ruby-band 0.1.11

data/README.rdoc

@@ -0,0 +1,70 @@
+= ruby-band
+
+Data mining and machine learning algorithms for Ruby
+
+== Installation
+
+Install the 'jbundle' gem for JRuby before trying to install the
+'ruby-band' gem. Maven is also required for .jars automatic download and
+installation. On Ubuntu/Debian Maven should already be installed and on OSX
+system you can get it from Brew
+
+If you want to use 'ruby-band' APIs without installing the gem you need to run
+command 'rake -T' once before requiring the gem in your script (this is
+necessary for jbundler to download the '.jar' files and subsequently set the
+Java classpath). Otherwise use:
+
+    gem install ruby-band
+
+== Description
+
+ruby-band was created by Alberto Arrigoni as part of Google’s Summer of Code 2013. It is part of SciRuby.
+
+== Usage
+
+For a short tutorial on ruby-band functions and capabilities please visit our wiki section here on Github
+
+== Developers
+
+To use the library 
+
+        require 'ruby-band'
+
+The API doc is online. For more code examples see also the test files in
+the source tree.
+        
+== Project home page
+
+Information on the source tree, documentation, issues and how to contribute, see
+
+  http://github.com/arrigonialberto86/ruby-band
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+== Contributing to ruby-band
+ 
+ ruby-band is part of SciRuby, a collaborative effort to bring scientific computation to Ruby. If you want to help, please do so!
+
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally. Cucumber tests (stored in the 'features' folder) are a great way to draft 
+tutorial sections along with tests.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+
+== Cite
+
+  If you use this software, please cite one of
+ 
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+
+== License
+
+Copyright (c) 2010–13, The Ruby Science Foundation.
+All rights reserved. See LICENSE.txt for further details.
+

data/Rakefile

@@ -0,0 +1,66 @@
+# encoding: utf-8
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+  require 'jbundler'
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `jruby -S bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "ruby-band"
+  gem.homepage = "http://github.com/arrigonialberto86/ruby-band"
+  gem.license = "MIT"
+  gem.summary = %Q{Data mining algorithms for JRuby}
+  gem.description = %Q{Data mining and machine learning algorithms for JRuby }
+  gem.email = "arrigonialberto86@gmail.com"
+  gem.authors = ["arrigonialberto86"]
+  gem.extensions = ["ext/mkrf_conf.rb"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'cucumber/rake/task'
+Cucumber::Rake::Task.new(:features)
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+#  test.pattern = 'test/**/test_*.rb'
+  test.test_files = FileList['test/test_*.rb']
+  test.verbose = true
+end
+
+task :test => [] do
+  begin
+    Rake::Task[:test].invoke
+  rescue
+  end
+  Rake::Task[:features].invoke
+end
+
+#require 'rcov/rcovtask'
+#Rcov::RcovTask.new do |test|
+#  test.libs << 'test'
+#  test.pattern = 'test/**/test_*.rb'
+#  test.verbose = true
+#  test.rcov_opts << '--exclude "gems/*"'
+#end
+
+task :default => :test
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "ruby-band #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.11

data/band_server/client.rb

@@ -0,0 +1,35 @@
+require 'rest_client'
+require 'uri'
+
+address = 'http://localhost:4567/'
+
+response_old = RestClient.post "#{address}create_dataset", { 'first' => { 'dataset' => File.new('first_dataset.csv'),'dataset_name' => 'dataset_1'}, 
+                                                             'second' => {'dataset' => File.new('second_dataset.csv'),'dataset_name' => 'dataset_2'} }
+
+
+puts 'List of the parsed datasets:'
+response_list =  RestClient.get "#{address}datasets", :cookies => response_old.cookies
+puts response_list
+
+# use filter on the training dataset
+RestClient.get "#{address}filter?filter_name=Filter::Unsupervised::Attribute::Discretize&&filter_options=-K_3&&dataset_in=dataset_1&&dataset_out=filtered_training_set",:cookies => response_old.cookies
+                               
+puts 'List of the datasets + the filtered training set'
+response_list =  RestClient.get "#{address}datasets", :cookies => response_old.cookies
+puts response_list
+
+puts 'Print a single dataset:'
+puts  RestClient.get "#{address}datasets/dataset_1", :cookies => response_old.cookies
+
+
+puts 'Train a classifier on the dataset_1:'
+puts RestClient.get "#{address}train_classifier?classifier_name=Classifier::Bayes::NaiveBayes&&classifier_options=-K&&dataset_in=dataset_1&&model_name=naive_classifier&&class_index=0",:cookies => response_old.cookies
+
+puts 'List all the trained classifiers:'
+puts  RestClient.get "#{address}classifiers", :cookies => response_old.cookies
+
+puts 'Show classifier statistics:'
+puts  RestClient.get "#{address}classifiers/naive_classifier", :cookies => response_old.cookies
+
+puts 'Crossvalidate the classifier:'
+puts  RestClient.get "#{address}crossvalidate_classifier?model_name=naive_classifier&&fold=5", :cookies => response_old.cookies

