled examples</span>
<span class="n">unlabeled</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">male_names</span><span class="p">[</span><span class="mi">2000</span><span class="p">:</span><span class="mi">2500</span><span class="p">]</span> <span class="o">+</span> <span class="n">female_names</span><span class="p">[:</span><span class="mi">500</span><span class="p">])</span>
<span class="c1"># Create a test set with correctly-labeled male and female names</span>
<span class="n">test</span> <span class="o">=</span> <span class="p">[(</span><span class="n">name</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">male_names</span><span class="p">[</span><span class="mi">2500</span><span class="p">:</span><span class="mi">2750</span><span class="p">]]</span> <span class="o">+</span> <span class="p">[</span>
<span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">female_names</span><span class="p">[</span><span class="mi">500</span><span class="p">:</span><span class="mi">750</span><span class="p">]</span>
<span class="p">]</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Train up a classifier.</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Training classifier..."</span><span class="p">)</span>
<span class="n">classifier</span> <span class="o">=</span> <span class="n">trainer</span><span class="p">(</span><span class="n">positive</span><span class="p">,</span> <span class="n">unlabeled</span><span class="p">)</span>
<span class="c1"># Run the classifier on the test data.</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">classifier</span><span class="p">,</span> <span class="p">[(</span><span class="n">features</span><span class="p">(</span><span class="n">n</span><span class="p">),</span> <span class="n">m</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">m</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</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="c1"># For classifiers that can find probabilities, show the log</span>
<span class="c1"># likelihood and some sample probability distributions.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">test_featuresets</span> <span class="o">=</span> <span class="p">[</span><span class="n">features</span><span class="p">(</span><span class="n">n</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">m</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</span><span class="p">]</span>
<span class="n">pdists</span> <span class="o">=</span> <span class="n">classifier</span><span class="o">.</span><span class="n">prob_classify_many</span><span class="p">(</span><span class="n">test_featuresets</span><span class="p">)</span>
<span class="n">ll</span> <span class="o">=</span> <span class="p">[</span><span class="n">pdist</span><span class="o">.</span><span class="n">logprob</span><span class="p">(</span><span class="n">gold</span><span class="p">)</span> <span class="k">for</span> <span class="p">((</span><span class="n">name</span><span class="p">,</span> <span class="n">gold</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">pdists</span><span class="p">)]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Avg. log likelihood: </span><span class="si">%6.4f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">ll</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">test</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="s2">"Unseen Names P(Male) P(Female)</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">*</span> <span class="mi">40</span><span class="p">)</span>
<span class="k">for</span> <span class="p">((</span><span class="n">name</span><span class="p">,</span> <span class="n">is_male</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">pdists</span><span class="p">)[:</span><span class="mi">5</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">is_male</span> <span class="o">==</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">fmt</span> <span class="o">=</span> <span class="s2">" </span><span class="si">%-15s</span><span class="s2"> *</span><span class="si">%6.4f</span><span class="s2"> </span><span class="si">%6.4f</span><span class="s2">"</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">fmt</span> <span class="o">=</span> <span class="s2">" </span><span class="si">%-15s</span><span class="s2"> </span><span class="si">%6.4f</span><span class="s2"> *</span><span class="si">%6.4f</span><span class="s2">"</span>
<span class="nb">print</span><span class="p">(</span><span class="n">fmt</span> <span class="o">%</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">pdist</span><span class="o">.</span><span class="n">prob</span><span class="p">(</span><span class="kc">True</span><span class="p">),</span> <span class="n">pdist</span><span class="o">.</span><span class="n">prob</span><span class="p">(</span><span class="kc">False</span><span class="p">)))</span>
<span class="k">except</span> <span class="ne">NotImplementedError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="c1"># Return the classifier</span>
<span class="k">return</span> <span class="n">classifier</span></div>
<span class="n">_inst_cache</span> <span class="o">=</span> <span class="p">{}</span>
<div class="viewcode-block" id="wsd_demo"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.wsd_demo">[docs]</a><span class="k">def</span> <span class="nf">wsd_demo</span><span class="p">(</span><span class="n">trainer</span><span class="p">,</span> <span class="n">word</span><span class="p">,</span> <span class="n">features</span><span class="p">,</span> <span class="n">n</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">from</span> <span class="nn">nltk.corpus</span> <span class="kn">import</span> <span class="n">senseval</span>
<span class="c1"># Get the instances.</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Reading data..."</span><span class="p">)</span>
<span class="k">global</span> <span class="n">_inst_cache</span>
<span class="k">if</span> <span class="n">word</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_inst_cache</span><span class="p">:</span>
