naive_bayes_rb 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d58fb9885c51f52a094b39943f6486029d15d810
+  data.tar.gz: a5d0d2d8f4d1db8febd0786c6b911016dfe4a5bf
+SHA512:
+  metadata.gz: 26ac613de8b7e622bba0e53a9a7322f176db1c37d842348276ecf8ee979b804fc563c9acf6822be404cebee5a848e90945c0ea6efea755ec3853c1dd1a7d2641
+  data.tar.gz: 7271432d30ddc176c31975344ed9260e5ac4fdb82f2c12cdfca4fb3a43a91ae31e7fdb90765268540ec13f3e7354f14226618537ef3b3cd470f86a27a85774d5

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.gem
+test.pb

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.2.1
+before_install: gem install bundler -v 1.13.5

data/Gemfile

@@ -0,0 +1,8 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in naive_bayes_rb.gemspec
+gemspec
+
+gem 'guard-rspec', require: false
+gem 'terminal-notifier-guard'
+gem 'pry'

data/Guardfile

@@ -0,0 +1,53 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+## Uncomment and set this to only include directories you want to watch
+# directories %w(app lib config test spec features) \
+#  .select{|d| Dir.exists?(d) ? d : UI.warning("Directory #{d} does not exist")}
+
+## Note: if you are using the `directories` clause above and you are not
+## watching the project directory ('.'), then you will want to move
+## the Guardfile to a watched dir and symlink it back, e.g.
+#
+#  $ mkdir config
+#  $ mv Guardfile config/
+#  $ ln -s config/Guardfile .
+#
+# and, you'll have to watch "config/Guardfile" instead of "Guardfile"
+
+# Note: The cmd option is now required due to the increasing number of ways
+#       rspec may be run, below are examples of the most common uses.
+#  * bundler: 'bundle exec rspec'
+#  * bundler binstubs: 'bin/rspec'
+#  * spring: 'bin/rspec' (This will use spring if running and you have
+#                          installed the spring binstubs per the docs)
+#  * zeus: 'zeus rspec' (requires the server to be started separately)
+#  * 'just' rspec: 'rspec'
+
+guard :rspec, cmd: "bundle exec rspec" do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # Feel free to open issues for suggestions and improvements
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+
+  # Rails files
+  rails = dsl.rails(view_extensions: %w(erb haml slim))
+  dsl.watch_spec_files_for(rails.app_files)
+  dsl.watch_spec_files_for(rails.views)
+
+  # Turnip features and steps
+  watch(%r{^spec/acceptance/(.+)\.feature$})
+  watch(%r{^spec/acceptance/steps/(.+)_steps\.rb$}) do |m|
+    Dir[File.join("**/#{m[1]}.feature")][0] || "spec/acceptance"
+  end
+end

data/README.md

@@ -0,0 +1,59 @@
+# NaiveBayesRb
+
+A very simple Ruby implementation of Naive Bayes classification model. 
+
+## Design Considerations
+
+1. the interface closely resembles the python [scikit-learn interface].
+2. enable model serialization and persistence, so that the model can be reused and even distributed and shared. With the default `MarshalSerializer`, it also allows custom serializer to be plugged in.
+
+[scikit-learn interface]: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.naive_bayes
+
+## Usage
+
+### basics
+
+```ruby
+nb = NaiveBayesRb::NaiveBayes.new
+train = [[1, 20], [2, 21], [3, 22], [4, 23]] 
+target = [1, 0, 1, 0] 
+test = [[0, 0], [4, 24]]
+predictions = nb.fit(train, target).predict(test) #=> [1, 0] 
+@nb.accuracy(prediction, [1, 1]) #=> 50
+```
+### Model Persistence
+
+```ruby
+NaiveBayesRb::NaiveBayes.serializer =       
+nb = NaiveBayesRb::NaiveBayes.new
+nb.fit(train, target).save('model.pb')
+```
+
+### Loading Persisted Model
+
+```ruby
+NaiveBayesRb::NaiveBayes.serializer =       
+nb = NaiveBayesRb::NaiveBayes.load('model.pb')
+```
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'naive_bayes_rb'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install naive_bayes_rb
+
+## Thanks
+
+I followed the tutorials from [this blog]. 
+
+[this blog]: https://machinelearningmastery.com/naive-bayes-classifier-scratch-python/

