analy_z 0.1.2 → 0.1.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/analy_z.rb +28 -8
- data/lib/analy_z/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 257d11a71d341c246d265954ebdd1f557332867d
|
4
|
+
data.tar.gz: 0ad929efdd028daa2509005473322951f9d37ba1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6da8e91ad8f952e7f2f0c9ee02c79557fda628f5b2995c60a119d0de91d71fd7937965c77d9ee2e7277fbaa24b1b83c82c20d95e4c1bb336a9b745da1d91e891
|
7
|
+
data.tar.gz: 448bbe2ae21c0bde8d4964e966cd6909de326cc63696b74a631d8a41b5923d292af8d0e6e6706fce47301cf9f73f3d1ae2f8f3435e601e9fad596e7d49a10a55
|
data/lib/analy_z.rb
CHANGED
@@ -5,6 +5,7 @@ module AnalyZ
|
|
5
5
|
class Analyzer
|
6
6
|
|
7
7
|
require 'pp'
|
8
|
+
require 'date'
|
8
9
|
require 'natto'
|
9
10
|
require 'nokogiri'
|
10
11
|
|
@@ -19,26 +20,42 @@ module AnalyZ
|
|
19
20
|
def initialize html_path, selector = 'body', type_ary = ['名詞']
|
20
21
|
@sentences = {}
|
21
22
|
Dir.glob(html_path).each do |f|
|
23
|
+
print '.'
|
22
24
|
@sentences[f] = parse_html(Nokogiri::HTML.parse(File.read(f), nil, nil).css(selector).to_html)
|
23
25
|
end
|
24
|
-
analyze_words(@sentences)
|
25
|
-
end
|
26
26
|
|
27
|
-
|
27
|
+
puts "\n=== creating sentences file ==="
|
28
|
+
txt = ""
|
29
|
+
@sentences.each do |k, sentences|
|
30
|
+
print '.'
|
31
|
+
txt << sentences.map{|s| s[0] }.join + '/=== EOS ===/'
|
32
|
+
end
|
33
|
+
|
34
|
+
text_file_path = "tmp/#{DateTime.now}.txt"
|
35
|
+
File.write(text_file_path, txt)
|
28
36
|
|
29
|
-
|
37
|
+
puts "\n=== analyzing... ==="
|
38
|
+
analyze_words(@sentences, text_file_path)
|
39
|
+
end
|
30
40
|
|
31
|
-
|
41
|
+
def analyze_words sentences, text_file_path, type_ary = ['名詞']
|
32
42
|
|
43
|
+
@words, @tf, @idf, @hse = {}, {}, {}, {}
|
44
|
+
|
45
|
+
puts "=== calculating tf and idf and hse ==="
|
33
46
|
sentences.each do |key, sentence_ary|
|
47
|
+
print '.'
|
34
48
|
text = sentence_ary.map {|s| s[0] }.join
|
35
49
|
@words[key] = parse_by_natto(text, type_ary)
|
36
50
|
@tf[key] = calc_tf(@words[key])
|
37
|
-
@idf[key] = calc_idf(@
|
51
|
+
@idf[key] = calc_idf(@words[key], text_file_path)
|
38
52
|
@hse[key] = calc_hse(@words[key], sentence_ary)
|
39
53
|
end
|
40
54
|
|
55
|
+
puts "\n=== calculating tf idf ==="
|
41
56
|
@tf_idf = calc_tf_idf(@tf, @idf)
|
57
|
+
|
58
|
+
puts "=== calculating hse tf idf ==="
|
42
59
|
@hse_tf_idf = calc_hse_tf_idf(@tf_idf, @hse)
|
43
60
|
|
44
61
|
end
|
@@ -103,10 +120,13 @@ module AnalyZ
|
|
103
120
|
end
|
104
121
|
end
|
105
122
|
|
106
|
-
def calc_idf
|
123
|
+
def calc_idf words, text_file_path
|
124
|
+
texts = File.read(text_file_path).split('/=== EOS ===/')
|
107
125
|
words.map do |word|
|
108
126
|
cnt = 0
|
109
|
-
|
127
|
+
texts.each do |text|
|
128
|
+
cnt += 1 if text.include?(word)
|
129
|
+
end
|
110
130
|
[word, Math.log(sentences.length / cnt.to_f)]
|
111
131
|
end
|
112
132
|
end
|
data/lib/analy_z/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: analy_z
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- nao215
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-04-
|
11
|
+
date: 2016-04-30 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: natto
|