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/Gemfile
ADDED
data/Gemfile.lock
ADDED
data/README.rdoc
CHANGED
@@ -1,14 +1,16 @@
|
|
1
1
|
= ankusa
|
2
2
|
|
3
|
-
Ankusa is a text classifier in Ruby that can use either Hadoop's HBase or Cassandra for storage. Because it uses HBase
|
3
|
+
Ankusa is a text classifier in Ruby that can use either Hadoop's HBase, Mongo, or Cassandra for storage. Because it uses HBase/Mongo/Cassandra as a backend, the training corpus can be many terabytes in size (though additional memory and single file storage abilities also exist for smaller corpora).
|
4
4
|
|
5
5
|
Ankusa currently provides both a Naive Bayes and Kullback-Leibler divergence classifier. It ignores common words (a.k.a, stop words) and stems all others. Additionally, it uses Laplacian smoothing in both classification methods.
|
6
6
|
|
7
7
|
== Installation
|
8
|
-
First, install HBase/Hadoop or Cassandra (>= 0.7.0-rc2). Then, install the appropriate gem:
|
8
|
+
First, install HBase/Hadoop, Mongo, or Cassandra (>= 0.7.0-rc2). Then, install the appropriate gem:
|
9
9
|
gem install hbaserb
|
10
10
|
# or
|
11
11
|
gem install cassandra
|
12
|
+
# or
|
13
|
+
gem install mongo
|
12
14
|
|
13
15
|
If you're using HBase, make sure the HBase Thrift interface has been started as well. Then:
|
14
16
|
gem install ankusa
|
@@ -81,7 +83,7 @@ The API is the same as the NaiveBayesClassifier, except rather than calling "cla
|
|
81
83
|
storage.close
|
82
84
|
|
83
85
|
== Storage Methods
|
84
|
-
Ankusa has a generalized storage interface that has been implemented for HBase, Cassandra, single file, and in-memory storage.
|
86
|
+
Ankusa has a generalized storage interface that has been implemented for HBase, Cassandra, Mongo, single file, and in-memory storage.
|
85
87
|
|
86
88
|
Memory storage can be used when you have a very small corpora
|
87
89
|
require 'ankusa/memory_storage'
|
data/Rakefile
CHANGED
@@ -15,35 +15,35 @@ RDoc::Task.new("doc") { |rdoc|
|
|
15
15
|
|
16
16
|
desc "Run all unit tests with memory storage"
|
17
17
|
Rake::TestTask.new("test_memory") { |t|
|
18
|
-
t.libs
|
18
|
+
t.libs += ["lib", "."]
|
19
19
|
t.test_files = FileList['test/hasher_test.rb', 'test/memory_classifier_test.rb']
|
20
20
|
t.verbose = true
|
21
21
|
}
|
22
22
|
|
23
23
|
desc "Run all unit tests with HBase storage"
|
24
24
|
Rake::TestTask.new("test_hbase") { |t|
|
25
|
-
t.libs
|
25
|
+
t.libs += ["lib", "."]
|
26
26
|
t.test_files = FileList['test/hasher_test.rb']
|
27
27
|
t.verbose = true
|
28
28
|
}
|
29
29
|
|
30
30
|
desc "Run all unit tests with Cassandra storage"
|
31
31
|
Rake::TestTask.new("test_cassandra") { |t|
|
32
|
-
t.libs
|
32
|
+
t.libs += ["lib", "."]
|
33
33
|
t.test_files = FileList['test/hasher_test.rb', 'test/cassandra_classifier_test.rb']
|
34
34
|
t.verbose = true
|
35
35
|
}
|
36
36
|
|
37
37
|
desc "Run all unit tests with FileSystem storage"
|
38
38
|
Rake::TestTask.new("test_filesystem") { |t|
|
39
|
-
t.libs
|
39
|
+
t.libs += ["lib", "."]
|
40
40
|
t.test_files = FileList['test/hasher_test.rb', 'test/file_system_classifier_test.rb']
|
41
41
|
t.verbose = true
|
42
42
|
}
|
43
43
|
|
44
44
|
desc "Run all unit tests with MongoDb storage"
|
45
45
|
Rake::TestTask.new("test_mongo_db") { |t|
|
46
|
-
t.libs
|
46
|
+
t.libs += ["lib", "."]
|
47
47
|
t.test_files = FileList['test/hasher_test.rb', 'test/mongo_db_classifier_test.rb']
|
48
48
|
t.verbose = true
|
49
49
|
}
|
data/lib/ankusa/naive_bayes.rb
CHANGED
@@ -13,7 +13,7 @@ module Ankusa
|
|
13
13
|
def classifications(text, classnames=nil)
|
14
14
|
result = log_likelihoods text, classnames
|
15
15
|
result.keys.each { |k|
|
16
|
-
result[k] = (result[k] == INFTY) ? 0 : Math.exp(result[k])
|
16
|
+
result[k] = (result[k] == -INFTY) ? 0 : Math.exp(result[k])
|
17
17
|
}
|
18
18
|
|
19
19
|
# normalize to get probs
|
@@ -30,8 +30,8 @@ module Ankusa
|
|
30
30
|
TextHash.new(text).each { |word, count|
|
31
31
|
probs = get_word_probs(word, classnames)
|
32
32
|
classnames.each { |k|
|
33
|
-
# log likelihood should be infinity if we've never seen the klass
|
34
|
-
result[k] += probs[k] > 0 ? (Math.log(probs[k]) * count) : INFTY
|
33
|
+
# log likelihood should be negative infinity if we've never seen the klass
|
34
|
+
result[k] += probs[k] > 0 ? (Math.log(probs[k]) * count) : -INFTY
|
35
35
|
}
|
36
36
|
}
|
37
37
|
|
data/lib/ankusa/version.rb
CHANGED
metadata
CHANGED
@@ -1,47 +1,33 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: ankusa
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.14
|
5
5
|
prerelease:
|
6
|
-
segments:
|
7
|
-
- 0
|
8
|
-
- 0
|
9
|
-
- 13
|
10
|
-
version: 0.0.13
|
11
6
|
platform: ruby
|
12
|
-
authors:
|
7
|
+
authors:
|
13
8
|
- Brian Muller
|
14
9
|
autorequire:
|
15
10
|
bindir: bin
|
16
11
|
cert_chain: []
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2012-08-15 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
21
15
|
name: fast-stemmer
|
22
|
-
|
23
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
16
|
+
requirement: &70197701802820 !ruby/object:Gem::Requirement
|
24
17
|
none: false
|
25
|
-
requirements:
|
26
|
-
- -
|
27
|
-
- !ruby/object:Gem::Version
|
28
|
-
hash: 23
|
29
|
-
segments:
|
30
|
-
- 1
|
31
|
-
- 0
|
32
|
-
- 0
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
33
21
|
version: 1.0.0
|
34
22
|
type: :runtime
|
35
|
-
|
36
|
-
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70197701802820
|
25
|
+
description: Text classifier with HBase, Cassandra, or Mongo storage
|
37
26
|
email: brian.muller@livingsocial.com
|
38
27
|
executables: []
|
39
|
-
|
40
28
|
extensions: []
|
41
|
-
|
42
29
|
extra_rdoc_files: []
|
43
|
-
|
44
|
-
files:
|
30
|
+
files:
|
45
31
|
- lib/ankusa/cassandra_storage.rb
|
46
32
|
- lib/ankusa/classifier.rb
|
47
33
|
- lib/ankusa/extensions.rb
|
@@ -55,91 +41,41 @@ files:
|
|
55
41
|
- lib/ankusa/stopwords.rb
|
56
42
|
- lib/ankusa/version.rb
|
57
43
|
- lib/ankusa.rb
|
44
|
+
- Gemfile
|
45
|
+
- Gemfile.lock
|
58
46
|
- LICENSE
|
59
47
|
- Rakefile
|
60
48
|
- README.rdoc
|
61
|
-
- docs/Ankusa/CassandraStorage.html
|
62
|
-
- docs/Ankusa/Classifier.html
|
63
|
-
- docs/Ankusa/FileSystemStorage.html
|
64
|
-
- docs/Ankusa/HBaseStorage.html
|
65
|
-
- docs/Ankusa/KLDivergenceClassifier.html
|
66
|
-
- docs/Ankusa/MemoryStorage.html
|
67
|
-
- docs/Ankusa/NaiveBayesClassifier.html
|
68
|
-
- docs/Ankusa/TextHash.html
|
69
|
-
- docs/Ankusa.html
|
70
|
-
- docs/created.rid
|
71
|
-
- docs/images/brick.png
|
72
|
-
- docs/images/brick_link.png
|
73
|
-
- docs/images/bug.png
|
74
|
-
- docs/images/bullet_black.png
|
75
|
-
- docs/images/bullet_toggle_minus.png
|
76
|
-
- docs/images/bullet_toggle_plus.png
|
77
|
-
- docs/images/date.png
|
78
|
-
- docs/images/find.png
|
79
|
-
- docs/images/loadingAnimation.gif
|
80
|
-
- docs/images/macFFBgHack.png
|
81
|
-
- docs/images/package.png
|
82
|
-
- docs/images/page_green.png
|
83
|
-
- docs/images/page_white_text.png
|
84
|
-
- docs/images/page_white_width.png
|
85
|
-
- docs/images/plugin.png
|
86
|
-
- docs/images/ruby.png
|
87
|
-
- docs/images/tag_green.png
|
88
|
-
- docs/images/wrench.png
|
89
|
-
- docs/images/wrench_orange.png
|
90
|
-
- docs/images/zoom.png
|
91
|
-
- docs/index.html
|
92
|
-
- docs/js/darkfish.js
|
93
|
-
- docs/js/jquery.js
|
94
|
-
- docs/js/quicksearch.js
|
95
|
-
- docs/js/thickbox-compressed.js
|
96
|
-
- docs/lib/ankusa/cassandra_storage_rb.html
|
97
|
-
- docs/lib/ankusa/classifier_rb.html
|
98
|
-
- docs/lib/ankusa/extensions_rb.html
|
99
|
-
- docs/lib/ankusa/file_system_storage_rb.html
|
100
|
-
- docs/lib/ankusa/hasher_rb.html
|
101
|
-
- docs/lib/ankusa/hbase_storage_rb.html
|
102
|
-
- docs/lib/ankusa/kl_divergence_rb.html
|
103
|
-
- docs/lib/ankusa/memory_storage_rb.html
|
104
|
-
- docs/lib/ankusa/naive_bayes_rb.html
|
105
|
-
- docs/lib/ankusa/stopwords_rb.html
|
106
|
-
- docs/lib/ankusa/version_rb.html
|
107
|
-
- docs/lib/ankusa_rb.html
|
108
|
-
- docs/rdoc.css
|
109
|
-
- docs/README_rdoc.html
|
110
|
-
- docs/String.html
|
111
49
|
homepage: https://github.com/livingsocial/ankusa
|
112
50
|
licenses: []
|
113
|
-
|
114
51
|
post_install_message:
|
115
52
|
rdoc_options: []
|
116
|
-
|
117
|
-
require_paths:
|
53
|
+
require_paths:
|
118
54
|
- lib
|
119
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
55
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
120
56
|
none: false
|
121
|
-
requirements:
|
122
|
-
- -
|
123
|
-
- !ruby/object:Gem::Version
|
124
|
-
|
125
|
-
segments:
|
57
|
+
requirements:
|
58
|
+
- - ! '>='
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '0'
|
61
|
+
segments:
|
126
62
|
- 0
|
127
|
-
|
128
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
63
|
+
hash: 2837888903817045284
|
64
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
129
65
|
none: false
|
130
|
-
requirements:
|
131
|
-
- -
|
132
|
-
- !ruby/object:Gem::Version
|
133
|
-
|
134
|
-
segments:
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
segments:
|
135
71
|
- 0
|
136
|
-
|
137
|
-
requirements:
|
72
|
+
hash: 2837888903817045284
|
73
|
+
requirements:
|
138
74
|
- Either hbaserb >= 0.0.3 or cassandra >= 0.7
|
139
75
|
rubyforge_project: ankusa
|
140
|
-
rubygems_version: 1.8.
