nekoneko_gen 0.1.0 → 0.1.1

data/lib/nekoneko_gen/text_classifier_generator.rb

@@ -83,7 +83,6 @@ require 'bimyou_segmenter'
 
 class #{@name}
   def self.predict(text)
-    vec = Hash.new(0)
     prev = nil
     vec = BimyouSegmenter.segment(text).map do |word|
       if (prev)
@@ -226,7 +225,6 @@ MODEL
                               '(^[々〇ヵヶ' + [0x3400].pack('U') + '-' + [0x9FFF].pack('U') +
                               [0xF900].pack('U') + '-' + [0xFAFF].pack('U') +
                               [0x20000].pack('U') + '-' + [0x2FFFF].pack('U') + ']+$)')
-    WORD_COUNT_THRESH = 2
     STOP_WORDS = {"の"=>1, "に"=>1, "て"=>1, "が"=>1, "た"=>1, "は"=>1, "で"=>1, "を"=>1, "と"=>1, "か"=>1, "も"=>1, "ない"=>1, "だ"=>1, "な"=>1, "です"=>1, "から"=>1, "ます"=>1, "う"=>1, "けど"=>1, "って"=>1, "ば"=>1, "よ"=>1, "まし"=>1, "たら"=>1, "ね"=>1, "ん"=>1, "なら"=>1, "でしょ"=>1, "とか"=>1, "じゃ"=>1, "まで"=>1, "ので"=>1, "ませ"=>1, "だけ"=>1, "へ"=>1, "なく"=>1, "という"=>1, "や"=>1, "でも"=>1, "ござい"=>1, "し"=>1, "たい"=>1, "だろ"=>1, "なかっ"=>1, "ある"=>1, "ず"=>1, "たり"=>1, "だっ"=>1, "しか"=>1, "くらい"=>1, "かも"=>1, "ながら"=>1, "でし"=>1, "また"=>1, "より"=>1, "のに"=>1, "わ"=>1, "など"=>1, "として"=>1, "ぬ"=>1, "あっ"=>1, "らしい"=>1, "ばかり"=>1, "ほど"=>1, "ぞ"=>1, "しかし"=>1, "なけれ"=>1, "ただ"=>1, "つ"=>1, "けれども"=>1, "んで"=>1, "ぐらい"=>1, "なんて"=>1, "について"=>1, "そうして"=>1, "ましょ"=>1, "さえ"=>1, "のみ"=>1, "たく"=>1, "あり"=>1, "る"=>1, "なんか"=>1, "べき"=>1, "だって"=>1, "それとも"=>1, "ちゃ"=>1, "なぁ"=>1, "それから"=>1, "さ"=>1, "ぜ"=>1, "によって"=>1, "ねえ"=>1, "っけ"=>1, "やら"=>1, "だから"=>1, "とも"=>1, "いや"=>1, "なり"=>1, "それでも"=>1, "なあ"=>1, "まい"=>1, "つつ"=>1, "そして"=>1, "それで"=>1, "かい"=>1, "すると"=>1, "しかも"=>1, "あろ"=>1, "らしく"=>1, "ずつ"=>1, "り"=>1, "たる"=>1, "又"=>1, "ねぇ"=>1, "に対して"=>1, "け"=>1, "こそ"=>1, "もしくは"=>1, "なきゃ"=>1, "だら"=>1, "そこで"=>1, "すら"=>1, "実は"=>1, "ところが"=>1, "なる"=>1, "による"=>1, "御座い"=>1, "じゃん"=>1, "つまり"=>1, "けれど"=>1, "ただし"=>1, "だの"=>1, "たかっ"=>1, "ざる"=>1, "ごとく"=>1, "に対する"=>1, "とかいう"=>1, "かしら"=>1, "なくっ"=>1, "そりゃ"=>1, "または"=>1, "べ"=>1, "にて"=>1, "において"=>1, "たろ"=>1, "無い"=>1, "あれ"=>1, "なぞ"=>1, "っと"=>1, "き"=>1, "にとって"=>1, "たって"=>1, "じ"=>1, "あるいは"=>1, "ど"=>1, "っす"=>1, "だり"=>1, "又は"=>1, "ばっかり"=>1, "てか"=>1, "けども"=>1, "と共に"=>1, "れ"=>1, "なかろ"=>1, "なお"=>1, "ものの"=>1, "に関する"=>1, "ばっか"=>1, "こうして"=>1, "程"=>1, "べし"=>1, "たとえば"=>1, "ども"=>1, "一方"=>1, "それでは"=>1, "かつ"=>1, "やし"=>1, "だけど"=>1, "なんぞ"=>1, "べく"=>1, "迄"=>1, "如く"=>1, "ってか"=>1, "すなわち"=>1, "さて"=>1, "どころか"=>1, "では"=>1, "を以て"=>1, "かぁ"=>1, "のう"=>1, "らしかっ"=>1, "そしたら"=>1, "にゃ"=>1, "まじ"=>1, "るる"=>1, "らし"=>1, "やん"=>1, "たけれ"=>1, "らしき"=>1, "しも"=>1, "べから"=>1, "或いは"=>1, "及び"=>1, "だが"=>1, "ごとき"=>1, "なし"=>1, "如き"=>1, "ねん"=>1, "但し"=>1, "ござる"=>1, "いえ"=>1, "故に"=>1, "即ち"=>1, "やっ"=>1, "なき"=>1, "無かっ"=>1, "なけりゃ"=>1, "即"=>1, "よって"=>1, "或は"=>1, "および"=>1, "尚"=>1, "否"=>1, "じゃろ"=>1, "っしょ"=>1, "尤も"=>1, "だに"=>1, "やす"=>1, "ござん"=>1, "ついで"=>1, "へん"=>1, "じゃっ"=>1, "わい"=>1, "次に"=>1, "之"=>1, "ける"=>1, "然し"=>1, "もっとも"=>1, "そうしたら"=>1, "無く"=>1, "やろ"=>1, "亦"=>1, "っし"=>1, "に対し"=>1, "乃至"=>1, "なれ"=>1, "御座る"=>1, "御座ん"=>1, "とう"=>1, "てえ"=>1, "但"=>1, "どし"=>1, "ざり"=>1, "といふ"=>1, "たれ"=>1, "したら"=>1, "もん"=>1, "やせ"=>1, "たくっ"=>1, "若しくは"=>1, "ずん"=>1, "あら"=>1, "ざれ"=>1, "無かろ"=>1, "無けれ"=>1, "ごとし"=>1, "たきゃ"=>1, "どす"=>1, "けり"=>1, "まじき"=>1, "ますれ"=>1, "たき"=>1, "てん"=>1, "たけりゃ"=>1, "無き"=>1, "無"=>1, "如し"=>1, "あん"=>1, "御座っ"=>1, "ありゃ"=>1, "かな"=>1, "ばかし"=>1}
   end
 end

