Created
November 20, 2019 13:13
-
-
Save F-3r/0b882ec57cdfc14604c1453ac0eb7fb4 to your computer and use it in GitHub Desktop.
Markov chain implementation for the arlt.rb bot
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Markov | |
PHRASE_SEPARATOR = /[\.;]/ | |
WORD_SEPARATOR = " " | |
attr_reader :knowledge, :order | |
def initialize(order: 2) | |
@knowledge = {} | |
@order = order | |
end | |
def read(text) | |
phrases(text).each do |phrase| | |
(Array.new(order, " ") + words(phrase)).each_cons(order + 1) { |*key, value | learn key, value } | |
end | |
knowledge | |
end | |
def compose() | |
generate(Array.new(order, " ")).drop(order).join(" ") << "." | |
end | |
def generate(chain) | |
key = chain.last(order).join(" ") | |
alternatives = knowledge[key] | |
following = alternatives ? alternatives.sample : nil | |
while following | |
chain << following | |
key = chain.last(order).join(" ") | |
alternatives = knowledge[key] | |
following = alternatives ? alternatives.sample : nil | |
end | |
chain | |
end | |
def learn(a, b) | |
key = a.join(" ") | |
knowledge[key] ||= [] | |
knowledge[key] << b | |
end | |
def words(text, sep: WORD_SEPARATOR) | |
text.split(sep).reject(&:empty?) | |
end | |
def phrases(text, sep: PHRASE_SEPARATOR) | |
text.split(sep).reject(&:empty?).each(&:strip!) | |
end | |
def store(file = "markov-#{order}.db") | |
File.write file, Marshal.dump(knowledge) | |
self | |
end | |
def load(file = "markov-#{order}.db") | |
@knowledge = Marshal.load File.read file | |
self | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment