ankusa 0.0.16 → 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +2 -0
- data/.ruby-gemset +1 -0
- data/.ruby-version +1 -0
- data/Gemfile +0 -2
- data/Gemfile.lock +1 -1
- data/README.rdoc +2 -1
- data/Rakefile +2 -0
- data/ankusa.gemspec +19 -0
- data/lib/ankusa/extensions.rb +1 -5
- data/lib/ankusa/version.rb +1 -1
- data/test/cassandra_classifier_test.rb +19 -0
- data/test/classifier_base.rb +130 -0
- data/test/config.yml +7 -0
- data/test/file_system_classifier_test.rb +27 -0
- data/test/hasher_test.rb +25 -0
- data/test/hbase_classifier_test.rb +23 -0
- data/test/helper.rb +8 -0
- data/test/memory_classifier_test.rb +20 -0
- data/test/mongo_db_classifier_test.rb +21 -0
- metadata +82 -45
data/.gitignore
ADDED
data/.ruby-gemset
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
ankusa
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
ruby-1.9.3
|
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
data/README.rdoc
CHANGED
@@ -1,4 +1,6 @@
|
|
1
1
|
= ankusa
|
2
|
+
{<img src="https://secure.travis-ci.org/bmuller/ankusa.png?branch=master" alt="Build Status" />}[https://travis-ci.org/bmuller/ankusa]
|
3
|
+
{<img src="https://gemnasium.com/bmuller/ankusa.png" alt="Dependency Status" />}[https://gemnasium.com/bmuller/ankusa]
|
2
4
|
|
3
5
|
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
6
|
|
@@ -18,7 +20,6 @@ If you're using HBase, make sure the HBase Thrift interface has been started as
|
|
18
20
|
== Basic Usage
|
19
21
|
Using the naive Bayes classifier:
|
20
22
|
|
21
|
-
require 'rubygems'
|
22
23
|
require 'ankusa'
|
23
24
|
require 'ankusa/hbase_storage'
|
24
25
|
|
data/Rakefile
CHANGED
data/ankusa.gemspec
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
$:.push File.expand_path("../lib", __FILE__)
|
2
|
+
require "ankusa/version"
|
3
|
+
|
4
|
+
Gem::Specification.new do |s|
|
5
|
+
s.name = "ankusa"
|
6
|
+
s.version = Ankusa::VERSION
|
7
|
+
s.authors = ["Brian Muller"]
|
8
|
+
s.description = "Text classifier with HBase, Cassandra, or Mongo storage"
|
9
|
+
s.summary = "Text classifier in Ruby that uses Hadoop's HBase, Cassandra, or Mongo for storage"
|
10
|
+
s.email = "bamuller@gmail.com"
|
11
|
+
s.files = `git ls-files`.split($/)
|
12
|
+
s.test_files = s.files.grep(%r{^(test|spec|features)/})
|
13
|
+
s.homepage = "https://github.com/bmuller/ankusa"
|
14
|
+
s.require_paths = ["lib"]
|
15
|
+
s.add_dependency('fast-stemmer', '>= 1.0.0')
|
16
|
+
s.add_development_dependency("rake")
|
17
|
+
s.requirements << "Either hbaserb >= 0.0.3 or cassandra >= 0.7"
|
18
|
+
s.rubyforge_project = "ankusa"
|
19
|
+
end
|
data/lib/ankusa/extensions.rb
CHANGED
@@ -1,13 +1,9 @@
|
|
1
|
-
require 'iconv'
|
2
|
-
|
3
1
|
class String
|
4
2
|
def numeric?
