analy_z 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: cafbd605a88e44b0b2e80aa2d919acaa099a0bc8
+  data.tar.gz: 71e59a86e64bf5f99ed72e520edbe444e1d86189
+SHA512:
+  metadata.gz: 2a97c6c54a3311af0e19517f0d5e09fbc461569d9c12d93be8e780a5efc22fd3766f7eafb0d2981993e4235abdd7d983b94b6d48148ccc0cbf780e586e716849
+  data.tar.gz: 10a3efaf2f55fa5b1146f070cf5ff983146f62197afeaffbe0407e68bf9376d0da7f453f82fe5665fe5d3cc9885a17d1660d6fd01cd123452fbeba3172d65010

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 2.1.1

data/Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in analy_z.gemspec
+gemspec
+
+gem 'nokogiri'
+gem 'natto'

data/README.md

@@ -0,0 +1,39 @@
+# AnalyZ
+
+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/analy_z`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'analy_z'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install analy_z
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, 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` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/analy_z/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/analy_z.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'analy_z/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "analy_z"
+  spec.version       = AnalyZ::VERSION
+  spec.authors       = ["nao215"]
+  spec.email         = ["xxxxxy.naoxxxxx@gmail.com"]
+
+  spec.summary       = %q{Text Analyzer}
+  spec.description   = %q{calcurate tf idf and hse(html semantic element) }
+  spec.homepage      = ""
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.9"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "analy_z"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/analy_z.rb