|
76
|
+
rubygems_version: 1.8.17
|
141
77
|
signing_key:
|
142
78
|
specification_version: 3
|
143
|
-
summary: Text classifier in Ruby that uses Hadoop's HBase or
|
79
|
+
summary: Text classifier in Ruby that uses Hadoop's HBase, Cassandra, or Mongo for
|
80
|
+
storage
|
144
81
|
test_files: []
|
145
|
-
|
data/docs/Ankusa.html
DELETED
@@ -1,229 +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</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/cassandra_storage_rb.html?TB_iframe=true&height=550&width=785"
|
38
|
-
class="thickbox" title="lib/ankusa/cassandra_storage.rb">lib/ankusa/cassandra_storage.rb</a></li>
|
39
|
-
|
40
|
-
<li><a href="./lib/ankusa/classifier_rb.html?TB_iframe=true&height=550&width=785"
|
41
|
-
class="thickbox" title="lib/ankusa/classifier.rb">lib/ankusa/classifier.rb</a></li>
|
42
|
-
|
43
|
-
<li><a href="./lib/ankusa/file_system_storage_rb.html?TB_iframe=true&height=550&width=785"
|
44
|
-
class="thickbox" title="lib/ankusa/file_system_storage.rb">lib/ankusa/file_system_storage.rb</a></li>
|
45
|
-
|
46
|
-
<li><a href="./lib/ankusa/hasher_rb.html?TB_iframe=true&height=550&width=785"
|
47
|
-
class="thickbox" title="lib/ankusa/hasher.rb">lib/ankusa/hasher.rb</a></li>
|
48
|
-
|
49
|
-
<li><a href="./lib/ankusa/hbase_storage_rb.html?TB_iframe=true&height=550&width=785"
|
50
|
-
class="thickbox" title="lib/ankusa/hbase_storage.rb">lib/ankusa/hbase_storage.rb</a></li>
|
51
|
-
|
52
|
-
<li><a href="./lib/ankusa/kl_divergence_rb.html?TB_iframe=true&height=550&width=785"
|
53
|
-
class="thickbox" title="lib/ankusa/kl_divergence.rb">lib/ankusa/kl_divergence.rb</a></li>
|
54
|
-
|
55
|
-
<li><a href="./lib/ankusa/memory_storage_rb.html?TB_iframe=true&height=550&width=785"
|
56
|
-
class="thickbox" title="lib/ankusa/memory_storage.rb">lib/ankusa/memory_storage.rb</a></li>
|
57
|
-
|
58
|
-
<li><a href="./lib/ankusa/naive_bayes_rb.html?TB_iframe=true&height=550&width=785"
|
59
|
-
class="thickbox" title="lib/ankusa/naive_bayes.rb">lib/ankusa/naive_bayes.rb</a></li>
|
60
|
-
|
61
|
-
<li><a href="./lib/ankusa/stopwords_rb.html?TB_iframe=true&height=550&width=785"
|
62
|
-
class="thickbox" title="lib/ankusa/stopwords.rb">lib/ankusa/stopwords.rb</a></li>
|
63
|
-
|
64
|
-
<li><a href="./lib/ankusa/version_rb.html?TB_iframe=true&height=550&width=785"
|
65
|
-
class="thickbox" title="lib/ankusa/version.rb">lib/ankusa/version.rb</a></li>
|
66
|
-
|
67
|
-
</ul>
|
68
|
-
</div>
|
69
|
-
</div>
|
70
|
-
|
71
|
-
|
72
|
-
</div>
|
73
|
-
|
74
|
-
<div id="class-metadata">
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
<!-- Namespace Contents -->
|
81
|
-
<div id="namespace-list-section" class="section">
|
82
|
-
<h3 class="section-header">Namespace</h3>
|
83
|
-
<ul class="link-list">
|
84
|
-
|
85
|
-
<li><span class="type">MODULE</span> <a href="Ankusa/Classifier.html">Ankusa::Classifier</a></li>
|
86
|
-
|
87
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/CassandraStorage.html">Ankusa::CassandraStorage</a></li>
|
88
|
-
|
89
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/FileSystemStorage.html">Ankusa::FileSystemStorage</a></li>
|
90
|
-
|
91
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/HBaseStorage.html">Ankusa::HBaseStorage</a></li>
|
92
|
-
|
93
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/KLDivergenceClassifier.html">Ankusa::KLDivergenceClassifier</a></li>
|
94
|
-
|
95
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/MemoryStorage.html">Ankusa::MemoryStorage</a></li>
|
96
|
-
|
97
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/NaiveBayesClassifier.html">Ankusa::NaiveBayesClassifier</a></li>
|
98
|
-
|
99
|
-
<li><span class="type">CLASS</span> <a href="Ankusa/TextHash.html">Ankusa::TextHash</a></li>
|
100
|
-
|
101
|
-
</ul>
|
102
|
-
</div>
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
</div>
|
109
|
-
|
110
|
-