|
5
3
|
true if Float(self) rescue false
|
6
4
|
end
|
7
5
|
|
8
6
|
def to_ascii
|
9
|
-
|
10
|
-
converter = Iconv.new('ASCII//IGNORE//TRANSLIT', 'UTF-8')
|
11
|
-
converter.iconv(self).unpack('U*').select { |cp| cp < 127 }.pack('U*') rescue ""
|
7
|
+
encode("UTF-8", :invalid => :replace, :undef => :replace, :replace => "").force_encoding('UTF-8') rescue ""
|
12
8
|
end
|
13
9
|
end
|
data/lib/ankusa/version.rb
CHANGED
@@ -0,0 +1,19 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'classifier_base'
|
2
|
+
require 'ankusa/cassandra_storage'
|
3
|
+
|
4
|
+
module CassandraClassifierBase
|
5
|
+
def initialize(name)
|
6
|
+
@storage = Ankusa::CassandraStorage.new CONFIG['cassandra_host'], CONFIG['cassandra_port'], "ankusa_test"
|
7
|
+
super(name)
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
class NBClassifierTest < Test::Unit::TestCase
|
12
|
+
include CassandraClassifierBase
|
13
|
+
include NBClassifierBase
|
14
|
+
end
|
15
|
+
|
16
|
+
class KLClassifierTest < Test::Unit::TestCase
|
17
|
+
include CassandraClassifierBase
|
18
|
+
include KLClassifierBase
|
19
|
+
end
|
@@ -0,0 +1,130 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'helper'
|
2
|
+
|
3
|
+
module ClassifierBase
|
4
|
+
def train
|
5
|
+
@classifier.train :spam, "spam and great spam" # spam:2 great:1
|
6
|
+
@classifier.train :good, "words for processing" # word:1 process:1
|
7
|
+
@classifier.train :good, "good word" # word:1 good:1
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_train
|
11
|
+
counts = @storage.get_word_counts(:spam)
|
12
|
+
assert_equal counts[:spam], 2
|
13
|
+
counts = @storage.get_word_counts(:word)
|
14
|
+
assert_equal counts[:good], 2
|
15
|
+
assert_equal @storage.get_total_word_count(:good), 4
|
16
|
+
assert_equal @storage.get_doc_count(:good), 2
|
17
|
+
assert_equal @storage.get_total_word_count(:spam), 3
|
18
|
+
assert_equal @storage.get_doc_count(:spam), 1
|
19
|
+
totals = @storage.doc_count_totals
|
20
|
+
assert_equal totals.values.inject { |x,y| x+y }, 3
|
21
|
+
assert_equal totals[:spam], 1
|
22
|
+
assert_equal totals[:good], 2
|
23
|
+
|
24
|
+
vocab = @storage.get_vocabulary_sizes
|
25
|
+
assert_equal vocab[:spam], 2
|
26
|
+
assert_equal vocab[:good], 3
|
27
|
+
end
|
28
|
+
|
29
|
+
def teardown
|
30
|
+
@storage.drop_tables
|
31
|
+
@storage.close
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
|
36
|
+
module NBClassifierBase
|
37
|
+
include ClassifierBase
|
38
|
+
|
39
|
+
def setup
|
40
|
+
@classifier = Ankusa::NaiveBayesClassifier.new @storage
|
41
|
+
train
|
42
|
+
end
|
43
|
+
|
44
|
+
def test_untrained
|
45
|
+
@storage.reset
|
46
|
+
|
47
|
+
string = "spam is tastey"
|
48
|
+
|
49
|
+
hash = {:spam => 0, :good => 0}
|
50
|
+
assert_equal hash, @classifier.classifications(string)
|
51
|
+
assert_equal nil, @classifier.classify(string)
|
52
|
+
end
|
53
|
+
|
54
|
+
|
55
|
+
def test_probs
|
56
|
+
spamlog = Math.log(3.0 / 5.0) + Math.log(1.0 / 5.0) + Math.log(2.0 / 5.0)
|
57
|
+
goodlog = Math.log(1.0 / 7.0) + Math.log(1.0 / 7.0) + Math.log(3.0 / 5.0)
|
58
|
+
|
59
|
+
# exponentiate
|
60
|
+
spamex = Math.exp(spamlog)
|
61
|
+
goodex = Math.exp(goodlog)
|
62
|
+
|
63
|
+
# normalize
|
64
|
+
spam = spamex / (spamex + goodex)
|
65
|
+
good = goodex / (spamex + goodex)
|
66
|
+
|
67
|
+
cs = @classifier.classifications("spam is tastey")
|
68
|
+
assert_equal cs[:spam], spam
|
69
|
+
assert_equal cs[:good], good
|
70
|
+
|
71
|
+
cs = @classifier.log_likelihoods("spam is tastey")
|
72
|
+
assert_equal cs[:spam], spamlog
