ruby_fast_text 0.3.5

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c8a62041da945594d545e6d0f45a3349dd9d6dd1
+  data.tar.gz: d75c61b72631f67669d347a42705a18983c02567
+SHA512:
+  metadata.gz: 83244f07a1cec29a4c03f796682c96bd6a7124d232b8ec35d735afe0fd6da66168596a0fdf4efbe1e91f0d6e870406d86cb5d7e23cfe35dd67831d1126c04211
+  data.tar.gz: 0aaab9dd2d5edb8bec947fa06c4eda27442ea5b3684cd52b83b86114d438fda97defd044ff831dcdb8adc2105e6ef7e93adf7a8206fd3e9e6b0496f8f2a748b4

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.vscode
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rake_tasks~

@@ -0,0 +1,7 @@
+build
+clean
+clobber
+install
+install:local
+release[remote]
+test

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.4.0
+before_install: gem install bundler -v 1.16.0

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 ruby_fast_text.gemspec
+gemspec

data/README.md

@@ -0,0 +1,35 @@
+# RubyFastText
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/ruby_fast_text`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ruby_fast_text'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ruby_fast_text
+
+## 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/[USERNAME]/ruby_fast_text.

data/Rakefile

@@ -0,0 +1,17 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task :default => :test
+
+namespace :install do
+  task :fast_text do
+    `git clone https://github.com/facebookresearch/fastText.git`
+    `cd fastText && make`
+  end
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "ruby_fast_text"
+
+# 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/ruby_fast_text.rb

@@ -0,0 +1,10 @@
+module RubyFastText
+  # Your code goes here...
+  require "ruby_fast_text/version"
+  require "ruby_fast_text/commands"
+  require "ruby_fast_text/classifier"
+  require "ruby_fast_text/word_vectors"
+  require "ruby_fast_text/skipgram"
+  require "ruby_fast_text/cbow"
+  require "ruby_fast_text/nn"
+end

data/lib/ruby_fast_text/cbow.rb

@@ -0,0 +1,13 @@
+module RubyFastText
+  class Cbow
+    extend RubyFastText::Commands
+    
+    def self.train(params)
+      path = params[:path]
+
+      Dir.chdir(path) do
+        system("fasttext cbow #{params_to_s(params)}")
+      end
+    end
+  end
+end

data/lib/ruby_fast_text/classifier.rb

@@ -0,0 +1,55 @@
+module RubyFastText
+  class Classifier
+    attr_accessor :classifier
+
+    attr_reader :probability
+    alias probability? probability
+
+    extend RubyFastText::Commands
+    
+    def initialize(params)
+      path = params[:path]
+      model = params[:model]
+      labels_number = params.fetch(:labels_number, 1)
+      @probability = params[:probability]
+      probability_param = probability ? 'predict-prob' : 'predict'
+      #p File.expand_path File.dirname(__FILE__)
+      #p $0
+      @classifier = Dir.chdir(path) do
+        IO.popen("fasttext #{probability_param} #{model} - #{labels_number}", 'r+')
+      end
+    end
+
+    def predict(sentence)
+      classifier.puts(sentence)
+      format_result(classifier.gets)
+    end
+
+    def self.train(params)
+      path = params[:path]
+      Dir.chdir(path) do
+        system("fasttext supervised #{params_to_s(params)}")
+      end
+    end
+
+    def self.test(params)
+      path = params[:path]
+      model = params[:model]
+      test_data = params[:test_data]
+      k = params.fetch(:k, 1)
+      Dir.chdir(path) do
+        system("fasttext test #{model} #{test_data} #{k}")
+      end
+    end
+
+
+    private
+    def format_result(result)
+      if probability?
+        Hash[*result.strip.split.flatten]
+      else
+        result.strip.split
+      end
+    end
+  end
+end

data/lib/ruby_fast_text/commands.rb

@@ -0,0 +1,14 @@
+module RubyFastText
+  module Commands
+    def params_to_s(params)
+      commands = %i[input output verbose minCount minCountLabel
+      wordNgrams bucket minn mann maxn t label lr lrUpdateRate
+      dim ws epoch neg loss thread pretrainedVectors saveOutput
+      cutoff retrain qnorm qout dsub]
+
+      params.select { |k, _v| commands.include? k}
+      .map { |k,v| "-#{k.to_s} #{v}"}
+      .join(" ")
+    end
+  end
+end

