ankusa 0.0.8 → 0.0.9
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +2 -1
- data/Rakefile +4 -26
- data/lib/ankusa.rb +1 -0
- data/lib/ankusa/classifier.rb +3 -0
- data/lib/ankusa/naive_bayes.rb +8 -4
- data/lib/ankusa/version.rb +3 -0
- metadata +6 -33
- data/docs/classes/Ankusa.html +0 -182
- data/docs/classes/Ankusa/CassandraStorage.html +0 -615
- data/docs/classes/Ankusa/Classifier.html +0 -315
- data/docs/classes/Ankusa/FileSystemStorage.html +0 -272
- data/docs/classes/Ankusa/HBaseStorage.html +0 -594
- data/docs/classes/Ankusa/KLDivergenceClassifier.html +0 -194
- data/docs/classes/Ankusa/MemoryStorage.html +0 -467
- data/docs/classes/Ankusa/NaiveBayesClassifier.html +0 -231
- data/docs/classes/Ankusa/TextHash.html +0 -275
- data/docs/classes/String.html +0 -172
- data/docs/created.rid +0 -1
- data/docs/files/README_rdoc.html +0 -294
- data/docs/files/lib/ankusa/cassandra_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/classifier_rb.html +0 -101
- data/docs/files/lib/ankusa/extensions_rb.html +0 -108
- data/docs/files/lib/ankusa/file_system_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/hasher_rb.html +0 -109
- data/docs/files/lib/ankusa/hbase_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/kl_divergence_rb.html +0 -101
- data/docs/files/lib/ankusa/memory_storage_rb.html +0 -101
- data/docs/files/lib/ankusa/naive_bayes_rb.html +0 -101
- data/docs/files/lib/ankusa/stopwords_rb.html +0 -101
- data/docs/files/lib/ankusa_rb.html +0 -112
- data/docs/fr_class_index.html +0 -36
- data/docs/fr_file_index.html +0 -38
- data/docs/fr_method_index.html +0 -95
- data/docs/index.html +0 -24
- data/docs/rdoc-style.css +0 -208
@@ -1,194 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="iso-8859-1"?>
|
2
|
-
<!DOCTYPE html
|
3
|
-
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
4
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
5
|
-
|
6
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
7
|
-
<head>
|
8
|
-
<title>Class: Ankusa::KLDivergenceClassifier</title>
|
9
|
-
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
|
10
|
-
<meta http-equiv="Content-Script-Type" content="text/javascript" />
|
11
|
-
<link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
|
12
|
-
<script type="text/javascript">
|
13
|
-
// <![CDATA[
|
14
|
-
|
15
|
-
function popupCode( url ) {
|
16
|
-
window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
|
17
|
-
}
|
18
|
-
|
19
|
-
function toggleCode( id ) {
|
20
|
-
if ( document.getElementById )
|
21
|
-
elem = document.getElementById( id );
|
22
|
-
else if ( document.all )
|
23
|
-
elem = eval( "document.all." + id );
|
24
|
-
else
|
25
|
-
return false;
|
26
|
-
|
27
|
-
elemStyle = elem.style;
|
28
|
-
|
29
|
-
if ( elemStyle.display != "block" ) {
|
30
|
-
elemStyle.display = "block"
|
31
|
-
} else {
|
32
|
-
elemStyle.display = "none"
|
33
|
-
}
|
34
|
-
|
35
|
-
return true;
|
36
|
-
}
|
37
|
-
|
38
|
-
// Make codeblocks hidden by default
|
39
|
-
document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }</style>" )
|
40
|
-
|
41
|
-
// ]]>
|
42
|
-
</script>
|
43
|
-
|
44
|
-
</head>
|
45
|
-
<body>
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
<div id="classHeader">
|
50
|
-
<table class="header-table">
|
51
|
-
<tr class="top-aligned-row">
|
52
|
-
<td><strong>Class</strong></td>
|
53
|
-
<td class="class-name-in-header">Ankusa::KLDivergenceClassifier</td>
|
54
|
-
</tr>
|
55
|
-
<tr class="top-aligned-row">
|
56
|
-
<td><strong>In:</strong></td>
|
57
|