data/band_server/client_alt.rb

@@ -0,0 +1,35 @@
+require 'rest_client'
+require 'uri'
+
+address = 'http://localhost:4567/'
+
+response_old = RestClient.post "#{address}create_dataset", { 'first' => { 'dataset' => File.new('first_dataset.csv'),'dataset_name' => 'dataset_1'}, 
+                                                             #'second' => {'dataset' => File.new('second_dataset.csv'),'dataset_name' => 'dataset_2'}, 
+															 'third' => {'dataset' => File.new('third_dataset.csv'),'dataset_name' => 'dataset_3'} }
+
+puts 'List of the parsed datasets:'
+response_list =  RestClient.get "#{address}datasets", :cookies => response_old.cookies
+puts response_list
+
+# use filter on the training dataset
+RestClient.get "#{address}filter?filter_name=Filter::Unsupervised::Attribute::Discretize&&filter_options=-K_3&&dataset_in=dataset_1&&dataset_out=filtered_training_set",:cookies => response_old.cookies
+                               
+puts 'List of the datasets + the filtered training set'
+response_list =  RestClient.get "#{address}datasets", :cookies => response_old.cookies
+puts response_list
+
+puts 'Print a single dataset:'
+puts  RestClient.get "#{address}datasets/dataset_1", :cookies => response_old.cookies
+
+
+puts 'Train a classifier on the dataset_1:'
+puts RestClient.get "#{address}train_classifier?classifier_name=Classifier::Bayes::NaiveBayes&&classifier_options=-K&&dataset_in=dataset_1&&model_name=naive_classifier&&class_index=0",:cookies => response_old.cookies
+
+puts 'List all the trained classifiers:'
+puts  RestClient.get "#{address}classifiers", :cookies => response_old.cookies
+
+puts 'Show classifier statistics:'
+puts  RestClient.get "#{address}classifiers/naive_classifier", :cookies => response_old.cookies
+
+puts 'Crossvalidate the classifier:'
+puts  RestClient.get "#{address}crossvalidate_classifier?model_name=naive_classifier&&fold=5", :cookies => response_old.cookies

data/band_server/first_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/band_server/second_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/band_server/simple_server.rb

@@ -0,0 +1,90 @@
+#### This simple example server should run on JRuby, while the client can be run
+### either on Ruby or JRuby
+
+
+require 'sinatra/base'
+require 'ruby-band'
+require 'JSON'
+
+class Trial < Sinatra::Base
+  use Rack::Session::Pool
+
+  get '/datasets' do
+    session[:datasets].keys.join(",\t")
+  end
+  get '/classifiers' do
+    session[:classifiers].keys.join(",\t")
+  end
+
+  # return a dataset using Json format
+  get '/datasets/:dataset_in' do
+    # force session to start by writing in the Hash ## ODDDDD
+    session[:init] = true
+    session[:datasets][params[:dataset_in]].to_json_format
+  end
+
+  get '/classifiers/:classifier_in' do
+    session[:init] = true
+    session[:classifiers][params[:classifier_in]]
+  end
+
+  get '/summary/:dataset_in' do
+    session[:init] = true
+    dataset_in = session[:datasets][params[:dataset_in]]
+    return dataset_in.summary[0].to_s,dataset_in.summary[1].to_s
+  end
+
+  post "/create_dataset" do
+    params.each_key do |key|
+      File.open('uploads/' + params[key]['dataset'][:filename], "w") do |f|
+        f.write(params[key]['dataset'][:tempfile].read)
+      end
+      session[:datasets] ||= Hash.new
+      session[:classifiers] ||= Hash.new  
+      session[:datasets][params[key]['dataset_name']] = Core::Parser::parse_CSV('uploads/' + params[key]['dataset'][:filename])
+    end
+    return "The dataset was successfully created!"
+  end
+
+  get '/filter' do
+    session[:init] = true
+    $dataset_in = session[:datasets][params[:dataset_in]]
+    filter = eval("Weka::#{params[:filter_name]}.new")
+    $params = params
+    filter.set do
+      filter_options $params[:filter_options].split("_").join(" ")
+      data $dataset_in 
+    end
+    filtered_data = filter.use
+    session[:datasets][params[:dataset_out]] = filtered_data
+  end
+
+  get '/train_classifier' do
+    session[:init] = true
+    @dataset_in = session[:datasets][params[:dataset_in]]
+    classifier = eval("Weka::#{params[:classifier_name]}.new")  
+    classifier.set_options params[:classifier_options].split("_").join(" ") if params[:classifier_options]
+    @dataset_in.setClassIndex(params[:class_index].to_i)
+    classifier.set_data @dataset_in
+    classifier.build_classifier(@dataset_in)
+    session[:classifiers][params[:model_name]] = classifier
+    classifier.to_s
+  end
+
+  get '/crossvalidate_classifier' do
+    session[:init] = true
+    classifier = session[:classifiers][params[:model_name]]
+    fold = params[:fold].to_i
+    eval = Weka::Classifier::Evaluation.new classifier.instance_eval("@dataset")
+    eval.crossValidateModel(classifier.class.new, classifier.instance_eval("@dataset"), fold.to_java(:int), Random.new(1))
+    eval.summary
+  end
+
+  post '/clear' do
+    session.clear
+    puts "Session is now cleared"
+  end
+
+end
+
+Trial.run!

