jnb_classifier 0.4.1 → 0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 471d53529cd3370211a12feaabc49e09afde67a3
-  data.tar.gz: 87a9c51b9d20d7e4f1447ec16b61c87ea6a22079
+  metadata.gz: 99aaba58f7a9e3c702d91490ced2e45f1413e252
+  data.tar.gz: 7430e3ab70b3aa959c43e5a518e4323878b65378
 SHA512:
-  metadata.gz: f8fec00adcc3ea7fd0136ecc9fadb1c8be81a61a590008bca7c0c77f7175211f0bacfa0fc1dac8d2ac256f7c8bf536bc107ffd764f4ddbf3d710bf8d7a33717f
-  data.tar.gz: 5507ed1ed18e4e67c67ffe4d7837caee1ad055f1fc535e048d92bf91e101cc4fb44ff884af8b4ac3a8774b1278600e386d2c01fb2d3069a6195971ba8810a383
+  metadata.gz: b1365b424c12f58ede00c7c44060808daf52e2b2ea41f7ed74fbe7ea5aacb1b735c9d0126ecea9220b7618768d370407d6d72cc5195ac7924363486b33ff8d58
+  data.tar.gz: 34781f0bef1ab8d812eda44dbb3be5b33c1e37110dfe4a8dbbfa560ddbb7cbfd5781067c1eb6219c1e88c13206def3381cbd5ce8eb00d9604145a412ede6cc17

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    jnb_classifier (0.4.1)
+    jnb_classifier (0.4.2)
       natto
 
 GEM

data/README.md

@@ -1,12 +1,40 @@
 # JnbClassifier
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/jnb_classifier`. To experiment with that code, run `bin/console` for an interactive prompt.
+Naive Bayes classifier for japanse text.
+
+## Description
+JnbClassifier helps you classify japanese text.
+
+You need Morphological Analysis Tool, Mecab and the dictionary to use JnbClassifier.
+
+If you use linux(ubuntu), you can install Mecab and the dictionary as follows.
+
+1:Mecab
+download site: https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7cENtOXlicTFaRUE
+
+```bash
+$ cd mecab-X.X
+$ ./configure
+$ make
+$ make check
+$ sudo make install
+```
+
+2:the dictionary for Mecab
+download site: https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7MWVlSDBCSXZMTXM
+
+```bash
+$ tar zxfv mecab-ipadic-2.7.0-XXXX.tar.gz
+$ cd mecab-ipadic-2.7.0-XXXX
+$ ./configure --with-charset=utf8
+$ make
+$ sudo make install
+```
 
