bio-band 0.1.3 → 0.1.4

data/Gemfile

@@ -7,6 +7,7 @@ source "http://rubygems.org"
 # Include everything needed to run rake, tests, features, etc.
 group :development do
   gem "shoulda", ">= 0"
+  gem "test-unit", ">= 0"
   gem "rdoc", "~> 3.12"
   gem "bundler", "~> 1.3.5"
   gem "jeweler", "~> 1.8.4"

data/Gemfile.lock

@@ -14,6 +14,8 @@ GEM
       multi_json (~> 1.3)
     diff-lcs (1.2.4)
     fastercsv (1.5.5)
+    gherkin (2.12.0)
+      multi_json (~> 1.3)
     gherkin (2.12.0-java)
       multi_json (~> 1.3)
     git (1.2.5)
@@ -26,6 +28,7 @@ GEM
       git (>= 1.2.5)
       rake
       rdoc
+    json (1.8.0)
     json (1.8.0-java)
     maven-tools (0.32.4)
     multi_json (1.7.4)
@@ -59,6 +62,7 @@ GEM
       multi_json (~> 1.0)
       simplecov-html (~> 0.7.1)
     simplecov-html (0.7.1)
+    test-unit (2.5.5)
     thor (0.18.1)
     transaction-simple (1.4.0.2)
 
@@ -77,3 +81,4 @@ DEPENDENCIES
   ruport
   shoulda
   simplecov
+  test-unit

data/Jarfile

@@ -1,4 +1,4 @@
-jar 'nz.ac.waikato.cms.weka:weka-stable','3.6.9'
+jar 'nz.ac.waikato.cms.weka:weka-stable','3.6.10'
 jar 'org.apache.commons:commons-math3','3.0'
 jar 'junit:junit','3.8.1'
 jar 'mysql:mysql-connector-java','5.1.6'

data/Jarfile.lock

@@ -1,4 +1,4 @@
-nz.ac.waikato.cms.weka:weka-stable:jar:3.6.9
+nz.ac.waikato.cms.weka:weka-stable:jar:3.6.10
 net.sf.squirrel-sql.thirdparty-non-maven:java-cup:jar:0.11a
 org.apache.commons:commons-math3:jar:3.0
 junit:junit:jar:3.8.1

data/README.rdoc

@@ -19,6 +19,8 @@ Otherwise use:
 
 == Usage
 
+See the Wiki section for in depth information on how to use this gem
+
 == Developers
 
 To use the library 

data/Rakefile

@@ -29,7 +29,8 @@ Jeweler::RubygemsDotOrgTasks.new
 require 'rake/testtask'
 Rake::TestTask.new(:test) do |test|
   test.libs << 'lib' << 'test'
-  test.pattern = 'test/**/test_*.rb'
+#  test.pattern = 'test/**/test_*.rb'
+  test.test_files = FileList['test/test_*.rb']
   test.verbose = true
 end
 

