fselector 0.4.1 → 0.4.2

data/README.md

@@ -8,8 +8,8 @@ FSelector: a Ruby gem for feature selection and ranking
 **Email**: [need47@gmail.com](mailto:need47@gmail.com)  
 **Copyright**: 2012  
 **License**: MIT License  
-**Latest Version**: 0.4.1  
-**Release Date**: April 10 2012
+**Latest Version**: 0.4.2  
+**Release Date**: April 11 2012
 
 Synopsis
 --------
@@ -41,7 +41,7 @@ Feature List
 
 **2. available feature selection/ranking algorithms**
     
-    algorithm                       alias       feature type
+    algorithm                       alias       feature_type
     --------------------------------------------------------
     Accuracy                        Acc         discrete
     AccuracyBalanced                Acc2        discrete
@@ -77,6 +77,10 @@ Feature List
     Relief_c                        Relief_c    continuous
     ReliefF_c                       ReliefF_c   continuous
     TScore                          TS          continuous
+    
+  **feature selection interace:**   
+    - for the algorithms of CFS\_d, FCBF and CFS\_c, use select\_feature!  
+    - for other algorithms, use either select\_feature\_by\_rank! or select\_feature\_by\_score!
 
 **3. feature selection approaches**
 
@@ -98,7 +102,7 @@ Feature List
     
 **5. availabe algorithms for replacing missing feature values**
     
-    algorithm          note                                  feature type                     
+    algorithm          note                                  feature_type                     
     --------------------------------------------------------------------------------------
     fixed_value        replace with a fixed value            discrete, continuous
     mean_value         replace with mean feature value       continuous

data/lib/fselector.rb

@@ -3,7 +3,7 @@
 #
 module FSelector
   # module version
-  VERSION = '0.4.1'
+  VERSION = '0.4.2'
 end
 
 ROOT = File.expand_path(File.dirname(__FILE__))

data/lib/fselector/algo_base/base.rb

@@ -3,7 +3,7 @@
 #
 module FSelector
   #
-  # base ranking algorithm
+  # base class
   #
   class Base
     # include FileIO
@@ -76,13 +76,13 @@ module FSelector
     end
     
     
-    # get classes
+    # get (uniq) classes labels as an array
     def get_classes
       @classes ||= @data.keys
     end
     
     
-    # get class labels
+    # get class labels for all samples as an array
     def get_class_labels
       if not @cv
         @cv = []
@@ -107,7 +107,7 @@ module FSelector
     end
 
     
-    # get unique features
+    # get (unique) features as an array
     def get_features
       @features ||= @data.map { |x| x[1].map { |y| y.keys } }.flatten.uniq
     end
@@ -122,7 +122,7 @@ module FSelector
     #   if mv==nil, include otherwise
     # @param [Symbol] ck class of interest.
     #   return feature values for all classes, otherwise return feature
-    # values for the specific class (ck)
+    #   values for the specific class (ck)
     #
     def get_feature_values(f, mv=nil, ck=nil)
       @fvs ||= {}
@@ -180,7 +180,7 @@ module FSelector
     end
     
     
-    # get non-data information
+    # get non-data information for a given key
     def get_opt(key)
       @opts.has_key?(key) ? @opts[key] : nil
     end
@@ -251,7 +251,9 @@ module FSelector
     # reconstruct data with selected features
     #
     # @return [Hash] data after feature selection
-    # @note derived class must implement its own get_subset()
+    # @note derived class must implement its own get_subset(), 
+    #   and data structure will be altered. For now, only the algorithms of 
+    #   CFS_c, CFS_d and FCBF implement such function
     #
     def select_feature!
       subset = get_feature_subset
@@ -337,7 +339,8 @@ module FSelector
     
     private
     
-    # clear variables when data structure is altered
+    # clear variables when data structure is altered, 
+    # except @opts (non-data information)
     def clear_vars
       @classes, @features, @fvs = nil, nil, nil
       @scores, @ranks, @sz = nil, nil, nil

