natto2classifier 0.1.3 → 0.3.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: f933e506e593fedf2eeb3c43e73c3de5fe39d84b
-  data.tar.gz: 6406772efd4fdba35779207d791d0a9c6e257092
+SHA256:
+  metadata.gz: 3ae8ae7a0796de33c72feb4ce5b5926ba945c0779ea3fae42ca17b6a04ed3e32
+  data.tar.gz: d7083a5371d528fed4ced8bcaf9a522d0db4c6abc62e9df15c63e2af62c8b77f
 SHA512:
-  metadata.gz: cecd63071da50fbc05b970aa730fcdeb1cb65fbd7a34ddd1e0834f1d845cd7c7fe0216626c504406878c6b9391d44f2be748c5864482babdc000a05d8f9f74a6
-  data.tar.gz: 9b12fd6dde86b47fb731f41112b7990cd74dc641ecffaf096c976b4b6dd967f60e433d1a0c53c70e68c1b114b991ffdceee0ccf32b1b325d5fdbeeb1b3e77eec
+  metadata.gz: 15cead65621e2f1d63e243605a3148377248a0940977efb545ad050d53914836ebf70d7b8792e5f7cf550835a77f7c296666d51e1b926b8dfea1e83864ced27a
+  data.tar.gz: 25977c17d175688768efd47a76d30136aae83fe48bc33138b7d80fc8e6b0415128ac765cf7ec9578c4a355138e431e86e1fda5ce5e0c1cfbdd73aafd6ee58691

data/.circleci/config.yml

@@ -0,0 +1,14 @@
+version: 2
+jobs:
+  test:
+    docker:
+      - image: kanayannet/natto2classifier:latest
+    steps:
+      - checkout
+      - run: bundle install
+      - run: bundle exec ruby test/natto2classifier_test.rb
+workflows:
+  version: 2
+  test:
+    jobs:
+      - test

data/.travis.yml

@@ -1,5 +1,21 @@
-sudo: false
 language: ruby
 rvm:
   - 2.4.3
-before_install: gem install bundler -v 1.16.1
+before_install: 
+  - gem install bundler -v 1.16.1
+  - sudo apt-get update -qq
+install:
+  # mecab
+  - wget --no-check-certificate https://github.com/buruzaemon/natto/raw/master/etc/mecab-0.996.tar.gz && tar zxf mecab-0.996.tar.gz
+  - pushd mecab-0.996 && ./configure --enable-utf8-only && make && sudo make install && popd
+  - sudo ldconfig
+  # mecab-ipadic
+  - wget --no-check-certificate https://github.com/buruzaemon/natto/raw/master/etc/mecab-ipadic-2.7.0-20070801.tar.gz && tar zxf mecab-ipadic-2.7.0-20070801.tar.gz
+  - pushd mecab-ipadic-2.7.0-20070801 && ./configure --with-charset=utf8 && make && sudo make install && popd
+  - sudo ldconfig
+  # gsl
+  - sudo apt-get install libgsl2 libgsl-dev
+  # explicitly install
+  - bundle install --path .bundle
+script:
+  - bundle exec ruby test/natto2classifier_test.rb

data/Gemfile.lock

@@ -1,9 +1,10 @@
 PATH
   remote: .
   specs:
-    natto2classifier (0.1.3)
+    natto2classifier (0.3.4)
       classifier-reborn
       natto
+      rb-gsl
 
 GEM
   remote: https://rubygems.org/
@@ -13,6 +14,7 @@ GEM
     coderay (1.1.2)
     fast-stemmer (1.0.2)
     ffi (1.9.23)
+    gsl (2.1.0.3)
     method_source (0.9.0)
     minitest (5.11.3)
     natto (1.1.1)
@@ -21,6 +23,8 @@ GEM
       coderay (~> 1.1.0)
       method_source (~> 0.9.0)
     rake (10.5.0)
+    rb-gsl (1.16.0.6)
+      gsl
 
 PLATFORMS
   ruby
@@ -33,4 +37,4 @@ DEPENDENCIES
   rake (~> 10.0)
 
 BUNDLED WITH
-   1.16.1
+   1.17.2

data/README.md

@@ -1,5 +1,7 @@
 # Natto2classifier
 
+[![Build Status](https://travis-ci.org/kanayannet/natto2classifier.svg?branch=master)](https://travis-ci.org/kanayannet/natto2classifier)
+
 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/natto2classifier`. To experiment with that code, run `bin/console` for an interactive prompt.
 
