ankusa 0.0.13 → 0.0.14
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -0
- data/Gemfile.lock +16 -0
- data/README.rdoc +5 -3
- data/Rakefile +5 -5
- data/lib/ankusa/naive_bayes.rb +3 -3
- data/lib/ankusa/version.rb +1 -1
- metadata +36 -100
- data/docs/Ankusa.html +0 -229
- data/docs/Ankusa/CassandraStorage.html +0 -801
- data/docs/Ankusa/Classifier.html +0 -440
- data/docs/Ankusa/FileSystemStorage.html +0 -376
- data/docs/Ankusa/HBaseStorage.html +0 -845
- data/docs/Ankusa/KLDivergenceClassifier.html +0 -265
- data/docs/Ankusa/MemoryStorage.html +0 -672
- data/docs/Ankusa/NaiveBayesClassifier.html +0 -313
- data/docs/Ankusa/TextHash.html +0 -390
- data/docs/README_rdoc.html +0 -268
- data/docs/String.html +0 -241
- data/docs/created.rid +0 -14
- data/docs/images/brick.png +0 -0
- data/docs/images/brick_link.png +0 -0
- data/docs/images/bug.png +0 -0
- data/docs/images/bullet_black.png +0 -0
- data/docs/images/bullet_toggle_minus.png +0 -0
- data/docs/images/bullet_toggle_plus.png +0 -0
- data/docs/images/date.png +0 -0
- data/docs/images/find.png +0 -0
- data/docs/images/loadingAnimation.gif +0 -0
- data/docs/images/macFFBgHack.png +0 -0
- data/docs/images/package.png +0 -0
- data/docs/images/page_green.png +0 -0
- data/docs/images/page_white_text.png +0 -0
- data/docs/images/page_white_width.png +0 -0
- data/docs/images/plugin.png +0 -0
- data/docs/images/ruby.png +0 -0
- data/docs/images/tag_green.png +0 -0
- data/docs/images/wrench.png +0 -0
- data/docs/images/wrench_orange.png +0 -0
- data/docs/images/zoom.png +0 -0
- data/docs/index.html +0 -212
- data/docs/js/darkfish.js +0 -116
- data/docs/js/jquery.js +0 -32
- data/docs/js/quicksearch.js +0 -114
- data/docs/js/thickbox-compressed.js +0 -10
- data/docs/lib/ankusa/cassandra_storage_rb.html +0 -54
- data/docs/lib/ankusa/classifier_rb.html +0 -52
- data/docs/lib/ankusa/extensions_rb.html +0 -54
- data/docs/lib/ankusa/file_system_storage_rb.html +0 -54
- data/docs/lib/ankusa/hasher_rb.html +0 -56
- data/docs/lib/ankusa/hbase_storage_rb.html +0 -54
- data/docs/lib/ankusa/kl_divergence_rb.html +0 -52
- data/docs/lib/ankusa/memory_storage_rb.html +0 -52
- data/docs/lib/ankusa/naive_bayes_rb.html +0 -52
- data/docs/lib/ankusa/stopwords_rb.html +0 -52
- data/docs/lib/ankusa/version_rb.html +0 -52
- data/docs/lib/ankusa_rb.html +0 -64
- data/docs/rdoc.css +0 -759
data/docs/Ankusa/Classifier.html
DELETED
@@ -1,440 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
-
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
|
3
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
4
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
5
|
-
<head>
|
6
|
-
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type" />
|
7
|
-
|
8
|
-
<title>Module: Ankusa::Classifier</title>
|
9
|
-
|
10
|
-
<link rel="stylesheet" href="../rdoc.css" type="text/css" media="screen" />
|
11
|
-
|
12
|
-
<script src="../js/jquery.js" type="text/javascript" charset="utf-8"></script>
|
13
|
-
<script src="../js/thickbox-compressed.js" type="text/javascript" charset="utf-8"></script>
|
14
|
-
<script src="../js/quicksearch.js" type="text/javascript" charset="utf-8"></script>
|
15
|
-
<script src="../js/darkfish.js" type="text/javascript" charset="utf-8"></script>
|
16
|
-
|
17
|
-
</head>
|
18
|
-
<body id="top" class="module">
|
19
|
-
|
20
|
-
<div id="metadata">
|
21
|
-
<div id="home-metadata">
|
22
|
-
<div id="home-section" class="section">
|
23
|
-
<h3 class="section-header">
|
24
|
-
<a href="../index.html">Home</a>
|
25
|
-
<a href="../index.html#classes">Classes</a>
|
26
|
-
<a href="../index.html#methods">Methods</a>
|
27
|
-
</h3>
|
28
|
-
</div>
|
29
|
-
</div>
|
30
|
-
|
31
|
-
<div id="file-metadata">
|
32
|
-
<div id="file-list-section" class="section">
|
33
|
-
<h3 class="section-header">In Files</h3>
|
34
|
-
<div class="section-body">
|
35
|
-
<ul>
|
36
|
-
|
37
|
-
<li><a href="../lib/ankusa/classifier_rb.html?TB_iframe=true&height=550&width=785"
|
38
|
-
class="thickbox" title="lib/ankusa/classifier.rb">lib/ankusa/classifier.rb</a></li>
|
39
|
-
|
40
|
-
</ul>
|
41
|
-
</div>
|
42
|
-
</div>
|
43
|
-
|
44
|
-
|
45
|
-
</div>
|
46
|
-
|
47
|
-
<div id="class-metadata">
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
<!-- Method Quickref -->
|
56
|
-
<div id="method-list-section" class="section">
|
57
|
-
<h3 class="section-header">Methods</h3>
|
58
|
-
<ul class="link-list">
|
59
|
-
|
60
|
-
<li><a href="#method-c-new">::new</a></li>
|
61
|
-
|
62
|
-
<li><a href="#method-i-doc_count_totals">#doc_count_totals</a></li>
