markov_chains 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.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +38 -0
- data/Rakefile +9 -0
- data/lib/markov_chains/dictionary.rb +75 -0
- data/lib/markov_chains/generator.rb +40 -0
- data/lib/markov_chains/version.rb +3 -0
- data/lib/markov_chains.rb +7 -0
- data/markov_chains.gemspec +22 -0
- data/test/test_dictionary.rb +19 -0
- data/test/test_generator.rb +13 -0
- metadata +86 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 045674e5b0e005db622a8d1c6bae356074e88049
|
4
|
+
data.tar.gz: a52da2defd03a2cc01f5d8312cf5481cd27b2b20
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: cf4da09f7460ecf5506a17eaeb2fde1ea04ea72dbc4d2f1f951d3f9b79a37a818168f9e4d796f56e1d921aed5f08be3d32427ae7f6e2ef46ffa26c6b9340711f
|
7
|
+
data.tar.gz: e40a5e57101f9bfd448e2ee9520ec240ecfaa3236e30ec31150af23a12a23d15be2f3211a58a1811bc60fba2999e5ca985bb8eec769cfcd8a218f62ccc6995d2
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 justindomingue
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
# Markov Chains
|
2
|
+
|
3
|
+
A simple random text generator from source text using markov chains.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'markov_chains'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install markov_chains
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
Create a generator and give it a source text:
|
24
|
+
|
25
|
+
text = "Why did the chicken cross the Mobius Strip?, To get to the same side..."
|
26
|
+
generator = MarkovChains::Generator.new(text)
|
27
|
+
|
28
|
+
Generate a number of sentences, here 5:
|
29
|
+
|
30
|
+
generator.get_sentences(5)
|
31
|
+
|
32
|
+
## Contributing
|
33
|
+
|
34
|
+
1. Fork it ( https://github.com/[justindomingue]/markov-chains/fork )
|
35
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
36
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
37
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
38
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
module MarkovChains
|
2
|
+
class Dictionary
|
3
|
+
|
4
|
+
# Initialized the dictionary with a text source.
|
5
|
+
#
|
6
|
+
# @example Create a new dictionary
|
7
|
+
# MarkovChains::Dictionary.new(string)
|
8
|
+
# @param [String] the text source
|
9
|
+
#
|
10
|
+
def initialize(text)
|
11
|
+
@words = Hash.new
|
12
|
+
@start_words = Array.new
|
13
|
+
|
14
|
+
wordlist = text.split
|
15
|
+
|
16
|
+
# Add first word as possible start word
|
17
|
+
@start_words.push wordlist[0]
|
18
|
+
|
19
|
+
# Process each word
|
20
|
+
wordlist.each_with_index do |word, index|
|
21
|
+
add(word, wordlist[index + 1]) if index <= wordlist.size - 2
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
# Returns a word based on the likelihood of it appearing after the input word
|
26
|
+
#
|
27
|
+
# @example Get a word likely to appear next to the word 'It'
|
28
|
+
# get('It')
|
29
|
+
#
|
30
|
+
# @param [String] word for which we want a possible next word
|
31
|
+
# @return [String] word that is likely to follow the input word
|
32
|
+
#
|
33
|
+
def get(word)
|
34
|
+
return "" if !@words[word]
|
35
|
+
followers = @words[word]
|
36
|
+
sum = followers.inject(0) {|sum,kv| sum += kv[1]}
|
37
|
+
random = rand(sum)+1
|
38
|
+
partial_sum = 0
|
39
|
+
next_word = followers.find do |word, count|
|
40
|
+
partial_sum += count
|
41
|
+
partial_sum >= random
|
42
|
+
end.first
|
43
|
+
next_word
|
44
|
+
end
|
45
|
+
|
46
|
+
# Returns a word beginning a sentence seen in the source
|
47
|
+
#
|
48
|
+
# @example Get a start word
|
49
|
+
# get_start_word()
|
50
|
+
# @return [String] a possible start word
|
51
|
+
#
|
52
|
+
def get_start_word
|
53
|
+
@start_words.sample
|
54
|
+
end
|
55
|
+
|
56
|
+
private
|
57
|
+
|
58
|
+
# Adds word-next_word combination to the dictionary
|
59
|
+
#
|
60
|
+
# @example Adding a word in a order 1 dictionary
|
61
|
+
# add_word("It", "has")
|
62
|
+
# @example Adding words in a order m dictionary
|
63
|
+
# add_word("It has", "been")
|
64
|
+
#
|
65
|
+
# @param word [string] root word
|
66
|
+
# @param next_word [string] word following the root word
|
67
|
+
#
|
68
|
+
def add(word, next_word)
|
69
|
+
@words[word] = Hash.new(0) if !@words[word]
|
70
|
+
@words[word][next_word] += 1
|
71
|
+
@start_words.push(next_word) if word.end_with? '.' and !word.nil?
