-
Notifications
You must be signed in to change notification settings - Fork 47
/
util.html
782 lines (641 loc) · 78.7 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
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
<!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.chunk.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.chunk.util</h1><div class="highlight"><pre>
<span></span><span class="c1"># Natural Language Toolkit: Chunk format conversions</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="kn">import</span> <span class="nn">re</span>
<span class="kn">from</span> <span class="nn">nltk.metrics</span> <span class="kn">import</span> <span class="n">accuracy</span> <span class="k">as</span> <span class="n">_accuracy</span>
<span class="kn">from</span> <span class="nn">nltk.tag.mapping</span> <span class="kn">import</span> <span class="n">map_tag</span>
<span class="kn">from</span> <span class="nn">nltk.tag.util</span> <span class="kn">import</span> <span class="n">str2tuple</span>
<span class="kn">from</span> <span class="nn">nltk.tree</span> <span class="kn">import</span> <span class="n">Tree</span>
<span class="c1">##//////////////////////////////////////////////////////</span>
<span class="c1">## EVALUATION</span>
<span class="c1">##//////////////////////////////////////////////////////</span>
<div class="viewcode-block" id="accuracy"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.accuracy">[docs]</a><span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="n">chunker</span><span class="p">,</span> <span class="n">gold</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Score the accuracy of the chunker against the gold standard.</span>
<span class="sd"> Strip the chunk information from the gold standard and rechunk it using</span>
<span class="sd"> the chunker, then compute the accuracy score.</span>
<span class="sd"> :type chunker: ChunkParserI</span>
<span class="sd"> :param chunker: The chunker being evaluated.</span>
<span class="sd"> :type gold: tree</span>
<span class="sd"> :param gold: The chunk structures to score the chunker on.</span>
<span class="sd"> :rtype: float</span>
<span class="sd"> """</span>
<span class="n">gold_tags</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">test_tags</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">gold_tree</span> <span class="ow">in</span> <span class="n">gold</span><span class="p">:</span>
<span class="n">test_tree</span> <span class="o">=</span> <span class="n">chunker</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">gold_tree</span><span class="o">.</span><span class="n">flatten</span><span class="p">())</span>
<span class="n">gold_tags</span> <span class="o">+=</span> <span class="n">tree2conlltags</span><span class="p">(</span><span class="n">gold_tree</span><span class="p">)</span>
<span class="n">test_tags</span> <span class="o">+=</span> <span class="n">tree2conlltags</span><span class="p">(</span><span class="n">test_tree</span><span class="p">)</span>
<span class="c1"># print 'GOLD:', gold_tags[:50]</span>
<span class="c1"># print 'TEST:', test_tags[:50]</span>
<span class="k">return</span> <span class="n">_accuracy</span><span class="p">(</span><span class="n">gold_tags</span><span class="p">,</span> <span class="n">test_tags</span><span class="p">)</span></div>
<span class="c1"># Patched for increased performance by Yoav Goldberg <yoavg@cs.bgu.ac.il>, 2006-01-13</span>
<span class="c1"># -- statistics are evaluated only on demand, instead of at every sentence evaluation</span>
<span class="c1">#</span>
<span class="c1"># SB: use nltk.metrics for precision/recall scoring?</span>
<span class="c1">#</span>
<div class="viewcode-block" id="ChunkScore"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore">[docs]</a><span class="k">class</span> <span class="nc">ChunkScore</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> A utility class for scoring chunk parsers. ``ChunkScore`` can</span>
<span class="sd"> evaluate a chunk parser's output, based on a number of statistics</span>
<span class="sd"> (precision, recall, f-measure, misssed chunks, incorrect chunks).</span>
<span class="sd"> It can also combine the scores from the parsing of multiple texts;</span>
<span class="sd"> this makes it significantly easier to evaluate a chunk parser that</span>
<span class="sd"> operates one sentence at a time.</span>
<span class="sd"> Texts are evaluated with the ``score`` method. The results of</span>
<span class="sd"> evaluation can be accessed via a number of accessor methods, such</span>
<span class="sd"> as ``precision`` and ``f_measure``. A typical use of the</span>
<span class="sd"> ``ChunkScore`` class is::</span>
<span class="sd"> >>> chunkscore = ChunkScore() # doctest: +SKIP</span>
<span class="sd"> >>> for correct in correct_sentences: # doctest: +SKIP</span>
<span class="sd"> ... guess = chunkparser.parse(correct.leaves()) # doctest: +SKIP</span>
<span class="sd"> ... chunkscore.score(correct, guess) # doctest: +SKIP</span>
<span class="sd"> >>> print('F Measure:', chunkscore.f_measure()) # doctest: +SKIP</span>
<span class="sd"> F Measure: 0.823</span>
<span class="sd"> :ivar kwargs: Keyword arguments:</span>
<span class="sd"> - max_tp_examples: The maximum number actual examples of true</span>
<span class="sd"> positives to record. This affects the ``correct`` member</span>
<span class="sd"> function: ``correct`` will not return more than this number</span>
<span class="sd"> of true positive examples. This does *not* affect any of</span>
<span class="sd"> the numerical metrics (precision, recall, or f-measure)</span>
<span class="sd"> - max_fp_examples: The maximum number actual examples of false</span>
<span class="sd"> positives to record. This affects the ``incorrect`` member</span>
<span class="sd"> function and the ``guessed`` member function: ``incorrect``</span>
<span class="sd"> will not return more than this number of examples, and</span>
<span class="sd"> ``guessed`` will not return more than this number of true</span>
<span class="sd"> positive examples. This does *not* affect any of the</span>
<span class="sd"> numerical metrics (precision, recall, or f-measure)</span>
<span class="sd"> - max_fn_examples: The maximum number actual examples of false</span>
<span class="sd"> negatives to record. This affects the ``missed`` member</span>
<span class="sd"> function and the ``correct`` member function: ``missed``</span>
<span class="sd"> will not return more than this number of examples, and</span>