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/lib/naive_bayes_rb.rb

@@ -0,0 +1,5 @@
+require "naive_bayes_rb/version"
+require "naive_bayes_rb/marshal_serializer"
+require "naive_bayes_rb/saved_model"
+require "naive_bayes_rb/stats"
+require "naive_bayes_rb/naive_bayes"

data/lib/naive_bayes_rb/marshal_serializer.rb

@@ -0,0 +1,12 @@
+module NaiveBayesRb
+  module MarshalSerializer 
+    extend self
+    def self.save(model, path)
+      File.open(path, 'wb') {|f| f.write( Marshal.dump(model) ) }
+    end
+
+    def self.load(path)
+      Marshal.load(File.binread(path))
+    end
+  end
+end

data/lib/naive_bayes_rb/naive_bayes.rb

@@ -0,0 +1,32 @@
+module NaiveBayesRb
+  class NaiveBayes
+    include SavedModel
+    
+    attr_accessor :model
+
+    def initialize
+      @model = {}
+    end
+
+    def fit(data, target)
+      @model = data.zip(target)
+                   .group_by(&:last)
+                   .inject({}) { |h, (k, v)| h[k] = Stats.mean_stdev(v.map(&:first)); h}
+      self
+    end
+
+    def predict(data)
+      data.map {|v| Stats.prediction(v, @model) }
+    end
+
+    def dimension
+      (@model.values || []).length
+    end
+
+    def accuracy(prediction, actual)
+      Stats.accuracy(prediction, actual)
+    end
+    
+  end
+end
+

data/lib/naive_bayes_rb/saved_model.rb

@@ -0,0 +1,27 @@
+module NaiveBayesRb
+  module SavedModel
+    def self.included(base)
+      base.extend(ClassMethods)
+    end
+    
+    module ClassMethods
+      def serializer=(serializer)
+        @serializer = serializer
+      end
+  
+      def serializer
+        @serializer
+      end
+  
+      def load(path)
+        self.new.tap do |nb|
+          nb.model = @serializer.load(path)
+        end
+      end
+    end
+  
+    def save(path)
+      self.class.serializer.save(self.model, path)
+    end
+  end
+end

data/lib/naive_bayes_rb/stats.rb

@@ -0,0 +1,48 @@
+module NaiveBayesRb
+  module Stats
+    extend self
+
+    def mean_stdev(data)
+      dimension = data[0].length-1
+      means = (0..dimension).map {|i| mean(data.map {|x| x[i]})}
+      stdevs = (0..dimension).map {|i| stdev(data.map {|x| x[i]})}
+      means.zip(stdevs)
+    end
+
+    def probability(value, mean, stdev)
+      exponent = Math.exp(-((value-mean)**2)/( 2 * stdev**2 ))
+      (1 / (Math.sqrt(2*Math::PI) * stdev) ) * exponent
+    end
+
+    def class_probability(value, summaries)
+      summaries.inject({}) { |h, (k, v)| 
+        h[k] = v.zip(Array(value)).inject(1) { |p, ms|
+          p * probability(ms[1], ms[0][0], ms[0][1])}; h}
+    end
+
+    def prediction(value, summaries)
+      class_probability(value, summaries).sort_by {|_, v| -v}.first.first
+    end
+
+    def accuracy(predictions, target)
+      predictions.zip(target)
+                 .map {|x| x[0] == x[1]}
+                 .count {|x| x}
+                 .send(:*, 100.0)
+                 .send(:/, predictions.length)
+    end
+
+    private
+
+      def mean(list)
+        list.inject(:+).to_f.div(list.length)
+      end
+
+      def stdev(list)
+        m = mean(list)
+        sum = list.inject(0){|accum, i| accum +(i-m)**2 }
+        Math.sqrt(sum/(list.length - 1).to_f)
+      end
+
+  end
+end

data/lib/naive_bayes_rb/version.rb

@@ -0,0 +1,3 @@
+module NaiveBayesRb
+  VERSION = "0.1.0"
+end

data/naive_bayes_rb.gemspec

@@ -0,0 +1,33 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'naive_bayes_rb/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "naive_bayes_rb"
+  spec.version       = NaiveBayesRb::VERSION
+  spec.authors       = ["Jack Xu"]
+  spec.email         = ["jackxxu@gmail.com"]
+  spec.summary       = %q{simply naive bayes implementation in ruby.}
+  spec.homepage      = "https://github.com/jackxxu/naive_bayes_rb"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against " \
+      "public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.13"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: naive_bayes_rb
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jack Xu
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-03-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: 
+email:
+- jackxxu@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- Guardfile
+- README.md
+- Rakefile
+- lib/naive_bayes_rb.rb
+- lib/naive_bayes_rb/marshal_serializer.rb
+- lib/naive_bayes_rb/naive_bayes.rb
+- lib/naive_bayes_rb/saved_model.rb
+- lib/naive_bayes_rb/stats.rb
+- lib/naive_bayes_rb/version.rb
+- naive_bayes_rb.gemspec
+homepage: https://github.com/jackxxu/naive_bayes_rb
+licenses: []
+metadata:
+  allowed_push_host: https://rubygems.org
+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: 
+rubygems_version: 2.4.6
+signing_key: 
+specification_version: 4
+summary: simply naive bayes implementation in ruby.
+test_files: []