analy_z 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.travis.yml +3 -0
- data/Gemfile +7 -0
- data/README.md +39 -0
- data/Rakefile +1 -0
- data/analy_z.gemspec +23 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/lib/analy_z.rb +161 -0
- data/lib/analy_z/version.rb +3 -0
- metadata +82 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: cafbd605a88e44b0b2e80aa2d919acaa099a0bc8
|
4
|
+
data.tar.gz: 71e59a86e64bf5f99ed72e520edbe444e1d86189
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2a97c6c54a3311af0e19517f0d5e09fbc461569d9c12d93be8e780a5efc22fd3766f7eafb0d2981993e4235abdd7d983b94b6d48148ccc0cbf780e586e716849
|
7
|
+
data.tar.gz: 10a3efaf2f55fa5b1146f070cf5ff983146f62197afeaffbe0407e68bf9376d0da7f453f82fe5665fe5d3cc9885a17d1660d6fd01cd123452fbeba3172d65010
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# AnalyZ
|
2
|
+
|
3
|
+
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.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'analy_z'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install analy_z
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
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.
|
30
|
+
|
31
|
+
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).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
1. Fork it ( https://github.com/[my-github-username]/analy_z/fork )
|
36
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
37
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
38
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
39
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/analy_z.gemspec
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'analy_z/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "analy_z"
|
8
|
+
spec.version = AnalyZ::VERSION
|
9
|
+
spec.authors = ["nao215"]
|
10
|
+
spec.email = ["xxxxxy.naoxxxxx@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Text Analyzer}
|
13
|
+
spec.description = %q{calcurate tf idf and hse(html semantic element) }
|
14
|
+
spec.homepage = ""
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.9"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "analy_z"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/analy_z.rb
ADDED
@@ -0,0 +1,161 @@
|
|
1
|
+
require "analy_z/version"
|
2
|
+
|
3
|
+
module AnalyZ
|
4
|
+
|
5
|
+
class Analyzer
|
6
|
+
|
7
|
+
require 'pp'
|
8
|
+
require 'natto'
|
9
|
+
require 'nokogiri'
|
10
|
+
|
11
|
+
attr_accessor :tf
|
12
|
+
attr_accessor :idf
|
13
|
+
attr_accessor :tf_idf
|
14
|
+
attr_accessor :hse_tf_idf
|
15
|
+
attr_accessor :words
|
16
|
+
attr_accessor :texts
|
17
|
+
attr_accessor :sentences
|
18
|
+
|
19
|
+
def initialize html, selector = 'body', type_ary = ['名詞']
|
20
|
+
@sentences = {}
|
21
|
+
Dir.glob("htmls/*.html").each do |f|
|
22
|
+
@sentences[f] = parse_html(Nokogiri::HTML.parse(File.read(f), nil, nil).css(selector).to_html)
|
23
|
+
end
|
24
|
+
analyze_words(@sentences)
|
25
|
+
end
|
26
|
+
|
27
|
+
def analyze_words sentences, type_ary = ['名詞']
|
28
|
+
|
29
|
+
@texts, @words, @tf, @idf, @hse = {}, {}, {}, {}, {}
|
30
|
+
|
31
|
+
sentences.each{|k, sentence| @texts[k] = sentence.map {|s| s[0]}.join }
|
32
|
+
|
33
|
+
sentences.each do |key, sentence_ary|
|
34
|
+
text = sentence_ary.map {|s| s[0] }.join
|
35
|
+
@words[key] = parse_by_natto(text, type_ary)
|
36
|
+
@tf[key] = calc_tf(@words[key])
|
37
|
+
@idf[key] = calc_idf(@texts, @words[key])
|
38
|
+
@hse[key] = calc_hse(@words[key], sentence_ary)
|
39
|
+
end
|
40
|
+
|
41
|
+
@tf_idf = calc_tf_idf(@tf, @idf)
|
42
|
+
@hse_tf_idf = calc_hse_tf_idf(@tf_idf, @hse)
|
43
|
+
|
44
|
+
end
|
45
|
+
|
46
|
+
def parse_html html
|
47
|
+
sentences, important_tags = [], []
|
48
|
+
tag_rep = /<(".*?"|'.*?'|[^'"])*?>/
|
49
|
+
h_tag_reg = /<[hH][1-4].*?>.*?<\/[hH][1-4]>/
|
50
|
+
|
51
|
+
important_tags = html.scan(h_tag_reg)
|
52
|
+
.map{|m| [m.gsub(/<(".*?"|'.*?'|[^'"])*?>/, ''), m.match(/[hH][1-4]/)[0] ]}
|
53
|
+
|
54
|
+
sentences = html.gsub(/\"/, '')
|
55
|
+
.split(tag_rep)
|
56
|
+
.delete_if{|el| el != ['h1', 'h2', 'h3', 'h4'] && el =~ /\s/ || el.length <= 1}
|
57
|
+
.map{|m| [m, 1]}
|
58
|
+
|
59
|
+
sentences.each_with_index do |sentence, i|
|
60
|
+
important_tags.each do |tag_data|