<span class="sd"> ``correct`` will not return more than this number of true</span>
<span class="sd"> negative examples. This does *not* affect any of the</span>
<span class="sd"> numerical metrics (precision, recall, or f-measure)</span>
<span class="sd"> - chunk_label: A regular expression indicating which chunks</span>
<span class="sd"> should be compared. Defaults to ``'.*'`` (i.e., all chunks).</span>
<span class="sd"> :type _tp: list(Token)</span>
<span class="sd"> :ivar _tp: List of true positives</span>
<span class="sd"> :type _fp: list(Token)</span>
<span class="sd"> :ivar _fp: List of false positives</span>
<span class="sd"> :type _fn: list(Token)</span>
<span class="sd"> :ivar _fn: List of false negatives</span>
<span class="sd"> :type _tp_num: int</span>
<span class="sd"> :ivar _tp_num: Number of true positives</span>
<span class="sd"> :type _fp_num: int</span>
<span class="sd"> :ivar _fp_num: Number of false positives</span>
<span class="sd"> :type _fn_num: int</span>
<span class="sd"> :ivar _fn_num: Number of false negatives.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ChunkScore.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.__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="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_correct</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">_guessed</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">_tp</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">_fp</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">_fn</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">_max_tp</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"max_tp_examples"</span><span class="p">,</span> <span class="mi">100</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_fp</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"max_fp_examples"</span><span class="p">,</span> <span class="mi">100</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_fn</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"max_fn_examples"</span><span class="p">,</span> <span class="mi">100</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_chunk_label</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"chunk_label"</span><span class="p">,</span> <span class="s2">".*"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fp_num</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fn_num</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tags_correct</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tags_total</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_measuresNeedUpdate</span> <span class="o">=</span> <span class="kc">False</span></div>
<span class="k">def</span> <span class="nf">_updateMeasures</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_measuresNeedUpdate</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_guessed</span> <span class="o">&</span> <span class="bp">self</span><span class="o">.</span><span class="n">_correct</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_correct</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_guessed</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_guessed</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_correct</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_tp</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fp_num</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_fp</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fn_num</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_fn</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_measuresNeedUpdate</span> <span class="o">=</span> <span class="kc">False</span>
<div class="viewcode-block" id="ChunkScore.score"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.score">[docs]</a> <span class="k">def</span> <span class="nf">score</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">correct</span><span class="p">,</span> <span class="n">guessed</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Given a correctly chunked sentence, score another chunked</span>
<span class="sd"> version of the same sentence.</span>
<span class="sd"> :type correct: chunk structure</span>
<span class="sd"> :param correct: The known-correct ("gold standard") chunked</span>
<span class="sd"> sentence.</span>
<span class="sd"> :type guessed: chunk structure</span>
<span class="sd"> :param guessed: The chunked sentence to be scored.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_correct</span> <span class="o">|=</span> <span class="n">_chunksets</span><span class="p">(</span><span class="n">correct</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_count</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_chunk_label</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_guessed</span> <span class="o">|=</span> <span class="n">_chunksets</span><span class="p">(</span><span class="n">guessed</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_count</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_chunk_label</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_measuresNeedUpdate</span> <span class="o">=</span> <span class="kc">True</span>
<span class="c1"># Keep track of per-tag accuracy (if possible)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">correct_tags</span> <span class="o">=</span> <span class="n">tree2conlltags</span><span class="p">(</span><span class="n">correct</span><span class="p">)</span>
<span class="n">guessed_tags</span> <span class="o">=</span> <span class="n">tree2conlltags</span><span class="p">(</span><span class="n">guessed</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="c1"># This exception case is for nested chunk structures,</span>
<span class="c1"># where tree2conlltags will fail with a ValueError: "Tree</span>
<span class="c1"># is too deeply nested to be printed in CoNLL format."</span>
<span class="n">correct_tags</span> <span class="o">=</span> <span class="n">guessed_tags</span> <span class="o">=</span> <span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tags_total</span> <span class="o">+=</span> <span class="nb">len</span><span class="p">(</span><span class="n">correct_tags</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tags_correct</span> <span class="o">+=</span> <span class="nb">sum</span><span class="p">(</span>
