see5 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 6d2b54a9d4d3c9f3271505bf233a46772cacfd1702312a68dab174b197265f59
+  data.tar.gz: cb5a5d275b08cb8ce7ca00be58c81fd015902578d31c1d6e8a7d1b5d2936225a
+SHA512:
+  metadata.gz: 903fb8b64822a99a15c14383fc57932af364bb1c355046b4b022b9588c2d7359c5bdbcf5221f4282ba9b1f9a4200f746d390d962367bcad8a39ecd61e2671839
+  data.tar.gz: 98594a2c2be18ede5633ee7ba66894d2ce2b2eddead9d10eb4531728c349b8b9db95e439f7ca1407d9c92a6abed363549127a7b731a8f5c53af984096d0fe1d5

data/.gitignore

@@ -0,0 +1,6 @@
+/.bundle/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rubocop.yml

@@ -0,0 +1,11 @@
+---
+Style/ClassAndModuleChildren:
+  Exclude:
+    - "test/**"
+
+Style/Documentation:
+  Exclude:
+    - "test/**"
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes

data/Gemfile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in ruby-see5.gemspec
+gemspec

data/README.md

@@ -0,0 +1,33 @@
+# Ruby::See5
+
+A Ruby frontend for the See5/C5.0 family of classifiers and modellers. Builds models from Ruby objects.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ruby-see5'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ruby-see5
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/elebow/ruby-see5.

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+task default: :test
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/test_*.rb"]
+end

data/lib/see5.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+require "see5/input_file_writer"
+require "see5/model"
+require "see5/rules_file_parser"
+require "see5/schema"
+require "see5/version"

data/lib/see5/input_file_writer.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+require_relative "schema"
+
+module See5
+  # Writes names and data files suitable for See5, Cubist, or GritBot.
+  class InputFileWriter
+    def self.write_files(data:, schema: nil, names_io: nil, data_io: nil)
+      new(data: data, schema: schema, names_io: names_io, data_io: data_io)
+        .write_files
+    end
+
+    def initialize(data:, schema: nil, names_io: nil, data_io: nil)
+      @data = data
+      @schema = schema # TODO: automatic schema from data objects' attributes
+      @names_io = names_io
+      @data_io = data_io
+    end
+
+    def write_files
+      write_names_file
+      write_data_file
+    end
+
+    def write_names_file
+      names_io.write(@schema.names_file_contents)
+    end
+
+    def write_data_file
+      # TODO: missing or N/A
+      @data.each do |record|
+        data_io.write(row(record))
+        data_io.write("\n")
+      end
+    end
+
+    private
+
+    def row(record)
+      @schema.attributes.map do |attr, _vals|
+        record.send(attr)
+      end.join(",")
+    end
+
+    def names_io
+      @names_io ||= File.open("/tmp/ruby-see5.names", "w")
+    end
+
+    def data_io
+      @data_io ||= File.open("/tmp/ruby-see5.data", "w")
+    end
+  end
+end

data/lib/see5/model.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+module See5
+  class Model
+    attr_reader :rules
+
+    def initialize(default_classification:, rules:)
+      @default_classification = default_classification
+      @rules = rules
+    end
+
+    def classify(data)
+      # See5 orders rules by confidence within each class (TODO verify),
+      # so the first matching rule is the one with the highest confidence.
+      first_matching_rule = rules.find { |rule| rule.match?(data) }
+
+      return first_matching_rule.classification unless first_matching_rule.nil?
+
+      @default_classification
+    end
+  end
+end

data/lib/see5/rule.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+module See5
+  class Rule
+    attr_reader :classification, :confidence, :rule_info, :conditions
+
+    def initialize(rule_info, conditions, class_info)
+      @rule_info = rule_info
+      @conditions = conditions
+      @classification = class_info[:classification]
+      @confidence = class_info[:confidence]
+    end
+
+    def match?(data)
+      conditions
+        .map { |attr, val| data[attr] == val }
+        .all? { |matched| matched == true }
+    end
+
+    def to_s
+      [
+        "See5::Rule",
+        "@classification=#{@classification}",
+        "@conditions=#{@conditions}"
+      ]
+        .join(", ")
+        .yield_self { |s| "#<#{s}>" }
+    end
+  end
+end