|
73
|
+
assert_equal cs[:good], goodlog
|
74
|
+
|
75
|
+
@classifier.train :somethingelse, "this is something else entirely spam"
|
76
|
+
cs = @classifier.classifications("spam is tastey", [:spam, :good])
|
77
|
+
assert_equal cs[:spam], spam
|
78
|
+
assert_equal cs[:good], good
|
79
|
+
|
80
|
+
# test for class we didn't train on
|
81
|
+
cs = @classifier.classifications("spam is super tastey if you are a zombie", [:spam, :nothing])
|
82
|
+
assert_equal cs[:nothing], 0
|
83
|
+
end
|
84
|
+
|
85
|
+
def test_prob_result
|
86
|
+
cs = @classifier.classifications("spam is tastey").sort_by { |c| -c[1] }.first.first
|
87
|
+
klass = @classifier.classify("spam is tastey")
|
88
|
+
assert_equal cs, klass
|
89
|
+
assert_equal klass, :spam
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
|
94
|
+
module KLClassifierBase
|
95
|
+
include ClassifierBase
|
96
|
+
|
97
|
+
def setup
|
98
|
+
@classifier = Ankusa::KLDivergenceClassifier.new @storage
|
99
|
+
train
|
100
|
+
end
|
101
|
+
|
102
|
+
def test_distances
|
103
|
+
ds = @classifier.distances("spam is tastey")
|
104
|
+
thprob_spam = 1.0 / 2.0
|
105
|
+
thprob_tastey = 1.0 / 2.0
|
106
|
+
|
107
|
+
train_prob_spam = (2 + 1).to_f / (3 + 2).to_f
|
108
|
+
train_prob_tastey = (0 + 1).to_f / (3 + 2).to_f
|
109
|
+
dist = thprob_spam * Math.log(thprob_spam / train_prob_spam)
|
110
|
+
dist += thprob_tastey * Math.log(thprob_tastey / train_prob_tastey)
|
111
|
+
assert_equal ds[:spam], dist
|
112
|
+
|
113
|
+
train_prob_spam = 1.0 / (4 + 3).to_f
|
114
|
+
train_prob_tastey = 1.0 / (4 + 3).to_f
|
115
|
+
dist = thprob_spam * Math.log(thprob_spam / train_prob_spam)
|
116
|
+
dist += thprob_tastey * Math.log(thprob_tastey / train_prob_tastey)
|
117
|
+
assert_equal ds[:good], dist
|
118
|
+
end
|
119
|
+
|
120
|
+
def test_distances_result
|
121
|
+
cs = @classifier.distances("spam is tastey").sort_by { |c| c[1] }.first.first
|
122
|
+
klass = @classifier.classify("spam is tastey")
|
123
|
+
assert_equal cs, klass
|
124
|
+
assert_equal klass, :spam
|
125
|
+
|
126
|
+
# assert distance from class we didn't train with is Infinity (1.0/0.0 is a way to get at Infinity)
|
127
|
+
cs = @classifier.distances("spam is tastey", [:spam, :nothing])
|
128
|
+
assert_equal cs[:nothing], (1.0/0.0)
|
129
|
+
end
|
130
|
+
end
|
data/test/config.yml
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'classifier_base'
|
2
|
+
require 'ankusa/file_system_storage'
|
3
|
+
|
4
|
+
module FileSystemClassifierBase
|
5
|
+
def initialize(name)
|
6
|
+
@storage = Ankusa::FileSystemStorage.new CONFIG['file_system_storage_file']
|
7
|
+
super name
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_storage
|
11
|
+
# train will be called in setup method, now reload storage and test training
|
12
|
+
@storage.save
|
13
|
+
@storage = Ankusa::FileSystemStorage.new CONFIG['file_system_storage_file']
|
14
|
+
test_train
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
class NBMemoryClassifierTest < Test::Unit::TestCase
|
19
|
+
include FileSystemClassifierBase
|
20
|
+
include NBClassifierBase
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
class KLMemoryClassifierTest < Test::Unit::TestCase
|
25
|
+
include FileSystemClassifierBase
|
26
|
+
include KLClassifierBase
|
27
|
+
end
|
data/test/hasher_test.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'helper'
|
2
|
+
|
3
|
+
class HasherTest < Test::Unit::TestCase
|
4
|
+
def setup
|
5
|
+
string = "Words word a the at fish fishing fishes? /^/ The at a of! @#$!"