|
63
|
-
|
64
|
-
<li><a href="#method-i-get_word_probs">#get_word_probs</a></li>
|
65
|
-
|
66
|
-
<li><a href="#method-i-train">#train</a></li>
|
67
|
-
|
68
|
-
<li><a href="#method-i-untrain">#untrain</a></li>
|
69
|
-
|
70
|
-
<li><a href="#method-i-vocab_sizes">#vocab_sizes</a></li>
|
71
|
-
|
72
|
-
</ul>
|
73
|
-
</div>
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
</div>
|
78
|
-
|
79
|
-
<div id="project-metadata">
|
80
|
-
|
81
|
-
|
82
|
-
<div id="fileindex-section" class="section project-section">
|
83
|
-
<h3 class="section-header">Files</h3>
|
84
|
-
<ul>
|
85
|
-
|
86
|
-
<li class="file"><a href="../README_rdoc.html">README.rdoc</a></li>
|
87
|
-
|
88
|
-
</ul>
|
89
|
-
</div>
|
90
|
-
|
91
|
-
|
92
|
-
<div id="classindex-section" class="section project-section">
|
93
|
-
<h3 class="section-header">Class/Module Index
|
94
|
-
<span class="search-toggle"><img src="../images/find.png"
|
95
|
-
height="16" width="16" alt="[+]"
|
96
|
-
title="show/hide quicksearch" /></span></h3>
|
97
|
-
<form action="#" method="get" accept-charset="utf-8" class="initially-hidden">
|
98
|
-
<fieldset>
|
99
|
-
<legend>Quicksearch</legend>
|
100
|
-
<input type="text" name="quicksearch" value=""
|
101
|
-
class="quicksearch-field" />
|
102
|
-
</fieldset>
|
103
|
-
</form>
|
104
|
-
|
105
|
-
<ul class="link-list">
|
106
|
-
|
107
|
-
<li><a href="../Ankusa.html">Ankusa</a></li>
|
108
|
-
|
109
|
-
<li><a href="../Ankusa/CassandraStorage.html">Ankusa::CassandraStorage</a></li>
|
110
|
-
|
111
|
-
<li><a href="../Ankusa/Classifier.html">Ankusa::Classifier</a></li>
|
112
|
-
|
113
|
-
<li><a href="../Ankusa/FileSystemStorage.html">Ankusa::FileSystemStorage</a></li>
|
114
|
-
|
115
|
-
<li><a href="../Ankusa/HBaseStorage.html">Ankusa::HBaseStorage</a></li>
|
116
|
-
|
117
|
-
<li><a href="../Ankusa/KLDivergenceClassifier.html">Ankusa::KLDivergenceClassifier</a></li>
|
118
|
-
|
119
|
-
<li><a href="../Ankusa/MemoryStorage.html">Ankusa::MemoryStorage</a></li>
|
120
|
-
|
121
|
-
<li><a href="../Ankusa/NaiveBayesClassifier.html">Ankusa::NaiveBayesClassifier</a></li>
|
122
|
-
|
123
|
-
<li><a href="../Ankusa/TextHash.html">Ankusa::TextHash</a></li>
|
124
|
-
|
125
|
-
<li><a href="../String.html">String</a></li>
|
126
|
-
|
127
|
-
</ul>
|
128
|
-
<div id="no-class-search-results" style="display: none;">No matching classes.</div>
|
129
|
-
</div>
|
130
|
-
|
131
|
-
|
132
|
-
</div>
|
133
|
-
</div>
|
134
|
-
|
135
|
-
<div id="documentation">
|
136
|
-
<h1 class="module">Ankusa::Classifier</h1>
|
137
|
-
|
138
|
-
<div id="description" class="description">
|
139
|
-
|
140
|
-
</div><!-- description -->
|
141
|
-
|
142
|
-
|
143
|
-
<div id="5Buntitled-5D" class="documentation-section">
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
<!-- Attributes -->
|
152
|
-
<div id="attribute-method-details" class="method-section section">
|
153
|
-
<h3 class="section-header">Attributes</h3>
|
154
|
-
|
155
|
-
|
156
|
-
<div id="classnames-attribute-method" class="method-detail">
|
157
|
-
<a name="classnames"></a>
|
158
|
-
|
159
|
-
<div class="method-heading attribute-method-heading">
|
160
|
-
<span class="method-name">classnames</span><span
|
161
|
-
class="attribute-access-type">[R]</span>
|
162
|
-
</div>
|
163
|
-
|
164
|
-
<div class="method-description">
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
</div>
|
169
|
-
</div>
|
170
|
-
|
171
|
-
</div><!-- attribute-method-details -->
|
172
|
-
|
173
|
-
|
174
|
-
<!-- Methods -->
|
175
|
-
|
176
|
-
<div id="public-class-method-details" class="method-section section">
|
177
|
-
<h3 class="section-header">Public Class Methods</h3>
|
178
|
-
|
179
|
-
|
180
|
-
<div id="new-method" class="method-detail ">
|
181
|
-
<a name="method-c-new"></a>
|
182
|
-
|
183
|
-
|
184
|
-
<div class="method-heading">
|
185
|
-
<span class="method-name">new</span><span
|
186
|
-
class="method-args">(storage)</span>
|
187
|
-
<span class="method-click-advice">click to toggle source</span>
|
188
|
-
</div>
|
189
|
-
|
190
|
-
|
191
|
-
<div class="method-description">
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
<div class="method-source-code" id="new-source">
|
198
|
-
<pre>
|
199
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 6</span>
|
200
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">storage</span>)
|
201
|
-
<span class="ruby-ivar">@storage</span> = <span class="ruby-identifier">storage</span>
|
202
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">init_tables</span>
