mmac 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +18 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/lib/mmac.rb +6 -0
- data/lib/mmac/cache/filter.txt +0 -0
- data/lib/mmac/framework.rb +180 -0
- data/lib/mmac/rule.rb +47 -0
- data/lib/mmac/version.rb +3 -0
- data/mmac.gemspec +21 -0
- data/test/test.rb +24 -0
- metadata +103 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Thanh Nguyen
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Mmac
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'mmac'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install mmac
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/mmac.rb
ADDED
File without changes
|
@@ -0,0 +1,180 @@
|
|
1
|
+
require File.dirname( __FILE__ ) + "/rule"
|
2
|
+
require 'ruby-progressbar'
|
3
|
+
module Mmac
|
4
|
+
#
|
5
|
+
# Main Manager for MMac (contains all options, rules, ...)
|
6
|
+
#
|
7
|
+
#
|
8
|
+
class Framework
|
9
|
+
#
|
10
|
+
# @return Array of data
|
11
|
+
#
|
12
|
+
attr_accessor :data
|
13
|
+
#
|
14
|
+
# @return number of data column except Label
|
15
|
+
#
|
16
|
+
attr_accessor :attrCount
|
17
|
+
#
|
18
|
+
# @return minSupp
|
19
|
+
#
|
20
|
+
attr_accessor :minSupp
|
21
|
+
#
|
22
|
+
# @return minConf
|
23
|
+
#
|
24
|
+
attr_accessor :minConf
|
25
|
+
#
|
26
|
+
# @return Array of Filter rules
|
27
|
+
#
|
28
|
+
attr_accessor :filters
|
29
|
+
#
|
30
|
+
# @return Array of Filter rules
|
31
|
+
#
|
32
|
+
attr_accessor :filtersPrint
|
33
|
+
|
34
|
+
def initialize inputFile, minSupp, minConf
|
35
|
+
@inputFile = inputFile
|
36
|
+
@data = []
|
37
|
+
@rules = []
|
38
|
+
@filters = []
|
39
|
+
@filtersPrint = []
|
40
|
+
@minSupp = minSupp
|
41
|
+
@minConf = minConf
|
42
|
+
@level = 0
|
43
|
+
|
44
|
+
puts ("MIN_SUPP: #{minSupp} - MIN_CONF: #{minConf}")
|
45
|
+
puts 'Input from file...'
|
46
|
+
parse_data(inputFile)
|
47
|
+
@attrCount = @data.first.conditions.count
|
48
|
+
puts ("Number of data: " + "#{@data.count}")
|
49
|
+
puts ("Number of attr: " + "#{@attrCount}")
|
50
|
+
end
|
51
|
+
|
52
|
+
def run
|
53
|
+
puts 'Learning...'
|
54
|
+
self.normalize
|
55
|
+
puts ("Total rules: " + "#{@filters.count}")
|
56
|
+
puts 'Done!'
|
57
|
+
# Write to Filter file
|
58
|
+
filtersPrint = @filters.map{|p| p.clone}
|
59
|
+
filtersPrint.each do |filter|
|
60
|
+
hash = Hash[filter.conditions]
|
61
|
+
filter.conditions = (0..(@attrCount-1)).map{|index| hash[index] || ""}
|
62
|
+
end
|
63
|
+
File.open(File.dirname(@inputFile) + '/filter.txt', 'w') {|f| f.write(filtersPrint.map{|p| p.conditions.join(",") + "," + p.labels}.join("\n"))}
|
64
|
+
end
|
65
|
+
|
66
|
+
def parse_data inputFile
|
67
|
+
line_array = File.readlines(inputFile)
|
68
|
+
line_array.each do |line|
|
69
|
+
*conditions, label = line.strip.split(',')
|
70
|
+
@data << Rule.new(Array[(0...conditions.size).zip conditions].flatten(1), label)
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
def normalize
|
75
|
+
# Apriori
|
76
|
+
filterSet = []
|
77
|
+
blackList = []
|
78
|
+
dataCount = @data.count
|
79
|
+
@level = @level + 1
|
80
|
+
puts ("Level " + "#{@level}")
|
81
|
+
|
82
|
+
1.upto(attrCount).flat_map do |n|
|
83
|
+
rules = []
|
84
|
+
filterCount = filterSet.count
|
85
|
+
@data.each do |data|
|
86
|
+
conditions = data.conditions
|
87
|
+
label = data.labels
|
88
|
+
|
89
|
+
# All combinations with n attrs
|
90
|
+
combinations = conditions.combination(n)
|
91
|
+
|
92
|
+
bList = blackList.map {|b| b.conditions if b.labels == label}.compact
|
93
|
+
rules += combinations.select{|c| !c.contain_any_in?(bList)}.map{|c| Rule.new(c, label)} # Remove all combinations that in blacklist
|
94
|
+
sleep 0.001
|
95
|
+
end
|
96
|
