bio-band 0.1.2 → 0.1.3

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.1.3

data/bio-band.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-band"
-  s.version = "0.1.2"
+  s.version = "0.1.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["arrigonialberto86"]
-  s.date = "2013-07-30"
+  s.date = "2013-09-02"
   s.description = "Data mining and machine learning algorithms for JRuby "
   s.email = "arrigonialberto86@gmail.com"
   s.executables = ["bio-band"]
@@ -55,6 +55,9 @@ Gem::Specification.new do |s|
     "lib/bio-band/core/type/instances.rb",
     "lib/bio-band/core/type/utils.rb",
     "lib/bio-band/weka.rb",
+    "lib/bio-band/weka/attribute_selection/attribute_selection_utils.rb",
+    "lib/bio-band/weka/attribute_selection/evaluators.rb",
+    "lib/bio-band/weka/attribute_selection/search.rb",
     "lib/bio-band/weka/classifiers/bayes/bayes.rb",
     "lib/bio-band/weka/classifiers/bayes/bayes_utils.rb",
     "lib/bio-band/weka/classifiers/evaluation.rb",
@@ -62,7 +65,9 @@ Gem::Specification.new do |s|
     "lib/bio-band/weka/classifiers/functions/functions_utils.rb",
     "lib/bio-band/weka/classifiers/lazy/lazy.rb",
     "lib/bio-band/weka/classifiers/lazy/lazy_utils.rb",
-    "lib/bio-band/weka/classifiers/rules/rules.rb ",
+    "lib/bio-band/weka/classifiers/mi/mi.rb",
+    "lib/bio-band/weka/classifiers/mi/mi_utils.rb",
+    "lib/bio-band/weka/classifiers/rules/rules.rb",
     "lib/bio-band/weka/classifiers/rules/rules_utils.rb",
     "lib/bio-band/weka/classifiers/trees/trees.rb",
     "lib/bio-band/weka/classifiers/trees/trees_utils.rb",

data/features/step_definitions/create_dataset.rb

@@ -4,37 +4,36 @@ Given(/^a nominal attribute, named "(.*?)", with values "(.*?)"$/) do |arg1, arg
 end
 
 Given(/^one numeric attribute, named "(.*?)"$/) do |arg1|
-	$second_att = arg1.to_sym
+  $second_att = arg1.to_sym
 end
 
 Given(/^another numeric attribute, names "(.*?)"$/) do |arg1|
-	$third_att = arg1.to_sym
+  $third_att = arg1.to_sym
 end
 
 Given(/^two data rows: "(.*?)","(.*?)"$/) do |arg1, arg2|
-	@first_row = arg1.split(',')
-	@second_row = arg2.split(',')
-	@first_row[1] = @first_row[1].to_f
-	@first_row[2] = @first_row[2].to_f
-	@second_row[1] = @second_row[1].to_f
-	@second_row[2] = @second_row[2].to_f
+  $first_row = arg1.split(',')
+  $second_row = arg2.split(',')
+  $first_row[1] = $first_row[1].to_f
+  $first_row[2] = $first_row[2].to_f
+  $second_row[1] = $second_row[1].to_f
+  $second_row[2] = $second_row[2].to_f
 end
 
 Then(/^I want to build en empty dataset for my use$/) do
-	class Dataset < Core::Type::Instances::Base
-		nominal $first_att, $values
-  	numeric $second_att
-  	string $third_att
+  $my_instance = Core::Type::Instances::Base.new do
+    nominal $first_att, $values
+    numeric $second_att
+    string $third_att
   end
-  @my_instance = Dataset.new
-  @my_instance.summary
+  $my_instance.summary
 end
 
 Then(/^I want to populate the dataset by row$/) do
-	@my_instance.populate_by_row([@first_row,@second_row])
-	@my_instance.summary
+  $my_instance.populate_by_row([$first_row,$second_row])
+  $my_instance.summary
 end
 
