tf_idf 0.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +33 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/lib/tf_idf.rb +80 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +10 -0
- data/spec/tf_idf_spec.rb +37 -0
- data/tf_idf.gemspec +58 -0
- metadata +86 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 reddavis
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
= Tf-Idf
|
2
|
+
|
3
|
+
http://en.wikipedia.org/wiki/Tf–idf
|
4
|
+
|
5
|
+
== Install
|
6
|
+
|
7
|
+
gem sources -a http://gems.github.com
|
8
|
+
sudo gem install tf_idf
|
9
|
+
|
10
|
+
== How To Use
|
11
|
+
require 'rubygems'
|
12
|
+
require 'tf_idf'
|
13
|
+
|
14
|
+
data = ['a a a a a a a a b b', 'a a']
|
15
|
+
|
16
|
+
# 1 is the ngram setter => http://en.wikipedia.org/wiki/N-gram
|
17
|
+
a = TfIdf.new(data, 1)
|
18
|
+
|
19
|
+
# To find the term frequencies
|
20
|
+
a.tf
|
21
|
+
#=> [{'b' => 0.2, 'a' => etc...}, {'a' => 1}]
|
22
|
+
|
23
|
+
# To find the inverse document frequency
|
24
|
+
a.idf
|
25
|
+
#=> {'b' => 0.301... etc...}
|
26
|
+
|
27
|
+
# And to find the tf-idf
|
28
|
+
a.tf_idf
|
29
|
+
#=> [{'b' => 0.0602, 'a' => etc...}, {etc...}]
|
30
|
+
|
31
|
+
== Copyright
|
32
|
+
|
33
|
+
Copyright (c) 2009 Red Davis. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "tf_idf"
|
8
|
+
gem.summary = %Q{A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf–idf}
|
9
|
+
gem.description = %Q{A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf–idf}
|
10
|
+
gem.email = "reddavis@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/reddavis/TF-IDF"
|
12
|
+
gem.authors = ["reddavis"]
|
13
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
14
|
+
gem.add_dependency('n_gram', ">= 0.0.0")
|
15
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
16
|
+
end
|
17
|
+
Jeweler::GemcutterTasks.new
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'spec/rake/spectask'
|
23
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
24
|
+
spec.libs << 'lib' << 'spec'
|
25
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
26
|
+
end
|
27
|
+
|
28
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
29
|
+
spec.libs << 'lib' << 'spec'
|
30
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
31
|
+
spec.rcov = true
|
32
|
+
end
|
33
|
+
|
34
|
+
task :spec => :check_dependencies
|
35
|
+
|
36
|
+
task :default => :spec
|
37
|
+
|
38
|
+
require 'rake/rdoctask'
|
39
|
+
Rake::RDocTask.new do |rdoc|
|
40
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
41
|
+
|
42
|
+
rdoc.rdoc_dir = 'rdoc'
|
43
|
+
rdoc.title = "tf_idf #{version}"
|
44
|
+
rdoc.rdoc_files.include('README*')
|
45
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.0
|
data/lib/tf_idf.rb
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
require 'n_gram'
|
2
|
+
|
3
|
+
class TfIdf
|
4
|
+
|
5
|
+
# n the n-grams of the data http://en.wikipedia.org/wiki/N-gram
|
6
|
+
def initialize(data, n=1)
|
7
|
+
@data = data
|
8
|
+
@n = n
|
9
|
+
end
|
10
|
+
|
11
|
+
def tf
|
12
|
+
@tf ||= calculate_term_frequencies
|
13
|
+
end
|
14
|
+
|
15
|
+
def idf
|
16
|
+
@idf ||= calculate_inverse_document_frequency
|
17
|
+
end
|
18
|
+
|
19
|
+
# This is basically calculated by multiplying tf by idf
|
20
|
+
def tf_idf
|
21
|
+
tf_idf = tf.clone
|
22
|
+
|
23
|
+
tf.each_with_index do |document, index|
|
24
|
+
document.each_pair do |term, tf_score|
|
25
|
+
tf_idf[index][term] = tf_score * idf[term]
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
tf_idf
|
30
|
+
end
|
31
|
+
|
32
|
+
def total_documents
|
33
|
+
@data.size.to_f
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
# IDF = total_documents / number_of_document_term_appears_in
|
39
|
+
# This calculates how important a term is.
|
40
|
+
def calculate_inverse_document_frequency
|
41
|
+
original_ngrams = n_gram.ngrams_of_all_data[@n].clone
|
42
|
+
|
43
|
+
original_ngrams.each_key do |term|
|
44
|
+
|
45
|
+
# Calculate how many documents the term appears in
|
46
|
+
count = 0.0
|
47
|
+
n_gram.ngrams_of_inputs.each do |document|
|
48
|
+
count += 1 if document[@n].key?(term)
|
49
|
+
end
|
50
|
+
|
51
|
+
original_ngrams[term] = Math.log10(total_documents / count)
|
52
|
+
end
|
53
|
+
|
54
|
+
original_ngrams
|
55
|
+
end
|
56
|
+
|
57
|
+
# TF = number_of_n_term_in_document / number_of_terms_in_document
|
58
|
+
# Calculates the number of times a term appears in the document
|
59
|
+
# It is then normalized (as some documents are longer than others)
|
60
|
+
def calculate_term_frequencies
|
61
|
+
original_ngrams = n_gram.ngrams_of_inputs.clone
|
62
|
+
|
63
|
+
original_ngrams.each_with_index do |document, index|
|
64
|
+
|
65
|
+
# Calculate the total number of terms
|
66
|
+
total_terms = 0.0
|
67
|
+
document[@n].each_value {|v| total_terms += v}
|
68
|
+
|
69
|
+
document[@n].each_pair do |key, value|
|
70
|
+
original_ngrams[index][@n][key] = (value.to_f / total_terms)
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
original_ngrams.map {|x| x.map {|y| y[@n] }}.flatten
|
75
|
+
end
|
76
|
+
|
77
|
+
def n_gram
|
78
|
+
@n_gram ||= NGram.new(@data, :n => @n)
|
79
|
+
end
|
80
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
data/spec/tf_idf_spec.rb
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
|
3
|
+
describe "TfIdf" do
|
4
|
+
describe "Term Frequency" do
|
5
|
+
before do
|
6
|
+
@a = TfIdf.new(data, 1)
|
7
|
+
end
|
8
|
+
|
9
|
+
it "should return 0.2" do
|
10
|
+
@a.tf[0]['b'].should == 0.2
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
describe "Inverse Document Frequency" do
|
15
|
+
before do
|
16
|
+
@a = TfIdf.new(data, 1)
|
17
|
+
end
|
18
|
+
|
19
|
+
it "should return 0.3010" do
|
20
|
+
@a.idf['b'].to_s.should match(/0.30102999/)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
before do
|
25
|
+
@a = TfIdf.new(data, 1)
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should return 0.0602" do
|
29
|
+
@a.tf_idf[0]['b'].to_s.should match(/0.0602/)
|
30
|
+
end
|
31
|
+
|
32
|
+
private
|
33
|
+
|
34
|
+
def data
|
35
|
+
['a a a a a a a a b b', 'a a']
|
36
|
+
end
|
37
|
+
end
|
data/tf_idf.gemspec
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{tf_idf}
|
8
|
+
s.version = "0.0.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["reddavis"]
|
12
|
+
s.date = %q{2009-12-18}
|
13
|
+
s.description = %q{A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf–idf}
|
14
|
+
s.email = %q{reddavis@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"lib/tf_idf.rb",
|
27
|
+
"spec/spec.opts",
|
28
|
+
"spec/spec_helper.rb",
|
29
|
+
"spec/tf_idf_spec.rb",
|
30
|
+
"tf_idf.gemspec"
|
31
|
+
]
|
32
|
+
s.homepage = %q{http://github.com/reddavis/TF-IDF}
|
33
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
34
|
+
s.require_paths = ["lib"]
|
35
|
+
s.rubygems_version = %q{1.3.5}
|
36
|
+
s.summary = %q{A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf–idf}
|
37
|
+
s.test_files = [
|
38
|
+
"spec/spec_helper.rb",
|
39
|
+
"spec/tf_idf_spec.rb"
|
40
|
+
]
|
41
|
+
|
42
|
+
if s.respond_to? :specification_version then
|
43
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
44
|
+
s.specification_version = 3
|
45
|
+
|
46
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
47
|
+
s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
|
48
|
+
s.add_runtime_dependency(%q<n_gram>, [">= 0.0.0"])
|
49
|
+
else
|
50
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
51
|
+
s.add_dependency(%q<n_gram>, [">= 0.0.0"])
|
52
|
+
end
|
53
|
+
else
|
54
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
55
|
+
s.add_dependency(%q<n_gram>, [">= 0.0.0"])
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
metadata
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tf_idf
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- reddavis
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-12-18 00:00:00 +00:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: rspec
|
17
|
+
type: :development
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 1.2.9
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: n_gram
|
27
|
+
type: :runtime
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.0.0
|
34
|
+
version:
|
35
|
+
description: "A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf\xE2\x80\x93idf"
|
36
|
+
email: reddavis@gmail.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- LICENSE
|
43
|
+
- README.rdoc
|
44
|
+
files:
|
45
|
+
- .document
|
46
|
+
- .gitignore
|
47
|
+
- LICENSE
|
48
|
+
- README.rdoc
|
49
|
+
- Rakefile
|
50
|
+
- VERSION
|
51
|
+
- lib/tf_idf.rb
|
52
|
+
- spec/spec.opts
|
53
|
+
- spec/spec_helper.rb
|
54
|
+
- spec/tf_idf_spec.rb
|
55
|
+
- tf_idf.gemspec
|
56
|
+
has_rdoc: true
|
57
|
+
homepage: http://github.com/reddavis/TF-IDF
|
58
|
+
licenses: []
|
59
|
+
|
60
|
+
post_install_message:
|
61
|
+
rdoc_options:
|
62
|
+
- --charset=UTF-8
|
63
|
+
require_paths:
|
64
|
+
- lib
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - ">="
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: "0"
|
70
|
+
version:
|
71
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: "0"
|
76
|
+
version:
|
77
|
+
requirements: []
|
78
|
+
|
79
|
+
rubyforge_project:
|
80
|
+
rubygems_version: 1.3.5
|
81
|
+
signing_key:
|
82
|
+
specification_version: 3
|
83
|
+
summary: "A TF-IDF in ruby - http://en.wikipedia.org/wiki/Tf\xE2\x80\x93idf"
|
84
|
+
test_files:
|
85
|
+
- spec/spec_helper.rb
|
86
|
+
- spec/tf_idf_spec.rb
|