data/lib/fselector/algo_base/base_CFS.rb

@@ -3,19 +3,16 @@
 #
 module FSelector
 #
-# base class for Correlation-based Feature Selection (CFS) algorithm, see specialized
-# versions for discrete feature (CFS\_d) and continuous feature (CFS\_c), respectively
+# base class for Correlation-based Feature Selection (CFS) algorithm, see specialized 
+# versions for discrete feature (CFS\_d) and continuous feature (CFS\_c), respectively.
 #
-# @note for simplicity, we use *sequential forward search* for optimal feature subset,
-# the original CFS that uses *best first search* only produces slightly better results
-# but demands much more computational resources
+# @note for simplicity, we use *sequential forward search* for optimal feature subset, 
+#   the original CFS that uses *best first search* only produces slightly better results 
+#   but demands much more computational resources
 #
 # ref: [Feature Selection for Discrete and Numeric Class Machine Learning](http://www.cs.waikato.ac.nz/ml/publications/1999/99MH-Feature-Select.pdf)
 #
   class BaseCFS < Base
-    # undefine superclass methods
-    undef :select_feature_by_score!
-    undef :select_feature_by_rank!
     
     private
     

data/lib/fselector/algo_base/base_Relief.rb

@@ -10,7 +10,7 @@ module FSelector
 #
 # ref: [The Feature Selection Problem: Traditional Methods and a New Algorithm](http://www.aaai.org/Papers/AAAI/1992/AAAI92-020.pdf)
 #
-  class BaseRelief < Base
+  class BaseRelief < Base    
     #
     # new()
     #

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    
     #
     # new()
     #

data/lib/fselector/algo_base/base_continuous.rb

@@ -3,7 +3,7 @@
 #
 module FSelector
 #
-# base ranking algorithm for handling continous feature
+# base algorithm for handling continous feature
 #
   class BaseContinuous < Base
     # include normalizer

data/lib/fselector/algo_base/base_discrete.rb

@@ -3,7 +3,7 @@
 #
 module FSelector
 #
-#  base ranking alogrithm for handling discrete feature
+#  base alogrithm for handling discrete feature
 #
 #     2 x 2 contingency table
 #     

data/lib/fselector/algo_continuous/CFS_c.rb

@@ -3,7 +3,8 @@
 #
 module FSelector
 #
-# Correlation-based Feature Selection (CFS) algorithm for continuous feature (CFS_c)
+# Correlation-based Feature Selection (CFS) algorithm for continuous feature (CFS\_c). 
+# For CFS\_c, use **select\_feature!** for feature selection
 #
 # ref: [Feature Selection for Discrete and Numeric Class Machine Learning](http://www.cs.waikato.ac.nz/ml/publications/1999/99MH-Feature-Select.pdf)
 #

data/lib/fselector/algo_discrete/CFS_d.rb

@@ -3,7 +3,8 @@
 #
 module FSelector
 #
-# Correlation-based Feature Selection (CFS) algorithm for discrete feature (CFS_d)
+# Correlation-based Feature Selection (CFS) algorithm for discrete feature (CFS\_d). 
+# For CFS\_d, use **select\_feature!** for feature selection
 #
 # ref: [Feature Selection for Discrete and Numeric Class Machine Learning](http://www.cs.waikato.ac.nz/ml/publications/1999/99MH-Feature-Select.pdf)
 #

data/lib/fselector/algo_discrete/FastCorrelationBasedFilter.rb

@@ -3,12 +3,13 @@
 #
 module FSelector
 #
-# Fast Correlation-Based Filter for feature with discrete data (FCBF)
+# Fast Correlation-Based Filter for feature with discrete data (FCBF), 
+# for FCBF, use **select\_feature!** for feature selection
 #
 # ref: [Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution](http://www.hpl.hp.com/conferences/icml2003/papers/144.pdf)
 #
   class FastCorrelationBasedFilter < BaseDiscrete
-    # include Entropy
+    # include Entropy module
     include Entropy
     
     #

data/lib/fselector/algo_discrete/InformationGain.rb

@@ -14,7 +14,7 @@ module FSelector
 # ref: [Using Information Gain to Analyze and Fine Tune the Performance of Supply Chain Trading Agents](http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.7895)
 #
   class InformationGain < BaseDiscrete
-    # include entropy module
+    # include Entropy module
     include Entropy
 
     private

data/lib/fselector/algo_discrete/Power.rb

@@ -15,9 +15,10 @@ module FSelector
 #
   class Power < BaseDiscrete    
     #
-    # new()
+    # initialize from existing data structure
     # 
     # @param [Integer] k power
+    # @param [Hash] data existing data structure
     #
     def initialize(k=5, data=nil)
       super(data)

