ankusa 0.0.2 → 0.0.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.rdoc +6 -4
- data/Rakefile +2 -2
- data/docs/classes/Ankusa.html +8 -8
- data/docs/classes/Ankusa/Classifier.html +82 -271
- data/docs/classes/Ankusa/HBaseStorage.html +537 -0
- data/docs/classes/Ankusa/MemoryStorage.html +439 -0
- data/docs/classes/Ankusa/TextHash.html +84 -29
- data/docs/classes/String.html +172 -0
- data/docs/created.rid +1 -1
- data/docs/files/README_rdoc.html +6 -4
- data/docs/files/lib/ankusa/classifier_rb.html +1 -1
- data/docs/files/lib/ankusa/extensions_rb.html +108 -0
- data/docs/files/lib/ankusa/hasher_rb.html +1 -1
- data/docs/files/lib/ankusa/hbase_storage_rb.html +108 -0
- data/docs/files/lib/ankusa/{nbclass_rb.html → memory_storage_rb.html} +4 -4
- data/docs/files/lib/ankusa_rb.html +4 -2
- data/docs/fr_class_index.html +3 -1
- data/docs/fr_file_index.html +3 -1
- data/docs/fr_method_index.html +41 -17
- data/lib/ankusa.rb +3 -1
- data/lib/ankusa/classifier.rb +37 -86
- data/lib/ankusa/extensions.rb +13 -0
- data/lib/ankusa/hasher.rb +24 -10
- data/lib/ankusa/hbase_storage.rb +109 -0
- data/lib/ankusa/memory_storage.rb +61 -0
- metadata +13 -7
- data/docs/classes/Ankusa/NBClass.html +0 -168
- data/lib/ankusa/nbclass.rb +0 -15
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
module Ankusa
|
|
2
|
+
|
|
3
|
+
class MemoryStorage
|
|
4
|
+
def initialize
|
|
5
|
+
init_tables
|
|
6
|
+
end
|
|
7
|
+
|
|
8
|
+
def classnames
|
|
9
|
+
@total_doc_counts.keys
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
def reset
|
|
13
|
+
init_tables
|
|
14
|
+
end
|
|
15
|
+
|
|
16
|
+
def drop_tables
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
def init_tables
|
|
20
|
+
@freqs = {}
|
|
21
|
+
@total_word_counts = Hash.new(0)
|
|
22
|
+
@total_doc_counts = Hash.new(0)
|
|
23
|
+
@klass_word_counts = {}
|
|
24
|
+
@klass_doc_counts = {}
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
def get_word_counts(word)
|
|
28
|
+
@freqs.fetch word, Hash.new(0)
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def get_total_word_count(klass)
|
|
32
|
+
@total_word_counts[klass]
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
def get_doc_count(klass)
|
|
36
|
+
@total_doc_counts[klass]
|
|
37
|
+
end
|
|
38
|
+
|
|
39
|
+
def incr_word_count(klass, word, count)
|
|
40
|
+
@freqs[word] ||= Hash.new(0)
|
|
41
|
+
@freqs[word][klass] += count
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
def incr_total_word_count(klass, count)
|
|
45
|
+
@total_word_counts[klass] += count
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def incr_doc_count(klass, count)
|
|
49
|
+
@total_doc_counts[klass] += count
|
|
50
|
+
end
|
|
51
|
+
|
|
52
|
+
def doc_count_total
|
|
53
|
+
@total_doc_counts.values.inject { |x,y| x+y }
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
def close
|
|
57
|
+
end
|
|
58
|
+
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
end
|
metadata
CHANGED
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: ankusa
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
hash:
|
|
4
|
+
hash: 25
|
|
5
5
|
prerelease: false
|
|
6
6
|
segments:
|
|
7
7
|
- 0
|
|
8
8
|
- 0
|
|
9
|
-
-
|
|
10
|
-
version: 0.0.
