n_gram 0.0.0
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.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +50 -0
- data/Rakefile +45 -0
- data/VERSION +1 -0
- data/lib/n_gram.rb +47 -0
- data/n_gram.gemspec +55 -0
- data/spec/n_gram_spec.rb +41 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- metadata +76 -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 +1,50 @@
|
|
1
|
+
= NGram
|
2
|
+
|
3
|
+
A simple NGram generator - http://en.wikipedia.org/wiki/N-gram.
|
4
|
+
|
5
|
+
== Install
|
6
|
+
|
7
|
+
gem sources -a http://gemcutter.org
|
8
|
+
sudo gem install n_gram
|
9
|
+
|
10
|
+
== How To Use
|
11
|
+
|
12
|
+
A single N-Gram
|
13
|
+
|
14
|
+
require 'rubygems'
|
15
|
+
require 'n_gram'
|
16
|
+
|
17
|
+
data = ['here is some text', 'here is more text']
|
18
|
+
|
19
|
+
n_gram = NGram.new(data, :n => 2)
|
20
|
+
|
21
|
+
# To see the N-Gram of the collection
|
22
|
+
ngram.ngrams_of_all_data
|
23
|
+
#=> {2 => {'here is' => 2 etc...}}
|
24
|
+
|
25
|
+
# To see the N-Grams of individual inputs
|
26
|
+
# If we want the N-Gram of data[0]
|
27
|
+
ngram.ngrams_of_inputs[0]
|
28
|
+
#=> {2 => {'here is' => 1 etc...}}
|
29
|
+
|
30
|
+
Multiple N-Grams
|
31
|
+
|
32
|
+
require 'rubygems'
|
33
|
+
require 'n_gram'
|
34
|
+
|
35
|
+
data = ['here is some text', 'here is more text']
|
36
|
+
|
37
|
+
n_gram = NGram.new(data, :n => [2,3])
|
38
|
+
|
39
|
+
# To see the N-Gram of the collection
|
40
|
+
ngram.ngrams_of_all_data
|
41
|
+
#=> {2 => {'here is' => 2 etc...}, 3 => {'here is some' => 1 etc...}}
|
42
|
+
|
43
|
+
# To see the N-Grams of individual inputs
|
44
|
+
# If we want the N-Gram of data[0]
|
45
|
+
ngram.ngrams_of_inputs[0]
|
46
|
+
#=> {2 => {'here is' => 1 etc...}, 3 => {'here is some' => 1 etc...}}
|
47
|
+
|
48
|
+
== Copyright
|
49
|
+
|
50
|
+
Copyright (c) 2009 Red Davis. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "n_gram"
|
8
|
+
gem.summary = %Q{A simple NGram generator}
|
9
|
+
gem.description = %Q{A simple NGram generator}
|
10
|
+
gem.email = "reddavis@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/reddavis/N-Gram"
|
12
|
+
gem.authors = ["reddavis"]
|
13
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
14
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
15
|
+
end
|
16
|
+
Jeweler::GemcutterTasks.new
|
17
|
+
rescue LoadError
|
18
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
19
|
+
end
|
20
|
+
|
21
|
+
require 'spec/rake/spectask'
|
22
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
23
|
+
spec.libs << 'lib' << 'spec'
|
24
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
25
|
+
end
|
26
|
+
|
27
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
28
|
+
spec.libs << 'lib' << 'spec'
|
29
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
30
|
+
spec.rcov = true
|
31
|
+
end
|
32
|
+
|
33
|
+
task :spec => :check_dependencies
|
34
|
+
|
35
|
+
task :default => :spec
|
36
|
+
|
37
|
+
require 'rake/rdoctask'
|
38
|
+
Rake::RDocTask.new do |rdoc|
|
39
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
40
|
+
|
41
|
+
rdoc.rdoc_dir = 'rdoc'
|
42
|
+
rdoc.title = "n_gram #{version}"
|
43
|
+
rdoc.rdoc_files.include('README*')
|
44
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
45
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.0
|
data/lib/n_gram.rb
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
class NGram
|
2
|
+
def initialize(data, options={})
|
3
|
+
@ns = options[:n].is_a?(Array) ? options[:n] : [options[:n]]
|
4
|
+
@data = data
|
5
|
+
|
6
|
+
@bucket_holder = []
|
7
|
+
@all_ngram = template_hash
|
8
|
+
|
9
|
+
process
|
10
|
+
end
|
11
|
+
|
12
|
+
# Provides an ngram for each item in the data array
|
13
|
+
def ngrams_of_inputs
|
14
|
+
@bucket_holder
|
15
|
+
end
|
16
|
+
|
17
|
+
# Provides an ngram of all the data
|
18
|
+
def ngrams_of_all_data
|
19
|
+
@all_ngram
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
def process
|
25
|
+
@data.each do |string|
|
26
|
+
