r_nlp 0.1.2 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -0
- data/Gemfile +1 -0
- data/lib/r_nlp/tf.rb +14 -7
- data/lib/r_nlp/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2d8f0021f488416a72a26484fdd9fde599e05244
|
4
|
+
data.tar.gz: 185b888000e5cae91aa135987de2a2fa761f4605
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 695a3828c1c8e0088e1e34f3e48d086067a228b9c4d239c4465c8913dcd91b2f7447435cd34105faee2e39963f29735ff7a5a8a220c454c56eee69ff0be43ba7
|
7
|
+
data.tar.gz: 127b0dba439b80b19be1528f2678f99678f55e22de23e9879720ae89dc209866cc76ea774c06f795a12cf1f6ef61d259add773bec95f1946c20257ef9d163019
|
data/.gitignore
CHANGED
data/Gemfile
CHANGED
data/lib/r_nlp/tf.rb
CHANGED
@@ -12,17 +12,24 @@ module RNlp
|
|
12
12
|
tf = Hash.new
|
13
13
|
if @lang == 'ja'
|
14
14
|
nm = Natto::MeCab.new
|
15
|
-
text.each do |line|
|
16
|
-
nm.parse(
|
17
|
-
|
18
|
-
tf[word.surface]
|
15
|
+
text.split("\n").each do |line|
|
16
|
+
nm.parse(line) do |word|
|
17
|
+
next if word.stat == 3
|
18
|
+
if tf[word.surface] == nil
|
19
|
+
tf[word.surface] = 1
|
20
|
+
else
|
21
|
+
tf[word.surface] += 1
|
22
|
+
end
|
19
23
|
end
|
20
24
|
end
|
21
25
|
elsif @lang == 'en'
|
22
|
-
text.each do |line|
|
26
|
+
text.split(" ").each do |line|
|
23
27
|
line.split(" ").each do |word|
|
24
|
-
|
25
|
-
|
28
|
+
if tf[word] == nil
|
29
|
+
tf[word] = 1
|
30
|
+
else
|
31
|
+
tf[word] += 1
|
32
|
+
end
|
26
33
|
end
|
27
34
|
end
|
28
35
|
else
|
data/lib/r_nlp/version.rb
CHANGED