 Then(/^I want to print my dataset as a bidimensional Ruby Array$/) do
-	puts @my_instance.to_a2d.inspect
+  puts $my_instance.to_a2d.inspect
 end

data/features/step_definitions/weka_clustering.rb

@@ -30,5 +30,5 @@ Then(/^I want to report result statistics$/) do
 end
 
 Then(/^I want to use Weka clustering cross\-validation$/) do
-  puts @clustered.validate
-end
+  puts @clustered.evaluate
+end

data/features/step_definitions/weka_filters.rb

@@ -1,29 +1,32 @@
 Given(/^the example ARFF file "(.*?)"$/) do |arff_file|
-	@arff = File.join('resources',arff_file)
+  @arff = File.join('resources',arff_file)
 end
 
 Given(/^the Weka Attribute Add filter$/) do
-	@filter = Weka::Filter::Unsupervised::Attribute::Add.new
+  @filter = Weka::Filter::Unsupervised::Attribute::Add.new
 end
 
 Then(/^I want to parse the file in order to create an Instances class object$/) do
-	@dataset_ARFF = Core::Parser::parse_ARFF(@arff)
-	@dataset_ARFF.summary
+  $dataset_ARFF = Core::Parser::parse_ARFF(@arff)
+  puts $dataset_ARFF.summary
 end
 
 Then(/^I want to print the available filter options and usage$/) do
-	@filter.filter_options
+  @filter.options_list
 end
 
 Then(/^I want to set the option String "(.*?)"$/) do |arg1|
-	@filter.set_filter_options(arg1)
-	@filter.set_data(@dataset_ARFF)
+  $arg1 =  arg1
+  @filter.set do 
+    filter_options $arg1
+    data $dataset_ARFF
+  end
 end
 
 Then(/^I want to add an attribute \(a column\) to the dataset using the Weka filter Add$/) do
-	@new_inst = @filter.use
+  @new_inst = @filter.use
 end
 
 Then(/^I want to print a "(.*?)" for the modified dataset$/) do |arg1|
-	@new_inst.send arg1.to_sym
+  @new_inst.send arg1.to_sym
 end

data/features/step_definitions/weka_parsers.rb

@@ -1,20 +1,20 @@
 Given /^the CSV file "(.*?)"$/ do |csv_file|
-	@csv = File.join('resources',csv_file)
-	@dataset_CSV = Core::Parser::parse_CSV(@csv)
+  @csv = File.join('resources',csv_file)
+  @dataset_CSV = Core::Parser::parse_CSV(@csv)
 end
 
 Then /^I want to print to stdout the summary for the CSV parsed Instances object$/ do
-	@dataset_CSV.summary
+  @dataset_CSV.summary
 end
 
 Given /^the ARFF file "(.*?)"$/ do |arff_file|
-	@arff = File.join('resources',arff_file)
-	puts @arff
-	@dataset_ARFF = Core::Parser::parse_ARFF(@arff)
+  @arff = File.join('resources',arff_file)
+  puts @arff
+  @dataset_ARFF = Core::Parser::parse_ARFF(@arff)
 end
 
 Then /^I want to print to stdout the summary for the ARFF parsed Instances object$/ do
-	@dataset_ARFF.summary
+  @dataset_ARFF.summary
 end
 
 Given(/^the database "(.*?)"$/) do |arg1|
@@ -22,7 +22,7 @@ Given(/^the database "(.*?)"$/) do |arg1|
 end
 
 Given(/^a table named "(.*?)"$/) do |arg1|
-	@target_table = arg1
+  @target_table = arg1
 end
 
 Then(/^I want to extract data from that table$/) do
@@ -34,11 +34,11 @@ Then(/^I want to print to stdout the summary for the parsed Instances object$/)
 end
 