-
<td>
|
58
|
-
<a href="../../files/lib/ankusa/kl_divergence_rb.html">
|
59
|
-
lib/ankusa/kl_divergence.rb
|
60
|
-
</a>
|
61
|
-
<br />
|
62
|
-
</td>
|
63
|
-
</tr>
|
64
|
-
|
65
|
-
<tr class="top-aligned-row">
|
66
|
-
<td><strong>Parent:</strong></td>
|
67
|
-
<td>
|
68
|
-
Object
|
69
|
-
</td>
|
70
|
-
</tr>
|
71
|
-
</table>
|
72
|
-
</div>
|
73
|
-
<!-- banner header -->
|
74
|
-
|
75
|
-
<div id="bodyContent">
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
<div id="contextContent">
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
</div>
|
84
|
-
|
85
|
-
<div id="method-list">
|
86
|
-
<h3 class="section-bar">Methods</h3>
|
87
|
-
|
88
|
-
<div class="name-list">
|
89
|
-
<a href="#M000041">classify</a>
|
90
|
-
<a href="#M000042">distances</a>
|
91
|
-
</div>
|
92
|
-
</div>
|
93
|
-
|
94
|
-
</div>
|
95
|
-
|
96
|
-
|
97
|
-
<!-- if includes -->
|
98
|
-
<div id="includes">
|
99
|
-
<h3 class="section-bar">Included Modules</h3>
|
100
|
-
|
101
|
-
<div id="includes-list">
|
102
|
-
<span class="include-name"><a href="Classifier.html">Classifier</a></span>
|
103
|
-
</div>
|
104
|
-
</div>
|
105
|
-
|
106
|
-
<div id="section">
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
<!-- if method_list -->
|
116
|
-
<div id="methods">
|
117
|
-
<h3 class="section-bar">Public Instance methods</h3>
|
118
|
-
|
119
|
-
<div id="method-M000041" class="method-detail">
|
120
|
-
<a name="M000041"></a>
|
121
|
-
|
122
|
-
<div class="method-heading">
|
123
|
-
<a href="#M000041" class="method-signature">
|
124
|
-
<span class="method-name">classify</span><span class="method-args">(text, classes=nil)</span>
|
125
|
-
</a>
|
126
|
-
</div>
|
127
|
-
|
128
|
-
<div class="method-description">
|
129
|
-
<p><a class="source-toggle" href="#"
|
130
|
-
onclick="toggleCode('M000041-source');return false;">[Source]</a></p>
|
131
|
-
<div class="method-source-code" id="M000041-source">
|
132
|
-
<pre>
|
133
|
-
<span class="ruby-comment cmt"># File lib/ankusa/kl_divergence.rb, line 6</span>
|
134
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classify</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classes</span>=<span class="ruby-keyword kw">nil</span>)
|
135
|
-
<span class="ruby-comment cmt"># return the class with the least distance from the word</span>
|
136
|
-
<span class="ruby-comment cmt"># distribution of the given text</span>
|
137
|
-
<span class="ruby-identifier">distances</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classes</span>).<span class="ruby-identifier">sort_by</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">c</span><span class="ruby-operator">|</span> <span class="ruby-identifier">c</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">first</span>.<span class="ruby-identifier">first</span>
|
138
|
-
<span class="ruby-keyword kw">end</span>
|
139
|
-
</pre>
|
140
|
-
</div>
|
141
|
-
</div>
|
142
|
-
</div>
|
143
|
-
|
144
|
-
<div id="method-M000042" class="method-detail">
|
145
|
-
<a name="M000042"></a>
|
146
|
-
|
147
|
-
<div class="method-heading">
|
148
|
-
<a href="#M000042" class="method-signature">
|
149
|
-
<span class="method-name">distances</span><span class="method-args">(text, classnames=nil)</span>
|
150
|
-
</a>
|
151
|
-
</div>
|
152
|
-
|
153
|
-
<div class="method-description">
|
154
|
-
<p>
|
155
|
-
Classes is an array of classes to look at
|
156
|
-
</p>
|
157
|
-
<p><a class="source-toggle" href="#"
|
158
|
-
onclick="toggleCode('M000042-source');return false;">[Source]</a></p>