-TODO: Delete this and the text above, and describe your gem
 
 ## Installation
 
-Add this line to your application's Gemfile:
+Add this line to your application's Gemfile
 
 ```ruby
 gem 'jnb_classifier'
@@ -22,7 +50,40 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+#### 1: Generate Document(label, attributes) from text 
+First you need create documents which neeed two parameters: category name and text. 
+
+```
+document1 = JnbClassifier::Document.new('hayao','私の住んでいる場所は風の谷ではありません。')
+#=> @label="hayao", @attributes={"私"=>1, "場所"=>1, "風"=>1, "谷"=>1}
+document2 = JnbClassifier::Document.new('hayao','私は魔女の宅急便が大好きです')   
+#=> @label="hayao", @attributes={"私"=>1, "魔女"=>1, "宅急便"=>1, "大好き"=>1}
+document3 = JnbClassifier::Document.new('hujiko','僕、ドラえもん。')
+#=> @label="hujiko", @attributes={"僕"=>1, "ドラえもん"=>1}
+```
+
+#### 2: Learn documents
+Your classifier can learn from documents you created.
+
+And the more you give apropriate samples, the smarter your classifier will be.
+
+```
+nb = nb = JnbClassifier::Classifier.new
+mb.learn(document1)
+mb.learn(document2)
+mb.learn(document3)
+```
+
+#### 3:Classify
+When you input attributes(hash), ,classify method return the category which is selected  by Naive Bayes.  
+
+```
+nb.classify({"私"=>1, "魔女"=>1, "宅急便"=>1} )
+#=> "hayao"
+nb.result
+#=> {"hayao"=>-16.72902719126572, "hujiko"=>-20.435583764494627}  # the values is logarithm.
+```
+
 
 ## Development
 

data/README.md.backup

@@ -0,0 +1,80 @@
+# JnbClassifier
+
+Naive Bayes classifier for japanse text.
+
+## Description
+JnbClassifier help you classify japanese text.
+
+You need Morphological Analysis Tool, Mecab and the dictionary to use JnbClassifier.
+
+If you use linux(ubuntu), you can install Mecab and the dictionary as follows.
+
+1:Mecab
+download site: https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7cENtOXlicTFaRUE
+
+```bash
+$ cd mecab-X.X
+$ ./configure
+$ make
+$ make check
+$ sudo make install
+```
+
+2:the dictionary for Mecab
+download site: https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7MWVlSDBCSXZMTXM
+
+```bash
+$ tar zxfv mecab-ipadic-2.7.0-XXXX.tar.gz
+$ cd mecab-ipadic-2.7.0-XXXX
+$ ./configure --with-charset=utf8
+$ make
+$ sudo make install
+```
+
+
+## Installation
+
+Add this line to your application's Gemfile
+
+```ruby
+gem 'jnb_classifier'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install jnb_classifier
+
+## Usage
+
+#### 1: generate hash from text 
+
+```
+document1 = JnbClassifier::Document.new('hayao','') 
+
+```
+
+
+
+
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/jnb_classifier. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the JnbClassifier project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/jnb_classifier/blob/master/CODE_OF_CONDUCT.md).

data/lib/jnb_classifier.rb

@@ -7,8 +7,8 @@ module JnbClassifier
     attr_reader :result
     
     def initialize
-      @frequency_table = Hash.new()       # frequency table for each class
-      @word_table = Hash.new()            # word feature table
+      @frequency_table = Hash.new         # frequency table for each class
+      @word_table = Hash.new              # word feature table
       @label_count = Hash.new(0)          # count by each label 
       @total_count = 0                    # total learned documents
       @result = Hash.new                             
@@ -36,13 +36,14 @@ module JnbClassifier
       
      # P(Label)
      @label_count.each{|label,freq|
-       label_p[label] = Math.log(freq.to_f / @total_count.to_f)
+       label_p[label] = Math.log(freq.fdiv(@total_count))
      }
 
-     # P(X|Label)
+     # P(X|Label)  
      @frequency_table.each_key{|label|
+       deno = @label_count[label] + @word_table.size()
        @word_table.each_key{|word|
-         laplace_word_p[label] += Math.log((@frequency_table[label][word] + 1).to_f / (@label_count[label] + @word_table.size()).to_f)
+         laplace_word_p[label] += Math.log( (@frequency_table[label][word] + 1).fdiv(deno) )
        }
        score[label] = laplace_word_p[label] + label_p[label]
      }
@@ -51,7 +52,7 @@ module JnbClassifier
      score.each{|label, value|
        @result[label] = value
      }
-     score.max{ |x, y| x[1] <=> y[1] } 
+     score.max_by{ |x| x[1] } 
     end
   end
 
@@ -60,23 +61,21 @@ module JnbClassifier
     attr_reader :label
     attr_reader :attributes
 
-    def initialize(label, file_name)
+    def initialize(label,doc)
       @label = label                               # String
-      @attributes = create_attributes(file_name)   # Hash
+      @attributes = create_attributes(doc)         # Hsah
     end
     
-    def create_attributes(file_name)
+    def create_attributes(doc)
       attributes = Hash.new(0)
-      File.open(file_name) {|f|
-	doc = f.read
-	nm = Natto::MeCab.new
-	nm.parse(doc) do |n|
-	  attributes[n.surface] += 1 if n.feature.match(/名詞/)
-	end
-      }
+      nm = Natto::MeCab.new
+      nm.parse(doc) do |n|
+	attributes[n.surface] += 1 if n.feature.match(/名詞/)
+      end
       attributes
     end
   end
 
 end
 
+

data/lib/jnb_classifier/version.rb

@@ -1,3 +1,3 @@
 module JnbClassifier
-  VERSION = "0.4.1"
+  VERSION = "0.4.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jnb_classifier
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.2
 platform: ruby
 authors:
 - chamao
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-11-03 00:00:00.000000000 Z
+date: 2017-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -81,6 +81,7 @@ files:
 - Gemfile.lock
 - LICENSE.txt
 - README.md
+- README.md.backup
 - Rakefile
 - bin/console
 - bin/setup