 Then(/^I want to convert the data into a bidimensional Ruby Array$/) do 
-	@dataset.to_a2d.should == [["sunny", 85.0, 85.0, "FALSE", "no"], ["sunny", 80.0, 90.0, "TRUE", "no"], ["overcast", 83.0, 86.0, "FALSE", "yes"],
-													 ["rainy", 70.0, 96.0, "FALSE", "yes"], ["rainy", 68.0, 80.0, "FALSE", "yes"], ["rainy", 65.0, 70.0, "TRUE", "no"], 
-													 ["overcast", 64.0, 65.0, "TRUE", "yes"], ["sunny", 72.0, 95.0, "FALSE", "no"], ["sunny", 69.0, 70.0, "FALSE", "yes"], 
-													 ["rainy", 75.0, 80.0, "FALSE", "yes"], ["sunny", 75.0, 70.0, "TRUE", "yes"], ["overcast", 72.0, 90.0, "TRUE", "yes"], 
-													 ["overcast", 81.0, 75.0, "FALSE", "yes"], ["rainy", 71.0, 91.0, "TRUE", "no"]]
+  @dataset.to_a2d.should == [["sunny", 85.0, 85.0, "FALSE", "no"], ["sunny", 80.0, 90.0, "TRUE", "no"], ["overcast", 83.0, 86.0, "FALSE", "yes"],
+                           ["rainy", 70.0, 96.0, "FALSE", "yes"], ["rainy", 68.0, 80.0, "FALSE", "yes"], ["rainy", 65.0, 70.0, "TRUE", "no"], 
+                           ["overcast", 64.0, 65.0, "TRUE", "yes"], ["sunny", 72.0, 95.0, "FALSE", "no"], ["sunny", 69.0, 70.0, "FALSE", "yes"], 
+                           ["rainy", 75.0, 80.0, "FALSE", "yes"], ["sunny", 75.0, 70.0, "TRUE", "yes"], ["overcast", 72.0, 90.0, "TRUE", "yes"], 
+                           ["overcast", 81.0, 75.0, "FALSE", "yes"], ["rainy", 71.0, 91.0, "TRUE", "no"]]
 end
 
 

data/lib/bio-band/core/type/instances.rb

@@ -3,6 +3,8 @@ require 'ruport'
 require 'json'
 
 module Core
+
+  java_import "weka.core.SerializationHelper"
   module Type
     
     java_import "weka.core.Instances"
@@ -46,7 +48,7 @@ module Core
       end
 
       # Return the number of columns (Attribute objects) in the dataset
-      def n_columns
+      def n_col
         return numAttributes
       end
 
@@ -55,6 +57,14 @@ module Core
         puts "Rows number:\t#{numInstances}\nColumns number:\t #{numAttributes}"
       end
 
+      def each_row
+        enumerate_instances.each {|inst| yield(inst)}
+      end
+
+      def each_column
+        enumerate_attributes.each {|attribute| yield(attribute)}
+      end
+
       # Check if this instance's attributes are all Numeric
       def check_numeric_instance
         enumerateAttributes.each do |att|
@@ -160,7 +170,7 @@ module Core
       # (check function): should check that the array is bidimensional and that
       # the lengths are equal
       def check_array(data)
-        return true
+        return true # still to be done
       end
 
       # An entire dataset is inserted 'by row' into the current Instances object 
@@ -236,9 +246,11 @@ module Core
 
         puts summary
 
-        count=0
-        enumerateInstances.each {|inst| count=count+1}
-        puts "\nNumber of rows: #{count}" 
+        unless enumerate_instances.nil?
+          count=0
+          enumerateInstances.each {|inst| count=count+1}
+          puts "\nNumber of rows: #{count}"
+        end 
       end
 
       # Merges two sets of Instances together. The resulting set will have all the
@@ -257,50 +269,51 @@ module Core
      #   return instances
      # end
 