data/lib/ruby_fast_text/nn.rb

@@ -0,0 +1,45 @@
+module RubyFastText
+  class NN
+    attr_accessor :predictor
+    attr_reader :k
+
+    def initialize(params)
+      path = params[:path]
+      model = params[:model]
+      @k = params.fetch(:k, 10)
+
+      @predictor = Dir.chdir(path) do
+        IO.popen("fasttext nn #{model} #{k}", 'r+')
+      end
+    end
+
+      # TODO: Fix, only getting one line out of the result
+    def neighbours(word)
+      predictor.puts(word)
+      format_result(read_lines)
+    end
+
+    private
+    def read_lines
+      # Should be done with predictor.readlines
+      # but process gets blocked...
+      lines = ''
+      k.times {
+        lines << predictor.gets
+      }
+      lines
+    end
+
+    def format_result(result)
+      # Deletes CLI comment on first line
+      # Separates lines into array
+      # Transforms each line into hash entry
+      result.sub!('Query word? ', '')
+            .split("\n")
+            .each_with_object({}) do |item, res|
+              key, value = item.split
+              res[key] = value
+            end
+    end
+  end
+end

data/lib/ruby_fast_text/skipgram.rb

@@ -0,0 +1,13 @@
+module RubyFastText
+  class Skipgram
+    extend RubyFastText::Commands
+    
+    def self.train(params)
+      path = params[:path]
+      
+      Dir.chdir(path) do
+        system("fasttext skipgram #{params_to_s(params)}")
+      end
+    end
+  end
+end

data/lib/ruby_fast_text/version.rb

@@ -0,0 +1,3 @@
+module RubyFastText
+  VERSION = "0.3.5"
+end

data/lib/ruby_fast_text/word_vectors.rb

@@ -0,0 +1,24 @@
+module RubyFastText
+  class WordVectors
+    attr_accessor :vectors
+    
+    def initialize(params)
+      path = params[:path]
+      model = params[:model]
+      @vectors = Dir.chdir(path) do
+        IO.popen("fasttext print-word-vectors #{model}", 'r+')
+      end
+    end
+
+    def get_vector(word)
+      vectors.puts(word)
+      format_result(vectors.gets)
+    end
+
+    private
+    def format_result(result)
+      result.split.drop(1)
+    end
+
+  end
+end

data/ruby_fast_text.gemspec

@@ -0,0 +1,29 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "ruby_fast_text/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "ruby_fast_text"
+  spec.version       = RubyFastText::VERSION
+  spec.authors       = ["amval"]
+  spec.email         = ["alberto.m.valdunciel@gmail.com"]
+
+  spec.summary       = %q{Ruby wrapper for FastText using the CLI.}
+  spec.description   = %q{Ruby wrapper for FastText using the CLI.}
+
+  # 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.
+
+
+  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", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest", "~> 5.0"
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: ruby_fast_text
+version: !ruby/object:Gem::Version
+  version: 0.3.5
+platform: ruby
+authors:
+- amval
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-01-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !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: 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'
+description: Ruby wrapper for FastText using the CLI.
+email:
+- alberto.m.valdunciel@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rake_tasks~"
+- ".travis.yml"
+- ".vscode/tasks.json"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/ruby_fast_text.rb
+- lib/ruby_fast_text/cbow.rb
+- lib/ruby_fast_text/classifier.rb
+- lib/ruby_fast_text/commands.rb
+- lib/ruby_fast_text/nn.rb
+- lib/ruby_fast_text/skipgram.rb
+- lib/ruby_fast_text/version.rb
+- lib/ruby_fast_text/word_vectors.rb
+- ruby_fast_text.gemspec
+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: 
+rubygems_version: 2.6.8
+signing_key: 
+specification_version: 4
+summary: Ruby wrapper for FastText using the CLI.
+test_files: []