|
203
|
-
<span class="ruby-ivar">@classnames</span> = <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">classnames</span>
|
204
|
-
<span class="ruby-keyword">end</span></pre>
|
205
|
-
</div><!-- new-source -->
|
206
|
-
|
207
|
-
</div>
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
212
|
-
</div><!-- new-method -->
|
213
|
-
|
214
|
-
|
215
|
-
</div><!-- public-class-method-details -->
|
216
|
-
|
217
|
-
<div id="public-instance-method-details" class="method-section section">
|
218
|
-
<h3 class="section-header">Public Instance Methods</h3>
|
219
|
-
|
220
|
-
|
221
|
-
<div id="train-method" class="method-detail ">
|
222
|
-
<a name="method-i-train"></a>
|
223
|
-
|
224
|
-
|
225
|
-
<div class="method-heading">
|
226
|
-
<span class="method-name">train</span><span
|
227
|
-
class="method-args">(klass, text)</span>
|
228
|
-
<span class="method-click-advice">click to toggle source</span>
|
229
|
-
</div>
|
230
|
-
|
231
|
-
|
232
|
-
<div class="method-description">
|
233
|
-
|
234
|
-
<p>text can be either an array of strings or a string klass is a symbol</p>
|
235
|
-
|
236
|
-
|
237
|
-
|
238
|
-
<div class="method-source-code" id="train-source">
|
239
|
-
<pre>
|
240
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 14</span>
|
241
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">train</span>(<span class="ruby-identifier">klass</span>, <span class="ruby-identifier">text</span>)
|
242
|
-
<span class="ruby-identifier">th</span> = <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">text</span>)
|
243
|
-
<span class="ruby-identifier">th</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span><span class="ruby-operator">|</span>
|
244
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_word_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span>
|
245
|
-
<span class="ruby-keyword">yield</span> <span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span> <span class="ruby-keyword">if</span> <span class="ruby-identifier">block_given?</span>
|
246
|
-
}
|
247
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_total_word_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-identifier">th</span>.<span class="ruby-identifier">word_count</span>
|
248
|
-
<span class="ruby-identifier">doccount</span> = (<span class="ruby-identifier">text</span>.<span class="ruby-identifier">kind_of?</span> <span class="ruby-constant">Array</span>) <span class="ruby-operator">?</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">length</span> <span class="ruby-operator">:</span> <span class="ruby-value">1</span>
|
249
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_doc_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-identifier">doccount</span>
|
250
|
-
<span class="ruby-ivar">@classnames</span> <span class="ruby-operator"><<</span> <span class="ruby-identifier">klass</span> <span class="ruby-keyword">unless</span> <span class="ruby-ivar">@classnames</span>.<span class="ruby-identifier">include?</span> <span class="ruby-identifier">klass</span>
|
251
|
-
<span class="ruby-comment"># cache is now dirty of these vars</span>
|
252
|
-
<span class="ruby-ivar">@doc_count_totals</span> = <span class="ruby-keyword">nil</span>
|
253
|
-
<span class="ruby-ivar">@vocab_sizes</span> = <span class="ruby-keyword">nil</span>
|
254
|
-
<span class="ruby-identifier">th</span>
|
255
|
-
<span class="ruby-keyword">end</span></pre>
|
256
|
-
</div><!-- train-source -->
|
257
|
-
|
258
|
-
</div>
|
259
|
-
|
260
|
-
|
261
|
-
|
262
|
-
|
263
|
-
</div><!-- train-method -->
|
264
|
-
|
265
|
-
|
266
|
-
<div id="untrain-method" class="method-detail ">
|
267
|
-
<a name="method-i-untrain"></a>
|
268
|
-
|
269
|
-
|
270
|
-
<div class="method-heading">
|
271
|
-
<span class="method-name">untrain</span><span
|
272
|
-
class="method-args">(klass, text)</span>
|
273
|
-
<span class="method-click-advice">click to toggle source</span>
|
274
|
-
</div>
|
275
|
-
|
276
|
-
|
277
|
-
<div class="method-description">
|
278
|
-
|
279
|
-
<p>text can be either an array of strings or a string klass is a symbol</p>
|
280
|
-
|
281
|
-
|
282
|
-
|
283
|
-
<div class="method-source-code" id="untrain-source">
|
284
|
-
<pre>
|
285
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 32</span>
|
286
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">untrain</span>(<span class="ruby-identifier">klass</span>, <span class="ruby-identifier">text</span>)
|
287
|
-