+
|
97
|
+
# collect conditions without dup
|
98
|
+
conRules = rules.map{|r| r.conditions}.uniq
|
99
|
+
# break if have 0 rules
|
100
|
+
break if conRules.count == 0
|
101
|
+
|
102
|
+
# Log using progressbar
|
103
|
+
progressbar = ProgressBar.create(:title => "N = #{n}", :starting_at => 0, :total => conRules.count, :length => 100)
|
104
|
+
|
105
|
+
conRules.each do |c|
|
106
|
+
# increase
|
107
|
+
progressbar.increment
|
108
|
+
|
109
|
+
arr = rules.select{|r| r.conditions == c}
|
110
|
+
actOccr = data.count{|d| (c - d.conditions).empty?}
|
111
|
+
|
112
|
+
set = arr.map{|a| a.labels}.uniq
|
113
|
+
set.each do |s|
|
114
|
+
suppCount = arr.count{|a| a.labels == s}
|
115
|
+
# Calculate sup and conf
|
116
|
+
supp = suppCount.fdiv(dataCount)
|
117
|
+
conf = suppCount.fdiv(actOccr)
|
118
|
+
|
119
|
+
if supp >= minSupp && conf >= minConf
|
120
|
+
filterSet << Rule.new(c, s, supp, conf, actOccr)
|
121
|
+
elsif supp < minSupp
|
122
|
+
blackList << Rule.new(c, s)
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
sleep 0.03
|
127
|
+
end
|
128
|
+
# break if all new combinations is < minSupp and minConf
|
129
|
+
break if filterSet.count == filterCount
|
130
|
+
sleep 0.05
|
131
|
+
end
|
132
|
+
|
133
|
+
originalOrder = filterSet.clone
|
134
|
+
filterSet = filterSet.sort_by{|s| [-s.conf, -s.supp, -s.actOccr, s.conditions.count, originalOrder.index(s)]}
|
135
|
+
@filters += filterSet
|
136
|
+
filterSet.each do |filter|
|
137
|
+
# Remove data that contain filter create T'
|
138
|
+
@data -= @data.select{|data| data.labels == filter.labels && (filter.conditions - data.conditions).empty?}
|
139
|
+
end
|
140
|
+
|
141
|
+
# Log Number of rule in level
|
142
|
+
puts ("Number of rules: " + "#{filterSet.count}")
|
143
|
+
# recursive until Data empty
|
144
|
+
if !@data.empty? && !filterSet.empty?
|
145
|
+
self.normalize
|
146
|
+
end
|
147
|
+
|
148
|
+
end
|
149
|
+
|
150
|
+
def set_label sample_file
|
151
|
+
test = []
|
152
|
+
line_array = File.readlines(sample_file)
|
153
|
+
line_array.each do |line|
|
154
|
+
conditions = line.strip.split(',')
|
155
|
+
rule = Rule.new(Array[(0...conditions.size).zip conditions].flatten(1), "")
|
156
|
+
# set label for test data
|
157
|
+
@filters.each do |filter|
|
158
|
+
if (filter.conditions - rule.conditions).empty?
|
159
|
+
rule.labels = filter.labels
|
160
|
+
break
|
161
|
+
end
|
162
|
+
end
|
163
|
+
test << rule
|
164
|
+
end
|
165
|
+
File.open(File.dirname(sample_file) + '/testOut.txt', 'w') {|f| f.write(test.map{|p| p.conditions.map{|c| c[1]}.join(",") + "," + p.labels}.join("\n"))}
|
166
|
+
end
|
167
|
+
|
168
|
+
end
|
169
|
+
end
|
170
|
+
|
171
|
+
class Array
|
172
|
+
def contain_any_in?(arrayOfOther)
|
173
|
+
arrayOfOther.each do |p|
|
174
|
+
if (p - self).empty?
|
175
|
+
return true
|
176
|
+
end
|
177
|
+
end
|
178
|
+
return false
|
179
|
+
end
|
180
|
+
end
|
data/lib/mmac/rule.rb
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
module Mmac
|
2
|
+
#
|
3
|
+
# Main Data/Rule for MMac (in here is mushroom, ...)
|
4
|
+
#
|
5
|
+
#
|
6
|
+
class Rule
|
7
|
+
#
|
8
|
+
# @return Array of conditions
|
9
|
+
#
|
10
|
+
attr_accessor :conditions
|
11
|
+
#
|
12
|
+
# @return array of labels: result of these conditions
|
13
|
+
#
|
14
|
+
attr_accessor :labels
|
15
|
+
#
|
16
|
+
# @return Supp of rule
|
17
|
+
#
|
18
|
+
attr_accessor :supp
|
19
|
+
#
|
20
|
+
# @return Conf of rule
|
21
|
+
#
|
22
|
+
attr_accessor :conf
|
23
|
+
#
|
24
|
+
# @return actOccr
|
25
|
+
#
|
26
|
+
attr_accessor :actOccr
|
27
|
+
|
28
|
+
def initialize (conditions, labels, *option)
|
29
|
+
@conditions = conditions
|
30
|
+
@labels = labels
|
31
|
+
if !option.empty?