|
61
|
+
rate = 2 * 1.75 if tag_data[1] == 'h1'
|
62
|
+
rate = 1.5 * 1.75 if tag_data[1] == 'h2'
|
63
|
+
rate = 1.17 * 1.75 if tag_data[1] == 'h3'
|
64
|
+
rate = 1.17 * 1.75 if tag_data[1] == 'h4'
|
65
|
+
sentences[i][1] = rate if sentence[0].include?(tag_data[0]) || tag_data[0].include?(sentence[0])
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
sentences
|
70
|
+
|
71
|
+
end
|
72
|
+
|
73
|
+
def parse_by_natto text, type_ary
|
74
|
+
words = []
|
75
|
+
|
76
|
+
Natto::MeCab.new.parse(text).split(/\n/).map do |row|
|
77
|
+
row = row.split(/\t|,/)
|
78
|
+
words << row[0] if type_ary.include?(row[1]) # row[0] is word, row[1] is a part of speech
|
79
|
+
end
|
80
|
+
|
81
|
+
words
|
82
|
+
end
|
83
|
+
|
84
|
+
def calc_tf words
|
85
|
+
freq_hash = {}
|
86
|
+
|
87
|
+
words.each_with_index do |word, i|
|
88
|
+
freq_hash[word] = freq_hash.has_key?(word) ? freq_hash[word] + 1 : 1
|
89
|
+
end
|
90
|
+
|
91
|
+
tf_list = freq_hash.sort_by {|k, v| v }.reverse.map do |k, v|
|
92
|
+
[k, v / words.length.to_f]
|
93
|
+
end
|
94
|
+
|
95
|
+
tf_list
|
96
|
+
end
|
97
|
+
|
98
|
+
def standardization_tf tf_ary_list, ave_word_num
|
99
|
+
return tf_ary_list.map do |tf_ary|
|
100
|
+
tf_ary.map do |tf|
|
101
|
+
[tf[0], tf[1] * (tf_ary.length / ave_word_num.to_f), tf_ary.length / ave_word_num.to_f]
|
102
|
+
end
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
def calc_idf sentences, words
|
107
|
+
words.map do |word|
|
108
|
+
cnt = 0
|
109
|
+
sentences.each {|k, v| cnt += 1 if v.include?(word) }
|
110
|
+
[word, Math.log(sentences.length / cnt.to_f)]
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
def calc_hse words, sentence_ary
|
115
|
+
sentence_ary = sentence_ary.select{|sentence| sentence[1] != 1}
|
116
|
+
words.map do |word|
|
117
|
+
rate = 1
|
118
|
+
sentence_ary.each do |sentence|
|
119
|
+
rate = sentence[1] if sentence[0].include?(word[0])
|
120
|
+
end
|
121
|
+
[word, rate]
|
122
|
+
end.uniq
|
123
|
+
end
|
124
|
+
|
125
|
+
def calc_tf_idf tf_list_hash, idf_list_hash
|
126
|
+
|
127
|
+
tf_idfs = {}
|
128
|
+
|
129
|
+
tf_list_hash.each do |k, tf|
|
130
|
+
tf_idf = []
|
131
|
+
idf_list_hash[k].each do |idf|
|
132
|
+
tf_idf << [idf[0], idf[1] * tf.assoc(idf[0])[1]]
|
133
|
+
end
|
134
|
+
tf_idfs[k] = tf_idf.sort{ |a, b| b[1] <=> a[1] }.uniq
|
135
|
+
end
|
136
|
+
|
137
|
+
tf_idfs
|
138
|
+
|
139
|
+
end
|
140
|
+
|
141
|
+
def calc_hse_tf_idf tf_idf_list_hash, hse
|
142
|
+
|
143
|
+
hse_tf_idf = {}
|
144
|
+
|
145
|
+
hse.each do |k, h|
|
146
|
+
hse[k] = hse[k].select {|h| h[1] != 1 }
|
147
|
+
end
|
148
|
+
|
149
|
+
tf_idf_list_hash.each do |k, tf_idf_list|
|
150
|
+
hse_tf_idf[k] = tf_idf_list.map do |tf_idf|
|
151
|
+
rate = hse[k].assoc(tf_idf[0]) ? hse[k].assoc(tf_idf[0])[1] : 1
|
152
|
+
[tf_idf[0], tf_idf[1] * rate]
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
hse_tf_idf
|
157
|
+
end
|
158
|
+
|
159
|
+
end
|
160
|
+
|
161
|
+
end
|
metadata
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: analy_z
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- nao215
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-04-29 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.9'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.9'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
description: 'calcurate tf idf and hse(html semantic element) '
|
42
|
+
email:
|
43
|
+
- xxxxxy.naoxxxxx@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- ".gitignore"
|
49
|
+
- ".rspec"
|
50
|
+
- ".travis.yml"
|
51
|
+
- Gemfile
|
52
|
+
- README.md
|
53
|
+
- Rakefile
|
54
|
+
- analy_z.gemspec
|
55
|
+
- bin/console
|
56
|
+
- bin/setup
|
57
|
+
- lib/analy_z.rb
|
58
|
+
- lib/analy_z/version.rb
|
59
|
+
homepage: ''
|
60
|
+
licenses: []
|
61
|
+
metadata: {}
|
62
|
+
post_install_message:
|
63
|
+
rdoc_options: []
|
64
|
+
require_paths:
|
65
|
+
- lib
|
66
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
67
|
+
requirements:
|
68
|
+
- - ">="
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
requirements: []
|
77
|
+
rubyforge_project:
|
78
|
+
rubygems_version: 2.4.7
|
79
|
+
signing_key:
|
80
|
+
specification_version: 4
|
81
|
+
summary: Text Analyzer
|
82
|
+
test_files: []
|