|
|
9
|
+
- 3
|
|
10
|
+
version: 0.0.3
|
|
11
11
|
platform: ruby
|
|
12
12
|
authors:
|
|
13
13
|
- Brian Muller
|
|
@@ -15,7 +15,7 @@ autorequire:
|
|
|
15
15
|
bindir: bin
|
|
16
16
|
cert_chain: []
|
|
17
17
|
|
|
18
|
-
date: 2010-
|
|
18
|
+
date: 2010-12-02 00:00:00 -05:00
|
|
19
19
|
default_executable:
|
|
20
20
|
dependencies:
|
|
21
21
|
- !ruby/object:Gem::Dependency
|
|
@@ -60,21 +60,27 @@ extra_rdoc_files: []
|
|
|
60
60
|
|
|
61
61
|
files:
|
|
62
62
|
- lib/ankusa/classifier.rb
|
|
63
|
+
- lib/ankusa/extensions.rb
|
|
63
64
|
- lib/ankusa/hasher.rb
|
|
64
|
-
- lib/ankusa/
|
|
65
|
+
- lib/ankusa/hbase_storage.rb
|
|
66
|
+
- lib/ankusa/memory_storage.rb
|
|
65
67
|
- lib/ankusa/stopwords.rb
|
|
66
68
|
- lib/ankusa.rb
|
|
67
69
|
- LICENSE
|
|
68
70
|
- Rakefile
|
|
69
71
|
- README.rdoc
|
|
70
72
|
- docs/classes/Ankusa/Classifier.html
|
|
71
|
-
- docs/classes/Ankusa/
|
|
73
|
+
- docs/classes/Ankusa/HBaseStorage.html
|
|
74
|
+
- docs/classes/Ankusa/MemoryStorage.html
|
|
72
75
|
- docs/classes/Ankusa/TextHash.html
|
|
73
76
|
- docs/classes/Ankusa.html
|
|
77
|
+
- docs/classes/String.html
|
|
74
78
|
- docs/created.rid
|
|
75
79
|
- docs/files/lib/ankusa/classifier_rb.html
|
|
80
|
+
- docs/files/lib/ankusa/extensions_rb.html
|
|
76
81
|
- docs/files/lib/ankusa/hasher_rb.html
|
|
77
|
-
- docs/files/lib/ankusa/
|
|
82
|
+
- docs/files/lib/ankusa/hbase_storage_rb.html
|
|
83
|
+
- docs/files/lib/ankusa/memory_storage_rb.html
|
|
78
84
|
- docs/files/lib/ankusa/stopwords_rb.html
|
|
79
85
|
- docs/files/lib/ankusa_rb.html
|
|
80
86
|
- docs/files/README_rdoc.html
|
|
@@ -1,168 +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::NBClass</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::NBClass</td>
|
|
54
|
-
</tr>
|
|
55
|
-
<tr class="top-aligned-row">
|
|
56
|
-
<td><strong>In:</strong></td>
|
|
57
|
-
<td>
|
|
58
|
-
<a href="../../files/lib/ankusa/nbclass_rb.html">
|
|
59
|
-
lib/ankusa/nbclass.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="#M000014">new</a>
|
|
90
|
-
</div>
|
|
91
|
-
</div>
|
|
92
|
-
|
|
93
|
-
</div>
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
<!-- if includes -->
|
|
97
|
-
|
|
98
|
-
<div id="section">
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
<div id="attribute-list">
|
|
105
|
-
<h3 class="section-bar">Attributes</h3>
|
|
106
|
-
|
|
107
|
-
<div class="name-list">
|
|
108
|
-
<table>
|
|
109
|
-
<tr class="top-aligned-row context-row">
|
|
110
|
-
<td class="context-item-name">doc_count</td>
|
|
111
|
-
<td class="context-item-value"> [R] </td>
|
|
112
|
-
<td class="context-item-desc"></td>
|
|
113
|
-
</tr>
|
|
114
|
-
<tr class="top-aligned-row context-row">
|
|
115
|
-
<td class="context-item-name">word_count</td>
|
|
116
|
-
<td class="context-item-value"> [R] </td>
|
|
117
|
-
<td class="context-item-desc"></td>
|
|
118
|
-
</tr>
|
|
119
|
-
</table>
|
|
120
|
-
</div>
|
|
121
|
-
</div>
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
<!-- if method_list -->
|
|
126
|
-
