rblearn 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/rblearn/CountVectorizer.rb +0 -3
- data/lib/rblearn/version.rb +1 -1
- metadata +1 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: baeb51c361fba549f4909d2d9dc082b56b07bc54
|
|
4
|
+
data.tar.gz: 17855594b1a780753f5a6e708be8603aaa3497db
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: beb24d4020d67d1b9e7e6455d682433adee10848dfdb5e01a940a22d470778120713e05d2d0780173ec4d87aa0399895c97509f145768a2bbe13793e5bddddf0
|
|
7
|
+
data.tar.gz: 060d38b1a4fd38c05f4937b447f037bab7f662ea13f9849443a5c479601f8781b149cc450f54602225aae0961e11dba0cd77432f10b4e12feb80cb3b32df654c
|
|
@@ -47,8 +47,6 @@ module Rblearn
|
|
|
47
47
|
end
|
|
48
48
|
|
|
49
49
|
all_vocaburaries.uniq!
|
|
50
|
-
word_frequency = word_frequency.sort{|(_, value1), (_, value2)| value2 <=> value1}
|
|
51
|
-
|
|
52
50
|
all_vocaburaries.each do |token|
|
|
53
51
|
tf = 1 + Math.log(word_frequency[token])
|
|
54
52
|
idf = Math.log(1+(document_size/document_frequency[token]))
|
|
@@ -56,7 +54,6 @@ module Rblearn
|
|
|
56
54
|
end
|
|
57
55
|
|
|
58
56
|
word_tfidf_score = word_tfidf_score.sort{|(_, v1), (_, v2)| v2 <=> v1}
|
|
59
|
-
|
|
60
57
|
feature_names = (0...(word_tfidf_score.size * @max_feature).to_i).map{|i| word_tfidf_score[i][0]}
|
|
61
58
|
|
|
62
59
|
token2index = {}
|
data/lib/rblearn/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: rblearn
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- himkt
|
|
@@ -142,4 +142,3 @@ signing_key:
|
|
|
142
142
|
specification_version: 4
|
|
143
143
|
summary: Simple repository for machine learning
|
|
144
144
|
test_files: []
|
|
145
|
-
has_rdoc:
|