<span class="n">_inst_cache</span><span class="p">[</span><span class="n">word</span><span class="p">]</span> <span class="o">=</span> <span class="p">[(</span><span class="n">i</span><span class="p">,</span> <span class="n">i</span><span class="o">.</span><span class="n">senses</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">senseval</span><span class="o">.</span><span class="n">instances</span><span class="p">(</span><span class="n">word</span><span class="p">)]</span>
<span class="n">instances</span> <span class="o">=</span> <span class="n">_inst_cache</span><span class="p">[</span><span class="n">word</span><span class="p">][:]</span>
<span class="k">if</span> <span class="n">n</span> <span class="o">></span> <span class="nb">len</span><span class="p">(</span><span class="n">instances</span><span class="p">):</span>
<span class="n">n</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">instances</span><span class="p">)</span>
<span class="n">senses</span> <span class="o">=</span> <span class="nb">list</span><span class="p">({</span><span class="n">l</span> <span class="k">for</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">l</span><span class="p">)</span> <span class="ow">in</span> <span class="n">instances</span><span class="p">})</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">" Senses: "</span> <span class="o">+</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">senses</span><span class="p">))</span>
<span class="c1"># Randomly split the names into a test & train set.</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Splitting into test & train..."</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">123456</span><span class="p">)</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">instances</span><span class="p">)</span>
<span class="n">train</span> <span class="o">=</span> <span class="n">instances</span><span class="p">[:</span> <span class="nb">int</span><span class="p">(</span><span class="mf">0.8</span> <span class="o">*</span> <span class="n">n</span><span class="p">)]</span>
<span class="n">test</span> <span class="o">=</span> <span class="n">instances</span><span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="mf">0.8</span> <span class="o">*</span> <span class="n">n</span><span class="p">)</span> <span class="p">:</span> <span class="n">n</span><span class="p">]</span>
<span class="c1"># Train up a classifier.</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Training classifier..."</span><span class="p">)</span>
<span class="n">classifier</span> <span class="o">=</span> <span class="n">trainer</span><span class="p">([(</span><span class="n">features</span><span class="p">(</span><span class="n">i</span><span class="p">),</span> <span class="n">l</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">l</span><span class="p">)</span> <span class="ow">in</span> <span class="n">train</span><span class="p">])</span>
<span class="c1"># Run the classifier on the test data.</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">classifier</span><span class="p">,</span> <span class="p">[(</span><span class="n">features</span><span class="p">(</span><span class="n">i</span><span class="p">),</span> <span class="n">l</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">l</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</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="c1"># For classifiers that can find probabilities, show the log</span>
<span class="c1"># likelihood and some sample probability distributions.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">test_featuresets</span> <span class="o">=</span> <span class="p">[</span><span class="n">features</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">n</span><span class="p">)</span> <span class="ow">in</span> <span class="n">test</span><span class="p">]</span>
<span class="n">pdists</span> <span class="o">=</span> <span class="n">classifier</span><span class="o">.</span><span class="n">prob_classify_many</span><span class="p">(</span><span class="n">test_featuresets</span><span class="p">)</span>
<span class="n">ll</span> <span class="o">=</span> <span class="p">[</span><span class="n">pdist</span><span class="o">.</span><span class="n">logprob</span><span class="p">(</span><span class="n">gold</span><span class="p">)</span> <span class="k">for</span> <span class="p">((</span><span class="n">name</span><span class="p">,</span> <span class="n">gold</span><span class="p">),</span> <span class="n">pdist</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">pdists</span><span class="p">)]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Avg. log likelihood: </span><span class="si">%6.4f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">ll</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">test</span><span class="p">)))</span>
<span class="k">except</span> <span class="ne">NotImplementedError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="c1"># Return the classifier</span>
<span class="k">return</span> <span class="n">classifier</span></div>
<div class="viewcode-block" id="check_megam_config"><a class="viewcode-back" href="../../../api/nltk.classify.util.html#nltk.classify.util.check_megam_config">[docs]</a><span class="k">def</span> <span class="nf">check_megam_config</span><span class="p">():</span>
<span class="sd">"""</span>
<span class="sd"> Checks whether the MEGAM binary is configured.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">_megam_bin</span>
<span class="k">except</span> <span class="ne">NameError</span> <span class="k">as</span> <span class="n">e</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">"Please configure your megam binary first, e.g.</span><span class="se">\n</span><span class="s2">"</span>
<span class="s2">">>> nltk.config_megam('/usr/bin/local/megam')"</span>
<span class="p">)</span>
<span class="k">raise</span> <span class="ne">NameError</span><span class="p">(</span><span class="n">err_msg</span><span class="p">)</span> <span class="kn">from</span> <span class="nn">e</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>