data/VERSION

@@ -1 +1 @@
-0.1.3
+0.1.4

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 +1,95 @@
+#### This simple example server should run on JRuby, while the client can be run
+### either on Ruby or JRuby
+
+
+require 'sinatra/base'
+require 'bio-band'
+require 'JSON'
+
+class Trial < Sinatra::Base
+  use Rack::Session::Pool
+
+  # list created datasets or classifiers
+  # get '/list/:data_class' do
+  #   session[params[:data_class]].keys.join(",\t")
+  # end
+
+  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/bio-band.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-band"
-  s.version = "0.1.3"
+  s.version = "0.1.4"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["arrigonialberto86"]
-  s.date = "2013-09-02"
+  s.date = "2013-09-11"
   s.description = "Data mining and machine learning algorithms for JRuby "
   s.email = "arrigonialberto86@gmail.com"
   s.executables = ["bio-band"]
@@ -27,6 +27,15 @@ Gem::Specification.new do |s|
     "README.rdoc",
     "Rakefile",
     "VERSION",
+    "band_server/client.rb",
+    "band_server/client_alt.rb",
+    "band_server/first_dataset.csv",
+    "band_server/second_dataset.csv",
+    "band_server/simple_server.rb",
+    "band_server/third_dataset.csv",
+    "band_server/uploads/first_dataset.csv",
+    "band_server/uploads/second_dataset.csv",
+    "band_server/uploads/third_dataset.csv",
     "bin/bio-band",
     "bio-band.gemspec",
     "ext/mkrf_conf.rb",
@@ -85,7 +94,11 @@ Gem::Specification.new do |s|
     "resources/weather.csv",
     "resources/weather.numeric.arff",
     "spec/bio-band_spec.rb",
-    "spec/spec_helper.rb"
+    "spec/spec_helper.rb",
+    "test/helper.rb",
+    "test/test_apacheCorrelation.rb",
+    "test/test_apacheInference.rb",
+    "test/test_bio-band.rb"
   ]
   s.homepage = "http://github.com/arrigonialberto86/bioruby-band"
   s.licenses = ["MIT"]
@@ -98,6 +111,7 @@ Gem::Specification.new do |s|
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_development_dependency(%q<shoulda>, [">= 0"])
+      s.add_development_dependency(%q<test-unit>, [">= 0"])
       s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_development_dependency(%q<bundler>, ["~> 1.3.5"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
@@ -110,6 +124,7 @@ Gem::Specification.new do |s|
       s.add_development_dependency(%q<bio>, [">= 1.4.2"])
     else
       s.add_dependency(%q<shoulda>, [">= 0"])
+      s.add_dependency(%q<test-unit>, [">= 0"])
       s.add_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_dependency(%q<bundler>, ["~> 1.3.5"])
       s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
@@ -123,6 +138,7 @@ Gem::Specification.new do |s|
     end
   else
     s.add_dependency(%q<shoulda>, [">= 0"])
+    s.add_dependency(%q<test-unit>, [">= 0"])
     s.add_dependency(%q<rdoc>, ["~> 3.12"])
     s.add_dependency(%q<bundler>, ["~> 1.3.5"])
     s.add_dependency(%q<jeweler>, ["~> 1.8.4"])

data/features/step_definitions/weka_classifiers.rb

@@ -30,11 +30,12 @@ Then(/^I want to print a summary for the dataset$/) do
 end
 
 Then(/^I want to set the class index for attribute with index "(.*?)"$/) do |arg1|
-    My_classifier.set_class_index(arg1.to_i)
+  My_classifier.set_class_index(arg1.to_i)
 end
 
 Then(/^I want to instantiate the classifier for my use$/) do
-  My_classifier.new
+  classifier = My_classifier.new
+  classifier.cross_validate(2)
 end
 
 

data/features/weka_classifiers.feature

@@ -1,16 +1,16 @@
 Feature: Using a Weka classifier
-	In order to classify an instance data
-	I want to use a Weka classifier
+  In order to classify an instance data
+  I want to use a Weka classifier
 
-	Scenario: Understand options and usage
-		Given the Weka "NaiveBayes" classifier
-		Then I want to print a "description"
-		And I want to print an options list
+  Scenario: Understand options and usage
+    Given the Weka "NaiveBayes" classifier
+    Then I want to print a "description"
+    And I want to print an options list
 
-	Scenario: Use a classifier on a data instance
-		Given the unsupervised Weka classifier "NaiveBayes"
-		Then I want to set option "-K" for it
-		And I want to set the dataset parsed from "weather.numeric.arff"
-		And I want to print a summary for the dataset
-		And I want to set the class index for attribute with index "0"
-		And I want to instantiate the classifier for my use
+  Scenario: Use a classifier on a data instance
+    Given the unsupervised Weka classifier "NaiveBayes"
+    Then I want to set option "-K" for it
+    And I want to set the dataset parsed from "weather.numeric.arff"
+    And I want to print a summary for the dataset
+    And I want to set the class index for attribute with index "0"
+    And I want to instantiate the classifier for my use