<span class="ruby-identifier">th</span> = <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">text</span>)
|
288
|
-
<span class="ruby-identifier">th</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span><span class="ruby-operator">|</span>
|
289
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_word_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-identifier">word</span>, <span class="ruby-operator">-</span><span class="ruby-identifier">count</span>
|
290
|
-
<span class="ruby-keyword">yield</span> <span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span> <span class="ruby-keyword">if</span> <span class="ruby-identifier">block_given?</span>
|
291
|
-
}
|
292
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_total_word_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-operator">-</span><span class="ruby-identifier">th</span>.<span class="ruby-identifier">word_count</span>
|
293
|
-
<span class="ruby-identifier">doccount</span> = (<span class="ruby-identifier">text</span>.<span class="ruby-identifier">kind_of?</span> <span class="ruby-constant">Array</span>) <span class="ruby-operator">?</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">length</span> <span class="ruby-operator">:</span> <span class="ruby-value">1</span>
|
294
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_doc_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-operator">-</span><span class="ruby-identifier">doccount</span>
|
295
|
-
<span class="ruby-comment"># cache is now dirty of these vars</span>
|
296
|
-
<span class="ruby-ivar">@doc_count_totals</span> = <span class="ruby-keyword">nil</span>
|
297
|
-
<span class="ruby-ivar">@vocab_sizes</span> = <span class="ruby-keyword">nil</span>
|
298
|
-
<span class="ruby-identifier">th</span>
|
299
|
-
<span class="ruby-keyword">end</span></pre>
|
300
|
-
</div><!-- untrain-source -->
|
301
|
-
|
302
|
-
</div>
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
</div><!-- untrain-method -->
|
308
|
-
|
309
|
-
|
310
|
-
</div><!-- public-instance-method-details -->
|
311
|
-
|
312
|
-
<div id="protected-instance-method-details" class="method-section section">
|
313
|
-
<h3 class="section-header">Protected Instance Methods</h3>
|
314
|
-
|
315
|
-
|
316
|
-
<div id="doc_count_totals-method" class="method-detail ">
|
317
|
-
<a name="method-i-doc_count_totals"></a>
|
318
|
-
|
319
|
-
|
320
|
-
<div class="method-heading">
|
321
|
-
<span class="method-name">doc_count_totals</span><span
|
322
|
-
class="method-args">()</span>
|
323
|
-
<span class="method-click-advice">click to toggle source</span>
|
324
|
-
</div>
|
325
|
-
|
326
|
-
|
327
|
-
<div class="method-description">
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
<div class="method-source-code" id="doc_count_totals-source">
|
334
|
-
<pre>
|
335
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 62</span>
|
336
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">doc_count_totals</span>
|
337
|
-
<span class="ruby-ivar">@doc_count_totals</span> <span class="ruby-operator">||=</span> <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">doc_count_totals</span>
|
338
|
-
<span class="ruby-keyword">end</span></pre>
|
339
|
-
</div><!-- doc_count_totals-source -->
|
340
|
-
|
341
|
-
</div>
|
342
|
-
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
</div><!-- doc_count_totals-method -->
|
347
|
-
|
348
|
-
|
349
|
-
<div id="get_word_probs-method" class="method-detail ">
|
350
|
-
<a name="method-i-get_word_probs"></a>
|
351
|
-
|
352
|
-
|
353
|
-
<div class="method-heading">
|
354
|
-
<span class="method-name">get_word_probs</span><span
|
355
|
-
class="method-args">(word, classnames)</span>
|
356
|
-
<span class="method-click-advice">click to toggle source</span>
|
357
|
-
</div>
|
358
|
-
|
359
|
-
|
360
|
-
<div class="method-description">
|
361
|
-
|
362
|
-
|
363
|
-
|
364
|
-
|
365
|
-
|
366
|
-
<div class="method-source-code" id="get_word_probs-source">
|
367
|
-
<pre>
|
368
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 48</span>
|
369
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">get_word_probs</span>(<span class="ruby-identifier">word</span>, <span class="ruby-identifier">classnames</span>)
|
370
|
-
<span class="ruby-identifier">probs</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> <span class="ruby-value">0</span>
|
371
|
-
<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">get_word_counts</span>(<span class="ruby-identifier">word</span>).<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">probs</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-identifier">v</span> <span class="ruby-keyword">if</span> <span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">include?</span> <span class="ruby-identifier">k</span> }
