yannitor 0.4.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: dc236f3fe8c163f62db1f98d1dffde1e3eb094a2
+  data.tar.gz: 177ff7bf154b494a1cf0f4802af2b331b2727b0d
+SHA512:
+  metadata.gz: 37ca690096112e3ba641a4b55a1d18f19fe10ad1588ba8213612173537796e5daa131e933497b75fb9d22582be8e4066f6d734a7633f3a9f0a5a9fcacb6951e4
+  data.tar.gz: 2439a2117a6bbf362ca4cd40a6576189d0a15645ed19f43a6ea2d3aac4cf70eef567de7ce7a7cd7394af64d0255301c4429326c0d0071ee5a77f89b69b22a2b0

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

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.3
+before_install: gem install bundler -v 1.14.6

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 danielius@wisemonks.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 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in yannitor.gemspec
+gemspec

data/README.md

@@ -0,0 +1,42 @@
+# Yannitor
+
+A simple data preprocessing layer built on top of Active Record.
+
+Currently supported encodings:
+* One hot (['Hello', 'dear', 'World'], 'Hello' => [1, 0, 0])
+* Min-max normalization ([10, 15, 20] => [0, 0.5, 1])
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'yannitor'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install yannitor
+
+## Usage
+```ruby
+class Property < ApplicationRecord
+  yannitor_features linear: ['area', 'floor', 'floor_count', 'year', 'room_count', 'sale_price'],
+                    one_hot: ['building_type', 'building_equipment']
+  ...
+end
+```
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` 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/dvisockas/yannitor. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+

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 "yannitor"
+
+# 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/lib/yannitor/cleaner.rb

@@ -0,0 +1,79 @@
+require 'active_record'
+# require 'active_record/version'
+# require 'active_support/core_ext/module'
+
+# begin
+#   require 'rails/engine'
+# end
+
+module Yannitor
+  module Broom
+    attr_accessor :features
+
+    def yannitor_is_cleaning(feats = {})
+      self.features = feats
+    end
+
+    def to_one_hot target_column, type = 'text'
+      sorted_value_array = self.pluck("distinct(#{target_column})")
+
+      _table_name   = self.table_name
+      values_select = %Q(SELECT value FROM (values ('#{ sorted_value_array.join("'), ('") }')) s(value))
+
+      self.select(%Q(
+        #{_table_name}.id,
+        ARRAY_AGG(CASE WHEN sorted_value_table.value::#{type} = #{_table_name}.#{target_column}::#{type} THEN 1 ELSE 0 END) AS o#{target_column}
+      )).joins(%Q(
+        LEFT JOIN (#{values_select}) AS sorted_value_table ON 1=1
+      )).group("#{_table_name}.id")
+    end
+
+    def vectorize
+      _table_name   = self.table_name
+
+      select('*, ' + features[:linear].map do |feature|
+        min = all.minimum(feature)
+        max = all.maximum(feature)
+        "CAST((#{_table_name}.#{feature}::float - #{min}::float) / (#{max}::float - #{min}::float) AS float) as n#{feature}"
+      end.join(', ')).all.map do |obj|
+
+        obj.class.features[:linear].map do |feature|
+          obj.send("n#{feature}").to_f
+        end
+      end
+    end
+
+    def nelect(feature)
+      _table_name   = self.table_name
+
+      min = all.minimum(feature)
+      max = all.maximum(feature)
+      
+      self.select("*, (#{_table_name}.#{feature}::float - #{min}::float) / (#{max}::float - #{min}::float)::float as n#{feature}")
+    end
+
+    def normalize(feature)
+      print "Normalizing #{feature}"
+      min = all.minimum(feature)
+      max = all.maximum(feature)
+      data = all.nelect(feature).map do |e|
+        e.send("n#{feature}".to_sym)
+      end
+
+      [data, min, max]
+    end
+
+    def to_file
+      CSV.open("data.csv", "wb", {col_sep: ' '}) do |csv|
+        all.vectorize.each { |v| csv << v }
+      end
+
+      nil
+    end
+
+  end
+end
+
+ActiveSupport.on_load(:active_record) do
+  extend Yannitor::Broom
+end

data/lib/yannitor/version.rb

@@ -0,0 +1,3 @@
+module Yannitor
+  VERSION = "0.4.0"
+end

data/lib/yannitor.rb

@@ -0,0 +1,6 @@
+require "yannitor/version"
+require "yannitor/cleaner"
+
+module Yannitor
+  # Your code goes here...
+end

data/yannitor.gemspec

@@ -0,0 +1,35 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'yannitor/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "yannitor"
+  spec.version       = Yannitor::VERSION
+  spec.authors       = ["Danielius Visockas"]
+  spec.email         = ["danielius@wisemonks.com"]
+
+  spec.summary       = %q{Gem for preprocessing Active record collections}
+  spec.description   = %q{I'll clean your data}
+  spec.homepage      = "https://github.com"
+
+  # 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'] = "'http://mygemserver.com'"
+  # 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", "~> 1.14"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification
+name: yannitor
+version: !ruby/object:Gem::Version
+  version: 0.4.0
+platform: ruby
+authors:
+- Danielius Visockas
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-11-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+- !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: I'll clean your data
+email:
+- danielius@wisemonks.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/yannitor.rb
+- lib/yannitor/cleaner.rb
+- lib/yannitor/version.rb
+- yannitor.gemspec
+homepage: https://github.com
+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: 
+rubygems_version: 2.6.14
+signing_key: 
+specification_version: 4
+summary: Gem for preprocessing Active record collections
+test_files: []