fselector 1.0.1 → 1.1.0

data/lib/fselector/algo_base/base_CFS.rb

@@ -12,7 +12,11 @@ module FSelector
 #
 # ref: [Feature Selection for Discrete and Numeric Class Machine Learning](http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.5673)
 #
-  class BaseCFS < Base
+  class BaseCFS < Base    
+    # initialize from an existing data structure
+    def initialize(data=nil)
+      super(data)
+    end
     
     private
     
@@ -62,8 +66,8 @@ module FSelector
     # CFS replaces missing values with the mean for continuous features and
     # the most seen value for discrete features
     def handle_missing_values
-      abort "[#{__FILE__}@#{__LINE__}]: "+
-             "derived CFS algo must implement its own handle_missing_values()"
+      abort "[#{__FILE__}@#{__LINE__}]: \n"+
+            "  derived CFS algo must implement its own handle_missing_values()"
     end
     
     
@@ -126,18 +130,27 @@ module FSelector
 	
 	  # calc the feature-class correlation of two vectors
     def do_rcf(cv, fv)
-      abort "[#{__FILE__}@#{__LINE__}]: "+
-             "derived CFS algo must implement its own do_rcf()"
+      abort "[#{__FILE__}@#{__LINE__}]: \n"+
+            "  derived CFS algo must implement its own do_rcf()"
     end # do_rcf
     
     
     # calc the feature-class correlation of two vectors
     def do_rff(fv, sv)
-      abort "[#{__FILE__}@#{__LINE__}]: "+
-             "derived CFS algo must implement its own do_rff()"
+      abort "[#{__FILE__}@#{__LINE__}]: \n"+
+            "  derived CFS algo must implement its own do_rff()"
     end # do_rff
     
     
+    # override clear\_vars for BaseCFS
+    def clear_vars
+      super
+      
+      @rcf_best, @rff_best = nil, nil
+      @f2rcf, @fs2rff, @f2idx = nil, nil, nil
+    end # clear_vars
+    
+    
   end # class
   
   

data/lib/fselector/algo_base/base_Relief.rb

@@ -13,7 +13,7 @@ module FSelector
   class BaseRelief < Base
     # include ReplaceMissingValue module
     include ReplaceMissingValues
-        
+    
     #
     # intialize from an existing data structure
     #
@@ -31,8 +31,8 @@ module FSelector
     # calculate contribution of each feature (f) across all classes
     def calc_contribution(f)
       if not get_classes.size == 2
-        abort "[#{__FILE__}@#{__LINE__}]: "+
-        "Relief applicable only to two-class problems without missing data"
+        abort "[#{__FILE__}@#{__LINE__}]: \n"+
+              "  Relief applicable only to two-class problems without missing data"
       end
       
       ## use all samples if @m not provided
@@ -105,8 +105,8 @@ module FSelector
     
     # difference beween the feature (f) of two samples
     def diff_feature(f, s1, s2)
-      abort "[#{__FILE__}@#{__LINE__}]: "+
-              "derived Relief algo must implement its own diff_feature()"
+      abort "[#{__FILE__}@#{__LINE__}]: \n"+
+            "  derived Relief algo must implement its own diff_feature()"
     end # diff_feature
     
     

data/lib/fselector/algo_base/base_ReliefF.rb

@@ -10,7 +10,7 @@ module FSelector
 #
 # ref: [Estimating Attributes: Analysis and Extensions of RELIEF](http://www.springerlink.com/content/fp23jh2h0426ww45/)
 #
-  class BaseReliefF < Base    
+  class BaseReliefF < Base      
     #
     # intialize from an existing data structure
     #
@@ -94,8 +94,8 @@ module FSelector
     
     # difference beween the feature (f) of two samples
     def diff_feature(f, s1, s2, k1, k2)
-      abort "[#{__FILE__}@#{__LINE__}]: "+
-              "derived ReliefF algo must implement its own diff_feature()"
+      abort "[#{__FILE__}@#{__LINE__}]: \n"+
+            "  derived ReliefF algo must implement its own diff_feature()"
     end # diff_feature
     
     
@@ -150,6 +150,14 @@ module FSelector
     end
     
     
+    # override clear\_vars for BaseReliefF
+    def clear_vars
+      super
+      
+      @f2mvp = nil
+    end # clear_vars
+    
+    
   end # class
   
   

data/lib/fselector/algo_base/base_discrete.rb

@@ -172,6 +172,14 @@ module FSelector
     end # calc_D
     
     
+    # override clear\_vars for BaseDiscrete
+    def clear_vars
+      super
+      
+      @A, @B, @C, @D = nil, nil, nil, nil
+    end # clear_vars
+    
+    
   end # class
 