<span class="mi">1</span> <span class="k">for</span> <span class="p">(</span><span class="n">t</span><span class="p">,</span> <span class="n">g</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">guessed_tags</span><span class="p">,</span> <span class="n">correct_tags</span><span class="p">)</span> <span class="k">if</span> <span class="n">t</span> <span class="o">==</span> <span class="n">g</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="ChunkScore.accuracy"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.accuracy">[docs]</a> <span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the overall tag-based accuracy for all text that have</span>
<span class="sd"> been scored by this ``ChunkScore``, using the IOB (conll2000)</span>
<span class="sd"> tag encoding.</span>
<span class="sd"> :rtype: float</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tags_total</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">1</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tags_correct</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tags_total</span></div>
<div class="viewcode-block" id="ChunkScore.precision"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.precision">[docs]</a> <span class="k">def</span> <span class="nf">precision</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the overall precision for all texts that have been</span>
<span class="sd"> scored by this ``ChunkScore``.</span>
<span class="sd"> :rtype: float</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="n">div</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fp_num</span>
<span class="k">if</span> <span class="n">div</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">0</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">/</span> <span class="n">div</span></div>
<div class="viewcode-block" id="ChunkScore.recall"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.recall">[docs]</a> <span class="k">def</span> <span class="nf">recall</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the overall recall for all texts that have been</span>
<span class="sd"> scored by this ``ChunkScore``.</span>
<span class="sd"> :rtype: float</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="n">div</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fn_num</span>
<span class="k">if</span> <span class="n">div</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">0</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">/</span> <span class="n">div</span></div>
<div class="viewcode-block" id="ChunkScore.f_measure"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.f_measure">[docs]</a> <span class="k">def</span> <span class="nf">f_measure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.5</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the overall F measure for all texts that have been</span>
<span class="sd"> scored by this ``ChunkScore``.</span>
<span class="sd"> :param alpha: the relative weighting of precision and recall.</span>
<span class="sd"> Larger alpha biases the score towards the precision value,</span>
<span class="sd"> while smaller alpha biases the score towards the recall</span>
<span class="sd"> value. ``alpha`` should have a value in the range [0,1].</span>
<span class="sd"> :type alpha: float</span>
<span class="sd"> :rtype: float</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="n">p</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">precision</span><span class="p">()</span>
<span class="n">r</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">recall</span><span class="p">()</span>
<span class="k">if</span> <span class="n">p</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">r</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> <span class="c1"># what if alpha is 0 or 1?</span>
<span class="k">return</span> <span class="mi">0</span>
<span class="k">return</span> <span class="mi">1</span> <span class="o">/</span> <span class="p">(</span><span class="n">alpha</span> <span class="o">/</span> <span class="n">p</span> <span class="o">+</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">alpha</span><span class="p">)</span> <span class="o">/</span> <span class="n">r</span><span class="p">)</span></div>
<div class="viewcode-block" id="ChunkScore.missed"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.missed">[docs]</a> <span class="k">def</span> <span class="nf">missed</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the chunks which were included in the</span>
<span class="sd"> correct chunk structures, but not in the guessed chunk</span>
<span class="sd"> structures, listed in input order.</span>
<span class="sd"> :rtype: list of chunks</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="n">chunks</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_fn</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">chunks</span><span class="p">]</span> <span class="c1"># discard position information</span></div>
<div class="viewcode-block" id="ChunkScore.incorrect"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.incorrect">[docs]</a> <span class="k">def</span> <span class="nf">incorrect</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the chunks which were included in the guessed chunk structures,</span>
<span class="sd"> but not in the correct chunk structures, listed in input order.</span>
<span class="sd"> :rtype: list of chunks</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="n">chunks</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_fp</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">chunks</span><span class="p">]</span> <span class="c1"># discard position information</span></div>
<div class="viewcode-block" id="ChunkScore.correct"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.correct">[docs]</a> <span class="k">def</span> <span class="nf">correct</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the chunks which were included in the correct</span>
<span class="sd"> chunk structures, listed in input order.</span>
<span class="sd"> :rtype: list of chunks</span>
<span class="sd"> """</span>
<span class="n">chunks</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_correct</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">chunks</span><span class="p">]</span> <span class="c1"># discard position information</span></div>
<div class="viewcode-block" id="ChunkScore.guessed"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ChunkScore.guessed">[docs]</a> <span class="k">def</span> <span class="nf">guessed</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the chunks which were included in the guessed</span>
<span class="sd"> chunk structures, listed in input order.</span>