|
372
|
-
<span class="ruby-identifier">vs</span> = <span class="ruby-identifier">vocab_sizes</span>
|
373
|
-
<span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">cn</span><span class="ruby-operator">|</span>
|
374
|
-
<span class="ruby-comment"># if we've never seen the class, the word prob is 0</span>
|
375
|
-
<span class="ruby-keyword">next</span> <span class="ruby-keyword">unless</span> <span class="ruby-identifier">vs</span>.<span class="ruby-identifier">has_key?</span> <span class="ruby-identifier">cn</span>
|
376
|
-
|
377
|
-
<span class="ruby-comment"># use a laplacian smoother</span>
|
378
|
-
<span class="ruby-identifier">probs</span>[<span class="ruby-identifier">cn</span>] = (<span class="ruby-identifier">probs</span>[<span class="ruby-identifier">cn</span>] <span class="ruby-operator">+</span> <span class="ruby-value">1</span>).<span class="ruby-identifier">to_f</span> <span class="ruby-operator">/</span> (<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">get_total_word_count</span>(<span class="ruby-identifier">cn</span>) <span class="ruby-operator">+</span> <span class="ruby-identifier">vs</span>[<span class="ruby-identifier">cn</span>]).<span class="ruby-identifier">to_f</span>
|
379
|
-
}
|
380
|
-
<span class="ruby-identifier">probs</span>
|
381
|
-
<span class="ruby-keyword">end</span></pre>
|
382
|
-
</div><!-- get_word_probs-source -->
|
383
|
-
|
384
|
-
</div>
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
</div><!-- get_word_probs-method -->
|
390
|
-
|
391
|
-
|
392
|
-
<div id="vocab_sizes-method" class="method-detail ">
|
393
|
-
<a name="method-i-vocab_sizes"></a>
|
394
|
-
|
395
|
-
|
396
|
-
<div class="method-heading">
|
397
|
-
<span class="method-name">vocab_sizes</span><span
|
398
|
-
class="method-args">()</span>
|
399
|
-
<span class="method-click-advice">click to toggle source</span>
|
400
|
-
</div>
|
401
|
-
|
402
|
-
|
403
|
-
<div class="method-description">
|
404
|
-
|
405
|
-
|
406
|
-
|
407
|
-
|
408
|
-
|
409
|
-
<div class="method-source-code" id="vocab_sizes-source">
|
410
|
-
<pre>
|
411
|
-
<span class="ruby-comment"># File lib/ankusa/classifier.rb, line 66</span>
|
412
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">vocab_sizes</span>
|
413
|
-
<span class="ruby-ivar">@vocab_sizes</span> <span class="ruby-operator">||=</span> <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">get_vocabulary_sizes</span>
|
414
|
-
<span class="ruby-keyword">end</span></pre>
|
415
|
-
</div><!-- vocab_sizes-source -->
|
416
|
-
|
417
|
-
</div>
|
418
|
-
|
419
|
-
|
420
|
-
|
421
|
-
|
422
|
-
</div><!-- vocab_sizes-method -->
|
423
|
-
|
424
|
-
|
425
|
-
</div><!-- protected-instance-method-details -->
|
426
|
-
|
427
|
-
</div><!-- 5Buntitled-5D -->
|
428
|
-
|
429
|
-
|
430
|
-
</div><!-- documentation -->
|
431
|
-
|
432
|
-
<div id="validator-badges">
|
433
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
434
|
-
<p><small>Generated with the <a href="http://deveiate.org/projects/Darkfish-Rdoc/">Darkfish
|
435
|
-
Rdoc Generator</a> 2</small>.</p>
|
436
|
-
</div>
|
437
|
-
|
438
|
-
</body>
|
439
|
-
</html>
|
440
|
-
|
@@ -1,376 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
-
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
|
3
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
4
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
5
|
-
<head>
|
6
|
-
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type" />
|
7
|
-
|
8
|
-
<title>Class: Ankusa::FileSystemStorage</title>
|
9
|
-
|
10
|
-
<link rel="stylesheet" href="../rdoc.css" type="text/css" media="screen" />
|
11
|
-
|
12
|
-
<script src="../js/jquery.js" type="text/javascript" charset="utf-8"></script>
|
13
|
-
<script src="../js/thickbox-compressed.js" type="text/javascript" charset="utf-8"></script>
|
14
|
-
<script src="../js/quicksearch.js" type="text/javascript" charset="utf-8"></script>
|
15
|
-
<script src="../js/darkfish.js" type="text/javascript" charset="utf-8"></script>
|
16
|
-
|
17
|
-
</head>
|
18
|
-
<body id="top" class="class">
|
19
|
-
|
20
|
-
<div id="metadata">
|
21
|
-
<div id="home-metadata">
|
22
|
-
<div id="home-section" class="section">
|
23
|
-
<h3 class="section-header">
|
24
|
-
<a href="../index.html">Home</a>
|
25
|
-
<a href="../index.html#classes">Classes</a>