|
6
|
+
@text_hash = Ankusa::TextHash.new string
|
7
|
+
@array = Ankusa::TextHash.new [string]
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_stemming
|
11
|
+
assert_equal @text_hash.length, 2
|
12
|
+
assert_equal @text_hash.word_count, 5
|
13
|
+
|
14
|
+
assert_equal @array.length, 2
|
15
|
+
assert_equal @array.word_count, 5
|
16
|
+
end
|
17
|
+
|
18
|
+
def test_valid_word
|
19
|
+
assert (not Ankusa::TextHash.valid_word? "accordingly")
|
20
|
+
assert (not Ankusa::TextHash.valid_word? "appropriate")
|
21
|
+
assert Ankusa::TextHash.valid_word? "^*&@"
|
22
|
+
assert Ankusa::TextHash.valid_word? "mother"
|
23
|
+
assert (not Ankusa::TextHash.valid_word? "21675")
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'classifier_base'
|
2
|
+
require 'ankusa/hbase_storage'
|
3
|
+
|
4
|
+
module HBaseClassifierBase
|
5
|
+
def initialize(name)
|
6
|
+
@freq_tablename = "ankusa_word_frequencies_test"
|
7
|
+
@sum_tablename = "ankusa_summary_test"
|
8
|
+
@storage = Ankusa::HBaseStorage.new CONFIG['hbase_host'], CONFIG['hbase_port'], @freq_tablename, @sum_tablename
|
9
|
+
@freq_table = @storage.hbase.get_table(@freq_tablename)
|
10
|
+
@sum_table = @storage.hbase.get_table(@sum_tablename)
|
11
|
+
super(name)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
class NBClassifierTest < Test::Unit::TestCase
|
16
|
+
include HBaseClassifierBase
|
17
|
+
include NBClassifierBase
|
18
|
+
end
|
19
|
+
|
20
|
+
class KLClassifierTest < Test::Unit::TestCase
|
21
|
+
include HBaseClassifierBase
|
22
|
+
include KLClassifierBase
|
23
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'classifier_base'
|
2
|
+
require 'ankusa/memory_storage'
|
3
|
+
|
4
|
+
module MemoryClassifierBase
|
5
|
+
def initialize(name)
|
6
|
+
@storage = Ankusa::MemoryStorage.new
|
7
|
+
super name
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
class NBMemoryClassifierTest < Test::Unit::TestCase
|
12
|
+
include MemoryClassifierBase
|
13
|
+
include NBClassifierBase
|
14
|
+
end
|
15
|
+
|
16
|
+
|
17
|
+
class KLMemoryClassifierTest < Test::Unit::TestCase
|
18
|
+
include MemoryClassifierBase
|
19
|
+
include KLClassifierBase
|
20
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require File.join File.dirname(__FILE__), 'classifier_base'
|
2
|
+
require 'ankusa/mongo_db_storage'
|
3
|
+
|
4
|
+
module MongoDbClassifierBase
|
5
|
+
def initialize(name)
|
6
|
+
@storage = Ankusa::MongoDbStorage.new :host => CONFIG['mongo_db_host'], :port => CONFIG['mongo_db_port'],
|
7
|
+
:username => CONFIG['mongo_db_username'], :password => CONFIG['mongo_db_password'],
|
8
|
+
:db => 'ankusa-test'
|
9
|
+
super(name)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
class NBClassifierTest < Test::Unit::TestCase
|
14
|
+
include MongoDbClassifierBase
|
15
|
+
include NBClassifierBase
|
16
|
+
end
|
17
|
+
|
18
|
+
class KLClassifierTest < Test::Unit::TestCase
|
19
|
+
include MongoDbClassifierBase
|
20
|
+
include KLClassifierBase
|
21
|
+
end
|
metadata
CHANGED
@@ -1,37 +1,64 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: ankusa
|
3
|
-
version: !ruby/object:Gem::Version
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
4
5
|
prerelease:
|
5
|
-
version: 0.0.16
|
6
6
|
platform: ruby
|
7
|
-
authors:
|
7
|
+
authors:
|
8
8
|
- Brian Muller
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2013-06-19 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
16
15
|
name: fast-stemmer
|
17
|
-
requirement:
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
18
17
|
none: false
|
19
|
-
requirements:
|
20
|
-
- -
|
21
|
-
- !ruby/object:Gem::Version
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
22
21
|
version: 1.0.0
|
23
22
|
type: :runtime
|
24
23
|
prerelease: false
|
25
|
-
version_requirements:
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 1.0.0
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
26
46
|
description: Text classifier with HBase, Cassandra, or Mongo storage
|
27
47
|
email: bamuller@gmail.com
|
28
48
|
executables: []
|
29
|
-
|
30
49
|
extensions: []
|
31
|
-
|
32
50
|
extra_rdoc_files: []
|
33
|
-
|
34
|
-
|
51
|
+
files:
|
52
|
+
- .gitignore
|
53
|
+
- .ruby-gemset
|
54
|
+
- .ruby-version
|
55
|
+
- Gemfile
|
56
|
+
- Gemfile.lock
|
57
|
+
- LICENSE
|
58
|
+
- README.rdoc
|
59
|
+
- Rakefile
|
60
|
+
- ankusa.gemspec
|
61
|
+
- lib/ankusa.rb
|
35
62
|
- lib/ankusa/cassandra_storage.rb
|
36
63
|
- lib/ankusa/classifier.rb
|
37
64
|
- lib/ankusa/extensions.rb
|
@@ -44,44 +71,54 @@ files:
|
|
44
71
|
- lib/ankusa/naive_bayes.rb
|
45
72
|
- lib/ankusa/stopwords.rb
|
46
73
|
- lib/ankusa/version.rb
|
47
|
-
-
|
48
|
-
-
|
49
|
-
-
|
50
|
-
-
|
51
|
-
-
|
52
|
-
-
|
74
|
+
- test/cassandra_classifier_test.rb
|
75
|
+
- test/classifier_base.rb
|
76
|
+
- test/config.yml
|
77
|
+
- test/file_system_classifier_test.rb
|
78
|
+
- test/hasher_test.rb
|
79
|
+
- test/hbase_classifier_test.rb
|
80
|
+
- test/helper.rb
|
81
|
+
- test/memory_classifier_test.rb
|
82
|
+
- test/mongo_db_classifier_test.rb
|
53
83
|
homepage: https://github.com/bmuller/ankusa
|
54
84
|
licenses: []
|
55
|
-
|
56
85
|
post_install_message:
|
57
86
|
rdoc_options: []
|
58
|
-
|
59
|
-
require_paths:
|
87
|
+
require_paths:
|
60
88
|
- lib
|
61
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
89
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
62
90
|
none: false
|
63
|
-
requirements:
|
64
|
-
- -
|
65
|
-
- !ruby/object:Gem::Version
|
66
|
-
|
67
|
-
segments:
|
91
|
+
requirements:
|
92
|
+
- - ! '>='
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: '0'
|
95
|
+
segments:
|
68
96
|
- 0
|
69
|
-
|
70
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
97
|
+
hash: 3381126087859790337
|
98
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
99
|
none: false
|
72
|
-
requirements:
|
73
|
-
- -
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
|
76
|
-
segments:
|
100
|
+
requirements:
|
101
|
+
- - ! '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
segments:
|
77
105
|
- 0
|
78
|
-
|
79
|
-
requirements:
|
106
|
+
hash: 3381126087859790337
|
107
|
+
requirements:
|
80
108
|
- Either hbaserb >= 0.0.3 or cassandra >= 0.7
|
81
109
|
rubyforge_project: ankusa
|
82
|
-
rubygems_version: 1.8.
|
110
|
+
rubygems_version: 1.8.25
|
83
111
|
signing_key:
|
84
112
|
specification_version: 3
|
85
|
-
summary: Text classifier in Ruby that uses Hadoop's HBase, Cassandra, or Mongo for
|
86
|
-
|
87
|
-
|
113
|
+
summary: Text classifier in Ruby that uses Hadoop's HBase, Cassandra, or Mongo for
|
114
|
+
storage
|
115
|
+
test_files:
|
116
|
+
- test/cassandra_classifier_test.rb
|
117
|
+
- test/classifier_base.rb
|
118
|
+
- test/config.yml
|
119
|
+
- test/file_system_classifier_test.rb
|
120
|
+
- test/hasher_test.rb
|
121
|
+
- test/hbase_classifier_test.rb
|
122
|
+
- test/helper.rb
|
123
|
+
- test/memory_classifier_test.rb
|
124
|
+
- test/mongo_db_classifier_test.rb
|