<div id="methods">
|
|
127
|
-
<h3 class="section-bar">Public Class methods</h3>
|
|
128
|
-
|
|
129
|
-
<div id="method-M000014" class="method-detail">
|
|
130
|
-
<a name="M000014"></a>
|
|
131
|
-
|
|
132
|
-
<div class="method-heading">
|
|
133
|
-
<a href="#M000014" class="method-signature">
|
|
134
|
-
<span class="method-name">new</span><span class="method-args">(name, summary_table, freq_table)</span>
|
|
135
|
-
</a>
|
|
136
|
-
</div>
|
|
137
|
-
|
|
138
|
-
<div class="method-description">
|
|
139
|
-
<p><a class="source-toggle" href="#"
|
|
140
|
-
onclick="toggleCode('M000014-source');return false;">[Source]</a></p>
|
|
141
|
-
<div class="method-source-code" id="M000014-source">
|
|
142
|
-
<pre>
|
|
143
|
-
<span class="ruby-comment cmt"># File lib/ankusa/nbclass.rb, line 6</span>
|
|
144
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">name</span>, <span class="ruby-identifier">summary_table</span>, <span class="ruby-identifier">freq_table</span>)
|
|
145
|
-
<span class="ruby-ivar">@name</span> = <span class="ruby-identifier">name</span>
|
|
146
|
-
<span class="ruby-ivar">@summary_table</span> = <span class="ruby-identifier">summary_table</span>
|
|
147
|
-
<span class="ruby-ivar">@freq_table</span> = <span class="ruby-identifier">freq_table</span>
|
|
148
|
-
<span class="ruby-ivar">@word_count</span> = <span class="ruby-ivar">@summary_table</span>.<span class="ruby-identifier">get</span>(<span class="ruby-ivar">@name</span>, <span class="ruby-value str">"totals:wordcount"</span>).<span class="ruby-identifier">first</span>.<span class="ruby-identifier">to_i64</span>.<span class="ruby-identifier">to_f</span>
|
|
149
|
-
<span class="ruby-ivar">@doc_count</span> = <span class="ruby-ivar">@summary_table</span>.<span class="ruby-identifier">get</span>(<span class="ruby-ivar">@name</span>, <span class="ruby-value str">"totals:doccount"</span>).<span class="ruby-identifier">first</span>.<span class="ruby-identifier">to_i64</span>.<span class="ruby-identifier">to_f</span>
|
|
150
|
-
<span class="ruby-keyword kw">end</span>
|
|
151
|
-
</pre>
|
|
152
|
-
</div>
|
|
153
|
-
</div>
|
|
154
|
-
</div>
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
</div>
|
|
158
|
-
|
|
159
|
-
|
|
160
|
-
</div>
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
<div id="validator-badges">
|
|
164
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
|
165
|
-
</div>
|
|
166
|
-
|
|
167
|
-
</body>
|
|
168
|
-
</html>
|
data/lib/ankusa/nbclass.rb
DELETED
|
@@ -1,15 +0,0 @@
|
|
|
1
|
-
module Ankusa
|
|
2
|
-
|
|
3
|
-
class NBClass
|
|
4
|
-
attr_reader :doc_count, :word_count
|
|
5
|
-
|
|
6
|
-
def initialize(name, summary_table, freq_table)
|
|
7
|
-
@name = name
|
|
8
|
-
@summary_table = summary_table
|
|
9
|
-
@freq_table = freq_table
|
|
10
|
-
@word_count = @summary_table.get(@name, "totals:wordcount").first.to_i64.to_f
|
|
11
|
-
@doc_count = @summary_table.get(@name, "totals:doccount").first.to_i64.to_f
|
|
12
|
-
end
|
|
13
|
-
end
|
|
14
|
-
|
|
15
|
-
end
|