|
26
|
-
<a href="../index.html#methods">Methods</a>
|
27
|
-
</h3>
|
28
|
-
</div>
|
29
|
-
</div>
|
30
|
-
|
31
|
-
<div id="file-metadata">
|
32
|
-
<div id="file-list-section" class="section">
|
33
|
-
<h3 class="section-header">In Files</h3>
|
34
|
-
<div class="section-body">
|
35
|
-
<ul>
|
36
|
-
|
37
|
-
<li><a href="../lib/ankusa/file_system_storage_rb.html?TB_iframe=true&height=550&width=785"
|
38
|
-
class="thickbox" title="lib/ankusa/file_system_storage.rb">lib/ankusa/file_system_storage.rb</a></li>
|
39
|
-
|
40
|
-
</ul>
|
41
|
-
</div>
|
42
|
-
</div>
|
43
|
-
|
44
|
-
|
45
|
-
</div>
|
46
|
-
|
47
|
-
<div id="class-metadata">
|
48
|
-
|
49
|
-
<!-- Parent Class -->
|
50
|
-
<div id="parent-class-section" class="section">
|
51
|
-
<h3 class="section-header">Parent</h3>
|
52
|
-
|
53
|
-
<p class="link">MemoryStorage</p>
|
54
|
-
|
55
|
-
</div>
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
<!-- Method Quickref -->
|
64
|
-
<div id="method-list-section" class="section">
|
65
|
-
<h3 class="section-header">Methods</h3>
|
66
|
-
<ul class="link-list">
|
67
|
-
|
68
|
-
<li><a href="#method-c-new">::new</a></li>
|
69
|
-
|
70
|
-
<li><a href="#method-i-drop_tables">#drop_tables</a></li>
|
71
|
-
|
72
|
-
<li><a href="#method-i-init_tables">#init_tables</a></li>
|
73
|
-
|
74
|
-
<li><a href="#method-i-reset">#reset</a></li>
|
75
|
-
|
76
|
-
<li><a href="#method-i-save">#save</a></li>
|
77
|
-
|
78
|
-
</ul>
|
79
|
-
</div>
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
</div>
|
84
|
-
|
85
|
-
<div id="project-metadata">
|
86
|
-
|
87
|
-
|
88
|
-
<div id="fileindex-section" class="section project-section">
|
89
|
-
<h3 class="section-header">Files</h3>
|
90
|
-
<ul>
|
91
|
-
|
92
|
-
<li class="file"><a href="../README_rdoc.html">README.rdoc</a></li>
|
93
|
-
|
94
|
-
</ul>
|
95
|
-
</div>
|
96
|
-
|
97
|
-
|
98
|
-
<div id="classindex-section" class="section project-section">
|
99
|
-
<h3 class="section-header">Class/Module Index
|
100
|
-
<span class="search-toggle"><img src="../images/find.png"
|
101
|
-
height="16" width="16" alt="[+]"
|
102
|
-
title="show/hide quicksearch" /></span></h3>
|
103
|
-
<form action="#" method="get" accept-charset="utf-8" class="initially-hidden">
|
104
|
-
<fieldset>
|
105
|
-
<legend>Quicksearch</legend>
|
106
|
-
<input type="text" name="quicksearch" value=""
|
107
|
-
class="quicksearch-field" />
|
108
|
-
</fieldset>
|
109
|
-
</form>
|
110
|
-
|
111
|
-
<ul class="link-list">
|
112
|
-
|
113
|
-
<li><a href="../Ankusa.html">Ankusa</a></li>
|
114
|
-
|
115
|
-
<li><a href="../Ankusa/CassandraStorage.html">Ankusa::CassandraStorage</a></li>
|
116
|
-
|
117
|
-
<li><a href="../Ankusa/Classifier.html">Ankusa::Classifier</a></li>
|
118
|
-
|
119
|
-
<li><a href="../Ankusa/FileSystemStorage.html">Ankusa::FileSystemStorage</a></li>
|
120
|
-
|
121
|
-
<li><a href="../Ankusa/HBaseStorage.html">Ankusa::HBaseStorage</a></li>
|
122
|
-
|
123
|
-
<li><a href="../Ankusa/KLDivergenceClassifier.html">Ankusa::KLDivergenceClassifier</a></li>
|
124
|
-
|
125
|
-
<li><a href="../Ankusa/MemoryStorage.html">Ankusa::MemoryStorage</a></li>
|
126
|
-
|
127
|
-
<li><a href="../Ankusa/NaiveBayesClassifier.html">Ankusa::NaiveBayesClassifier</a></li>
|
128
|
-
|
129
|
-
<li><a href="../Ankusa/TextHash.html">Ankusa::TextHash</a></li>
|
130
|
-
|
131
|
-
<li><a href="../String.html">String</a></li>
|
132
|
-
|
133
|
-
</ul>
|
134
|
-
<div id="no-class-search-results" style="display: none;">No matching classes.</div>
|
135
|
-
</div>
|
136
|
-
|
137
|
-
|
138
|
-
</div>
|
139
|
-
</div>
|
140
|
-
|
141
|
-
<div id="documentation">
|
142
|
-
<h1 class="class">Ankusa::FileSystemStorage</h1>
|
143
|
-
|
144
|
-
<div id="description" class="description">
|
145
|
-
|
146
|
-
</div><!-- description -->
|
147
|
-
|
148
|
-
|
149
|
-
<div id="5Buntitled-5D" class="documentation-section">
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
|
157
|
-
|
158
|
-
<!-- Methods -->
|
159
|
-
|
160
|
-
<div id="public-class-method-details" class="method-section section">
|
161
|
-
<h3 class="section-header">Public Class Methods</h3>
|
162
|
-
|
163
|
-
|
164
|
-
<div id="new-method" class="method-detail ">
|
165
|
-
<a name="method-c-new"></a>
|
166
|
-
|
167
|
-
|
168
|
-
<div class="method-heading">
|
169
|
-
<span class="method-name">new</span><span
|
170
|
-
class="method-args">(file)</span>
|
171
|
-
<span class="method-click-advice">click to toggle source</span>
|
172
|
-
</div>
|
173
|
-
|
174
|
-
|
175
|
-
