my_first_markov 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: f1324ccda2ff0616ce6bd7597baf3f3149ef11d7
+  data.tar.gz: e49d8a1c525324edc4d9a72668221e114d96530f
+SHA512:
+  metadata.gz: efbf5fe647b7fab8ce2c4a730628a7a6a5aa2a7cbb28b4d75275114db54649da1356609cc70b645d6806512359f0cdfb8d9ff909d78bdfd942a517fd4dd9cfd4
+  data.tar.gz: ce8ae7a0726c9c07ba4f428d888b69cf3db5be46d18b880bae28b2acfffda429785d218f6b49aed0d79b62b05b61eb5fb7fc7a46e5d3b7610bdd049f0edf7352

data/.gitignore

@@ -0,0 +1,2 @@
+pkg/*.gem
+tags

data/.ruby-gemset

@@ -0,0 +1 @@
+markov

data/.ruby-version

@@ -0,0 +1 @@
+ruby-2.3.1

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in my_first_markov.gemspec
+gemspec

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/my_first_markov.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+
+begin
+  require "rubygems"
+  gem "my_first_markov"
+  require "my_first_markov"
+rescue LoadError => e
+  warn "LoadError: #{e.message.inspect}"
+  require_relative "../lib/my_first_markov"
+end
+
+if File.basename(__FILE__) == File.basename($PROGRAM_NAME)
+  starting_entry = ARGV[0]
+  file = ARGV[1]
+  next_method = ARGV[2]
+  split_on = ARGV[3]
+
+  if [starting_entry, file].include?(nil) || (starting_entry =~ /(\-\-\?)|(\-\-help)/i)
+    msg = <<-EOH
+      $0 <some starting entry> <file-glob of entry observations> <split_on: word* | character> <next_method: random_next* | most_likely_next>
+      e.g.
+      $0  this                  ./test/sample_text.txt        [random_next]         [word]
+      > apple
+
+      $0  a                    ./test/sample_text.txt         [random_next]         character
+      > p
+    EOH
+    warn(msg)
+    exit
+  end
+
+  puts MyFirstMarkov::Chain.from_file(file, split_on, starting_entry, next_method)
+end

data/lib/my_first_markov/chain.rb

@@ -0,0 +1,93 @@
+module MyFirstMarkov
+  class Chain
+
+    def self.next_methods
+      ["random_next", "most_likely_next"]
+    end
+
+    def self.default_next_method
+      next_methods.first
+    end
+
+    def self.split_on_values
+      ["word", "character"]
+    end
+
+    def self.default_split_on_value
+      split_on_values.first
+    end
+
+    def self.from_file(file, split_on, starting_entry, next_method)
+      unless split_on && MyFirstMarkov::Chain.split_on_values.include?(split_on.downcase)
+        split_on = MyFirstMarkov::Chain.default_split_on_value
+      end
+      split_on.downcase!
+
+      unless next_method && MyFirstMarkov::Chain.next_methods.include?(next_method.downcase)
+        next_method = MyFirstMarkov::Chain.default_next_method
+      end
+      next_method.downcase!
+
+      unless File.exists?(file)
+        fail("Unknown file: #{file.inspect}")
+      end
+
+      data = File.read(file)
+      ("word" == split_on) ? entries = data.split : entries = data.split(//)
+      entries ||= []
+
+      new(entries).send(next_method, starting_entry)
+    end
+
+    def initialize(ordered_list)
+      @entries = Hash.new
+      ordered_list.each_with_index do |entry, index|
+        next_entry_idx = next_idx_or_nil(index, ordered_list.size)
+        add(entry, ordered_list[next_entry_idx]) if next_entry_idx
+      end
+    end
+
+    def add(entry, next_entry)
+      @entries[entry] ||= Hash.new(0)
+      @entries[entry][next_entry] += 1
+    end
+
+    def most_likely_next(entry)
+      _next(entry) do |observation_total, next_entries_and_observations|
+        next_entries_and_observations
+          .sort {|a,b| b.last <=> a.last} # sort (in reverse) by observations
+          .first # choose an array with the largest observation (could be many with same #)
+          .first # the "entry" part, not the "num_observations"
+      end
+    end
+
+    def random_next(entry)
+      _next(entry) do |observation_total, next_entries_and_observations|
+        random_threshold = rand(observation_total) + 1
+        partial_observation_sum = 0
+
+        next_entries_and_observations.find { |next_entry, num_observations|
+          partial_observation_sum += num_observations
+          partial_observation_sum >= random_threshold
+        }.first # we want the "entry" not the "num_observations"
+      end
+    end
+
+
+    private
+
+    def _next(entry, &block)
+      return "" unless @entries.key?(entry)
+
+      # remember each entry contains a hash of the form {subsequent_entry: num_of_observations, other_subsequent_entry: num_of_observaions, ...}
+      # calling reduce on a hash converts to an array [[s_entry, observation_count], ...]
+      num_of_observations = @entries[entry].reduce(0) {|sum,entry_observations| sum += entry_observations.last}
+      return block.call(num_of_observations, @entries[entry])
+    end
+
+    def next_idx_or_nil(idx, list_size)
+      last_idx_in_list = list_size - 1
+      (idx + 1 < last_idx_in_list) ? idx + 1 : nil
+    end
+  end
+end

data/lib/my_first_markov/version.rb

@@ -0,0 +1,3 @@
+module MyFirstMarkov
+  VERSION = "0.0.1"
+end

data/lib/my_first_markov.rb

@@ -0,0 +1,3 @@
+module MyFirstMarkov
+end
+require_relative "./my_first_markov/chain.rb"

data/my_first_markov.gemspec

@@ -0,0 +1,25 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "my_first_markov/version"
+
+Gem::Specification.new do |s|
+  s.name        = "my_first_markov"
+  s.version     = MyFirstMarkov::VERSION
+  s.authors     = ["Jay Tee"]
+  s.email       = ["jaytee@jayteesf.com"]
+  s.homepage    = ""
+  s.summary     = %q{Markov Chain implementation}
+  s.description = %q{Pass it a list of entries (words, letters, ???) then, give it an entry and query for a "next" entry - the most likely next or perhaps some random threshold based next-entry }
+
+  s.rubyforge_project = "my_first_markov"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_development_dependency 'rspec'
+
+  # specify any dependencies here; for example:
+  # s.add_runtime_dependency "rest-client"
+end

data/test/sample_text.txt

@@ -0,0 +1 @@
+apple this apple is a text\nthis apple was a text\nthis is a big apple text\nthis could be an apple big old apple text\nthis apple is not apple  text apple

metadata

@@ -0,0 +1,72 @@
+--- !ruby/object:Gem::Specification
+name: my_first_markov
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Jay Tee
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-01-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 'Pass it a list of entries (words, letters, ???) then, give it an entry
+  and query for a "next" entry - the most likely next or perhaps some random threshold
+  based next-entry '
+email:
+- jaytee@jayteesf.com
+executables:
+- my_first_markov.rb
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".ruby-gemset"
+- ".ruby-version"
+- Gemfile
+- Rakefile
+- bin/my_first_markov.rb
+- lib/my_first_markov.rb
+- lib/my_first_markov/chain.rb
+- lib/my_first_markov/version.rb
+- my_first_markov.gemspec
+- test/sample_text.txt
+homepage: ''
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: my_first_markov
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Markov Chain implementation
+test_files:
+- test/sample_text.txt