|
159
|
-
<div class="method-source-code" id="M000042-source">
|
160
|
-
<pre>
|
161
|
-
<span class="ruby-comment cmt"># File lib/ankusa/kl_divergence.rb, line 14</span>
|
162
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">distances</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classnames</span>=<span class="ruby-keyword kw">nil</span>)
|
163
|
-
<span class="ruby-identifier">classnames</span> <span class="ruby-operator">||=</span> <span class="ruby-ivar">@classnames</span>
|
164
|
-
<span class="ruby-identifier">distances</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> <span class="ruby-value">0</span>
|
165
|
-
|
166
|
-
<span class="ruby-identifier">th</span> = <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">text</span>)
|
167
|
-
<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>
|
168
|
-
<span class="ruby-identifier">thprob</span> = <span class="ruby-identifier">count</span>.<span class="ruby-identifier">to_f</span> <span class="ruby-operator">/</span> <span class="ruby-identifier">th</span>.<span class="ruby-identifier">length</span>.<span class="ruby-identifier">to_f</span>
|
169
|
-
<span class="ruby-identifier">probs</span> = <span class="ruby-identifier">get_word_probs</span>(<span class="ruby-identifier">word</span>, <span class="ruby-identifier">classnames</span>)
|
170
|
-
<span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span>
|
171
|
-
<span class="ruby-identifier">distances</span>[<span class="ruby-identifier">k</span>] <span class="ruby-operator">+=</span> (<span class="ruby-identifier">thprob</span> <span class="ruby-operator">*</span> <span class="ruby-constant">Math</span>.<span class="ruby-identifier">log</span>(<span class="ruby-identifier">thprob</span> <span class="ruby-operator">/</span> <span class="ruby-identifier">probs</span>[<span class="ruby-identifier">k</span>]) <span class="ruby-operator">*</span> <span class="ruby-identifier">count</span>)
|
172
|
-
}
|
173
|
-
}
|
174
|
-
|
175
|
-
<span class="ruby-identifier">distances</span>
|
176
|
-
<span class="ruby-keyword kw">end</span>
|
177
|
-
</pre>
|
178
|
-
</div>
|
179
|
-
</div>
|
180
|
-
</div>
|
181
|
-
|
182
|
-
|
183
|
-
</div>
|
184
|
-
|
185
|
-
|
186
|
-
</div>
|
187
|
-
|
188
|
-
|
189
|
-
<div id="validator-badges">
|
190
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
191
|
-
</div>
|
192
|
-
|
193
|
-
</body>
|
194
|
-
</html>
|
@@ -1,467 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="iso-8859-1"?>
|
2
|
-
<!DOCTYPE html
|
3
|
-
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
4
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
5
|
-
|
6
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
7
|
-
<head>
|
8
|
-
<title>Class: Ankusa::MemoryStorage</title>
|
9
|
-
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
|
10
|
-
<meta http-equiv="Content-Script-Type" content="text/javascript" />
|
11
|
-
<link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
|
12
|
-
<script type="text/javascript">
|
13
|
-
// <![CDATA[
|
14
|
-
|
15
|
-
function popupCode( url ) {
|
16
|
-
window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
|
17
|
-
}
|
18
|
-
|
19
|
-
function toggleCode( id ) {
|
20
|
-
if ( document.getElementById )
|
21
|
-
elem = document.getElementById( id );
|
22
|
-
else if ( document.all )
|
23
|
-
elem = eval( "document.all." + id );
|
24
|
-
else
|
25
|
-
return false;
|
26
|
-
|
27
|
-
elemStyle = elem.style;
|
28
|
-
|
29
|
-
if ( elemStyle.display != "block" ) {