<div class="method-description">
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
<div class="method-source-code" id="new-source">
|
182
|
-
<pre>
|
183
|
-
<span class="ruby-comment"># File lib/ankusa/file_system_storage.rb, line 7</span>
|
184
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">file</span>)
|
185
|
-
<span class="ruby-ivar">@file</span> = <span class="ruby-identifier">file</span>
|
186
|
-
<span class="ruby-identifier">init_tables</span>
|
187
|
-
<span class="ruby-keyword">end</span></pre>
|
188
|
-
</div><!-- new-source -->
|
189
|
-
|
190
|
-
</div>
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
</div><!-- new-method -->
|
196
|
-
|
197
|
-
|
198
|
-
</div><!-- public-class-method-details -->
|
199
|
-
|
200
|
-
<div id="public-instance-method-details" class="method-section section">
|
201
|
-
<h3 class="section-header">Public Instance Methods</h3>
|
202
|
-
|
203
|
-
|
204
|
-
<div id="drop_tables-method" class="method-detail ">
|
205
|
-
<a name="method-i-drop_tables"></a>
|
206
|
-
|
207
|
-
|
208
|
-
<div class="method-heading">
|
209
|
-
<span class="method-name">drop_tables</span><span
|
210
|
-
class="method-args">()</span>
|
211
|
-
<span class="method-click-advice">click to toggle source</span>
|
212
|
-
</div>
|
213
|
-
|
214
|
-
|
215
|
-
<div class="method-description">
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
|
221
|
-
<div class="method-source-code" id="drop_tables-source">
|
222
|
-
<pre>
|
223
|
-
<span class="ruby-comment"># File lib/ankusa/file_system_storage.rb, line 20</span>
|
224
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">drop_tables</span>
|
225
|
-
<span class="ruby-constant">File</span>.<span class="ruby-identifier">delete</span>(<span class="ruby-ivar">@file</span>) <span class="ruby-keyword">rescue</span> <span class="ruby-constant">Errno</span><span class="ruby-operator">::</span><span class="ruby-constant">ENOENT</span>
|
226
|
-
<span class="ruby-identifier">reset</span>
|
227
|
-
<span class="ruby-keyword">end</span></pre>
|
228
|
-
</div><!-- drop_tables-source -->
|
229
|
-
|
230
|
-
</div>
|
231
|
-
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
</div><!-- drop_tables-method -->
|
236
|
-
|
237
|
-
|
238
|
-
<div id="init_tables-method" class="method-detail ">
|
239
|
-
<a name="method-i-init_tables"></a>
|
240
|
-
|
241
|
-
|
242
|
-
<div class="method-heading">
|
243
|
-
<span class="method-name">init_tables</span><span
|
244
|
-
class="method-args">()</span>
|
245
|
-
<span class="method-click-advice">click to toggle source</span>
|
246
|
-
</div>
|
247
|
-
|
248
|
-
|
249
|
-
<div class="method-description">
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
|
254
|
-
|
255
|
-
<div class="method-source-code" id="init_tables-source">
|
256
|
-
<pre>
|
257
|
-
<span class="ruby-comment"># File lib/ankusa/file_system_storage.rb, line 25</span>
|
258
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">init_tables</span>
|
259
|
-
<span class="ruby-identifier">data</span> = {}
|
260
|
-
<span class="ruby-keyword">begin</span>
|
261
|
-
<span class="ruby-constant">File</span>.<span class="ruby-identifier">open</span>(<span class="ruby-ivar">@file</span>) <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">f</span><span class="ruby-operator">|</span>
|
262
|
-
<span class="ruby-identifier">data</span> = <span class="ruby-constant">Marshal</span>.<span class="ruby-identifier">load</span>(<span class="ruby-identifier">f</span>)
|
263
|
-
<span class="ruby-keyword">end</span>
|
264
|
-
<span class="ruby-ivar">@freqs</span> = <span class="ruby-identifier">data</span>[<span class="ruby-value">:freqs</span>]
|
265
|
-
<span class="ruby-ivar">@total_word_counts</span> = <span class="ruby-identifier">data</span>[<span class="ruby-value">:total_word_counts</span>]
|
266
|
-
<span class="ruby-ivar">@total_doc_counts</span> = <span class="ruby-identifier">data</span>[<span class="ruby-value">:total_doc_counts</span>]
|
267
|
-
<span class="ruby-ivar">@klass_word_counts</span> = <span class="ruby-identifier">data</span>[<span class="ruby-value">:klass_word_counts</span>]
|
268
|
-
<span class="ruby-ivar">@klass_doc_counts</span> = <span class="ruby-identifier">data</span>[<span class="ruby-value">:klass_word_counts</span>]
|
269
|
-
<span class="ruby-keyword">rescue</span> <span class="ruby-constant">Errno</span><span class="ruby-operator">::</span><span class="ruby-constant">ENOENT</span>
|
270
|
-
<span class="ruby-identifier">reset</span>
|
271
|
-
