classiphier 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 093b4da304370f8aaffa04b90743f771097d6b26
4
+ data.tar.gz: 94e320a2947aa9977139b381911eb0d3899165da
5
+ SHA512:
6
+ metadata.gz: d3edad30af44221424e44c0d28a4697dfa363ef951ec88f0aa361598dcdfa6a526c7061bef00d45bf4b500883566bad0c02aa78b8b0e4e4f0aead080d9a1029c
7
+ data.tar.gz: 06e871475c080a8af1bd44f4015ee2e20c486d1e1ff952633503a49f3620aa68185c6d989d007c9a9890bdababc4fc7ff042269e12789bb26a9c470fd82054ab
data/.gitignore ADDED
@@ -0,0 +1,10 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
10
+ .rvmrc
data/.travis.yml ADDED
@@ -0,0 +1,3 @@
1
+ language: ruby
2
+ rvm:
3
+ - 2.2.2
data/Gemfile ADDED
@@ -0,0 +1,5 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Specify your gem's dependencies in classiphier.gemspec
4
+ gemspec
5
+ gem 'minitest'
data/LICENSE.txt ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2015 Alejandro Gutiérrez
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,31 @@
1
+ # Classiphier
2
+ [![Build Status](https://travis-ci.org/alejandrogutierrez/classiphier.png?branch=master)](https://travis-ci.org/alejandrogutierrez/classiphier)
3
+
4
+ Classifier module using Bayesian's theorem.
5
+
6
+ *This is another implementation based on cardmagic/classifier.*
7
+
8
+
9
+
10
+ ## Installation
11
+ Add this line to your Gemfile:
12
+
13
+ ```ruby
14
+ gem 'classiphier'
15
+ ```
16
+ Run the bundle command to install it.
17
+
18
+
19
+
20
+ ## Getting started
21
+ ```ruby
22
+ require 'classiphier'
23
+
24
+ classifier = Classiphier::Bayes.new
25
+ classifier.train :positive, 'This is a great tweet. I like it!'
26
+ classifier.train :positive, 'With great power comes great responsibility'
27
+ classifier.train :negative, 'This tweet is not good. I hate it!'
28
+ classifier.train :negative, 'Here are some bad words, I hate you'
29
+
30
+ classifier.classify 'I like these tweets' # => :positive
31
+ ```
data/Rakefile ADDED
@@ -0,0 +1,9 @@
1
+ require 'bundler/gem_tasks'
2
+ require 'rake/testtask'
3
+
4
+ Rake::TestTask.new do |t|
5
+ t.libs << 'test'
6
+ t.pattern = 'test/**/*_test.rb'
7
+ end
8
+
9
+ task default: :test
data/bin/console ADDED
@@ -0,0 +1,14 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require 'bundler/setup'
4
+ require 'classiphier'
5
+
6
+ # You can add fixtures and/or initialization code here to make experimenting
7
+ # with your gem easier. You can also use a different console, if you like.
8
+
9
+ # (If you use this, don't forget to add pry to your Gemfile!)
10
+ # require "pry"
11
+ # Pry.start
12
+
13
+ require 'irb'
14
+ IRB.start
data/bin/setup ADDED
@@ -0,0 +1,7 @@
1
+ #!/bin/bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+
5
+ bundle install
6
+
7
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,25 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'classiphier/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = 'classiphier'
8
+ spec.version = Classiphier::VERSION
9
+ spec.authors = ['Alejandro Gutiérrez']
10
+ spec.email = ['alejandrodevs@gmail.com']
11
+
12
+ spec.summary = "Classifier module using Bayesian's theorem."
13
+ spec.description = "Classifier module using Bayesian's theorem."
14
+ spec.homepage = 'https://github.com/alejandrogutierrez/classiphier'
15
+ spec.license = 'MIT'
16
+
17
+ spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
18
+ spec.bindir = 'exe'
19
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
20
+ spec.require_paths = ['lib']
21
+
22
+ spec.add_development_dependency 'bundler', '~> 1.10'
23
+ spec.add_development_dependency 'rake', '~> 10.0'
24
+ spec.add_dependency 'fast-stemmer', '~> 1.0'
25
+ end
@@ -0,0 +1,31 @@
1
+ module Classiphier
2
+ class Bayes
3
+ def initialize
4
+ @data = Data.new
5
+ end
6
+
7
+ def train(category, sentence)
8
+ @data.perform!