<span class="sd"> :rtype: list of chunks</span>
<span class="sd"> """</span>
<span class="n">chunks</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_guessed</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">chunks</span><span class="p">]</span> <span class="c1"># discard position information</span></div>
<span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updateMeasures</span><span class="p">()</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp_num</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fn_num</span>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a concise representation of this ``ChunkScoring``.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<ChunkScoring of "</span> <span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span> <span class="o">+</span> <span class="s2">" chunks>"</span>
<span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a verbose representation of this ``ChunkScoring``.</span>
<span class="sd"> This representation includes the precision, recall, and</span>
<span class="sd"> f-measure scores. For other information about the score,</span>
<span class="sd"> use the accessor methods (e.g., ``missed()`` and ``incorrect()``).</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"ChunkParse score:</span><span class="se">\n</span><span class="s2">"</span>
<span class="o">+</span> <span class="p">(</span><span class="sa">f</span><span class="s2">" IOB Accuracy: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">()</span> <span class="o">*</span> <span class="mi">100</span><span class="si">:</span><span class="s2">5.1f</span><span class="si">}</span><span class="s2">%%</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
<span class="o">+</span> <span class="p">(</span><span class="sa">f</span><span class="s2">" Precision: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">precision</span><span class="p">()</span> <span class="o">*</span> <span class="mi">100</span><span class="si">:</span><span class="s2">5.1f</span><span class="si">}</span><span class="s2">%%</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
<span class="o">+</span> <span class="p">(</span><span class="sa">f</span><span class="s2">" Recall: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">recall</span><span class="p">()</span> <span class="o">*</span> <span class="mi">100</span><span class="si">:</span><span class="s2">5.1f</span><span class="si">}</span><span class="s2">%%</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
<span class="o">+</span> <span class="p">(</span><span class="sa">f</span><span class="s2">" F-Measure: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">f_measure</span><span class="p">()</span> <span class="o">*</span> <span class="mi">100</span><span class="si">:</span><span class="s2">5.1f</span><span class="si">}</span><span class="s2">%%"</span><span class="p">)</span>
<span class="p">)</span></div>
<span class="c1"># extract chunks, and assign unique id, the absolute position of</span>
<span class="c1"># the first word of the chunk</span>
<span class="k">def</span> <span class="nf">_chunksets</span><span class="p">(</span><span class="n">t</span><span class="p">,</span> <span class="n">count</span><span class="p">,</span> <span class="n">chunk_label</span><span class="p">):</span>
<span class="n">pos</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">chunks</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">child</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">child</span><span class="p">,</span> <span class="n">Tree</span><span class="p">):</span>
<span class="k">if</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">chunk_label</span><span class="p">,</span> <span class="n">child</span><span class="o">.</span><span class="n">label</span><span class="p">()):</span>
<span class="n">chunks</span><span class="o">.</span><span class="n">append</span><span class="p">(((</span><span class="n">count</span><span class="p">,</span> <span class="n">pos</span><span class="p">),</span> <span class="n">child</span><span class="o">.</span><span class="n">freeze</span><span class="p">()))</span>
<span class="n">pos</span> <span class="o">+=</span> <span class="nb">len</span><span class="p">(</span><span class="n">child</span><span class="o">.</span><span class="n">leaves</span><span class="p">())</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pos</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="nb">set</span><span class="p">(</span><span class="n">chunks</span><span class="p">)</span>
<div class="viewcode-block" id="tagstr2tree"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.tagstr2tree">[docs]</a><span class="k">def</span> <span class="nf">tagstr2tree</span><span class="p">(</span>
<span class="n">s</span><span class="p">,</span> <span class="n">chunk_label</span><span class="o">=</span><span class="s2">"NP"</span><span class="p">,</span> <span class="n">root_label</span><span class="o">=</span><span class="s2">"S"</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"/"</span><span class="p">,</span> <span class="n">source_tagset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">target_tagset</span><span class="o">=</span><span class="kc">None</span>
<span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Divide a string of bracketted tagged text into</span>
<span class="sd"> chunks and unchunked tokens, and produce a Tree.</span>
<span class="sd"> Chunks are marked by square brackets (``[...]``). Words are</span>
<span class="sd"> delimited by whitespace, and each word should have the form</span>
<span class="sd"> ``text/tag``. Words that do not contain a slash are</span>
<span class="sd"> assigned a ``tag`` of None.</span>
<span class="sd"> :param s: The string to be converted</span>
<span class="sd"> :type s: str</span>
<span class="sd"> :param chunk_label: The label to use for chunk nodes</span>
<span class="sd"> :type chunk_label: str</span>
<span class="sd"> :param root_label: The label to use for the root of the tree</span>
<span class="sd"> :type root_label: str</span>
<span class="sd"> :rtype: Tree</span>
<span class="sd"> """</span>
<span class="n">WORD_OR_BRACKET</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"\[|\]|[^\[\]\s]+"</span><span class="p">)</span>
<span class="n">stack</span> <span class="o">=</span> <span class="p">[</span><span class="n">Tree</span><span class="p">(</span><span class="n">root_label</span><span class="p">,</span> <span class="p">[])]</span>