|
30
|
-
elemStyle.display = "block"
|
31
|
-
} else {
|
32
|
-
elemStyle.display = "none"
|
33
|
-
}
|
34
|
-
|
35
|
-
return true;
|
36
|
-
}
|
37
|
-
|
38
|
-
// Make codeblocks hidden by default
|
39
|
-
document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }</style>" )
|
40
|
-
|
41
|
-
// ]]>
|
42
|
-
</script>
|
43
|
-
|
44
|
-
</head>
|
45
|
-
<body>
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
<div id="classHeader">
|
50
|
-
<table class="header-table">
|
51
|
-
<tr class="top-aligned-row">
|
52
|
-
<td><strong>Class</strong></td>
|
53
|
-
<td class="class-name-in-header">Ankusa::MemoryStorage</td>
|
54
|
-
</tr>
|
55
|
-
<tr class="top-aligned-row">
|
56
|
-
<td><strong>In:</strong></td>
|
57
|
-
<td>
|
58
|
-
<a href="../../files/lib/ankusa/memory_storage_rb.html">
|
59
|
-
lib/ankusa/memory_storage.rb
|
60
|
-
</a>
|
61
|
-
<br />
|
62
|
-
</td>
|
63
|
-
</tr>
|
64
|
-
|
65
|
-
<tr class="top-aligned-row">
|
66
|
-
<td><strong>Parent:</strong></td>
|
67
|
-
<td>
|
68
|
-
Object
|
69
|
-
</td>
|
70
|
-
</tr>
|
71
|
-
</table>
|
72
|
-
</div>
|
73
|
-
<!-- banner header -->
|
74
|
-
|
75
|
-
<div id="bodyContent">
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
<div id="contextContent">
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
</div>
|
84
|
-
|
85
|
-
<div id="method-list">
|
86
|
-
<h3 class="section-bar">Methods</h3>
|
87
|
-
|
88
|
-
<div class="name-list">
|
89
|
-
<a href="#M000028">classnames</a>
|
90
|
-
<a href="#M000040">close</a>
|
91
|
-
<a href="#M000039">doc_count_totals</a>
|
92
|
-
<a href="#M000030">drop_tables</a>
|
93
|
-
<a href="#M000035">get_doc_count</a>
|
94
|
-
<a href="#M000034">get_total_word_count</a>
|
95
|
-
<a href="#M000032">get_vocabulary_sizes</a>
|
96
|
-
<a href="#M000033">get_word_counts</a>
|
97
|
-
<a href="#M000038">incr_doc_count</a>
|
98
|
-
<a href="#M000037">incr_total_word_count</a>
|
99
|
-
<a href="#M000036">incr_word_count</a>
|
100
|
-
<a href="#M000031">init_tables</a>
|
101
|
-
<a href="#M000027">new</a>
|
102
|
-
<a href="#M000029">reset</a>
|
103
|
-
</div>
|
104
|
-
</div>
|
105
|
-
|
106
|
-
</div>
|
107
|
-
|
108
|
-
|
109
|
-
<!-- if includes -->
|
110
|
-
|
111
|
-
<div id="section">
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
<!-- if method_list -->
|
121
|
-
<div id="methods">
|
122
|
-
<h3 class="section-bar">Public Class methods</h3>
|
123
|
-
|
124
|
-
<div id="method-M000027" class="method-detail">
|
125
|
-
<a name="M000027"></a>
|
126
|
-
|
127
|
-
<div class="method-heading">
|
128
|
-
<a href="#M000027" class="method-signature">
|
129
|
-
<span class="method-name">new</span><span class="method-args">()</span>
|
130
|
-
</a>
|
131
|
-
</div>
|
132
|
-
|
133
|
-
<div class="method-description">
|
134
|
-
<p><a class="source-toggle" href="#"
|
135
|
-
onclick="toggleCode('M000027-source');return false;">[Source]</a></p>
|
136
|
-
<div class="method-source-code" id="M000027-source">
|
137
|
-
<pre>
|
138
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 4</span>
|
139
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>
|
140
|
-
<span class="ruby-identifier">init_tables</span>
|
141
|
-
<span class="ruby-keyword kw">end</span>
|
142
|
-
</pre>
|
143
|
-
</div>
|
144
|
-
</div>
|
145
|
-
</div>
|
146
|
-
|
147
|
-
<h3 class="section-bar">Public Instance methods</h3>
|
148
|
-
|
149
|
-
<div id="method-M000028" class="method-detail">
|
150
|
-
<a name="M000028"></a>
|
151
|
-
|
152
|
-
<div class="method-heading">