-      @@positions = []
       # This method is used for attributes definition in uninitialized Instances-derived classes
-      def self.att(attr_type,name,*values)
+      def att(attr_type,name,*values)
         att = Core::Type.create_numeric_attr(name.to_java(:string)) if attr_type == :numeric
         att = Core::Type.create_nominal_attr(name.to_java(:string),values[0]) if attr_type == :nominal
         att = Core::Type.create_date_attr(name.to_java(:string),values[0]) if attr_type == :date
         att = att = Core::Type.create_string_attr(name.to_java(:string)) if attr_type == :string      
-        @@positions << att
+        @positions << att
       end
 
       # This method is used for Nominal attributes definition in uninitialized Instances-derived classes
       # * *Args*    :
       #   - +name+ -> Attribute name, a String
       #   - +values+ -> An array of values for the nominal attribute
-      def self.nominal(name,values)
+      def nominal(name,values)
         att :nominal, name, values
       end
 
       # This method is used for Numeric attributes definition in uninitialized Instances-derived classes
       # * *Args*    :
       #   - +name+ -> Attribute name, a String
-      def self.numeric(name)
+      def numeric(name)
         att :numeric, name
       end
 
       # This method is used for Date attributes definition in uninitialized Instances-derived classes
       # * *Args*    :
       #   - +name+ -> Attribute name, a String
-      def self.date(name)
+      def date(name)
         att :date, name
       end
 
       # This method is used for String attributes definition in uninitialized Instances-derived classes
       # * *Args*    :
       #   - +name+ -> Attribute name, a String
-      def self.string(name)
+      def string(name)
         att :string, name
       end
 
       # Class used for the creation of a new dataset (Instances class)
       class Base < Instances
-        def initialize
+        def initialize(&block)
           attributes_vector = FastVector.new
-          @@positions.each {|value| attributes_vector.addElement(value)}
+          @positions = []
+          self.instance_eval(&block) if block
+          @positions.each {|value| attributes_vector.addElement(value)}
           super('Instances',attributes_vector,0)
         end
       end
@@ -325,7 +338,13 @@ module Core
       attributes.each {|value| attributes_vector.addElement(value)}
       return Instances.new(name,attributes_vector,0)
     end
+
+  end
+  # Helper class for serialization
+  # Works with classifiers, filters, clusterers...
+  class SerializationHelper
   end
+  
 end
 
 

data/lib/bio-band/weka.rb

@@ -9,4 +9,6 @@ require 'bio-band/weka/classifiers/functions/functions'
 require 'bio-band/weka/classifiers/trees/trees'
 require 'bio-band/weka/classifiers/lazy/lazy'
 require 'bio-band/weka/classifiers/rules/rules'
-require 'bio-band/weka/clusterers/clusterers'
+require 'bio-band/weka/clusterers/clusterers'
+require 'bio-band/weka/attribute_selection/evaluators'
+require 'bio-band/weka/attribute_selection/search'

data/lib/bio-band/weka/attribute_selection/attribute_selection_utils.rb

@@ -0,0 +1,18 @@
+module Attribute_selection_Utils
+  java_import "weka.core.Utils"
+
+  #Instance methods list
+  def options_list
+    listOptions.map {|key| "#{key.synopsis} #{key.description}"}.join("\n")
+  end 
+
+  def select_options(options_string)
+    options = Utils.splitOptions(options_string)
+    set_options(options)
+  end
+
+  def description
+    globalInfo
+ end
+
+end

data/lib/bio-band/weka/attribute_selection/evaluators.rb

@@ -0,0 +1,21 @@
+$:.unshift File.dirname(__FILE__)
+require 'attribute_selection_utils'
+
+module Weka
+  module Attribute_selection
+    module Evaluator
+      java_import 'weka.attributeSelection.CfsSubsetEval'
+      java_import 'weka.attributeSelection.ChiSquaredAttributeEval'
+
+      class CfsSubsetEval
+        include Attribute_selection_Utils 
+        java_alias :use_options , :setOptions, [Java::Java.lang.String[]]
+      end
+
+      class ChiSquaredAttributeEval
+        include Attribute_selection_Utils  
+      end
+
+    end 
+  end
+end