<span class="k">for</span> <span class="n">match</span> <span class="ow">in</span> <span class="n">WORD_OR_BRACKET</span><span class="o">.</span><span class="n">finditer</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="n">text</span> <span class="o">=</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">()</span>
<span class="k">if</span> <span class="n">text</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"["</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">stack</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Unexpected [ at char </span><span class="si">{</span><span class="n">match</span><span class="o">.</span><span class="n">start</span><span class="p">()</span><span class="si">:</span><span class="s2">d</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<span class="n">chunk</span> <span class="o">=</span> <span class="n">Tree</span><span class="p">(</span><span class="n">chunk_label</span><span class="p">,</span> <span class="p">[])</span>
<span class="n">stack</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">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="n">stack</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">text</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"]"</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">stack</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Unexpected ] at char </span><span class="si">{</span><span class="n">match</span><span class="o">.</span><span class="n">start</span><span class="p">()</span><span class="si">:</span><span class="s2">d</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<span class="n">stack</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">sep</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">stack</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">append</span><span class="p">(</span><span class="n">text</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">word</span><span class="p">,</span> <span class="n">tag</span> <span class="o">=</span> <span class="n">str2tuple</span><span class="p">(</span><span class="n">text</span><span class="p">,</span> <span class="n">sep</span><span class="p">)</span>
<span class="k">if</span> <span class="n">source_tagset</span> <span class="ow">and</span> <span class="n">target_tagset</span><span class="p">:</span>
<span class="n">tag</span> <span class="o">=</span> <span class="n">map_tag</span><span class="p">(</span><span class="n">source_tagset</span><span class="p">,</span> <span class="n">target_tagset</span><span class="p">,</span> <span class="n">tag</span><span class="p">)</span>
<span class="n">stack</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">append</span><span class="p">((</span><span class="n">word</span><span class="p">,</span> <span class="n">tag</span><span class="p">))</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">stack</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Expected ] at char </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span><span class="si">:</span><span class="s2">d</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">stack</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></div>
<span class="c1">### CONLL</span>
<span class="n">_LINE_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"(\S+)\s+(\S+)\s+([IOB])-?(\S+)?"</span><span class="p">)</span>
<div class="viewcode-block" id="conllstr2tree"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.conllstr2tree">[docs]</a><span class="k">def</span> <span class="nf">conllstr2tree</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">chunk_types</span><span class="o">=</span><span class="p">(</span><span class="s2">"NP"</span><span class="p">,</span> <span class="s2">"PP"</span><span class="p">,</span> <span class="s2">"VP"</span><span class="p">),</span> <span class="n">root_label</span><span class="o">=</span><span class="s2">"S"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a chunk structure for a single sentence</span>
<span class="sd"> encoded in the given CONLL 2000 style string.</span>
<span class="sd"> This function converts a CoNLL IOB string into a tree.</span>
<span class="sd"> It uses the specified chunk types</span>
<span class="sd"> (defaults to NP, PP and VP), and creates a tree rooted at a node</span>
<span class="sd"> labeled S (by default).</span>
<span class="sd"> :param s: The CoNLL string to be converted.</span>
<span class="sd"> :type s: str</span>
<span class="sd"> :param chunk_types: The chunk types to be converted.</span>
<span class="sd"> :type chunk_types: tuple</span>
<span class="sd"> :param root_label: The node label to use for the root.</span>
<span class="sd"> :type root_label: str</span>
<span class="sd"> :rtype: Tree</span>
<span class="sd"> """</span>
<span class="n">stack</span> <span class="o">=</span> <span class="p">[</span><span class="n">Tree</span><span class="p">(</span><span class="n">root_label</span><span class="p">,</span> <span class="p">[])]</span>
<span class="k">for</span> <span class="n">lineno</span><span class="p">,</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">s</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="k">if</span> <span class="ow">not</span> <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">():</span>
<span class="k">continue</span>
<span class="c1"># Decode the line.</span>
<span class="n">match</span> <span class="o">=</span> <span class="n">_LINE_RE</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
<span class="k">if</span> <span class="n">match</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="sa">f</span><span class="s2">"Error on line </span><span class="si">{</span><span class="n">lineno</span><span class="si">:</span><span class="s2">d</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="n">tag</span><span class="p">,</span> <span class="n">state</span><span class="p">,</span> <span class="n">chunk_type</span><span class="p">)</span> <span class="o">=</span> <span class="n">match</span><span class="o">.</span><span class="n">groups</span><span class="p">()</span>
<span class="c1"># If it's a chunk type we don't care about, treat it as O.</span>
<span class="k">if</span> <span class="n">chunk_types</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">chunk_type</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">chunk_types</span><span class="p">:</span>
<span class="n">state</span> <span class="o">=</span> <span class="s2">"O"</span>
<span class="c1"># For "Begin"/"Outside", finish any completed chunks -</span>