data/band_server/third_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/band_server/uploads/first_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/band_server/uploads/second_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/band_server/uploads/third_dataset.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

data/bin/ruby-band

@@ -0,0 +1,83 @@
+#!/usr/bin/env ruby
+#
+# BioRuby ruby-band Plugin RubyBand
+# Author:: arrigonialberto86
+# Copyright:: 2013
+
+USAGE = "Describe ruby-band"
+
+gempath = File.dirname(File.dirname(__FILE__))
+$: << File.join(gempath,'lib')
+
+VERSION_FILENAME=File.join(gempath,'VERSION')
+version = File.new(VERSION_FILENAME).read.chomp
+
+# print banner
+print "ruby-band #{version} by arrigonialberto86 2013\n"
+
+if ARGV.size == 0
+  print USAGE
+end
+
+require 'ruby-band'
+require 'optparse'
+
+# Uncomment when using the bio-logger 
+# require 'bio-logger'
+# Bio::Log::CLI.logger('stderr')
+# Bio::Log::CLI.trace('info')
+
+options = {:example_switch=>false,:show_help=>false}
+opts = OptionParser.new do |o|
+  o.banner = "Usage: #{File.basename($0)} [options] reponame\ne.g. #{File.basename($0)} the-perfect-gem"
+
+  o.on('--example_parameter [EXAMPLE_PARAMETER]', 'TODO: put a description for the PARAMETER') do |example_parameter|
+    # TODO: your logic here, below an example
+    options[:example_parameter] = 'this is a parameter'
+  end
+  
+  o.separator ""
+  o.on("--switch-example", 'TODO: put a description for the SWITCH') do
+    # TODO: your logic here, below an example
+    self[:example_switch] = true
+  end
+
+  # Uncomment the following when using the bio-logger 
+  # o.separator ""
+  # o.on("--logger filename",String,"Log to file (default stderr)") do | name |
+  #   Bio::Log::CLI.logger(name)
+  # end
+  #
+  # o.on("--trace options",String,"Set log level (default INFO, see bio-logger)") do | s |
+  #   Bio::Log::CLI.trace(s)
+  # end
+  # 
+  # o.on("-q", "--quiet", "Run quietly") do |q|
+  #   Bio::Log::CLI.trace('error')
+  # end
+  # 
+  # o.on("-v", "--verbose", "Run verbosely") do |v|
+  #   Bio::Log::CLI.trace('info')
+  # end
+  # 
+  # o.on("--debug", "Show debug messages") do |v|
+  #   Bio::Log::CLI.trace('debug')
+  # end
+
+  o.separator ""
+  o.on_tail('-h', '--help', 'display this help and exit') do
+    options[:show_help] = true
+  end
+end
+
+begin
+  opts.parse!(ARGV)
+
+  # Uncomment the following when using the bio-logger 
+  # Bio::Log::CLI.configure('ruby-band')
+
+  # TODO: your code here
+  # use options for your logic
+rescue OptionParser::InvalidOption => e
+  options[:invalid_argument] = e.message
+end