|
153
|
-
<a href="#M000028" class="method-signature">
|
154
|
-
<span class="method-name">classnames</span><span class="method-args">()</span>
|
155
|
-
</a>
|
156
|
-
</div>
|
157
|
-
|
158
|
-
<div class="method-description">
|
159
|
-
<p><a class="source-toggle" href="#"
|
160
|
-
onclick="toggleCode('M000028-source');return false;">[Source]</a></p>
|
161
|
-
<div class="method-source-code" id="M000028-source">
|
162
|
-
<pre>
|
163
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 8</span>
|
164
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classnames</span>
|
165
|
-
<span class="ruby-ivar">@total_doc_counts</span>.<span class="ruby-identifier">keys</span>
|
166
|
-
<span class="ruby-keyword kw">end</span>
|
167
|
-
</pre>
|
168
|
-
</div>
|
169
|
-
</div>
|
170
|
-
</div>
|
171
|
-
|
172
|
-
<div id="method-M000040" class="method-detail">
|
173
|
-
<a name="M000040"></a>
|
174
|
-
|
175
|
-
<div class="method-heading">
|
176
|
-
<a href="#M000040" class="method-signature">
|
177
|
-
<span class="method-name">close</span><span class="method-args">()</span>
|
178
|
-
</a>
|
179
|
-
</div>
|
180
|
-
|
181
|
-
<div class="method-description">
|
182
|
-
<p><a class="source-toggle" href="#"
|
183
|
-
onclick="toggleCode('M000040-source');return false;">[Source]</a></p>
|
184
|
-
<div class="method-source-code" id="M000040-source">
|
185
|
-
<pre>
|
186
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 64</span>
|
187
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">close</span>
|
188
|
-
<span class="ruby-keyword kw">end</span>
|
189
|
-
</pre>
|
190
|
-
</div>
|
191
|
-
</div>
|
192
|
-
</div>
|
193
|
-
|
194
|
-
<div id="method-M000039" class="method-detail">
|
195
|
-
<a name="M000039"></a>
|
196
|
-
|
197
|
-
<div class="method-heading">
|
198
|
-
<a href="#M000039" class="method-signature">
|
199
|
-
<span class="method-name">doc_count_totals</span><span class="method-args">()</span>
|
200
|
-
</a>
|
201
|
-
</div>
|
202
|
-
|
203
|
-
<div class="method-description">
|
204
|
-
<p><a class="source-toggle" href="#"
|
205
|
-
onclick="toggleCode('M000039-source');return false;">[Source]</a></p>
|
206
|
-
<div class="method-source-code" id="M000039-source">
|
207
|
-
<pre>
|
208
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 60</span>
|
209
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">doc_count_totals</span>
|
210
|
-
<span class="ruby-ivar">@total_doc_counts</span>
|
211
|
-
<span class="ruby-keyword kw">end</span>
|
212
|
-
</pre>
|
213
|
-
</div>
|
214
|
-
</div>
|
215
|
-
</div>
|
216
|
-
|
217
|
-
<div id="method-M000030" class="method-detail">
|
218
|
-
<a name="M000030"></a>
|
219
|
-
|
220
|
-
<div class="method-heading">
|
221
|
-
<a href="#M000030" class="method-signature">
|
222
|
-
<span class="method-name">drop_tables</span><span class="method-args">()</span>
|
223
|
-
</a>
|
224
|
-
</div>
|
225
|
-
|
226
|
-
<div class="method-description">
|
227
|
-
<p><a class="source-toggle" href="#"
|
228
|
-
onclick="toggleCode('M000030-source');return false;">[Source]</a></p>
|
229
|
-
<div class="method-source-code" id="M000030-source">
|
230
|
-
<pre>
|
231
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 16</span>
|
232
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">drop_tables</span>
|
233
|
-
<span class="ruby-keyword kw">end</span>
|
234
|
-
</pre>
|
235
|
-
</div>
|
236
|
-
</div>
|
237
|
-
</div>
|
238
|
-
|
239
|
-
<div id="method-M000035" class="method-detail">
|
240
|
-