 

data/lib/fselector/algo_continuous/BSS_WSS.rb

@@ -18,7 +18,9 @@ module FSelector
 # ref: [Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data](http://amstat.tandfonline.com/doi/abs/10.1198/016214502753479248)
 #
   class BetweenWithinClassesSumOfSquare < BaseContinuous
-        
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+    
     private    
     
     # calculate contribution of each feature (f) across all classes

data/lib/fselector/algo_continuous/CFS_c.rb

@@ -13,8 +13,10 @@ module FSelector
     include Normalizer
     include Discretizer
     
-    private
+    # this algo outputs a subset of feature
+    @algo_type = :feature_subset_selection
     
+    private
     
     # replace missing values with mean feature value
     def handle_missing_values

data/lib/fselector/algo_continuous/FTest.rb

@@ -23,6 +23,8 @@ module FSelector
 # ref: [Wikipedia](http://en.wikipedia.org/wiki/F-test#Formula_and_calculation) and [Minimum redundancy feature selection from microarray gene expression data](http://penglab.janelia.org/papersall/docpdf/2004_JBCB_feasel-04-06-15.pdf)
 #
   class FTest < BaseContinuous
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
         
     private    
     

data/lib/fselector/algo_continuous/PMetric.rb

@@ -14,14 +14,16 @@ module FSelector
 # ref: [Filter versus wrapper gene selection approaches in DNA microarray domains](http://www.sciencedirect.com/science/article/pii/S0933365704000193)
 #
   class PMetric < BaseContinuous
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private    
     
     # calculate contribution of each feature (f) across all classes
     def calc_contribution(f)
       if not get_classes.size == 2
-        abort "[#{__FILE__}@#{__LINE__}]: "+
-              "suitable only for two-class problem with continuous feature"
+        abort "[#{__FILE__}@#{__LINE__}]: \n"+
+              "  suitable only for two-class problem with continuous feature"
       end
       
       # collect data for class 1 and 2, respectively   

data/lib/fselector/algo_continuous/ReliefF_c.rb

@@ -14,6 +14,9 @@ module FSelector
     include Normalizer
     include Discretizer
     
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+    
     private    
     
     # difference beween the feature (f) of two samples
@@ -57,6 +60,14 @@ module FSelector
     end # get_normalization_unit
     
     
+    # override clear\_vars for ReliefF_c
+    def clear_vars
+      super
+      
+      @f2nu = nil
+    end # clear_vars
+    
+    
   end # class
   
   

data/lib/fselector/algo_continuous/Relief_c.rb

@@ -13,15 +13,18 @@ module FSelector
     # include normalizer and discretizer
     include Normalizer
     include Discretizer
-        
+    
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+       
     private
     
     # difference beween the feature (f) of two samples
     # specialized version for continuous feature
     def diff_feature(f, s1, s2)
       if not s1.has_key?(f) or not s2.has_key?(f)
-        abort "[#{__FILE__}@#{__LINE__}]: "+
-              "Relief does not allow missing values"
+        abort "[#{__FILE__}@#{__LINE__}]: \n"+
+              "  Relief does not allow missing values"
       end
       
       nu = get_normalization_unit(f)
@@ -45,6 +48,14 @@ module FSelector
     end # get_normalization_unit
     
     
+    # override clear\_vars for Relief_c
+    def clear_vars
+      super
+      
+      @f2nu = nil
+    end # clear_vars
+    
+    
   end # class
   
   

data/lib/fselector/algo_continuous/TScore.rb

@@ -14,14 +14,16 @@ module FSelector
 # ref: [Filter versus wrapper gene selection approaches](http://www.sciencedirect.com/science/article/pii/S0933365704000193)
 #
   class TScore < BaseContinuous
-        
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+     
     private    
     
     # calculate contribution of each feature (f) across all classes
     def calc_contribution(f)
       if not get_classes.size == 2
-        abort "[#{__FILE__}@#{__LINE__}]: "+
-              "suitable only for two-class problem with continuous feature"
+        abort "[#{__FILE__}@#{__LINE__}]: \n"+
+              "  suitable only for two-class problem with continuous feature"
       end
       
       # collect data for class 1 and 2, respectively   

data/lib/fselector/algo_continuous/WilcoxonRankSum.rb

@@ -14,14 +14,16 @@ module FSelector
 # ref: [An Efficient and Robust Statistical Modeling Approach to Discover Differentially Expressed Genes Using Genomic Expression Profiles](http://genome.cshlp.org/content/11/7/1227)
 #
   class WilcoxonRankSum < BaseContinuous
-        
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+    
     private    
     