|
32
|
+
@supp = option[0]
|
33
|
+
@conf = option[1]
|
34
|
+
@actOccr = option[2]
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
def ==(other)
|
39
|
+
self.conditions == other.conditions && self.labels == other.labels
|
40
|
+
end
|
41
|
+
|
42
|
+
def isParent?(other)
|
43
|
+
(self.conditions - other.conditions).empty? && self.labels == other.labels
|
44
|
+
end
|
45
|
+
|
46
|
+
end
|
47
|
+
end
|
data/lib/mmac/version.rb
ADDED
data/mmac.gemspec
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'mmac/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "mmac"
|
8
|
+
gem.version = Mmac::VERSION
|
9
|
+
gem.authors = ["Thanh Nguyen"]
|
10
|
+
gem.email = ["congthanh991@gmail.com"]
|
11
|
+
gem.description = ["MMAC Project"]
|
12
|
+
gem.summary = ["MMAC Library"]
|
13
|
+
gem.homepage = ""
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.add_dependency 'pry'
|
20
|
+
gem.add_dependency 'ruby-progressbar'
|
21
|
+
end
|
data/test/test.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# encoding: utf-8
|
3
|
+
|
4
|
+
require_relative '../lib/mmac'
|
5
|
+
|
6
|
+
puts 'Run program...'
|
7
|
+
MIN_SUPP = 0.2
|
8
|
+
MIN_CONF = 0.4
|
9
|
+
framework = Mmac::Framework.new(File.dirname( __FILE__ ) + '/file/data.txt', MIN_SUPP, MIN_CONF)
|
10
|
+
framework.run
|
11
|
+
|
12
|
+
puts 'Run Data Test'
|
13
|
+
framework.set_label(File.dirname( __FILE__ ) + '/file/test.txt')
|
14
|
+
|
15
|
+
f1 = IO.readlines(File.dirname( __FILE__ ) + "/file/testOut.txt").map(&:chomp)
|
16
|
+
f2 = IO.readlines(File.dirname( __FILE__ ) + "/file/data.txt" ).map(&:chomp)
|
17
|
+
|
18
|
+
diff = f1 - f2
|
19
|
+
puts ("Number of diff: #{diff.count}")
|
20
|
+
puts ("Percent of success test: #{((1 - diff.count.fdiv(f1.count))*100).round(2)}%")
|
21
|
+
|
22
|
+
File.open(File.dirname( __FILE__ ) + "/file/diff.txt","w"){ |f| f.write(diff.join("\n")) }
|
23
|
+
|
24
|
+
puts 'Done!'
|
metadata
ADDED
@@ -0,0 +1,103 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: mmac
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Thanh Nguyen
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-11-15 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: pry
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: ruby-progressbar
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
description: ! '["MMAC Project"]'
|
47
|
+
email:
|
48
|
+
- congthanh991@gmail.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- Gemfile
|
55
|
+
- LICENSE.txt
|
56
|
+
- README.md
|
57
|
+
- Rakefile
|
58
|
+
- lib/mmac.rb
|
59
|
+
- lib/mmac/cache/filter.txt
|
60
|
+
- lib/mmac/framework.rb
|
61
|
+
- lib/mmac/rule.rb
|
62
|
+
- lib/mmac/version.rb
|
63
|
+
- mmac.gemspec
|
64
|
+
- test/file/data.txt
|
65
|
+
- test/file/diff.txt
|
66
|
+
- test/file/domain.txt
|
67
|
+
- test/file/filter.txt
|
68
|
+
- test/file/test.txt
|
69
|
+
- test/file/testOut.txt
|
70
|
+
- test/test.rb
|
71
|
+
homepage: ''
|
72
|
+
licenses: []
|
73
|
+
post_install_message:
|
74
|
+
rdoc_options: []
|
75
|
+
require_paths:
|
76
|
+
- lib
|
77
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
78
|
+
none: false
|
79
|
+
requirements:
|
80
|
+
- - ! '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
84
|
+
none: false
|
85
|
+
requirements:
|
86
|
+
- - ! '>='
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
requirements: []
|
90
|
+
rubyforge_project:
|
91
|
+
rubygems_version: 1.8.24
|
92
|
+
signing_key:
|
93
|
+
specification_version: 3
|
94
|
+
summary: ! '["MMAC Library"]'
|
95
|
+
test_files:
|
96
|
+
- test/file/data.txt
|
97
|
+
- test/file/diff.txt
|
98
|
+
- test/file/domain.txt
|
99
|
+
- test/file/filter.txt
|
100
|
+
- test/file/test.txt
|
101
|
+
- test/file/testOut.txt
|
102
|
+
- test/test.rb
|
103
|
+
has_rdoc:
|