svm_toolkit 1.1.7-java → 1.1.8-java

data/lib/svm_toolkit/evaluators.rb

@@ -1,169 +1,169 @@
-module SvmToolkit
-
-  # The Evaluator classes provides some classes and methods to construct 
-  # classes for evaluating the performance of a model against a dataset.  
-  # Different evaluators measure different kinds of performance.  
-  #
-  # Evaluator classes are accessed by name, with an optional positive label name.
-  # For example:
-  #
-  #   Evaluator::OverallAccuracy # => class evaluates overall accuracy
-  #   Evaluator::ClassPrecision(label) # => class evaluates precision for class "label"
-  # 
-  # Evaluators are wrapped around confusion matrices, outputting the required 
-  # statistical measure, and support the following methods:
-  #
-  # add_result(actual, prediction):: called to add information about each instance
-  #                                  when testing a model.
-  # value:: retrieves the appropriate measure of performance, based on the class name.
-  # to_s:: returns a string naming the evaluator and giving its value.
-  #
-  class Evaluator
-
-    # Defines an Evaluator returning the value of precision for given class
-    # label.
-    #
-    def Evaluator.ClassPrecision label
-      Class.new(Evaluator) do 
-        @@label = label
-
-        # Returns the precision.
-        #
-        def value
-          @cm.precision(@@label)
-        end
-
-        def to_s # :nodoc:
-          "Precision for label #{@@label}: #{value}"
-        end
-      end
-    end
-
-    # Defines an Evaluator returning the value of recall for given class
-    # label.
-    #
-    def Evaluator.ClassRecall label
-      Class.new(Evaluator) do 
-        @@label = label
-
-        def value # :nodoc:
-          @cm.recall(@@label)
-        end
-
-        def to_s # :nodoc:
-          "Recall for label #{@@label}: #{value}"
-        end
-      end
-    end
-
-    # Defines an Evaluator returning the value of the F-measure for given class
-    # label.
-    #
-    def Evaluator.FMeasure label
-      Class.new(Evaluator) do 
-        @@label = label
-
-        def value # :nodoc:
-          @cm.f_measure(@@label)
-        end
-
-        def to_s # :nodoc:
-          "F-measure for label #{@@label}: #{value}"
-        end
-      end
-    end
-
-    # Defines an Evaluator returning the value of Cohen's Kappa statistics for
-    # given class label.
-    #
-    def Evaluator.Kappa label
-      Class.new(Evaluator) do 
-        @@label = label
-
-        def value # :nodoc:
-          @cm.kappa(@@label)
-        end
-
-        def to_s # :nodoc:
-          "Kappa for label #{@@label}: #{value}"
-        end
-      end
-    end
-
-    # Defines an Evaluator returning the value of the Matthews Correlation
-    # Coefficient for given class label.
-    #
-    def Evaluator.MatthewsCorrelationCoefficient label
-      Class.new(Evaluator) do 
-        @@label = label
-
-        def value # :nodoc:
-          @cm.matthews_correlation(@@label)
-        end
-
-        def to_s # :nodoc:
-          "Matthews correlation coefficient: #{value}"
-        end
-      end
-    end
-
-    # Creates a new Evaluator, with a confusion matrix to store results.
-    #
-    def initialize
-      @cm = ConfusionMatrix.new
-    end
-
-    # Adds result to the underlying confusion matrix.
-    #
-    def add_result(actual, prediction)
-      @cm.add_for(actual, prediction)
-    end
-
-    # This object is better than given object, if the given object is an 
-    # instance of nil, or the value of this object is better.
-    #
-    def better_than? other
-      other.nil? or self.value > other.value
-    end
-
-    # Prints the confusion matrix.
-    #
-    def display
-      puts @cm
-    end
-  end
-
-  # Defines an Evaluator returning the value of overall accuracy.
-  #
-  class OverallAccuracy < Evaluator
-    # Returns the overall accuracy, as a percentage.
-    #
-    def value
-      100 * @cm.overall_accuracy
-    end
-
-    # Returns a string naming this evaluator and giving its value.