bucket = template_hash
|
27
|
+
|
28
|
+
words = string.split(' ')
|
29
|
+
|
30
|
+
(words.size).times do |index|
|
31
|
+
@ns.each do |n|
|
32
|
+
bucket[n][words[index,n].join(' ')] += 1
|
33
|
+
@all_ngram[n][words[index,n].join(' ')] += 1
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
@bucket_holder << bucket
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def template_hash
|
42
|
+
Hash.new do |hash, key|
|
43
|
+
hash[key] = Hash.new {|hash, key| hash[key] = 0}
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
data/n_gram.gemspec
ADDED
@@ -0,0 +1,55 @@
|
|
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{n_gram}
|
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 simple NGram generator}
|
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/n_gram.rb",
|
27
|
+
"n_gram.gemspec",
|
28
|
+
"spec/n_gram_spec.rb",
|
29
|
+
"spec/spec.opts",
|
30
|
+
"spec/spec_helper.rb"
|
31
|
+
]
|
32
|
+
s.homepage = %q{http://github.com/reddavis/N-Gram}
|
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 simple NGram generator}
|
37
|
+
s.test_files = [
|
38
|
+
"spec/n_gram_spec.rb",
|
39
|
+
"spec/spec_helper.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
|
+
else
|
49
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
50
|
+
end
|
51
|
+
else
|
52
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
data/spec/n_gram_spec.rb
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
|
3
|
+
describe "NGram" do
|
4
|
+
|
5
|
+
before do
|
6
|
+
@n_gram = NGram.new(text, :n => 2)
|
7
|
+
end
|
8
|
+
|
9
|
+
describe "All Grams" do
|
10
|
+
it "should return true" do
|
11
|
+
@n_gram.ngrams_of_all_data.key?(2).should be_true
|
12
|
+
end
|
13
|
+
|
14
|
+
it "should return 4" do
|
15
|
+
@n_gram.ngrams_of_all_data[2]['this is'].should == 4
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
describe "NGrams for seperate input" do
|
20
|
+
it "should return 2" do
|
21
|
+
@n_gram.ngrams_of_inputs.size.should == 2
|
22
|
+
end
|
23
|
+
|
24
|
+
it "should return 2" do
|
25
|
+
@n_gram.ngrams_of_inputs[0][2]['this is'].should == 2
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should return 1" do
|
29
|
+
@n_gram.ngrams_of_inputs[1][2]['is hello'].should == 1
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
private
|
34
|
+
|
35
|
+
def text
|
36
|
+
[
|
37
|
+
"this is a just a sentence nothing else this is a all it is",
|
38
|
+
"this is a just a sentence nothing else this is a all it is hello"
|
39
|
+
]
|
40
|
+
end
|
41
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,76 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: n_gram
|
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
|
+
description: A simple NGram generator
|
26
|
+
email: reddavis@gmail.com
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files:
|
32
|
+
- LICENSE
|
33
|
+
- README.rdoc
|
34
|
+
files:
|
35
|
+
- .document
|
36
|
+
- .gitignore
|
37
|
+
- LICENSE
|
38
|
+
- README.rdoc
|
39
|
+
- Rakefile
|
40
|
+
- VERSION
|
41
|
+
- lib/n_gram.rb
|
42
|
+
- n_gram.gemspec
|
43
|
+
- spec/n_gram_spec.rb
|
44
|
+
- spec/spec.opts
|
45
|
+
- spec/spec_helper.rb
|
46
|
+
has_rdoc: true
|
47
|
+
homepage: http://github.com/reddavis/N-Gram
|
48
|
+
licenses: []
|
49
|
+
|
50
|
+
post_install_message:
|
51
|
+
rdoc_options:
|
52
|
+
- --charset=UTF-8
|
53
|
+
require_paths:
|
54
|
+
- lib
|
55
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
56
|
+
requirements:
|
57
|
+
- - ">="
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: "0"
|
60
|
+
version:
|
61
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
62
|
+
requirements:
|
63
|
+
- - ">="
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: "0"
|
66
|
+
version:
|
67
|
+
requirements: []
|
68
|
+
|
69
|
+
rubyforge_project:
|
70
|
+
rubygems_version: 1.3.5
|
71
|
+
signing_key:
|
72
|
+
specification_version: 3
|
73
|
+
summary: A simple NGram generator
|
74
|
+
test_files:
|
75
|
+
- spec/n_gram_spec.rb
|
76
|
+
- spec/spec_helper.rb
|