<a name="M000035"></a>
|
241
|
-
|
242
|
-
<div class="method-heading">
|
243
|
-
<a href="#M000035" class="method-signature">
|
244
|
-
<span class="method-name">get_doc_count</span><span class="method-args">(klass)</span>
|
245
|
-
</a>
|
246
|
-
</div>
|
247
|
-
|
248
|
-
<div class="method-description">
|
249
|
-
<p><a class="source-toggle" href="#"
|
250
|
-
onclick="toggleCode('M000035-source');return false;">[Source]</a></p>
|
251
|
-
<div class="method-source-code" id="M000035-source">
|
252
|
-
<pre>
|
253
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 43</span>
|
254
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">get_doc_count</span>(<span class="ruby-identifier">klass</span>)
|
255
|
-
<span class="ruby-ivar">@total_doc_counts</span>[<span class="ruby-identifier">klass</span>]
|
256
|
-
<span class="ruby-keyword kw">end</span>
|
257
|
-
</pre>
|
258
|
-
</div>
|
259
|
-
</div>
|
260
|
-
</div>
|
261
|
-
|
262
|
-
<div id="method-M000034" class="method-detail">
|
263
|
-
<a name="M000034"></a>
|
264
|
-
|
265
|
-
<div class="method-heading">
|
266
|
-
<a href="#M000034" class="method-signature">
|
267
|
-
<span class="method-name">get_total_word_count</span><span class="method-args">(klass)</span>
|
268
|
-
</a>
|
269
|
-
</div>
|
270
|
-
|
271
|
-
<div class="method-description">
|
272
|
-
<p><a class="source-toggle" href="#"
|
273
|
-
onclick="toggleCode('M000034-source');return false;">[Source]</a></p>
|
274
|
-
<div class="method-source-code" id="M000034-source">
|
275
|
-
<pre>
|
276
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 39</span>
|
277
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">get_total_word_count</span>(<span class="ruby-identifier">klass</span>)
|
278
|
-
<span class="ruby-ivar">@total_word_counts</span>[<span class="ruby-identifier">klass</span>]
|
279
|
-
<span class="ruby-keyword kw">end</span>
|
280
|
-
</pre>
|
281
|
-
</div>
|
282
|
-
</div>
|
283
|
-
</div>
|
284
|
-
|
285
|
-
<div id="method-M000032" class="method-detail">
|
286
|
-
<a name="M000032"></a>
|
287
|
-
|
288
|
-
<div class="method-heading">
|
289
|
-
<a href="#M000032" class="method-signature">
|
290
|
-
<span class="method-name">get_vocabulary_sizes</span><span class="method-args">()</span>
|
291
|
-
</a>
|
292
|
-
</div>
|
293
|
-
|
294
|
-
<div class="method-description">
|
295
|
-
<p><a class="source-toggle" href="#"
|
296
|
-
onclick="toggleCode('M000032-source');return false;">[Source]</a></p>
|
297
|
-
<div class="method-source-code" id="M000032-source">
|
298
|
-
<pre>
|
299
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 27</span>
|
300
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">get_vocabulary_sizes</span>
|
301
|
-
<span class="ruby-identifier">count</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> <span class="ruby-value">0</span>
|
302
|
-
<span class="ruby-ivar">@freqs</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span>, <span class="ruby-identifier">ks</span><span class="ruby-operator">|</span>
|
303
|
-
<span class="ruby-identifier">ks</span>.<span class="ruby-identifier">keys</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">count</span>[<span class="ruby-identifier">k</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> }
|
304
|
-
}
|
305
|
-
<span class="ruby-identifier">count</span>
|
306
|
-
<span class="ruby-keyword kw">end</span>
|
307
|
-
</pre>
|
308
|
-
</div>
|
309
|
-
</div>
|
310
|
-
</div>
|
311
|
-
|
312
|
-
<div id="method-M000033" class="method-detail">