-    #
-    def to_s
-      "Overall accuracy: #{value}%"
-    end
-  end
-
-  # Defines an Evaluator returning the value of geometric mean.
-  #
-  class GeometricMean < Evaluator
-    # Returns the geometric mean.
-    #
-    def value
-      @cm.geometric_mean
-    end
-
-    # Returns a string naming this evaluator and giving its value.
-    #
-    def to_s
-      "Geometric mean: #{value}"
-    end
-  end
-
-end
-
+module SvmToolkit
+
+  # The Evaluator classes provides some classes and methods to construct 
+  # classes for evaluating the performance of a model against a dataset.  
+  # Different evaluators measure different kinds of performance.  
+  #
+  # Evaluator classes are accessed by name, with an optional positive label name.
+  # For example:
+  #
+  #   Evaluator::OverallAccuracy # => class evaluates overall accuracy
+  #   Evaluator::ClassPrecision(label) # => class evaluates precision for class "label"
+  # 
+  # Evaluators are wrapped around confusion matrices, outputting the required 
+  # statistical measure, and support the following methods:
+  #
+  # add_result(actual, prediction):: called to add information about each instance
+  #                                  when testing a model.
+  # value:: retrieves the appropriate measure of performance, based on the class name.
+  # to_s:: returns a string naming the evaluator and giving its value.
+  #
+  class Evaluator
+
+    # Defines an Evaluator returning the value of precision for given class
+    # label.
+    #
+    def Evaluator.ClassPrecision label
+      Class.new(Evaluator) do 
+        @@label = label
+
+        # Returns the precision.
+        #
+        def value
+          @cm.precision(@@label)
+        end
+
+        def to_s # :nodoc:
+          "Precision for label #{@@label}: #{value}"
+        end
+      end
+    end
+
+    # Defines an Evaluator returning the value of recall for given class
+    # label.
+    #
+    def Evaluator.ClassRecall label
+      Class.new(Evaluator) do 
+        @@label = label
+
+        def value # :nodoc:
+          @cm.recall(@@label)
+        end
+
+        def to_s # :nodoc:
+          "Recall for label #{@@label}: #{value}"
+        end
+      end
+    end
+
+    # Defines an Evaluator returning the value of the F-measure for given class
+    # label.
+    #
+    def Evaluator.FMeasure label
+      Class.new(Evaluator) do 
+        @@label = label
+
+        def value # :nodoc:
+          @cm.f_measure(@@label)
+        end
+
+        def to_s # :nodoc:
+          "F-measure for label #{@@label}: #{value}"
+        end
+      end
+    end
+
+    # Defines an Evaluator returning the value of Cohen's Kappa statistics for
+    # given class label.
+    #
+    def Evaluator.Kappa label
+      Class.new(Evaluator) do 
+        @@label = label
+
+        def value # :nodoc:
+          @cm.kappa(@@label)
+        end
+
+        def to_s # :nodoc:
+          "Kappa for label #{@@label}: #{value}"
+        end
+      end
+    end
+
+    # Defines an Evaluator returning the value of the Matthews Correlation
+    # Coefficient for given class label.
+    #
+    def Evaluator.MatthewsCorrelationCoefficient label
+      Class.new(Evaluator) do 
+        @@label = label
+
+        def value # :nodoc:
+          @cm.matthews_correlation(@@label)
+        end
+
+        def to_s # :nodoc:
+          "Matthews correlation coefficient: #{value}"
+        end
+      end
+    end
+
+    # Creates a new Evaluator, with a confusion matrix to store results.
+    #
+    def initialize
+      @cm = ConfusionMatrix.new
+    end
+
+    # Adds result to the underlying confusion matrix.
+    #
+    def add_result(actual, prediction)
+      @cm.add_for(actual, prediction)
+    end
+
+    # This object is better than given object, if the given object is an 
+    # instance of nil, or the value of this object is better.
+    #
+    def better_than? other
+      other.nil? or self.value > other.value
+    end
+
+    # Prints the confusion matrix.
+    #
+    def display
+      puts @cm
+    end
+  end
+
+  # Defines an Evaluator returning the value of overall accuracy.