data/lib/see5/rules_file_parser.rb

@@ -0,0 +1,101 @@
+# frozen_string_literal: true
+
+require_relative "rule"
+
+module See5
+  # Read See5 rules output and return an array of hashes representing the rules
+  # Note that this is the output normally sent to stdout, NOT the .rules file!
+  # The .rules file lacks some important information like confidence.
+  class RulesFileParser
+    def self.parse_file(fname)
+      new(fname).model
+    end
+
+    def initialize(fname)
+      @file = File.open(fname)
+      @rules = []
+
+      parse_file
+    end
+
+    def model
+      {
+        default_classification: @default_classification,
+        rules: @rules
+      }
+    end
+
+    def parse_file
+      discard_header
+
+      while (line = lines.next)
+        if line.start_with?("Rule ")
+          @rules << parse_rule(line)
+        elsif line.start_with?("Default class:")
+          @default_classification = line.split(":").last.strip
+
+          break
+        end
+      end
+    end
+
+    private
+
+    def lines
+      # TODO: lazy unnecessary given that rules are small?
+      @file.each_line.lazy
+    end
+
+    # Discard the file header and advance to the rules section
+    # TODO: save the data from the header, in case user wants it?
+    def discard_header
+      while (line = lines.next)
+        break if line == "Rules:\n"
+      end
+      # discard the final blank line
+      lines.next
+    end
+
+    def parse_rule(line)
+      rule_info = parse_rule_info_line(line)
+      conditions = []
+
+      while (line = lines.next.strip)
+        if line.start_with?("->")
+          class_info = parse_class_line(line)
+
+          break
+        end
+
+        conditions << parse_condition_line(line)
+      end
+
+      Rule.new(rule_info, conditions.to_h, class_info)
+    end
+
+    def parse_class_line(line)
+      matches = line.match(/class ([\w]+)  \[(.+)\]/)
+
+      {
+        classification: matches[1],
+        confidence: matches[2].to_f
+      }
+    end
+
+    def parse_rule_info_line(line)
+      matches = line.match(%r{Rule \d+: \((\d+)(?:/)?([^,]*), lift (.+)\)})
+
+      {
+        cases_covered: matches[1].to_i,
+        cases_not_covered: matches[2]&.to_i,
+        lift: matches[3].to_f
+      }
+    end
+
+    def parse_condition_line(line)
+      (attr, val) = line.split("=").map(&:strip)
+
+      [attr.to_sym, val]
+    end
+  end
+end

data/lib/see5/schema.rb

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+module See5
+  class Schema
+    attr_reader :class_attribute, :attributes
+
+    def initialize(classes:, attributes:, class_attribute: nil)
+      @classes = classes
+      @attributes = attributes
+      @class_attribute = class_attribute&.to_sym || :class_attribute
+
+      # if the class attribute doesn't exist in the attributes, add it
+      unless @attributes.key?(@class_attribute)
+        @attributes[@class_attribute] = @classes
+      end
+    end
+
+    def names_file_contents
+      class_attribute.to_s + # TODO: continuous class attribute
+        "\n" +
+        attributes.map do |attr, vals|
+          "#{attr}: #{vals.join(',')}"
+        end.join("\n")
+    end
+  end
+end

data/lib/see5/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module See5
+  VERSION = "0.1.0"
+end

data/see5.gemspec

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+
+lib = File.expand_path("lib", __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "see5/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "see5"
+  spec.version       = See5::VERSION
+  spec.authors       = ["Eddie Lebow"]
+  spec.email         = ["elebow@users.noreply.github.com"]
+
+  spec.summary       = "A Ruby frontend for the See5/C5.0 family of classifiers and modellers."
+  #spec.description   = "TODO: Write a longer description or delete this line."
+  spec.homepage      = "https://github.com/elebow/ruby-see5"
+
+  if spec.respond_to?(:metadata)
+    spec.metadata["homepage_uri"] = spec.homepage
+    spec.metadata["source_code_uri"] = "https://github.com/elebow/ruby-see5"
+    spec.metadata["changelog_uri"] = "https://github.com/elebow/ruby-see5/blob/master/CHANGELOG.md"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against " \
+      "public gem pushes."
+  end
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |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", "~> 1.17"
+  spec.add_development_dependency "minitest", "~> 5.0"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: see5
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Eddie Lebow
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2020-03-03 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+- !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'
+description: 
+email:
+- elebow@users.noreply.github.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rubocop.yml"
+- Gemfile
+- README.md
+- Rakefile
+- lib/see5.rb
+- lib/see5/input_file_writer.rb
+- lib/see5/model.rb
+- lib/see5/rule.rb
+- lib/see5/rules_file_parser.rb
+- lib/see5/schema.rb
+- lib/see5/version.rb
+- see5.gemspec
+homepage: https://github.com/elebow/ruby-see5
+licenses: []
+metadata:
+  homepage_uri: https://github.com/elebow/ruby-see5
+  source_code_uri: https://github.com/elebow/ruby-see5
+  changelog_uri: https://github.com/elebow/ruby-see5/blob/master/CHANGELOG.md
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: A Ruby frontend for the See5/C5.0 family of classifiers and modellers.
+test_files: []