     # calculate contribution of each feature (f) across all classes
     def calc_contribution(f)
       if not get_classes.size == 2
-        abort "[#{__FILE__}@#{__LINE__}]: "+
-              "suitable only for two-class problem with continuous feature"
+        abort "[#{__FILE__}@#{__LINE__}]: \n"+
+              "  suitable only for two-class problem with continuous feature"
       end
       
       # collect data for class 1 and 2, respectively     

data/lib/fselector/algo_discrete/Accuracy.rb

@@ -10,6 +10,8 @@ module FSelector
 #            tp+fn+tn+fp     A+B+C+D
 #
   class Accuracy < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/AccuracyBalanced.rb

@@ -10,6 +10,8 @@ module FSelector
 # ref: [An extensive empirical study of feature selection metrics for text classification](http://dl.acm.org/citation.cfm?id=944974)
 #
   class AccuracyBalanced < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/BiNormalSeparation.rb

@@ -13,7 +13,9 @@ module FSelector
 # ref: [An extensive empirical study of feature selection metrics for text classification](http://dl.acm.org/citation.cfm?id=944974)
 #
   class BiNormalSeparation < BaseDiscrete
-        
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+     
     private
     
     # calculate contribution of each feature (f) for each class (k)

data/lib/fselector/algo_discrete/CFS_d.rb

@@ -12,6 +12,9 @@ module FSelector
     # include Entropy module
     include Entropy
     
+    # this algo outputs a subset of feature
+    @algo_type = :feature_subset_selection
+    
     private
     
     # replace missing values with most seen feature value

data/lib/fselector/algo_discrete/ChiSquaredTest.rb

@@ -19,6 +19,9 @@ module FSelector
 # ref: [Wikipedia](http://en.wikipedia.org/wiki/Chi-squared_test) and [A Comparative Study on Feature Selection Methods for Drug Discovery](http://pubs.acs.org/doi/abs/10.1021/ci049875d)
 #
   class ChiSquaredTest < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+    
     #
     # initialize from an existing data structure
     #

data/lib/fselector/algo_discrete/CorrelationCoefficient.rb

@@ -13,6 +13,8 @@ module FSelector
 # ref: [Optimally Combining Positive and Negative Features for Text Categorization](http://www.site.uottawa.ca/~nat/Workshop2003/zheng.pdf)
 #
   class CorrelationCoefficient < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
         

data/lib/fselector/algo_discrete/DocumentFrequency.rb

@@ -10,6 +10,8 @@ module FSelector
 # ref: [An extensive empirical study of feature selection metrics for text classification](http://dl.acm.org/citation.cfm?id=944974)
 #
   class DocumentFrequency < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/F1Measure.rb

@@ -16,6 +16,8 @@ module FSelector
 # ref: [An extensive empirical study of feature selection metrics for text classification](http://dl.acm.org/citation.cfm?id=944974)
 #
   class F1Measure < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/FastCorrelationBasedFilter.rb

@@ -12,6 +12,9 @@ module FSelector
     # include Entropy module
     include Entropy
     
+    # this algo outputs a subset of feature
+    @algo_type = :feature_subset_selection
+    
     #
     # initialize from an existing data structure
     #
@@ -116,7 +119,15 @@ module FSelector
       end
       
       fq
-    end
+    end # get_next_element
+    
+    
+    # override clear\_vars for FastCorrelationBasedFilter
+    def clear_vars
+      super
+      
+      @f2hf = nil
+    end # clear_vars
     
      
   end # class 

data/lib/fselector/algo_discrete/FishersExactTest.rb

@@ -16,7 +16,9 @@ module FSelector
 # ref: [Wikipedia](http://en.wikipedia.org/wiki/Fisher\'s_exact_test)
 #
   class FishersExactTest < BaseDiscrete
-        
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+       
     private
         
     # calculate contribution of each feature (f) for each class (k)

data/lib/fselector/algo_discrete/GMean.rb

@@ -12,6 +12,8 @@ module FSelector
 #                (TP+FN) * (TN+FP)          (A+C) * (B+D)
 #
   class GMean < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/GSSCoefficient.rb

@@ -16,6 +16,8 @@ module FSelector
 # ref: [A Comparative Study on Feature Selection Methods for Drug Discovery](http://pubs.acs.org/doi/abs/10.1021/ci049875d)
 #
   class GSSCoefficient < BaseDiscrete
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
     
     private
     

data/lib/fselector/algo_discrete/GiniIndex.rb

@@ -13,7 +13,9 @@ module FSelector
 # ref: [Advancing Feaure Selection Research - ASU Feature Selection Repository](http://featureselection.asu.edu/featureselection_techreport.pdf)
 #
   class GiniIndex < BaseDiscrete
-          
+    # this algo outputs weight for each feature
+    @algo_type = :feature_weighting
+    
     private
     
     # calculate contribution of each feature (f) across all classes