+  #
+  class OverallAccuracy < Evaluator
+    # Returns the overall accuracy, as a percentage.
+    #
+    def value
+      100 * @cm.overall_accuracy
+    end
+
+    # Returns a string naming this evaluator and giving its value.
+    #
+    def to_s
+      "Overall accuracy: #{value}%"
+    end
+  end
+
+  # Defines an Evaluator returning the value of geometric mean.
+  #
+  class GeometricMean < Evaluator
+    # Returns the geometric mean.
+    #
+    def value
+      @cm.geometric_mean
+    end
+
+    # Returns a string naming this evaluator and giving its value.
+    #
+    def to_s
+      "Geometric mean: #{value}"
+    end
+  end
+
+end
+

data/lib/svm_toolkit/model.rb

@@ -1,124 +1,122 @@
-module SvmToolkit
-
-  # Extends the Java Model class with some additional methods.
-  #
-  class Model
-
-    # Evaluate model on given data set (an instance of Problem), 
-    # returning the number of errors made.
-    # Optional parameters include:
-    # * :evaluator => Evaluator::OverallAccuracy, the name of the class to use for computing performance
-    # * :print_results => false, whether to print the result for each instance
-    def evaluate_dataset(data, params = {})
-      evaluator = params.fetch(:evaluator, Evaluator::OverallAccuracy)
-      print_results = params.fetch(:print_results, false)
-      performance = evaluator.new
-      data.l.times do |i|
-        pred = Svm.svm_predict(self, data.x[i])
-        performance.add_result(data.y[i], pred)
-        if print_results
-          puts "Instance #{i}, Prediction: #{pred}, True label: #{data.y[i]}"
-        end
-      end
-      return performance
-    end
-
-    # Return the value of w squared for the hyperplane.
-    # -- returned as an array if there is not just one value.
-    def w_squared
-      if self.w_2.size == 1
-        self.w_2[0]
-      else
-        self.w_2.to_a
-      end
-    end
-
-    # Return an array of indices of the training instances used as 
-    # support vectors.
-    def support_vector_indices
-      result = []
-      unless sv_indices.nil?
-        sv_indices.size.times do |i|
-          result << sv_indices[i]
-        end
-      end
-
-      return result
-    end
-
-    # Return the SVM problem type for this model
-    def svm_type
-      self.param.svm_type
-    end
-
-    # Return the kernel type for this model
-    def kernel_type
-      self.param.kernel_type
-    end
-
-    # Return the value of the degree parameter
-    def degree
-      self.param.degree
-    end
-
-    # Return the value of the gamma parameter
-    def gamma
-      self.param.gamma
-    end
-
-    # Return the value of the cost parameter
-    def cost
-      self.param.cost
-    end
-
-    # Return the number of classes handled by this model.
-    def number_classes
-      self.nr_class
-    end
-
-    # Save model to given filename.
-    # Raises IOError on any error.
-    def save filename
-      begin
-        Svm.svm_save_model(filename, self)
-      rescue java.io.IOException
-        raise IOError.new "Error in saving SVM model to file"
-      end
-    end
-
-    # Load model from given filename.
-    # Raises IOError on any error.
-    def self.load filename
-      begin
-        Svm.svm_load_model(filename)
-      rescue java.io.IOException
-        raise IOError.new "Error in loading SVM model from file"
-      end
-    end
-
-    #
-    # Predict the class of given instance number in given problem.
-    #
-    def predict(problem, instance_number)
-      Svm.svm_predict(self, problem.x[instance_number])
-    end
-
-    #
-    # Return the values of given instance number of given problem against 
-    # each decision boundary.
-    # (This is the distance of the instance from each boundary.)
-    #
-    # Return value is an array if more than one decision boundary.
-    #
-    def predict_values(problem, instance_number)
-      dist = Array.new(number_classes*(number_classes-1)/2, 0).to_java(:double)
-      Svm.svm_predict_values(self, problem.x[instance_number], dist)
-      if dist.size == 1
-        return dist[0]
-      else
-        return dist.to_a
-      end
-    end
-  end
-end
-
+module SvmToolkit
+
+  # Holds information for a trained SVM model.