<span class="ruby-keyword">end</span>
|
272
|
-
<span class="ruby-keyword">end</span></pre>
|
273
|
-
</div><!-- init_tables-source -->
|
274
|
-
|
275
|
-
</div>
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
</div><!-- init_tables-method -->
|
281
|
-
|
282
|
-
|
283
|
-
<div id="reset-method" class="method-detail ">
|
284
|
-
<a name="method-i-reset"></a>
|
285
|
-
|
286
|
-
|
287
|
-
<div class="method-heading">
|
288
|
-
<span class="method-name">reset</span><span
|
289
|
-
class="method-args">()</span>
|
290
|
-
<span class="method-click-advice">click to toggle source</span>
|
291
|
-
</div>
|
292
|
-
|
293
|
-
|
294
|
-
<div class="method-description">
|
295
|
-
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
<div class="method-source-code" id="reset-source">
|
301
|
-
<pre>
|
302
|
-
<span class="ruby-comment"># File lib/ankusa/file_system_storage.rb, line 12</span>
|
303
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">reset</span>
|
304
|
-
<span class="ruby-ivar">@freqs</span> = {}
|
305
|
-
<span class="ruby-ivar">@total_word_counts</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-value">0</span>)
|
306
|
-
<span class="ruby-ivar">@total_doc_counts</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-value">0</span>)
|
307
|
-
<span class="ruby-ivar">@klass_word_counts</span> = {}
|
308
|
-
<span class="ruby-ivar">@klass_doc_counts</span> = {}
|
309
|
-
<span class="ruby-keyword">end</span></pre>
|
310
|
-
</div><!-- reset-source -->
|
311
|
-
|
312
|
-
</div>
|
313
|
-
|
314
|
-
|
315
|
-
|
316
|
-
|
317
|
-
</div><!-- reset-method -->
|
318
|
-
|
319
|
-
|
320
|
-
<div id="save-method" class="method-detail ">
|
321
|
-
<a name="method-i-save"></a>
|
322
|
-
|
323
|
-
|
324
|
-
<div class="method-heading">
|
325
|
-
<span class="method-name">save</span><span
|
326
|
-
class="method-args">(file = nil)</span>
|
327
|
-
<span class="method-click-advice">click to toggle source</span>
|
328
|
-
</div>
|
329
|
-
|
330
|
-
|
331
|
-
<div class="method-description">
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
-
<div class="method-source-code" id="save-source">
|
338
|
-
<pre>
|
339
|
-
<span class="ruby-comment"># File lib/ankusa/file_system_storage.rb, line 41</span>
|
340
|
-
<span class="ruby-keyword">def</span> <span class="ruby-identifier">save</span>(<span class="ruby-identifier">file</span> = <span class="ruby-keyword">nil</span>)
|
341
|
-
<span class="ruby-identifier">file</span> <span class="ruby-operator">||=</span> <span class="ruby-ivar">@file</span>
|
342
|
-
<span class="ruby-identifier">data</span> = { <span class="ruby-value">:freqs</span> =<span class="ruby-operator">></span> <span class="ruby-ivar">@freqs</span>,
|
343
|
-
<span class="ruby-value">:total_word_counts</span> =<span class="ruby-operator">></span> <span class="ruby-ivar">@total_word_counts</span>,
|
344
|
-
<span class="ruby-value">:total_doc_counts</span> =<span class="ruby-operator">></span> <span class="ruby-ivar">@total_doc_counts</span>,
|
345
|
-
<span class="ruby-value">:klass_word_counts</span> =<span class="ruby-operator">></span> <span class="ruby-ivar">@klass_word_counts</span>,
|
346
|
-
<span class="ruby-value">:klass_doc_counts</span> =<span class="ruby-operator">></span> <span class="ruby-ivar">@klass_doc_counts</span> }
|
347
|
-
<span class="ruby-constant">File</span>.<span class="ruby-identifier">open</span>(<span class="ruby-identifier">file</span>, <span class="ruby-string">'w+'</span>) <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">f</span><span class="ruby-operator">|</span>
|
348
|
-
<span class="ruby-constant">Marshal</span>.<span class="ruby-identifier">dump</span>(<span class="ruby-identifier">data</span>, <span class="ruby-identifier">f</span>)
|
349
|
-
<span class="ruby-keyword">end</span>
|
350
|
-
<span class="ruby-keyword">end</span></pre>
|
351
|
-
</div><!-- save-source -->
|
352
|
-
|
353
|
-
</div>
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
</div><!-- save-method -->
|
359
|
-
|
360
|
-
|
361
|
-
</div><!-- public-instance-method-details -->
|
362
|
-
|
363
|
-
</div><!-- 5Buntitled-5D -->
|
364
|
-
|
365
|
-
|
366
|
-
</div><!-- documentation -->
|
367
|
-
|
368
|
-
<div id="validator-badges">
|
369
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
370
|
-
<p><small>Generated with the <a href="http://deveiate.org/projects/Darkfish-Rdoc/">Darkfish
|
371
|
-
Rdoc Generator</a> 2</small>.</p>
|
372
|
-
</div>
|
373
|
-
|
374
|
-
</body>
|
375
|
-
</html>
|
376
|
-
|