learn_kit 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: ca7aeb09d91fc1451ba01359299e250c379b932a289951ff976b9a8024bc00cb
+  data.tar.gz: f1422a68f87762cedba48736a8bebdac372ae8e9c52f0e3bc750b48d356c1b63
+SHA512:
+  metadata.gz: a94136b6145991bb659c5b8e2e6306bef7ebb56d0852e479e2f1ae68283afd3eadcee28e730581bf609bfdea8a5e6ece20a21fd892390362c4ec79e663d40b4f
+  data.tar.gz: b1ff7601ce22526978ba5b3981e91fbd821b5e9356097274297213b62a154e7d779df7813d78d6cbf3fa23bc00cb2a52462ee09a03ec0ae9d65e7912ae19d508

data/.gitignore

@@ -0,0 +1,12 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--require spec_helper
+--format documentation
+--color

data/.rubocop.yml

@@ -0,0 +1,57 @@
+AllCops:
+  Exclude:
+    - bin/*
+  TargetRubyVersion: 2.5.0
+
+Metrics/AbcSize:
+  Enabled: false
+
+Metrics/BlockLength:
+  Enabled: false
+
+Metrics/ClassLength:
+  Enabled: false
+
+Metrics/LineLength:
+  Enabled: false
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/ModuleLength:
+  Enabled: false
+
+Metrics/CyclomaticComplexity:
+  Max: 20
+
+Layout/IndentationWidth:
+  Width: 2
+
+Layout/CaseIndentation:
+  EnforcedStyle: case
+  SupportedStyles:
+    - case
+    - end
+  IndentOneStep: true
+
+Layout/AlignHash:
+  Enabled: false
+
+Style/GuardClause:
+  Enabled: false
+
+Naming:
+  Enabled: false
+
+Style/FormatStringToken:
+  EnforcedStyle: template
+
+Style/ExpandPathArguments:
+  Enabled: false
+
+Style/FrozenStringLiteralComment:
+  Enabled: false
+
+Style/RescueStandardError:
+  Enabled: false
+

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.5.1
+before_install: gem install bundler -v 1.15.4

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at kortirso@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in open_street_map.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2018 kortirso
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,72 @@
+# LearnKit
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'learn_kit'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install learn_kit
+
+### K-Nearest Neighbors
+
+Initialize classificator with data set consists from labels and features:
+
+```ruby
+  data_set = { label1: [[-1, -1], [-2, -1], [-3, -2]], label2: [[1, 1], [2, 1], [3, 2], [-2, -2]] }
+  clf = LearnKit::Knn.new(data_set: data_set)
+```
+
+Predict label for new feature:
+
+```ruby
+  clf.predict(k: 3, algorithm: 'brute', weight: 'uniform', point: [-1, -2])
+```
+    k - number of nearest neighbors
+    algorithm - algorithm for calculation of distances, one of the [brute]
+    weight - method of weighted neighbors, one of the [uniform|distance]
+    point - new feature for prediction
+
+### Naive Bayes
+
+#### Gaussian
+
+Initialize classificator with data set consists from labels and features:
+
+```ruby
+  data_set = { label1: [[-1, -1], [-2, -1], [-3, -2]], label2: [[1, 1], [2, 1], [3, 2], [-2, -2]] }
+  clf = LearnKit::NaiveBayes::Gaussian.new(data_set: data_set)
+```
+
+Make fit of test data:
+
+```ruby
+  clf.fit
+```
+
+Predict label for new feature:
+
+```ruby
+  clf.predict([-1, -2])
+```
+
+Or show probability for all labels:
+
+```ruby
+  clf.predict_proba([-1, -2])
+```
+
+Calculate accuracy for test data:
+
+```ruby
+  clf.score
+```

data/Rakefile

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

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'learn_kit'
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require 'irb'
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/learn_kit.gemspec

@@ -0,0 +1,30 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'learn_kit/version'
+
+Gem::Specification.new do |spec|
+  spec.name = 'learn_kit'
+  spec.version = LearnKit::VERSION
+  spec.authors = ['kortirso']
+  spec.email = ['kortirso@gmail.com']
+
+  spec.summary = 'Machine Learning library'
+  spec.description = 'Tools for machine learning with ruby'
+  spec.homepage = 'https://github.com/kortirso/learn_kit'
+  spec.license = 'MIT'
+
+  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.required_ruby_version = '>= 2.5.0'
+
+  spec.add_development_dependency 'bundler', '~> 1.15'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rubocop', '~> 0.57.2'
+  spec.add_dependency 'descriptive_statistics'
+end