<span class="c1"># also do so for "Inside" which don't match the previous token.</span>
<span class="n">mismatch_I</span> <span class="o">=</span> <span class="n">state</span> <span class="o">==</span> <span class="s2">"I"</span> <span class="ow">and</span> <span class="n">chunk_type</span> <span class="o">!=</span> <span class="n">stack</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">label</span><span class="p">()</span>
<span class="k">if</span> <span class="n">state</span> <span class="ow">in</span> <span class="s2">"BO"</span> <span class="ow">or</span> <span class="n">mismatch_I</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">stack</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">stack</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
<span class="c1"># For "Begin", start a new chunk.</span>
<span class="k">if</span> <span class="n">state</span> <span class="o">==</span> <span class="s2">"B"</span> <span class="ow">or</span> <span class="n">mismatch_I</span><span class="p">:</span>
<span class="n">chunk</span> <span class="o">=</span> <span class="n">Tree</span><span class="p">(</span><span class="n">chunk_type</span><span class="p">,</span> <span class="p">[])</span>
<span class="n">stack</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">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="n">stack</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="c1"># Add the new word token.</span>
<span class="n">stack</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">append</span><span class="p">((</span><span class="n">word</span><span class="p">,</span> <span class="n">tag</span><span class="p">))</span>
<span class="k">return</span> <span class="n">stack</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></div>
<div class="viewcode-block" id="tree2conlltags"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.tree2conlltags">[docs]</a><span class="k">def</span> <span class="nf">tree2conlltags</span><span class="p">(</span><span class="n">t</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a list of 3-tuples containing ``(word, tag, IOB-tag)``.</span>
<span class="sd"> Convert a tree to the CoNLL IOB tag format.</span>
<span class="sd"> :param t: The tree to be converted.</span>
<span class="sd"> :type t: Tree</span>
<span class="sd"> :rtype: list(tuple)</span>
<span class="sd"> """</span>
<span class="n">tags</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">child</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">category</span> <span class="o">=</span> <span class="n">child</span><span class="o">.</span><span class="n">label</span><span class="p">()</span>
<span class="n">prefix</span> <span class="o">=</span> <span class="s2">"B-"</span>
<span class="k">for</span> <span class="n">contents</span> <span class="ow">in</span> <span class="n">child</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">contents</span><span class="p">,</span> <span class="n">Tree</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Tree is too deeply nested to be printed in CoNLL format"</span>
<span class="p">)</span>
<span class="n">tags</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">contents</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">contents</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">prefix</span> <span class="o">+</span> <span class="n">category</span><span class="p">))</span>
<span class="n">prefix</span> <span class="o">=</span> <span class="s2">"I-"</span>
<span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span>
<span class="n">tags</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">child</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">child</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="s2">"O"</span><span class="p">))</span>
<span class="k">return</span> <span class="n">tags</span></div>
<div class="viewcode-block" id="conlltags2tree"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.conlltags2tree">[docs]</a><span class="k">def</span> <span class="nf">conlltags2tree</span><span class="p">(</span>
<span class="n">sentence</span><span class="p">,</span> <span class="n">chunk_types</span><span class="o">=</span><span class="p">(</span><span class="s2">"NP"</span><span class="p">,</span> <span class="s2">"PP"</span><span class="p">,</span> <span class="s2">"VP"</span><span class="p">),</span> <span class="n">root_label</span><span class="o">=</span><span class="s2">"S"</span><span class="p">,</span> <span class="n">strict</span><span class="o">=</span><span class="kc">False</span>
<span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Convert the CoNLL IOB format to a tree.</span>
<span class="sd"> """</span>
<span class="n">tree</span> <span class="o">=</span> <span class="n">Tree</span><span class="p">(</span><span class="n">root_label</span><span class="p">,</span> <span class="p">[])</span>
<span class="k">for</span> <span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">,</span> <span class="n">chunktag</span><span class="p">)</span> <span class="ow">in</span> <span class="n">sentence</span><span class="p">:</span>
<span class="k">if</span> <span class="n">chunktag</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">strict</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Bad conll tag sequence"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Treat as O</span>
<span class="n">tree</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">chunktag</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"B-"</span><span class="p">):</span>
<span class="n">tree</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Tree</span><span class="p">(</span><span class="n">chunktag</span><span class="p">[</span><span class="mi">2</span><span class="p">:],</span> <span class="p">[(</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">)]))</span>
<span class="k">elif</span> <span class="n">chunktag</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"I-"</span><span class="p">):</span>
<span class="k">if</span> <span class="p">(</span>
<span class="nb">len</span><span class="p">(</span><span class="n">tree</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span>
<span class="ow">or</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tree</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="n">Tree</span><span class="p">)</span>
<span class="ow">or</span> <span class="n">tree</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">label</span><span class="p">()</span> <span class="o">!=</span> <span class="n">chunktag</span><span class="p">[</span><span class="mi">2</span><span class="p">:]</span>
<span class="p">):</span>
<span class="k">if</span> <span class="n">strict</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Bad conll tag sequence"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Treat as B-*</span>
<span class="n">tree</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Tree</span><span class="p">(</span><span class="n">chunktag</span><span class="p">[</span><span class="mi">2</span><span class="p">:],</span> <span class="p">[(</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">)]))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">tree</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">append</span><span class="p">((</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">chunktag</span> <span class="o">==</span> <span class="s2">"O"</span><span class="p">:</span>
<span class="n">tree</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">word</span><span class="p">,</span> <span class="n">postag</span><span class="p">))</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="sa">f</span><span class="s2">"Bad conll tag </span><span class="si">{</span><span class="n">chunktag</span><span class="si">!r}</span><span class="s2">"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">tree</span></div>
<div class="viewcode-block" id="tree2conllstr"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.tree2conllstr">[docs]</a><span class="k">def</span> <span class="nf">tree2conllstr</span><span class="p">(</span><span class="n">t</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a multiline string where each line contains a word, tag and IOB tag.</span>
<span class="sd"> Convert a tree to the CoNLL IOB string format</span>
<span class="sd"> :param t: The tree to be converted.</span>
<span class="sd"> :type t: Tree</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="n">lines</span> <span class="o">=</span> <span class="p">[</span><span class="s2">" "</span><span class="o">.</span><span class="n">join</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="n">tree2conlltags</span><span class="p">(</span><span class="n">t</span><span class="p">)]</span>
<span class="k">return</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">lines</span><span class="p">)</span></div>
<span class="c1">### IEER</span>
<span class="n">_IEER_DOC_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="sa">r</span><span class="s2">"<DOC>\s*"</span>
<span class="sa">r</span><span class="s2">"(<DOCNO>\s*(?P<docno>.+?)\s*</DOCNO>\s*)?"</span>
<span class="sa">r</span><span class="s2">"(<DOCTYPE>\s*(?P<doctype>.+?)\s*</DOCTYPE>\s*)?"</span>
<span class="sa">r</span><span class="s2">"(<DATE_TIME>\s*(?P<date_time>.+?)\s*</DATE_TIME>\s*)?"</span>
<span class="sa">r</span><span class="s2">"<BODY>\s*"</span>
<span class="sa">r</span><span class="s2">"(<HEADLINE>\s*(?P<headline>.+?)\s*</HEADLINE>\s*)?"</span>
<span class="sa">r</span><span class="s2">"<TEXT>(?P<text>.*?)</TEXT>\s*"</span>
<span class="sa">r</span><span class="s2">"</BODY>\s*</DOC>\s*"</span><span class="p">,</span>
<span class="n">re</span><span class="o">.</span><span class="n">DOTALL</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">_IEER_TYPE_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">'<b_\w+\s+[^>]*?type="(?P<type>\w+)"'</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_ieer_read_text</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">root_label</span><span class="p">):</span>
<span class="n">stack</span> <span class="o">=</span> <span class="p">[</span><span class="n">Tree</span><span class="p">(</span><span class="n">root_label</span><span class="p">,</span> <span class="p">[])]</span>
<span class="c1"># s will be None if there is no headline in the text</span>
<span class="c1"># return the empty list in place of a Tree</span>
<span class="k">if</span> <span class="n">s</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">piece_m</span> <span class="ow">in</span> <span class="n">re</span><span class="o">.</span><span class="n">finditer</span><span class="p">(</span><span class="sa">r</span><span class="s2">"<[^>]+>|[^\s<]+"</span><span class="p">,</span> <span class="n">s</span><span class="p">):</span>
<span class="n">piece</span> <span class="o">=</span> <span class="n">piece_m</span><span class="o">.</span><span class="n">group</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="n">piece</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"<b_"</span><span class="p">):</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">_IEER_TYPE_RE</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">piece</span><span class="p">)</span>
<span class="k">if</span> <span class="n">m</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"XXXX"</span><span class="p">,</span> <span class="n">piece</span><span class="p">)</span>
<span class="n">chunk</span> <span class="o">=</span> <span class="n">Tree</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"type"</span><span class="p">),</span> <span class="p">[])</span>
<span class="n">stack</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">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="n">stack</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">piece</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"<e_"</span><span class="p">):</span>
<span class="n">stack</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
<span class="c1"># elif piece.startswith('<'):</span>
<span class="c1"># print "ERROR:", piece</span>
<span class="c1"># raise ValueError # Unexpected HTML</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">stack</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">append</span><span class="p">(</span><span class="n">piece</span><span class="p">)</span>
<span class="k">except</span> <span class="p">(</span><span class="ne">IndexError</span><span class="p">,</span> <span class="ne">ValueError</span><span class="p">)</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">"Bad IEER string (error at character </span><span class="si">{</span><span class="n">piece_m</span><span class="o">.</span><span class="n">start</span><span class="p">()</span><span class="si">:</span><span class="s2">d</span><span class="si">}</span><span class="s2">)"</span>