@@ -0,0 +1,161 @@
+require "analy_z/version"
+
+module AnalyZ
+
+  class Analyzer
+
+    require 'pp'
+    require 'natto'
+    require 'nokogiri'
+
+    attr_accessor :tf
+    attr_accessor :idf
+    attr_accessor :tf_idf
+    attr_accessor :hse_tf_idf
+    attr_accessor :words
+    attr_accessor :texts
+    attr_accessor :sentences
+
+    def initialize html, selector = 'body', type_ary = ['名詞']
+      @sentences = {}
+      Dir.glob("htmls/*.html").each do |f|
+        @sentences[f] = parse_html(Nokogiri::HTML.parse(File.read(f), nil, nil).css(selector).to_html)
+      end
+      analyze_words(@sentences)
+    end
+
+    def analyze_words sentences, type_ary = ['名詞']
+
+      @texts, @words, @tf, @idf, @hse = {}, {}, {}, {}, {}
+
+      sentences.each{|k, sentence| @texts[k] = sentence.map {|s| s[0]}.join }
+
+      sentences.each do |key, sentence_ary|
+        text = sentence_ary.map {|s| s[0] }.join
+        @words[key] = parse_by_natto(text, type_ary)
+        @tf[key] = calc_tf(@words[key])
+        @idf[key] = calc_idf(@texts, @words[key])
+        @hse[key] = calc_hse(@words[key], sentence_ary)
+      end
+
+      @tf_idf = calc_tf_idf(@tf, @idf)
+      @hse_tf_idf = calc_hse_tf_idf(@tf_idf, @hse)
+
+    end
+
+    def parse_html html
+      sentences, important_tags = [], []
+      tag_rep = /<(".*?"|'.*?'|[^'"])*?>/
+      h_tag_reg = /<[hH][1-4].*?>.*?<\/[hH][1-4]>/
+
+      important_tags = html.scan(h_tag_reg)
+        .map{|m| [m.gsub(/<(".*?"|'.*?'|[^'"])*?>/, ''), m.match(/[hH][1-4]/)[0] ]}
+
+      sentences = html.gsub(/\"/, '')
+          .split(tag_rep)
+          .delete_if{|el| el != ['h1', 'h2', 'h3', 'h4'] && el =~ /\s/ || el.length <= 1}
+          .map{|m| [m, 1]}
+
+      sentences.each_with_index do |sentence, i|
+        important_tags.each do |tag_data|
+          rate = 2    * 1.75  if tag_data[1] == 'h1'
+          rate = 1.5  * 1.75  if tag_data[1] == 'h2'
+          rate = 1.17 * 1.75  if tag_data[1] == 'h3'
+          rate = 1.17 * 1.75  if tag_data[1] == 'h4'
+          sentences[i][1] = rate if sentence[0].include?(tag_data[0]) || tag_data[0].include?(sentence[0])
+        end
+      end
+
+      sentences
+
+    end
+
+    def parse_by_natto text, type_ary
+      words = []
+
+      Natto::MeCab.new.parse(text).split(/\n/).map do |row|
+        row = row.split(/\t|,/)
+        words << row[0] if type_ary.include?(row[1]) # row[0] is word, row[1] is a part of speech
+      end
+
+      words
+    end
+
+    def calc_tf words
+      freq_hash = {}
+
+      words.each_with_index do |word, i|
+        freq_hash[word] = freq_hash.has_key?(word) ? freq_hash[word] + 1 : 1
+      end
+
+      tf_list = freq_hash.sort_by {|k, v| v }.reverse.map do |k, v|
+        [k, v / words.length.to_f]
+      end
+
+      tf_list    
+    end
+
+    def standardization_tf tf_ary_list, ave_word_num
+      return tf_ary_list.map do |tf_ary|
+        tf_ary.map do |tf|
+          [tf[0], tf[1] * (tf_ary.length / ave_word_num.to_f), tf_ary.length / ave_word_num.to_f]
+        end
+      end
+    end
+
+    def calc_idf sentences, words
+      words.map do |word|
+        cnt = 0
+        sentences.each {|k, v| cnt += 1 if v.include?(word) }
+        [word, Math.log(sentences.length / cnt.to_f)]
+      end
+    end
+
+    def calc_hse words, sentence_ary
+      sentence_ary = sentence_ary.select{|sentence| sentence[1] != 1}
+      words.map do |word|
+        rate = 1
+        sentence_ary.each do |sentence|
+          rate = sentence[1] if sentence[0].include?(word[0])
+        end
+        [word, rate]
+      end.uniq
+    end
+
+    def calc_tf_idf tf_list_hash, idf_list_hash
+
+      tf_idfs = {}
+
+      tf_list_hash.each do |k, tf|
+        tf_idf = []
+        idf_list_hash[k].each do |idf|
+          tf_idf << [idf[0], idf[1] * tf.assoc(idf[0])[1]]
+        end
+        tf_idfs[k] = tf_idf.sort{ |a, b| b[1] <=> a[1] }.uniq
+      end
+
+      tf_idfs
+
+    end
+
+    def calc_hse_tf_idf tf_idf_list_hash, hse
+
+      hse_tf_idf = {}
+
+      hse.each do |k, h|
+        hse[k] = hse[k].select {|h| h[1] != 1 }
+      end
+
+      tf_idf_list_hash.each do |k, tf_idf_list|
+        hse_tf_idf[k] = tf_idf_list.map do |tf_idf|
+          rate = hse[k].assoc(tf_idf[0]) ? hse[k].assoc(tf_idf[0])[1] : 1
+          [tf_idf[0], tf_idf[1] * rate]
+        end
+      end
+
+      hse_tf_idf
+    end
+
+  end
+
+end

data/lib/analy_z/version.rb

@@ -0,0 +1,3 @@
+module AnalyZ
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,82 @@
+--- !ruby/object:Gem::Specification
+name: analy_z
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- nao215
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-04-29 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: 'calcurate tf idf and hse(html semantic element) '
+email:
+- xxxxxy.naoxxxxx@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- analy_z.gemspec
+- bin/console
+- bin/setup
+- lib/analy_z.rb
+- lib/analy_z/version.rb
+homepage: ''
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.7
+signing_key: 
+specification_version: 4
+summary: Text Analyzer
+test_files: []