data/lib/learn_kit.rb

@@ -0,0 +1,7 @@
+require_relative 'learn_kit/version'
+require_relative 'learn_kit/naive_bayes/gaussian'
+require_relative 'learn_kit/knn'
+
+# main module
+module LearnKit
+end

data/lib/learn_kit/knn.rb

@@ -0,0 +1,19 @@
+require_relative 'knn/predict'
+
+module LearnKit
+  # K-Nearest Neighbors algorithm
+  class Knn
+    class LearnFailure < StandardError; end
+
+    include LearnKit::Knn::Predict
+
+    attr_reader :data_set, :points
+
+    # input data
+    # { label1: [[f1, f2, f3], [f1, f2, f3]], label2: [[f4, f5, f6], [f4, f5, f6]] }
+    def initialize(args = {})
+      @data_set = args[:data_set]
+      @points = []
+    end
+  end
+end

data/lib/learn_kit/knn/predict.rb

@@ -0,0 +1,79 @@
+module LearnKit
+  class Knn
+    # Fit test data
+    module Predict
+      UNIFORM_WEIGHT = 1
+
+      # input data
+      # { k: 3, algorithm: 'brute', weight: 'uniform', point: [1, 2, 3] }
+      # algorithms: brute
+      # weights: uniform, distance
+      def predict(args = {})
+        calc_distances(args) if points.size.zero?
+        prediction(sort_points(args))
+      rescue LearnFailure => ex
+        puts "LearnFailure: #{ex.message}"
+      end
+
+      private
+
+      # calc distances
+      def calc_distances(args)
+        case args[:algorithm]
+          when 'brute' then brute_algorithm(args)
+          else []
+        end
+      end
+
+      # calculation with brute algorithm
+      def brute_algorithm(args)
+        data_set.keys.each do |key|
+          data_set[key].each do |value|
+            raise LearnFailure, "Different points size, error key - #{key}, error value - #{value}" if args[:point].size != value.size
+            points << { distance: calc_distance(args[:point], value), label: key }
+          end
+        end
+      end
+
+      # sort points by distance, select first K, add weight
+      def sort_points(args)
+        points
+          .sort_by { |point| point[:distance] }
+          .first(args[:k])
+          .map do |point|
+            point[:weight] = calc_point_weight(args[:weight], point[:distance])
+            point
+          end
+      end
+
+      # calc distance between 2 points
+      def calc_distance(point1, point2, summ = 0)
+        point1.each.with_index do |a, index|
+          summ += (a - point2[index])**2
+        end
+        Math.sqrt(summ)
+      end
+
+      # prediction
+      def prediction(sorted_points, result = {})
+        sorted_points.each do |point|
+          if result[point[:label]].nil?
+            result[point[:label]] = point[:weight]
+          else
+            result[point[:label]] += point[:weight]
+          end
+        end
+        result.sort_by { |_k, v| v }.reverse[0][0]
+      end
+
+      # calc point weight based on selected type
+      def calc_point_weight(weight, distance)
+        case weight
+          when 'uniform' then UNIFORM_WEIGHT
+          when 'distance' then 1 / distance**2
+          else UNIFORM_WEIGHT
+        end
+      end
+    end
+  end
+end

data/lib/learn_kit/naive_bayes/gaussian.rb

@@ -0,0 +1,25 @@
+require_relative 'gaussian/fit'
+require_relative 'gaussian/predict'
+require_relative 'gaussian/score'
+
+module LearnKit
+  module NaiveBayes
+    # Gaussian NB
+    class Gaussian
+      include LearnKit::NaiveBayes::Gaussian::Fit
+      include LearnKit::NaiveBayes::Gaussian::Predict
+      include LearnKit::NaiveBayes::Gaussian::Score
+
+      attr_reader :data_set, :labels, :feature_size, :fit_results
+
+      # input data
+      # { label1: [[f1, f2, f3], [f1, f2, f3]], label2: [[f4, f5, f6], [f4, f5, f6]] }
+      def initialize(args = {})
+        @data_set = args[:data_set]
+        @labels = data_set.keys
+        @feature_size = data_set.values.first[0].size
+        @fit_results = {}
+      end
+    end
+  end
+end