data/lib/bio-band/weka/attribute_selection/search.rb

@@ -0,0 +1,26 @@
+$:.unshift File.dirname(__FILE__)
+require 'attribute_selection_utils'
+
+module Weka
+  module Attribute_selection
+    module Search
+      
+      java_import 'weka.attributeSelection.GreedyStepwise'
+      java_import 'weka.attributeSelection.RankSearch'
+      java_import 'weka.attributeSelection.Ranker'
+
+      class GreedyStepwise
+        include Attribute_selection_Utils 
+      end
+
+      class Ranker
+        include Attribute_selection_Utils 
+      end
+
+      class RankSearch
+        include Attribute_selection_Utils 
+      end
+
+    end 
+  end
+end

data/lib/bio-band/weka/classifiers/bayes/bayes.rb

@@ -2,64 +2,84 @@ $:.unshift File.dirname(__FILE__)
 require 'bayes_utils'
 
 module Weka
-	module Classifier
-		module Bayes
-			java_import "weka.classifiers.bayes.NaiveBayes"
-			java_import "weka.classifiers.bayes.BayesianLogisticRegression"
-			java_import "weka.classifiers.bayes.AODE"
-			java_import "weka.classifiers.bayes.ComplementNaiveBayes"
-			java_import "weka.classifiers.bayes.WAODE"
+  module Classifier
+    module Bayes
+      java_import "weka.classifiers.bayes.NaiveBayes"
+      java_import "weka.classifiers.bayes.BayesianLogisticRegression"
+      java_import "weka.classifiers.bayes.AODE"
+      java_import "weka.classifiers.bayes.ComplementNaiveBayes"
+      java_import "weka.classifiers.bayes.WAODE"
 
-			class NaiveBayes
-				include Bayes_utils
-				class Base < NaiveBayes
-					def initialize
-						super
-            init_classifier
-					end
-				end
-			end
+      class NaiveBayes
+        include Bayes_utils
+        class Base < NaiveBayes
+          def initialize(&block)
+            super
+            if block_given?
+              init_instance_classifier(&block)
+            else
+              init_classifier  
+            end
+          end
+        end
+      end
 
-			class AODE
-				include Bayes_utils
-				class Base < AODE
-					def initialize
-						super
-            init_classifier
-					end
-				end
-			end
+      class AODE
+        include Bayes_utils
+        class Base < AODE
+          def initialize(&block)
+            super
+            if block_given?
+              init_instance_classifier(&block)
+            else
+              init_classifier  
+            end
+          end
+        end
+      end
 
-			class BayesianLogisticRegression
-				include Bayes_utils
-				class Base < BayesianLogisticRegression
-					def initialize
-						super
-            init_classifier
-					end
-				end
-			end
+      class BayesianLogisticRegression
+        include Bayes_utils
+        class Base < BayesianLogisticRegression
+          def initialize(&block)
+            super
+            if block_given?
+              init_instance_classifier(&block)
+            else
+              init_classifier  
+            end
+          end
+        end
+      end
 
-			class ComplementNaiveBayes
-				include Bayes_utils
-				class Base < ComplementNaiveBayes
-					def initialize
-						super
-            init_classifier
-					end
-				end
-			end
+      class ComplementNaiveBayes
+        include Bayes_utils
+        class Base < ComplementNaiveBayes
+          def initialize(&block)
+            super
+            if block_given?
+              init_instance_classifier(&block)
+            else
+              init_classifier  
+            end
+          end
+        end
+      end
 
-			class WAODE
-				include Bayes_utils
-				class Base < WAODE
-					def initialize
-						super
-            init_classifier
-					end
-				end
-			end
+      class WAODE
+        include Bayes_utils
+        class Base < WAODE
+          def initialize(&block)
+            super
+            if block_given?
+              init_instance_classifier(&block)
+            else
+              init_classifier  
+            end
+          end
+        end
+      end
 
-		end
-	end
+    end
+  end
 end