data/lib/fselector/chisq_calc.rb

@@ -9,13 +9,11 @@
 # original C code is in the public domain.
 #
 # chisq2pval(chisq, df) -- calculate p-value from given 
-#                   chi-square value (chisq) and degree of freedom (df)
+#                   chi-square value (chisq) and degree of freedom (df)  
 # pval2chisq(pval, df) -- chi-square value from given
 #                   p-value (pvalue) and degree of freedom (df)
 #
 module ChiSquareCalculator
-  #
-  # module constants
   BIGX = 20.0 # max value to represent exp(x)
   LOG_SQRT_PI = 0.5723649429247000870717135 # log(sqrt(pi))
   I_SQRT_PI = 0.5641895835477562869480795 # 1 / sqrt(pi)
@@ -23,7 +21,6 @@ module ChiSquareCalculator
   CHI_EPSILON = 0.000001 # Accuracy of critchi approximation
   CHI_MAX = 99999.0 # Maximum chi-square value
   
-  #
   #
   # POCHISQ  --  probability of chi-square value
   #
@@ -37,6 +34,9 @@ module ChiSquareCalculator
   #
   #   ACM TOMS June 1985, page 185
   #
+  # @param [Float] x chi-square value
+  # @param [Integer] df degree of freedom
+  # @return [Float] p-value
   def pochisq(x, df)
     a, y, s = nil, nil, nil
     e, c, z = nil, nil, nil
@@ -99,6 +99,9 @@ module ChiSquareCalculator
   # search for a value within CHI_EPSILON,
   # relying on the monotonicity of pochisq()
   #
+  # @param [Float] p p-value
+  # @param [Integer] df degree of freedom
+  # @return [Float] chi-square value
   def critchi(p, df)
     minchisq = 0.0
     maxchisq = CHI_MAX

data/lib/fselector/entropy.rb

@@ -7,6 +7,8 @@ module Entropy
   #
   #     H(X) = -1 * sigma_i (P(x_i) logP(x_i))
   #
+  # @param [Array] arrX array of interest
+  # @return [Float] H(X)
    def get_marginal_entropy(arrX)
     h = 0.0
     n = arrX.size.to_f
@@ -27,6 +29,10 @@ module Entropy
   #     
   #     where H(X|y_j) = -1 * sigma_i (P(x_i|y_j) logP(x_i|y_j))
   #
+  # @param [Array] arrX the first array
+  # @param [Array] arrY the second array
+  # @return [Float] H(X|Y)
+  # @note arrX and arrY must be of same length
    def get_conditional_entropy(arrX, arrY)
     abort "[#{__FILE__}@#{__LINE__}]: "+
           "array must be of same length" if not arrX.size == arrY.size
@@ -60,6 +66,10 @@ module Entropy
   #     
   #     i.e. H(X,Y) == H(Y,X)
   #
+  # @param [Array] arrX the first array
+  # @param [Array] arrY the second array
+  # @return [Float] H(X,Y)
+  # @note arrX and arrY must be of same length
    def get_joint_entropy(arrX, arrY)
     abort "[#{__FILE__}@#{__LINE__}]: "+
         "array must be of same length" if not arrX.size == arrY.size

data/lib/fselector/util.rb

@@ -35,6 +35,10 @@ class Array
   
   
   # scale to [min, max]
+  #
+  # @param [Float] min lower bound
+  # @param [Float] max upper bound
+  # @return [Array<Float>] scaled numbers
   def to_scale(min=0.0, max=1.0)
     if (min >= max)
       abort "[#{__FILE__}@#{__LINE__}]: "+
@@ -54,9 +58,11 @@ class Array
   end
   
   
-  # convert to zscore
+  # convert to z-score
   #
   # ref: [Wikipedia](http://en.wikipedia.org/wiki/Standard_score)
+  #
+  # @return [Array<Float>] converted z-scores
   def to_zscore
     ave = self.ave
     sd = self.sd
@@ -72,11 +78,14 @@ class Array
   end
   
   
-  # pearson's correlation coefficient
+  # pearson's correlation coefficient, 
   # two vectors must be of the same length
+  #
+  # @param [Array] v the second array
+  # @return [Float] pearson's r
   def pearson_r(v)
     sm, vm = self.ave, v.ave
-    a, b, c = 00, 0.0, 0.0
+    a, b, c = 0.0, 0.0, 0.0
     
     self.each_with_index do |s, i|
       a += (s-sm)*(v[i]-vm)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fselector
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-10 00:00:00.000000000 Z
+date: 2012-04-11 00:00:00.000000000 Z
 dependencies: []
 description: FSelector is a Ruby gem that aims to integrate various feature selection/ranking
   algorithms and related functions into one single package. Welcome to contact me