data/lib/nekoneko_gen/version.rb

@@ -1,4 +1,4 @@
 # -*- coding: utf-8 -*-
 module NekonekoGen
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/test/nekoneko_gen_test.rb

@@ -14,11 +14,11 @@ class NekonekoGenTest < Test::Unit::TestCase
   end
   def cleanup!
     begin
-      #File.unlink(@output_file2)
+      File.unlink(@output_file2)
     rescue
     end
     begin
-      #File.unlink(@output_file3)
+      File.unlink(@output_file3)
     rescue
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nekoneko_gen
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-28 00:00:00.000000000Z
+date: 2012-05-29 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bimyou_segmenter
-  requirement: &12499360 !ruby/object:Gem::Requirement
+  requirement: &7671220 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *12499360
+  version_requirements: *7671220
 - !ruby/object:Gem::Dependency
   name: json
-  requirement: &12498260 !ruby/object:Gem::Requirement
+  requirement: &7668960 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *12498260
+  version_requirements: *7668960
 - !ruby/object:Gem::Dependency
   name: test-unit
-  requirement: &12497600 !ruby/object:Gem::Requirement
+  requirement: &7641320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,7 +43,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *12497600
+  version_requirements: *7641320
 description: Japanese Text Classifier Generator
 email:
 - nagadomi@nurs.or.jp