|
313
|
-
<a name="M000033"></a>
|
314
|
-
|
315
|
-
<div class="method-heading">
|
316
|
-
<a href="#M000033" class="method-signature">
|
317
|
-
<span class="method-name">get_word_counts</span><span class="method-args">(word)</span>
|
318
|
-
</a>
|
319
|
-
</div>
|
320
|
-
|
321
|
-
<div class="method-description">
|
322
|
-
<p><a class="source-toggle" href="#"
|
323
|
-
onclick="toggleCode('M000033-source');return false;">[Source]</a></p>
|
324
|
-
<div class="method-source-code" id="M000033-source">
|
325
|
-
<pre>
|
326
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 35</span>
|
327
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">get_word_counts</span>(<span class="ruby-identifier">word</span>)
|
328
|
-
<span class="ruby-ivar">@freqs</span>.<span class="ruby-identifier">fetch</span> <span class="ruby-identifier">word</span>, <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-value">0</span>)
|
329
|
-
<span class="ruby-keyword kw">end</span>
|
330
|
-
</pre>
|
331
|
-
</div>
|
332
|
-
</div>
|
333
|
-
</div>
|
334
|
-
|
335
|
-
<div id="method-M000038" class="method-detail">
|
336
|
-
<a name="M000038"></a>
|
337
|
-
|
338
|
-
<div class="method-heading">
|
339
|
-
<a href="#M000038" class="method-signature">
|
340
|
-
<span class="method-name">incr_doc_count</span><span class="method-args">(klass, count)</span>
|
341
|
-
</a>
|
342
|
-
</div>
|
343
|
-
|
344
|
-
<div class="method-description">
|
345
|
-
<p><a class="source-toggle" href="#"
|
346
|
-
onclick="toggleCode('M000038-source');return false;">[Source]</a></p>
|
347
|
-
<div class="method-source-code" id="M000038-source">
|
348
|
-
<pre>
|
349
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 56</span>
|
350
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">incr_doc_count</span>(<span class="ruby-identifier">klass</span>, <span class="ruby-identifier">count</span>)
|
351
|
-
<span class="ruby-ivar">@total_doc_counts</span>[<span class="ruby-identifier">klass</span>] <span class="ruby-operator">+=</span> <span class="ruby-identifier">count</span>
|
352
|
-
<span class="ruby-keyword kw">end</span>
|
353
|
-
</pre>
|
354
|
-
</div>
|
355
|
-
</div>
|
356
|
-
</div>
|
357
|
-
|
358
|
-
<div id="method-M000037" class="method-detail">
|
359
|
-
<a name="M000037"></a>
|
360
|
-
|
361
|
-
<div class="method-heading">
|
362
|
-
<a href="#M000037" class="method-signature">
|
363
|
-
<span class="method-name">incr_total_word_count</span><span class="method-args">(klass, count)</span>
|
364
|
-
</a>
|
365
|
-
</div>
|
366
|
-
|
367
|
-
<div class="method-description">
|
368
|
-
<p><a class="source-toggle" href="#"
|
369
|
-
onclick="toggleCode('M000037-source');return false;">[Source]</a></p>
|
370
|
-
<div class="method-source-code" id="M000037-source">
|
371
|
-
<pre>
|
372
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 52</span>
|
373
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">incr_total_word_count</span>(<span class="ruby-identifier">klass</span>, <span class="ruby-identifier">count</span>)
|
374
|
-
<span class="ruby-ivar">@total_word_counts</span>[<span class="ruby-identifier">klass</span>] <span class="ruby-operator">+=</span> <span class="ruby-identifier">count</span>
|
375
|
-
<span class="ruby-keyword kw">end</span>
|
376
|
-
</pre>
|
377
|
-
</div>
|
378
|
-
</div>
|
379
|
-
</div>
|
380
|
-
|
381
|
-
<div id="method-M000036" class="method-detail">
|
382
|
-
<a name="M000036"></a>
|
383
|
-
|
384
|
-
<div class="method-heading">
|
385