<div id="project-metadata">
|
111
|
-
|
112
|
-
|
113
|
-
<div id="fileindex-section" class="section project-section">
|
114
|
-
<h3 class="section-header">Files</h3>
|
115
|
-
<ul>
|
116
|
-
|
117
|
-
<li class="file"><a href="./README_rdoc.html">README.rdoc</a></li>
|
118
|
-
|
119
|
-
</ul>
|
120
|
-
</div>
|
121
|
-
|
122
|
-
|
123
|
-
<div id="classindex-section" class="section project-section">
|
124
|
-
<h3 class="section-header">Class/Module Index
|
125
|
-
<span class="search-toggle"><img src="./images/find.png"
|
126
|
-
height="16" width="16" alt="[+]"
|
127
|
-
title="show/hide quicksearch" /></span></h3>
|
128
|
-
<form action="#" method="get" accept-charset="utf-8" class="initially-hidden">
|
129
|
-
<fieldset>
|
130
|
-
<legend>Quicksearch</legend>
|
131
|
-
<input type="text" name="quicksearch" value=""
|
132
|
-
class="quicksearch-field" />
|
133
|
-
</fieldset>
|
134
|
-
</form>
|
135
|
-
|
136
|
-
<ul class="link-list">
|
137
|
-
|
138
|
-
<li><a href="./Ankusa.html">Ankusa</a></li>
|
139
|
-
|
140
|
-
<li><a href="./Ankusa/CassandraStorage.html">Ankusa::CassandraStorage</a></li>
|
141
|
-
|
142
|
-
<li><a href="./Ankusa/Classifier.html">Ankusa::Classifier</a></li>
|
143
|
-
|
144
|
-
<li><a href="./Ankusa/FileSystemStorage.html">Ankusa::FileSystemStorage</a></li>
|
145
|
-
|
146
|
-
<li><a href="./Ankusa/HBaseStorage.html">Ankusa::HBaseStorage</a></li>
|
147
|
-
|
148
|
-
<li><a href="./Ankusa/KLDivergenceClassifier.html">Ankusa::KLDivergenceClassifier</a></li>
|
149
|
-
|
150
|
-
<li><a href="./Ankusa/MemoryStorage.html">Ankusa::MemoryStorage</a></li>
|
151
|
-
|
152
|
-
<li><a href="./Ankusa/NaiveBayesClassifier.html">Ankusa::NaiveBayesClassifier</a></li>
|
153
|
-
|
154
|
-
<li><a href="./Ankusa/TextHash.html">Ankusa::TextHash</a></li>
|
155
|
-
|
156
|
-
<li><a href="./String.html">String</a></li>
|
157
|
-
|
158
|
-
</ul>
|
159
|
-
<div id="no-class-search-results" style="display: none;">No matching classes.</div>
|
160
|
-
</div>
|
161
|
-
|
162
|
-
|
163
|
-
</div>
|
164
|
-
</div>
|
165
|
-
|
166
|
-
<div id="documentation">
|
167
|
-
<h1 class="module">Ankusa</h1>
|
168
|
-
|
169
|
-
<div id="description" class="description">
|
170
|
-
|
171
|
-
<p>At the moment you’ll have to do:</p>
|
172
|
-
|
173
|
-
<p>create keyspace ankusa with replication_factor = 1</p>
|
174
|
-
|
175
|
-
<p>from the cassandra-cli. This should be fixed with new release candidate for
|
176
|
-
cassandra</p>
|
177
|
-
|
178
|
-
</div><!-- description -->
|
179
|
-
|
180
|
-
|
181
|
-
<div id="5Buntitled-5D" class="documentation-section">
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
<!-- Constants -->
|
188
|
-
<div id="constants-list" class="section">
|
189
|
-
<h3 class="section-header">Constants</h3>
|
190
|
-
<dl>
|
191
|
-
|
192
|
-
<dt><a name="INFTY">INFTY</a></dt>
|
193
|
-
|
194
|
-
<dd class="description"></dd>
|
195
|
-
|
196
|
-
|
197
|
-
<dt><a name="STOPWORDS">STOPWORDS</a></dt>
|
198
|
-
|
199
|
-
<dd class="description"><p>These are taken from MySQL - <a
|
200
|
-
href="http://dev.mysql.com/tech-resources/articles/full-text-revealed.html">dev.mysql.com/tech-resources/articles/full-text-revealed.html</a></p></dd>
|
201
|
-
|
202
|
-
|
203
|
-
<dt><a name="VERSION">VERSION</a></dt>
|
204
|
-
|
205
|
-
<dd class="description"></dd>
|
206
|
-
|
207
|
-
|
208
|
-
</dl>
|
209
|
-
</div>
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
<!-- Methods -->
|
215
|
-
|
216
|
-
</div><!-- 5Buntitled-5D -->
|
217
|
-
|
218
|
-
|
219
|
-
</div><!-- documentation -->
|
220
|
-
|
221
|
-
<div id="validator-badges">
|
222
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
223
|
-
<p><small>Generated with the <a href="http://deveiate.org/projects/Darkfish-Rdoc/">Darkfish
|
224
|
-
Rdoc Generator</a> 2</small>.</p>
|
225
|
-
</div>
|
226
|
-
|
227
|
-
</body>
|
228
|
-
</html>
|
229
|
-
|