 ## Installation
@@ -12,7 +14,7 @@ gem 'natto2classifier'
 
 And then execute:
 
-    $ bundle
+    $ bundle install
 
 Or install it yourself as:
 
@@ -20,11 +22,34 @@ Or install it yourself as:
 
 ## Usage
 
+### Baysian methods
+
+```
+bayes = Natto2classifier::Bayes.new '朝食', '夕食'
+bayes.train '朝食', '今日の朝食は納豆だ'
+bayes.train '夕食', '今日の夕食は湯豆腐だ'
+bayes.classify '納豆はいつも朝食べている' #=> '朝食'
+```
+
+### LSI methods
+
 ```
-classifier = Natto2classifier::Bayes.new '朝食', '夕食'
-classifier.train '朝食', '今日の朝食は納豆だ'
-classifier.train '夕食', '今日の夕食は湯豆腐だ'
-classifier.classify '納豆はいつも朝食べている' #=> '朝食'
+lsi = Natto2classifier::LSI.new
+lsi.add_item '今日の朝食は納豆だ', '朝食'
+lsi.add_item '今日の夕食は湯豆腐だ', '夕食'
+lsi.classify '納豆はいつも朝食べている' #=> '朝食'
+lsi.find_related '納豆はいつも朝食べている' #=> ['今日 キョウ の ノ 朝食 チョウショク は ハ 納豆 ナットウ だ ダ', '今日 キョウ の ノ 夕食 ユウショク は ハ 湯豆腐 ユドウフ だ ダ']
+```
+
+### validate methods
+
+```
+sample_data = CSV.read('./data/train.csv')
+bayes = Natto2classifier::Bayes.new '朝食', '夕食'
+cross_validate(bayes, sample_data) #=> report...
+
+test_data, training_data = sample_data.partition.with_index { |_, i| (i % 2).zero? }
+validate(bayes, training_data, test_data) #=> {"夕食"=>{"夕食"=>3, "朝食"=>0}, "朝食"=>{"夕食"=>...}}
 ```
 
 ## Development
@@ -35,7 +60,7 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/natto2classifier. 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.
+Bug reports and pull requests are welcome on GitHub at https://github.com/kanayannet/natto2classifier. 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
 
@@ -43,4 +68,4 @@ The gem is available as open source under the terms of the [MIT License](https:/
 
 ## Code of Conduct
 
-Everyone interacting in the Natto2classifier project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/natto2classifier/blob/master/CODE_OF_CONDUCT.md).
+Everyone interacting in the Natto2classifier project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/kanayannet/natto2classifier/blob/master/CODE_OF_CONDUCT.md).

data/data/train.csv

@@ -1,5 +1,5 @@
 朝食,卵かけご飯は醤油とあう
-朝食,目玉焼きは塩故障派だ。
+朝食,目玉焼きは塩胡椒派だ。
 朝食,納豆かけご飯はとても健康によい
 朝食,食パンはオーソドックスな朝食だ
 朝食,スクランブルエッグはホテルの朝食でよく出る

data/lib/natto2classifier.rb

@@ -1,20 +1,6 @@
 require 'natto2classifier/version'
 require 'natto2classifier/natto'
 require 'classifier-reborn'
-
-module Natto2classifier
-  # It is a library that classifies Japanese language.
-  class Bayes < ClassifierReborn::Bayes
-    alias_method :__train__, :train
-    alias_method :__classify__, :classify
-    private :__train__, :__classify__
-
-    def train(category, word)
-      __train__ category, Natto2classifier::Natto.parse(word).join(' ')
-    end
-
-    def classify(word)
-      __classify__ Natto2classifier::Natto.parse(word).join(' ')
-    end
-  end
-end
+require 'natto2classifier/bayes'
+require 'natto2classifier/lsi'
+require 'natto2classifier/validator'

