r_nlp 0.1.4 → 0.1.5
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/r_nlp/idf.rb +27 -0
- data/lib/r_nlp/tf.rb +5 -4
- data/lib/r_nlp/version.rb +1 -1
- data/lib/r_nlp.rb +1 -0
- metadata +2 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3d61657fc30af65e20df603b8ab79b6a85671d02
|
4
|
+
data.tar.gz: 97517fb59114c31571d9af656428c483583b113c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7eca6f24c111164ca86573a1edc0ff34863e93f6c321b5139fa649408a70c926389ad817ed2a957fab5735297165cc17f0f8a5b142ef363199dd840330e4d7b1
|
7
|
+
data.tar.gz: 8d0a61c57d946406ee892fac514a1ccfaf74a0a73edc8196a21747fd28c674a495d0c4e2fdd8135c707ea161aea813ae8734756f2d698d6a60c30080c237a52b
|
data/lib/r_nlp/idf.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
module RNlp
|
4
|
+
class Idf
|
5
|
+
# compatible with ja or en
|
6
|
+
attr_reader :lang
|
7
|
+
def initialize(lang)
|
8
|
+
@lang = lang
|
9
|
+
unless lang == 'ja' || lang == 'en'
|
10
|
+
puts "#{@lang} is not compatible language\nlang should be 'ja' or 'en'"
|
11
|
+
exit
|
12
|
+
end
|
13
|
+
end
|
14
|
+
# documents should be array of string
|
15
|
+
def calc_idf(word, documents)
|
16
|
+
@word = word
|
17
|
+
@documents = documents
|
18
|
+
n = @documents.size
|
19
|
+
df = 0.0
|
20
|
+
@documents.each do |document|
|
21
|
+
df += 1 if document =~ /#{@word}/
|
22
|
+
end
|
23
|
+
idf = Math.log2(n/df) + 1
|
24
|
+
return idf
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
data/lib/r_nlp/tf.rb
CHANGED
@@ -7,6 +7,10 @@ module RNlp
|
|
7
7
|
attr_reader :lang
|
8
8
|
def initialize(lang)
|
9
9
|
@lang = lang
|
10
|
+
unless lang == 'ja' || lang == 'en'
|
11
|
+
puts "lang #{@lang} is not compatible."
|
12
|
+
exit
|
13
|
+
end
|
10
14
|
end
|
11
15
|
def count(text)
|
12
16
|
tf = Hash.new
|
@@ -23,7 +27,7 @@ module RNlp
|
|
23
27
|
end
|
24
28
|
end
|
25
29
|
elsif @lang == 'en'
|
26
|
-
text.split("
|
30
|
+
text.split("\n").each do |line|
|
27
31
|
line.split(" ").each do |word|
|
28
32
|
if tf[word] == nil
|
29
33
|
tf[word] = 1
|
@@ -32,9 +36,6 @@ module RNlp
|
|
32
36
|
end
|
33
37
|
end
|
34
38
|
end
|
35
|
-
else
|
36
|
-
puts "lang #{@lang} is not compatible."
|
37
|
-
exit
|
38
39
|
end
|
39
40
|
return tf
|
40
41
|
end
|
data/lib/r_nlp/version.rb
CHANGED
data/lib/r_nlp.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: r_nlp
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- himkt
|
@@ -70,6 +70,7 @@ files:
|
|
70
70
|
- bin/console
|
71
71
|
- bin/setup
|
72
72
|
- lib/r_nlp.rb
|
73
|
+
- lib/r_nlp/idf.rb
|
73
74
|
- lib/r_nlp/tf.rb
|
74
75
|
- lib/r_nlp/version.rb
|
75
76
|
- r_nlp.gemspec
|