|
72
|
+
end
|
73
|
+
|
74
|
+
end
|
75
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
module MarkovChains
|
2
|
+
class Generator
|
3
|
+
|
4
|
+
# Initializes the generator
|
5
|
+
#
|
6
|
+
# @example Create a new generator
|
7
|
+
# MarkovChains::Generator.new(text)
|
8
|
+
#
|
9
|
+
# @param Text source to generate sentences from
|
10
|
+
#
|
11
|
+
def initialize(text)
|
12
|
+
@dict = MarkovChains::Dictionary.new(text)
|
13
|
+
end
|
14
|
+
|
15
|
+
# Returns a given number of randonly generated sentences
|
16
|
+
#
|
17
|
+
# @example Get 5 sentences
|
18
|
+
# get_sentences(5)
|
19
|
+
#
|
20
|
+
# @param n [int] number of sentences to generate
|
21
|
+
# @return Array conataining generated sentences
|
22
|
+
#
|
23
|
+
def get_sentences(n)
|
24
|
+
sentences = []
|
25
|
+
|
26
|
+
n.times do
|
27
|
+
sentence = ""
|
28
|
+
word = @dict.get_start_word
|
29
|
+
until sentence.scan(/\.|\?|!/).size == 1
|
30
|
+
sentence << word << " "
|
31
|
+
word = @dict.get(word)
|
32
|
+
end
|
33
|
+
|
34
|
+
sentences.push sentence
|
35
|
+
end
|
36
|
+
|
37
|
+
sentences
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'markov_chains/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "markov_chains"
|
8
|
+
spec.version = MarkovChains::VERSION
|
9
|
+
spec.authors = ["justindomingue"]
|
10
|
+
spec.email = ["justin.domingue@hotmail.com"]
|
11
|
+
spec.summary = 'A simple random text generator using markov chains.'
|
12
|
+
spec.homepage = "https://github.com/justindomingue/markov_chains"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0")
|
16
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
21
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
22
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'markov_chains'
|
3
|
+
|
4
|
+
class DictionaryTest < Minitest::Test
|
5
|
+
def setup
|
6
|
+
source = "Why did the chicken cross the road?"
|
7
|
+
@dict = MarkovChains::Dictionary.new(source)
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_get
|
11
|
+
assert_equal "did", @dict.get("Why")
|
12
|
+
assert_equal true, %w(chicken road).include?( @dict.get("the"))
|
13
|
+
assert_equal "", @dict.get("Not there...")
|
14
|
+
end
|
15
|
+
|
16
|
+
def test_get_start_word
|
17
|
+
assert_equal "Why", @dict.get_start_word()
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'markov_chains'
|
3
|
+
|
4
|
+
class GeneratorTest < Minitest::Test
|
5
|
+
def setup
|
6
|
+
source = "Why did the chicken cross the Mobius Strip? To get to the same side!"
|
7
|
+
@generator = MarkovChains::Generator.new source
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_get_sentences
|
11
|
+
assert_equal 5, @generator.get_sentences(5).count
|
12
|
+
end
|
13
|
+
end
|
metadata
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: markov_chains
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- justindomingue
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-12-30 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.7'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.7'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
description:
|
42
|
+
email:
|
43
|
+
- justin.domingue@hotmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- ".gitignore"
|
49
|
+
- Gemfile
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- Rakefile
|
53
|
+
- lib/markov_chains.rb
|
54
|
+
- lib/markov_chains/dictionary.rb
|
55
|
+
- lib/markov_chains/generator.rb
|
56
|
+
- lib/markov_chains/version.rb
|
57
|
+
- markov_chains.gemspec
|
58
|
+
- test/test_dictionary.rb
|
59
|
+
- test/test_generator.rb
|
60
|
+
homepage: https://github.com/justindomingue/markov_chains
|
61
|
+
licenses:
|
62
|
+
- MIT
|
63
|
+
metadata: {}
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options: []
|
66
|
+
require_paths:
|
67
|
+
- lib
|
68
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
69
|
+
requirements:
|
70
|
+
- - ">="
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: '0'
|
73
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - ">="
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
requirements: []
|
79
|
+
rubyforge_project:
|
80
|
+
rubygems_version: 2.4.3
|
81
|
+
signing_key:
|
82
|
+
specification_version: 4
|
83
|
+
summary: A simple random text generator using markov chains.
|
84
|
+
test_files:
|
85
|
+
- test/test_dictionary.rb
|
86
|
+
- test/test_generator.rb
|