epitome 0.2.0 → 0.2.1
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/README.md +1 -1
- data/epitome.gemspec +1 -0
- data/lib/epitome/corpus.rb +5 -1
- data/lib/epitome/version.rb +1 -1
- metadata +16 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 572165e1f187d05239a75bd18b14a4406070cd5a
|
4
|
+
data.tar.gz: 03c28d28f1ba2666d47ad6cd2fb735bdf4b28d92
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 16b7611cbd38a1dc10981cd6cb75b20b71ec8c255dcd49859659d6522ad6e03aabdf2bb18d28ed0d6f4bc406c2b6525663316dc8bc76b136c5c774e44169bdfa
|
7
|
+
data.tar.gz: b3fb26c7bb937066c3986733ccfd3b53f3b52806ac537ad8786cbbb59b4231e271cf3886185baae9be15d273f73c0170e8c1d8943adc3e7a72053fef4dc0ac16
|
data/README.md
CHANGED
data/epitome.gemspec
CHANGED
@@ -22,6 +22,7 @@ Gem::Specification.new do |spec|
|
|
22
22
|
spec.add_development_dependency "bundler", "~> 1.9"
|
23
23
|
spec.add_development_dependency "rake", "~> 10.0"
|
24
24
|
spec.add_development_dependency "minitest"
|
25
|
+
spec.add_development_dependency "pry"
|
25
26
|
spec.add_dependency "scalpel"
|
26
27
|
spec.add_dependency "stopwords-filter"
|
27
28
|
end
|
data/lib/epitome/corpus.rb
CHANGED
@@ -1,5 +1,6 @@
|
|
1
1
|
require 'matrix'
|
2
2
|
require 'stopwords'
|
3
|
+
require 'pry'
|
3
4
|
|
4
5
|
module Epitome
|
5
6
|
class Corpus
|
@@ -95,7 +96,10 @@ module Epitome
|
|
95
96
|
def idf(word)
|
96
97
|
# Number of documents in which word appears
|
97
98
|
# Inverse Frequency Smooth (as per wikipedia article)
|
98
|
-
Math.log( @n_docs / n_docs_including_w(word) )
|
99
|
+
result = Math.log( @n_docs / n_docs_including_w(word) )
|
100
|
+
|
101
|
+
# Return 1 to avoid words having all the same td_idf by multiplying by 0
|
102
|
+
return result == 0 ? 1.0 : result
|
99
103
|
end
|
100
104
|
|
101
105
|
def tf(sentence, word)
|
data/lib/epitome/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: epitome
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- McFreely
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-06-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -52,6 +52,20 @@ dependencies:
|
|
52
52
|
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
55
69
|
- !ruby/object:Gem::Dependency
|
56
70
|
name: scalpel
|
57
71
|
requirement: !ruby/object:Gem::Requirement
|