data/lib/natto2classifier/bayes.rb

@@ -0,0 +1,17 @@
+
+module Natto2classifier
+  # It is a library that classifies Japanese language.
+  class Bayes < ClassifierReborn::Bayes
+    alias_method :__train__, :train
+    alias_method :__classify__, :classify
+    private :__train__, :__classify__
+
+    def train(category, word)
+      __train__ category, Natto2classifier::Natto.parse(word).join(' ')
+    end
+
+    def classify(word)
+      __classify__ Natto2classifier::Natto.parse(word).join(' ')
+    end
+  end
+end

data/lib/natto2classifier/lsi.rb

@@ -0,0 +1,22 @@
+
+module Natto2classifier
+  # It is a library that classifies Japanese language.
+  class LSI < ClassifierReborn::LSI
+    alias_method :__add_item__, :add_item
+    alias_method :__classify__, :classify
+    alias_method :__find_related__, :find_related
+    private :__add_item__, :__classify__, :__find_related__
+
+    def add_item(word, category)
+      __add_item__ Natto2classifier::Natto.parse(word).join(' '), category
+    end
+
+    def classify(word)
+      __classify__ Natto2classifier::Natto.parse(word).join(' ')
+    end
+
+    def find_related(word)
+      __find_related__ Natto2classifier::Natto.parse(word).join(' ')
+    end
+  end
+end

data/lib/natto2classifier/natto.rb

@@ -4,10 +4,13 @@ require 'natto'
 module Natto2classifier
   class Natto
     def self.parse(word)
-      nm = ::Natto::MeCab.new('-F%m\s%f[7]')
+      nm = ::Natto::MeCab.new
       results = []
-      nm.enum_parse(word.to_s).each do |n|
-        results << n.feature if !n.is_eos?
+      nm.parse(word.to_s) do |n|
+        break if n.is_eos?
+        kana = n.feature.split(',')[7]
+        results << n.surface
+        results << kana if !kana.nil? && kana != '*'
       end
       results
     end

data/lib/natto2classifier/validator.rb

@@ -0,0 +1,6 @@
+
+module Natto2classifier
+  module Validator
+    include ClassifierReborn::ClassifierValidator
+  end
+end

data/lib/natto2classifier/version.rb

@@ -1,3 +1,3 @@
 module Natto2classifier
-  VERSION = "0.1.3"
+  VERSION = "0.3.4"
 end

data/natto2classifier.gemspec

@@ -27,4 +27,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "pry"
   spec.add_runtime_dependency "natto"
   spec.add_runtime_dependency "classifier-reborn"
+  spec.add_runtime_dependency "rb-gsl"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: natto2classifier
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.3.4
 platform: ruby
 authors:
 - kanayannet
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2018-04-26 00:00:00.000000000 Z
+date: 2020-09-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -94,6 +94,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rb-gsl
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: It is a library that classifies Japanese language. It depends on classifier-reborn
   and natto.
 email:
@@ -102,6 +116,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".circleci/config.yml"
 - ".gitignore"
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
@@ -114,14 +129,17 @@ files:
 - bin/setup
 - data/train.csv
 - lib/natto2classifier.rb
+- lib/natto2classifier/bayes.rb
+- lib/natto2classifier/lsi.rb
 - lib/natto2classifier/natto.rb
+- lib/natto2classifier/validator.rb
 - lib/natto2classifier/version.rb
 - natto2classifier.gemspec
 homepage: https://github.com/kanayannet/natto2classifier
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -136,9 +154,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.14
-signing_key: 
+rubygems_version: 3.0.3
+signing_key:
 specification_version: 4
 summary: It is a library that classifies Japanese language.
 test_files: []