|
-
<a href="#M000036" class="method-signature">
|
386
|
-
<span class="method-name">incr_word_count</span><span class="method-args">(klass, word, count)</span>
|
387
|
-
</a>
|
388
|
-
</div>
|
389
|
-
|
390
|
-
<div class="method-description">
|
391
|
-
<p><a class="source-toggle" href="#"
|
392
|
-
onclick="toggleCode('M000036-source');return false;">[Source]</a></p>
|
393
|
-
<div class="method-source-code" id="M000036-source">
|
394
|
-
<pre>
|
395
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 47</span>
|
396
|
-
<span class="ruby-keyword kw">def</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>)
|
397
|
-
<span class="ruby-ivar">@freqs</span>[<span class="ruby-identifier">word</span>] <span class="ruby-operator">||=</span> <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-value">0</span>)
|
398
|
-
<span class="ruby-ivar">@freqs</span>[<span class="ruby-identifier">word</span>][<span class="ruby-identifier">klass</span>] <span class="ruby-operator">+=</span> <span class="ruby-identifier">count</span>
|
399
|
-
<span class="ruby-keyword kw">end</span>
|
400
|
-
</pre>
|
401
|
-
</div>
|
402
|
-
</div>
|
403
|
-
</div>
|
404
|
-
|
405
|
-
<div id="method-M000031" class="method-detail">
|
406
|
-
<a name="M000031"></a>
|
407
|
-
|
408
|
-
<div class="method-heading">
|
409
|
-
<a href="#M000031" class="method-signature">
|
410
|
-
<span class="method-name">init_tables</span><span class="method-args">()</span>
|
411
|
-
</a>
|
412
|
-
</div>
|
413
|
-
|
414
|
-
<div class="method-description">
|
415
|
-
<p><a class="source-toggle" href="#"
|
416
|
-
onclick="toggleCode('M000031-source');return false;">[Source]</a></p>
|
417
|
-
<div class="method-source-code" id="M000031-source">
|
418
|
-
<pre>
|
419
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 19</span>
|
420
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">init_tables</span>
|
421
|
-
<span class="ruby-ivar">@freqs</span> = {}
|
422
|
-
<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>)
|
423
|
-
<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>)
|
424
|
-
<span class="ruby-ivar">@klass_word_counts</span> = {}
|
425
|
-
<span class="ruby-ivar">@klass_doc_counts</span> = {}
|
426
|
-
<span class="ruby-keyword kw">end</span>
|
427
|
-
</pre>
|
428
|
-
</div>
|
429
|
-
</div>
|
430
|
-
</div>
|
431
|
-
|
432
|
-
<div id="method-M000029" class="method-detail">
|
433
|
-
<a name="M000029"></a>
|
434
|
-
|
435
|
-
<div class="method-heading">
|
436
|
-
<a href="#M000029" class="method-signature">
|
437
|
-
<span class="method-name">reset</span><span class="method-args">()</span>
|
438
|
-
</a>
|
439
|
-
</div>
|
440
|
-
|
441
|
-
<div class="method-description">
|
442
|
-
<p><a class="source-toggle" href="#"
|
443
|
-
onclick="toggleCode('M000029-source');return false;">[Source]</a></p>
|
444
|
-
<div class="method-source-code" id="M000029-source">
|
445
|
-
<pre>
|
446
|
-
<span class="ruby-comment cmt"># File lib/ankusa/memory_storage.rb, line 12</span>
|
447
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">reset</span>
|
448
|
-
<span class="ruby-identifier">init_tables</span>
|
449
|
-
<span class="ruby-keyword kw">end</span>
|
450
|
-
</pre>
|
451
|
-
</div>
|
452
|
-
</div>
|
453
|
-
</div>
|
454
|
-
|
455
|
-
|
456
|
-
</div>
|
457
|
-
|
458
|
-
|
459
|
-
</div>
|
460
|
-
|
461
|
-
|
462
|
-
<div id="validator-badges">
|
463
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
464
|
-
</div>
|
465
|
-
|
466
|
-
</body>
|
467
|
-
</html>
|