natto2classifier 0.2.0 → 0.3.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 51ad6e9876016e7a4202e0c5e97e2c1e67d208c4
-  data.tar.gz: 9684166a82e326f30b5b21a63658cd708540baad
+SHA256:
+  metadata.gz: cc64abd451078f00dbc116e3285248f1948acabf670642a4fe66e4b90f371cfb
+  data.tar.gz: 7c0e6ad7d763513d9a443a4fc1c65332464f2821ac986f2c81a5834360750970
 SHA512:
-  metadata.gz: b2811c6898c36d2e5d37267023a2f6121e38fa953e3c3d7191225b8d704c0c1d83c651f20353a09530739c46a8d0239f1d638153ffc221cd21509f6785323e44
-  data.tar.gz: a9e57167f00b04feac3653cbe2a8362ac0cfc0946dad2e34912764173a03ca35c8db77404feb285cde009e8380a26033b8e501ab53b9a6e873d7cfc63be52e77
+  metadata.gz: a1b2ecb24ef6bd19690e41e59232f353309862ef7007ffa8e4cfbabfceb883001a3dcdd50cadd015dc038542566b99fd117caddc7d6778afff2c37849d052dc0
+  data.tar.gz: 23f9c9af1ea91106c83741d003dd7c56b4b608bab789bf518e185f28f8bd2ffefbfecf981b7aeb8d5417f59c2fade90237ca505cb1330784eb82e30786d0244d

data/.circleci/config.yml

@@ -5,6 +5,7 @@ jobs:
       - image: kanayannet/natto2classifier:latest
     steps:
       - checkout
+      - run: echo 'run test'
       - run: bundle install
       - run: bundle exec ruby test/natto2classifier_test.rb
 workflows:
@@ -12,13 +13,3 @@ workflows:
   test:
     jobs:
       - test
-  scheduled-workflow:
-    triggers:
-      - schedule:
-          cron: "0 * * * *"
-          filters:
-            branches:
-              only:
-                - master
-    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

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    natto2classifier (0.2.0)
+    natto2classifier (0.3.5)
       classifier-reborn
       natto
       rb-gsl
@@ -13,16 +13,16 @@ GEM
       fast-stemmer (~> 1.0)
     coderay (1.1.2)
     fast-stemmer (1.0.2)
-    ffi (1.9.23)
+    ffi (1.13.1)
     gsl (2.1.0.3)
     method_source (0.9.0)
     minitest (5.11.3)
-    natto (1.1.1)
+    natto (1.2.0)
       ffi (>= 1.9.0)
     pry (0.11.3)
       coderay (~> 1.1.0)
       method_source (~> 0.9.0)
-    rake (10.5.0)
+    rake (13.0.1)
     rb-gsl (1.16.0.6)
       gsl
 
@@ -34,7 +34,7 @@ DEPENDENCIES
   minitest (~> 5.0)
   natto2classifier!
   pry
-  rake (~> 10.0)
+  rake (~> 13.0)
 
 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
@@ -39,6 +41,17 @@ 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
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
@@ -47,7 +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
 
@@ -55,4 +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/lib/natto2classifier.rb

@@ -3,3 +3,4 @@ require 'natto2classifier/natto'
 require 'classifier-reborn'
 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 = "0.2.0"
+  VERSION = "0.3.5"
 end

data/natto2classifier.gemspec

@@ -22,7 +22,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_development_dependency "bundler", "~> 1.16"
-  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rake", "~> 13.0"
   spec.add_development_dependency "minitest", "~> 5.0"
   spec.add_development_dependency "pry"
   spec.add_runtime_dependency "natto"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: natto2classifier
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.5
 platform: ruby
 authors:
 - kanayannet
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2018-04-27 00:00:00.000000000 Z
+date: 2020-09-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -30,14 +30,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -129,14 +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
@@ -151,9 +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: []