<span class="p">)</span> <span class="kn">from</span> <span class="nn">e</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">stack</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Bad IEER string"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">stack</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<div class="viewcode-block" id="ieerstr2tree"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.ieerstr2tree">[docs]</a><span class="k">def</span> <span class="nf">ieerstr2tree</span><span class="p">(</span>
<span class="n">s</span><span class="p">,</span>
<span class="n">chunk_types</span><span class="o">=</span><span class="p">[</span>
<span class="s2">"LOCATION"</span><span class="p">,</span>
<span class="s2">"ORGANIZATION"</span><span class="p">,</span>
<span class="s2">"PERSON"</span><span class="p">,</span>
<span class="s2">"DURATION"</span><span class="p">,</span>
<span class="s2">"DATE"</span><span class="p">,</span>
<span class="s2">"CARDINAL"</span><span class="p">,</span>
<span class="s2">"PERCENT"</span><span class="p">,</span>
<span class="s2">"MONEY"</span><span class="p">,</span>
<span class="s2">"MEASURE"</span><span class="p">,</span>
<span class="p">],</span>
<span class="n">root_label</span><span class="o">=</span><span class="s2">"S"</span><span class="p">,</span>
<span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a chunk structure containing the chunked tagged text that is</span>
<span class="sd"> encoded in the given IEER style string.</span>
<span class="sd"> Convert a string of chunked tagged text in the IEER named</span>
<span class="sd"> entity format into a chunk structure. Chunks are of several</span>
<span class="sd"> types, LOCATION, ORGANIZATION, PERSON, DURATION, DATE, CARDINAL,</span>
<span class="sd"> PERCENT, MONEY, and MEASURE.</span>
<span class="sd"> :rtype: Tree</span>
<span class="sd"> """</span>
<span class="c1"># Try looking for a single document. If that doesn't work, then just</span>
<span class="c1"># treat everything as if it was within the <TEXT>...</TEXT>.</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">_IEER_DOC_RE</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">s</span><span class="p">)</span>
<span class="k">if</span> <span class="n">m</span><span class="p">:</span>
<span class="k">return</span> <span class="p">{</span>
<span class="s2">"text"</span><span class="p">:</span> <span class="n">_ieer_read_text</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"text"</span><span class="p">),</span> <span class="n">root_label</span><span class="p">),</span>
<span class="s2">"docno"</span><span class="p">:</span> <span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"docno"</span><span class="p">),</span>
<span class="s2">"doctype"</span><span class="p">:</span> <span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"doctype"</span><span class="p">),</span>
<span class="s2">"date_time"</span><span class="p">:</span> <span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"date_time"</span><span class="p">),</span>
<span class="c1">#'headline': m.group('headline')</span>
<span class="c1"># we want to capture NEs in the headline too!</span>
<span class="s2">"headline"</span><span class="p">:</span> <span class="n">_ieer_read_text</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"headline"</span><span class="p">),</span> <span class="n">root_label</span><span class="p">),</span>
<span class="p">}</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">_ieer_read_text</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">root_label</span><span class="p">)</span></div>
<div class="viewcode-block" id="demo"><a class="viewcode-back" href="../../../api/nltk.chunk.util.html#nltk.chunk.util.demo">[docs]</a><span class="k">def</span> <span class="nf">demo</span><span class="p">():</span>
<span class="n">s</span> <span class="o">=</span> <span class="s2">"[ Pierre/NNP Vinken/NNP ] ,/, [ 61/CD years/NNS ] old/JJ ,/, will/MD join/VB [ the/DT board/NN ] ./."</span>
<span class="kn">import</span> <span class="nn">nltk</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">nltk</span><span class="o">.</span><span class="n">chunk</span><span class="o">.</span><span class="n">tagstr2tree</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">chunk_label</span><span class="o">=</span><span class="s2">"NP"</span><span class="p">)</span>
<span class="n">t</span><span class="o">.</span><span class="n">pprint</span><span class="p">()</span>
<span class="nb">print</span><span class="p">()</span>
<span class="n">s</span> <span class="o">=</span> <span class="s2">"""</span>
<span class="s2">These DT B-NP</span>
<span class="s2">research NN I-NP</span>
<span class="s2">protocols NNS I-NP</span>
<span class="s2">offer VBP B-VP</span>
<span class="s2">to TO B-PP</span>
<span class="s2">the DT B-NP</span>
<span class="s2">patient NN I-NP</span>
<span class="s2">not RB O</span>
<span class="s2">only RB O</span>
<span class="s2">the DT B-NP</span>
<span class="s2">very RB I-NP</span>
<span class="s2">best JJS I-NP</span>
<span class="s2">therapy NN I-NP</span>
<span class="s2">which WDT B-NP</span>
<span class="s2">we PRP B-NP</span>
<span class="s2">have VBP B-VP</span>
<span class="s2">established VBN I-VP</span>
<span class="s2">today NN B-NP</span>
<span class="s2">but CC B-NP</span>
<span class="s2">also RB I-NP</span>
<span class="s2">the DT B-NP</span>
<span class="s2">hope NN I-NP</span>
<span class="s2">of IN B-PP</span>
<span class="s2">something NN B-NP</span>
<span class="s2">still RB B-ADJP</span>
<span class="s2">better JJR I-ADJP</span>
<span class="s2">. . O</span>
<span class="s2">"""</span>
<span class="n">conll_tree</span> <span class="o">=</span> <span class="n">conllstr2tree</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">chunk_types</span><span class="o">=</span><span class="p">(</span><span class="s2">"NP"</span><span class="p">,</span> <span class="s2">"PP"</span><span class="p">))</span>
<span class="n">conll_tree</span><span class="o">.</span><span class="n">pprint</span><span class="p">()</span>
<span class="c1"># Demonstrate CoNLL output</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"CoNLL output:"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">nltk</span><span class="o">.</span><span class="n">chunk</span><span class="o">.</span><span class="n">tree2conllstr</span><span class="p">(</span><span class="n">conll_tree</span><span class="p">))</span>
<span class="nb">print</span><span class="p">()</span></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
<span class="n">demo</span><span class="p">()</span>
</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>