9
+ @data[:data][category] ||= Data.new
10
+ @data[:data][category].train(sentence)
11
+ end
12
+
13
+ def classify(sentence)
14
+ classifications(sentence).min_by { |a| -a[1] }[0]
15
+ end
16
+
17
+ def classifications(sentence)
18
+ Hash.new(0).tap do |score|
19
+ @data[:data].each do |category, data|
20
+ sentence.words.each do |word|
21
+ value = data[:data].fetch(word, 0.1).to_f
22
+ score[category] += Math.log(value / data[:words])
23
+ end
24
+
25
+ value = @data[:data][category][:count].to_f
26
+ score[category] += Math.log(value / @data[:count])
27
+ end
28
+ end
29
+ end
30
+ end
31
+ end
@@ -0,0 +1,21 @@
1
+ module Classiphier
2
+ class Data < Hash
3
+ def initialize
4
+ self[:data] = {}
5
+ self.default = 0
6
+ end
7
+
8
+ def train(sentence)
9
+ perform!
10
+ sentence.words.each do |word|
11
+ self[:data][word] ||= 0
12
+ self[:data][word] += 1
13
+ self[:words] += 1
14
+ end
15
+ end
16
+
17
+ def perform!
18
+ self[:count] += 1
19
+ end
20
+ end
21
+ end
@@ -0,0 +1,7 @@
1
+ class String
2
+ def words
3
+ result = downcase.gsub(/[^\w\s]/, '').split
4
+ result.delete_if { |w| w.size <= 2 }
5
+ result.map(&:stem)
6
+ end
7
+ end
@@ -0,0 +1,3 @@
1
+ module Classiphier
2
+ VERSION = '0.1.0'
3
+ end
@@ -0,0 +1,8 @@
1
+ require 'fast-stemmer'
2
+ require 'classiphier/version'
3
+ require 'classiphier/extensions/string'
4
+
5
+ module Classiphier
6
+ autoload :Data, 'classiphier/data'
7
+ autoload :Bayes, 'classiphier/bayes'
8
+ end
metadata ADDED
@@ -0,0 +1,100 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: classiphier
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Alejandro Gutiérrez
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2015-07-17 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: bundler
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '1.10'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.10'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '10.0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '10.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: fast-stemmer
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '1.0'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '1.0'
55
+ description: Classifier module using Bayesian's theorem.
56
+ email:
57
+ - alejandrodevs@gmail.com
58
+ executables: []
59
+ extensions: []
60
+ extra_rdoc_files: []
61
+ files:
62
+ - ".gitignore"
63
+ - ".travis.yml"
64
+ - Gemfile
65
+ - LICENSE.txt
66
+ - README.md
67
+ - Rakefile
68
+ - bin/console
69
+ - bin/setup
70
+ - classiphier.gemspec
71
+ - lib/classiphier.rb
72
+ - lib/classiphier/bayes.rb
73
+ - lib/classiphier/data.rb
74
+ - lib/classiphier/extensions/string.rb
75
+ - lib/classiphier/version.rb
76
+ homepage: https://github.com/alejandrogutierrez/classiphier
77
+ licenses:
78
+ - MIT
79
+ metadata: {}
80
+ post_install_message:
81
+ rdoc_options: []
82
+ require_paths:
83
+ - lib
84
+ required_ruby_version: !ruby/object:Gem::Requirement
85
+ requirements:
86
+ - - ">="
87
+ - !ruby/object:Gem::Version
88
+ version: '0'
89
+ required_rubygems_version: !ruby/object:Gem::Requirement
90
+ requirements:
91
+ - - ">="
92
+ - !ruby/object:Gem::Version
93
+ version: '0'
94
+ requirements: []
95
+ rubyforge_project:
96
+ rubygems_version: 2.4.8
97
+ signing_key:
98
+ specification_version: 4
99
+ summary: Classifier module using Bayesian's theorem.
100
+ test_files: []