+  class Model
+
+    # Evaluate model on given data set (an instance of Problem), 
+    # returning the number of errors made.
+    # Optional parameters include:
+    # * :evaluator => Evaluator::OverallAccuracy, the name of the class to use for computing performance
+    # * :print_results => false, whether to print the result for each instance
+    def evaluate_dataset(data, params = {})
+      evaluator = params.fetch(:evaluator, Evaluator::OverallAccuracy)
+      print_results = params.fetch(:print_results, false)
+      performance = evaluator.new
+      data.l.times do |i|
+        pred = Svm.svm_predict(self, data.x[i])
+        performance.add_result(data.y[i], pred)
+        if print_results
+          puts "Instance #{i}, Prediction: #{pred}, True label: #{data.y[i]}"
+        end
+      end
+      return performance
+    end
+
+    # Return the value of w squared for the hyperplane.
+    # -- returned as an array if there is not just one value.
+    def w_squared
+      if self.w_2.size == 1
+        self.w_2[0]
+      else
+        self.w_2.to_a
+      end
+    end
+
+    # Return an array of indices of the training instances used as 
+    # support vectors.
+    def support_vector_indices
+      result = []
+      unless sv_indices.nil?
+        sv_indices.size.times do |i|
+          result << sv_indices[i]
+        end
+      end
+
+      return result
+    end
+
+    # Return the SVM problem type for this model
+    def svm_type
+      self.param.svm_type
+    end
+
+    # Return the kernel type for this model
+    def kernel_type
+      self.param.kernel_type
+    end
+
+    # Return the value of the degree parameter
+    def degree
+      self.param.degree
+    end
+
+    # Return the value of the gamma parameter
+    def gamma
+      self.param.gamma
+    end
+
+    # Return the value of the cost parameter
+    def cost
+      self.param.cost
+    end
+
+    # Return the number of classes handled by this model.
+    def number_classes
+      self.nr_class
+    end
+
+    # Save model to given filename.
+    # Raises IOError on any error.
+    def save filename
+      begin
+        Svm.svm_save_model(filename, self)
+      rescue java.io.IOException
+        raise IOError.new "Error in saving SVM model to file"
+      end
+    end
+
+    # Load model from given filename.
+    # Raises IOError on any error.
+    def self.load filename
+      begin
+        Svm.svm_load_model(filename)
+      rescue java.io.IOException
+        raise IOError.new "Error in loading SVM model from file"
+      end
+    end
+
+    #
+    # Predict the class of given instance number in given problem.
+    #
+    def predict(problem, instance_number)
+      Svm.svm_predict(self, problem.x[instance_number])
+    end
+
+    # Return the values of given instance number of given problem against 
+    # each decision boundary.
+    # (This is the distance of the instance from each boundary.)
+    #
+    # Return value is an array if more than one decision boundary.
+    #
+    def predict_values(problem, instance_number)
+      dist = Array.new(number_classes*(number_classes-1)/2, 0).to_java(:double)
+      Svm.svm_predict_values(self, problem.x[instance_number], dist)
+      if dist.size == 1
+        return dist[0]
+      else
+        return dist.to_a
+      end
+    end
+  end
+end
+

data/lib/svm_toolkit/node.rb

@@ -1,21 +1,17 @@
-module SvmToolkit
-
-  # Extends the Java Node class.
-  #
-  # Node is used to store the index/value pair for an individual 
-  # feature of an instance.
-  #
-  class Node
-
-    # Constructor:
-    # index:: Index of this node in feature set.
-    # value:: Value of this node in feature set.
-    def initialize(index, value)
-      super()
-      self.index = index
-      self.value = value
-    end
-  end
-
-end
-
+module SvmToolkit
+
+  # Used to store the index/value pair for an individual 
+  # feature of an instance.
+  class Node
+
+    # Constructor accepts index and value of this node 
+    # in feature set.
+    def initialize(index, value)
+      super()
+      self.index = index
+      self.value = value
+    end
+  end
+
+end
+