data/lib/learn_kit/naive_bayes/gaussian/fit.rb

@@ -0,0 +1,38 @@
+require 'descriptive_statistics'
+
+module LearnKit
+  module NaiveBayes
+    class Gaussian
+      # Fit test data
+      module Fit
+        # output data
+        # { label1: [{fs_std1: 1, fs_mean1: 2, fs_var1: 3}, {..}, {..}], label2: [{fs_std1: 1, fs_mean1: 2, fs_var1: 3}, {..}, {..}] }
+        def fit
+          labels.each do |label_name|
+            fit_results[label_name] = []
+            (0...feature_size).each do |index|
+              fs = feature_set(index, label_name)
+              # statistical properties of the feature set
+              fs_std = fs.standard_deviation
+              fs_mean = fs.mean
+              fs_var = fs.variance
+              fit_results[label_name] << { fs_std: fs_std, fs_mean: fs_mean, fs_var: fs_var }
+            end
+          end
+        end
+
+        private
+
+        # Get all the features of a certain index in a given label in one set
+        # index - feature index in training set
+        # label_name - label name
+        def feature_set(index, label_name, feature_set = [])
+          data_set[label_name].each do |feature|
+            feature_set << feature[index]
+          end
+          feature_set
+        end
+      end
+    end
+  end
+end

data/lib/learn_kit/naive_bayes/gaussian/predict.rb

@@ -0,0 +1,59 @@
+module LearnKit
+  module NaiveBayes
+    class Gaussian
+      # Predict new data
+      module Predict
+        # returns prediction of label for feature
+        # input data
+        # [f1, f2, f3]
+        # output data
+        # :label2
+        def predict(feature_values)
+          res = labels.sort_by do |label_name|
+            class_probability(feature_values, label_name)
+          end
+          res[-1]
+        end
+
+        # returns labels with probabilities
+        # input data
+        # [f1, f2, f3]
+        # output data
+        # { label1: 0.01, label2: 0.02 }
+        def predict_proba(feature_values, result = {})
+          labels.each do |label_name|
+            result[label_name] = class_probability(feature_values, label_name)
+          end
+          result
+        end
+
+        private
+
+        # compute the final naive Bayesian probability for a given set of features being a part of a given label
+        def class_probability(feature_values, label_name)
+          class_fraction = 1.0 / labels.size
+          feature_bayes = feature_mult(feature_values, label_name)
+          feature_bayes * class_fraction
+        end
+
+        # multiply together the feature probabilities for all of the features in a label for given values
+        def feature_mult(feature_values, label_name, res = 1.0)
+          feature_values.each.with_index do |feature_value, index|
+            res *= feature_probability(index, feature_value, label_name)
+          end
+          res
+        end
+
+        def feature_probability(index, value, label_name)
+          # select result from training
+          fit_result = fit_results[label_name][index]
+          # deal with the edge case of a 0 standard deviation
+          return fit_result[:fs_mean] == value ? 1.0 : 0.0 if fit_result[:fs_std].zero?
+          # calculate the gaussian probability
+          exp = - ((value - fit_result[:fs_mean])**2) / (2 * fit_result[:fs_var])
+          (1.0 / Math.sqrt(2 * Math::PI * fit_result[:fs_var])) * (Math::E**exp)
+        end
+      end
+    end
+  end
+end

data/lib/learn_kit/naive_bayes/gaussian/score.rb

@@ -0,0 +1,20 @@
+module LearnKit
+  module NaiveBayes
+    class Gaussian
+      # Calc accuracy for test data
+      module Score
+        # calculate accuracy for test data
+        def score(total = 0, correct = 0)
+          labels.each do |label_name|
+            data_set[label_name].each do |feature|
+              predicted_label = predict(feature)
+              correct += 1 if predicted_label == label_name
+              total += 1
+            end
+          end
+          total.zero? ? 0 : (correct * 100.0 / total).round(4)
+        end
+      end
+    end
+  end
+end

data/lib/learn_kit/version.rb

@@ -0,0 +1,3 @@
+module LearnKit
+  VERSION = '0.0.1'.freeze
+end

metadata

@@ -0,0 +1,134 @@
+--- !ruby/object:Gem::Specification
+name: learn_kit
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- kortirso
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-09-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.57.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.57.2
+- !ruby/object:Gem::Dependency
+  name: descriptive_statistics
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Tools for machine learning with ruby
+email:
+- kortirso@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- learn_kit.gemspec
+- lib/learn_kit.rb
+- lib/learn_kit/knn.rb
+- lib/learn_kit/knn/predict.rb
+- lib/learn_kit/naive_bayes/gaussian.rb
+- lib/learn_kit/naive_bayes/gaussian/fit.rb
+- lib/learn_kit/naive_bayes/gaussian/predict.rb
+- lib/learn_kit/naive_bayes/gaussian/score.rb
+- lib/learn_kit/version.rb
+homepage: https://github.com/kortirso/learn_kit
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.5.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: Machine Learning library
+test_files: []