love_is 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/love_is/generator.rb +32 -0
- data/lib/love_is/node.rb +62 -0
- data/lib/love_is/parser.rb +20 -0
- data/lib/love_is.rb +8 -0
- metadata +48 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c47bfbb06c55765459c1f9080d35bf098b855233
|
4
|
+
data.tar.gz: 3aa2c252c09af30c32125841ca39fb528e3c6c84
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 12271194b7454d53fa39ea62e7ad3eefeecce2c49fb84d3cf341c52c45176336c857f03b395796f6d5a643c53cc5a4a599191b2417b70ffd1043eb051ca6e67b
|
7
|
+
data.tar.gz: 3d2adc3c9478b84b5409b56ecd3992e3ba2d19882583c0297d32f00d1b5d02b0ba4415381441d27099202fa94d1a9f5e8473e233d4b31016b2e95061ecf5053c
|
@@ -0,0 +1,32 @@
|
|
1
|
+
class LoveIs::Generator
|
2
|
+
include LoveIs::Parser
|
3
|
+
attr_reader :ngram, :chain, :tree
|
4
|
+
|
5
|
+
def initialize(ngram = 3)
|
6
|
+
@tree = LoveIs::Node.new(nil, 1, [])
|
7
|
+
@ngram = ngram
|
8
|
+
@chain = []
|
9
|
+
end
|
10
|
+
|
11
|
+
def generate(chain_length = 1000)
|
12
|
+
@chain = []
|
13
|
+
initial_values
|
14
|
+
(chain_length - ngram).times do
|
15
|
+
break unless word = next_value
|
16
|
+
@chain << word
|
17
|
+
end
|
18
|
+
chain[1..-1].join(' ')
|
19
|
+
end
|
20
|
+
|
21
|
+
def initial_values
|
22
|
+
ngram.times.inject(@tree.child('*')) do |node|
|
23
|
+
@chain << node.value
|
24
|
+
node.next
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def next_value
|
29
|
+
node = @tree[*chain[(-ngram + 1)..-1]]
|
30
|
+
node ? node.next.value : nil
|
31
|
+
end
|
32
|
+
end
|
data/lib/love_is/node.rb
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
class LoveIs::Node
|
2
|
+
attr_reader :value
|
3
|
+
attr_accessor :probability, :childs, :weight
|
4
|
+
|
5
|
+
def initialize(value = nil, weight = 1, childs = [])
|
6
|
+
@value = value
|
7
|
+
@weight = weight
|
8
|
+
set_childs(childs)
|
9
|
+
end
|
10
|
+
|
11
|
+
def set_childs(childs)
|
12
|
+
@childs = childs
|
13
|
+
unless @childs.all? { |x| x.probability }
|
14
|
+
probabilities
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
def probabilities
|
19
|
+
normalize_weights
|
20
|
+
t = 0.0
|
21
|
+
@childs.map! { |x| t += x.weight; x.probability = t; x }
|
22
|
+
@childs.each(&:probabilities) if childs && childs.any?
|
23
|
+
end
|
24
|
+
|
25
|
+
def normalize_weights
|
26
|
+
sum = weights.inject(&:+).to_f
|
27
|
+
@childs.map! { |x| x.weight /= sum; x }
|
28
|
+
end
|
29
|
+
|
30
|
+
def child(key)
|
31
|
+
childs.find { |x| x.value == key }
|
32
|
+
end
|
33
|
+
|
34
|
+
def [](*keys)
|
35
|
+
keys.inject(self) { |r, x| break(nil) unless r; r.child(x) }
|
36
|
+
end
|
37
|
+
|
38
|
+
def []=(*keys, weight)
|
39
|
+
keys.inject(self) do |r, x|
|
40
|
+
r.childs << LoveIs::Node.new(x, 0, []) unless r.child(x)
|
41
|
+
r.child(x).weight = weight
|
42
|
+
r.child(x)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def inc(*keys)
|
47
|
+
keys.inject(self) do |r, x|
|
48
|
+
r.childs << LoveIs::Node.new(x, 0, []) unless r.child(x)
|
49
|
+
r.child(x).weight += 1
|
50
|
+
r.child(x)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def weights
|
55
|
+
childs.map { |x| x.weight }
|
56
|
+
end
|
57
|
+
|
58
|
+
def next
|
59
|
+
random_value = Random.new.rand
|
60
|
+
childs.find { |x| random_value - x.probability <= 0 }
|
61
|
+
end
|
62
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
module LoveIs::Parser
|
2
|
+
SENTENCE_BEGIN = '*'
|
3
|
+
|
4
|
+
def parse_file(filename)
|
5
|
+
text = File.read(File.expand_path(filename))
|
6
|
+
parse(text, @ngram)
|
7
|
+
end
|
8
|
+
|
9
|
+
def parse(text, length)
|
10
|
+
text.split("\n").map { |x| sentence2array(x) }.each do |sentence|
|
11
|
+
sentence.each_cons(length) { |sequence| @tree.inc(*sequence) }
|
12
|
+
end
|
13
|
+
@tree.probabilities
|
14
|
+
self
|
15
|
+
end
|
16
|
+
|
17
|
+
def sentence2array(sentence)
|
18
|
+
sentence.split(/\s/).unshift(SENTENCE_BEGIN)
|
19
|
+
end
|
20
|
+
end
|
data/lib/love_is.rb
ADDED
metadata
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: love_is
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sergey Smagin
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-12-07 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Markov chains generator.
|
14
|
+
email: smaginsergey1310@gmail.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/love_is.rb
|
20
|
+
- lib/love_is/generator.rb
|
21
|
+
- lib/love_is/node.rb
|
22
|
+
- lib/love_is/parser.rb
|
23
|
+
homepage: https://github.com/s-mage/love_is
|
24
|
+
licenses:
|
25
|
+
- MIT
|
26
|
+
metadata: {}
|
27
|
+
post_install_message:
|
28
|
+
rdoc_options: []
|
29
|
+
require_paths:
|
30
|
+
- lib
|
31
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
32
|
+
requirements:
|
33
|
+
- - '>='
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: '0'
|
36
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
requirements: []
|
42
|
+
rubyforge_project:
|
43
|
+
rubygems_version: 2.0.3
|
44
|
+
signing_key:
|
45
|
+
specification_version: 4
|
46
|
+
summary: Love Is ...
|
47
|
+
test_files: []
|
48
|
+
has_rdoc:
|