similarity 0.2.4 → 0.2.5
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/similarity/corpus.rb +11 -0
- data/lib/similarity/term_document_matrix.rb +10 -5
- metadata +75 -64
data/lib/similarity/corpus.rb
CHANGED
@@ -68,6 +68,17 @@ class Corpus
|
|
68
68
|
end
|
69
69
|
end
|
70
70
|
|
71
|
+
def similar_documents(document)
|
72
|
+
index = documents.index(document)
|
73
|
+
return nil if index.nil?
|
74
|
+
|
75
|
+
results = documents.each_with_index.map do |doc, doc_index|
|
76
|
+
similarity = similarity_matrix[index, doc_index]
|
77
|
+
[doc, similarity]
|
78
|
+
end
|
79
|
+
results.sort { |a,b| b.last <=> a.last }
|
80
|
+
end
|
81
|
+
|
71
82
|
def weights(document)
|
72
83
|
idx = @documents.index(document)
|
73
84
|
terms = @terms.to_a.map {|term| term.first}
|
@@ -1,17 +1,22 @@
|
|
1
1
|
require 'gsl'
|
2
2
|
|
3
3
|
class TermDocumentMatrix
|
4
|
-
attr_reader :matrix, :labels
|
4
|
+
attr_reader :matrix, :labels, :number_of_terms, :number_of_documents, :non_zeros
|
5
5
|
|
6
6
|
def initialize(corpus)
|
7
7
|
@matrix = GSL::Matrix.alloc(corpus.terms.size, corpus.document_count)
|
8
|
+
@non_zeros = 0
|
9
|
+
@number_of_terms = corpus.terms.size
|
10
|
+
@number_of_documents = corpus.documents.size
|
8
11
|
|
9
|
-
corpus.
|
10
|
-
|
11
|
-
|
12
|
-
|
12
|
+
corpus.terms.each_with_index do |term, term_index|
|
13
|
+
term = term.first
|
14
|
+
idf = corpus.inverse_document_frequency(term)
|
15
|
+
|
16
|
+
corpus.documents.each_with_index do |document, document_index|
|
13
17
|
weight = document.term_frequency(term) * idf
|
14
18
|
@matrix[term_index, document_index] = weight
|
19
|
+
@non_zeros += 1 unless weight.zero?
|
15
20
|
end
|
16
21
|
end
|
17
22
|
|
metadata
CHANGED
@@ -1,104 +1,115 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: similarity
|
3
|
-
version: !ruby/object:Gem::Version
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.2.5
|
4
5
|
prerelease:
|
5
|
-
version: 0.2.4
|
6
6
|
platform: ruby
|
7
|
-
authors:
|
7
|
+
authors:
|
8
8
|
- Chris Lowis
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
dependencies:
|
16
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2011-05-25 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
17
15
|
name: gsl
|
18
|
-
|
19
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
20
17
|
none: false
|
21
|
-
requirements:
|
22
|
-
- -
|
23
|
-
- !ruby/object:Gem::Version
|
24
|
-
version:
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
25
22
|
type: :runtime
|
26
|
-
version_requirements: *id001
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: rake
|
29
23
|
prerelease: false
|
30
|
-
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
31
33
|
none: false
|
32
|
-
requirements:
|
33
|
-
- -
|
34
|
-
- !ruby/object:Gem::Version
|
35
|
-
version:
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
36
38
|
type: :development
|
37
|
-
version_requirements: *id002
|
38
|
-
- !ruby/object:Gem::Dependency
|
39
|
-
name: faker
|
40
39
|
prerelease: false
|
41
|
-
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: faker
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
42
49
|
none: false
|
43
|
-
requirements:
|
44
|
-
- -
|
45
|
-
- !ruby/object:Gem::Version
|
46
|
-
version:
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
47
54
|
type: :development
|
48
|
-
version_requirements: *id003
|
49
|
-
- !ruby/object:Gem::Dependency
|
50
|
-
name: ruby-graphviz
|
51
55
|
prerelease: false
|
52
|
-
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: ruby-graphviz
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
53
65
|
none: false
|
54
|
-
requirements:
|
55
|
-
- -
|
56
|
-
- !ruby/object:Gem::Version
|
57
|
-
version:
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
58
70
|
type: :development
|
59
|
-
|
60
|
-
|
61
|
-
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
description: ! 'Document similarity calculations using cosine similarity and TF-IDF
|
79
|
+
weights
|
62
80
|
|
81
|
+
'
|
63
82
|
email: chris.lowis@bbc.co.uk
|
64
83
|
executables: []
|
65
|
-
|
66
84
|
extensions: []
|
67
|
-
|
68
85
|
extra_rdoc_files: []
|
69
|
-
|
70
|
-
files:
|
86
|
+
files:
|
71
87
|
- lib/similarity/corpus.rb
|
72
88
|
- lib/similarity/document.rb
|
73
89
|
- lib/similarity/term_document_matrix.rb
|
74
90
|
- lib/similarity.rb
|
75
|
-
|
76
|
-
homepage: ""
|
91
|
+
homepage: ''
|
77
92
|
licenses: []
|
78
|
-
|
79
93
|
post_install_message:
|
80
94
|
rdoc_options: []
|
81
|
-
|
82
|
-
require_paths:
|
95
|
+
require_paths:
|
83
96
|
- lib
|
84
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
98
|
none: false
|
86
|
-
requirements:
|
87
|
-
- -
|
88
|
-
- !ruby/object:Gem::Version
|
89
|
-
version:
|
90
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - ! '>='
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '0'
|
103
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
91
104
|
none: false
|
92
|
-
requirements:
|
93
|
-
- -
|
94
|
-
- !ruby/object:Gem::Version
|
95
|
-
version:
|
105
|
+
requirements:
|
106
|
+
- - ! '>='
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
version: '0'
|
96
109
|
requirements: []
|
97
|
-
|
98
110
|
rubyforge_project: similarity
|
99
|
-
rubygems_version: 1.
|
111
|
+
rubygems_version: 1.8.23
|
100
112
|
signing_key:
|
101
113
|
specification_version: 3
|
102
114
|
summary: Document similarity calculations using cosine similarity and TF-IDF weights
|
103
115
|
test_files: []
|
104
|
-
|