statsample 0.6.5 → 0.6.7

data/lib/statsample/regression/multiple/gslengine.rb

@@ -1,4 +1,4 @@
-if HAS_GSL
+if Statsample.has_gsl?
 module Statsample
 module Regression
 module Multiple

data/lib/statsample/regression/multiple/matrixengine.rb

@@ -101,7 +101,7 @@ class MatrixEngine < BaseEngine
   # Get R^2 for the regression
   # Equal to 
   # * 1-(|R| / |R_x|) or
-  # * Sum(b_i*r_yi)
+  # * Sum(b_i*r_yi) <- used
   def r2
     @n_predictors.times.inject(0) {|ac,i| ac+@coeffs_stan[i]* @matrix_y[i,0]} 
   end
@@ -113,13 +113,16 @@ class MatrixEngine < BaseEngine
     c=coeffs
     @y_mean - @fields.inject(0){|a,k| a + (c[k] * @x_mean[k])}
   end
+  # Hash of b or raw coefficients
   def coeffs
     assign_names(@coeffs)    
   end
+  # Hash of beta or standarized coefficients
+
   def standarized_coeffs
     assign_names(@coeffs_stan)
   end
-  
+  # Total sum of squares
   def sst
     @y_sd**2*(cases-1.0)
   end
@@ -134,9 +137,11 @@ class MatrixEngine < BaseEngine
   end
   
   # Tolerance for a given variable
-  # defined as (1-r2) of regression of other independent variables
+  # defined as (1-R^2) of regression of other independent variables
   # over the selected
-  # http://talkstats.com/showthread.php?t=5056
+  # Reference:
+  # 
+  # * http://talkstats.com/showthread.php?t=5056
   def tolerance(var)
     lr=Statsample::Regression::Multiple::MatrixEngine.new(@matrix_x, var)
     1-lr.r2
@@ -146,7 +151,8 @@ class MatrixEngine < BaseEngine
   # * Tolerance of the coeffients: Higher tolerances implies higher error
   # * Higher r2 implies lower error
   
-  # Reference: Cohen et al. (2003). Applied Multiple Reggression / Correlation Analysis for the Behavioral Sciences
+  # Reference:
+  # * Cohen et al. (2003). Applied Multiple Reggression / Correlation Analysis for the Behavioral Sciences
   #
   def coeffs_se
     out={}
@@ -188,7 +194,7 @@ class MatrixEngine < BaseEngine
     matrix.collect {|i| Math::sqrt(i) if i>0 }[0,0]
   end
   
-  def to_reportbuilder(generator)
+  def to_reportbuilder(generator) # :nodoc:
     anchor=generator.add_toc_entry(_("Multiple Regression: ")+@name)
     generator.add_html "<div class='multiple-regression'>#{@name}<a name='#{anchor}'></a>"
     c=coeffs

data/lib/statsample/regression/multiple.rb

@@ -1,9 +1,7 @@
 require 'statsample/regression/multiple/baseengine'
 module Statsample
   module Regression
-    # Module for Linear Multiple Regression Analysis.
-    # 
-    # You can call Statsample::Regression::Multiple.listwise,  Statsample::Regression::Multiple.pairwise or instance directly the engines.
+    # Module for OLS Multiple Regression Analysis.
     # 
     #  Use:.
     #
@@ -13,7 +11,7 @@ module Statsample
     #  c=1000.times.collect {rand}.to_scale
     #  ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
     #  ds['y']=ds.collect{|row| row['a']*5+row['b']*3+row['c']*2+rand()}
-    #  lr=Statsample::Regression::Multiple.listwise(ds,'y')
+    #  lr=Statsample::Regression.multiple(ds,'y')
     #  puts lr.summary
     #  Summary for regression of a,b,c over y
     #  *************************************************************
@@ -42,29 +40,6 @@ module Statsample
     #  -----------------------------------------------
     # 
     module Multiple
-      # Creates an object for listwise regression. 
-      # Alglib is faster, so is prefered over GSL
-      #   lr=Statsample::Regression::Multiple.listwise(ds,'y')
-      def self.listwise(ds,y_var)
-        if HAS_ALGIB
-          AlglibEngine.new(ds,y_var)
-        elsif HAS_GSL
-          GslEngine.new(ds,y_var)
-        else
-          ds2=ds.dup_only_valid
-          RubyEngine.new(ds2,y_var)
-        end
-      end
-      
-      # Creates an object for pairwise regression
-      # For now, always retrieves a RubyEngine
-      #    lr=Statsample::Regression::Multiple.listwise(ds,'y')
-      def self.pairwise(ds,y_var)
-        RubyEngine.new(ds,y_var)
-      end
-      def self.listwise_by_exp(ds,exp)
-        raise "Not implemented yet"
-      end
       # Obtain r2 for regressors
       def self.r2_from_matrices(rxx,rxy)
         matrix=(rxy.transpose*rxx.inverse*rxy)
@@ -76,21 +51,19 @@ module Statsample
           0.0
         end
         def initialize(matrix,y_var, opts=Hash.new)
-           matrix.extend Statsample::CovariateMatrix
-           @matrix=matrix
-           @fields=matrix.fields-y_var
-           @y_var=y_var
-           @q=@y_var.size
-           @matrix_cor=matrix.correlation
-           @matrix_cor_xx = @matrix_cor.submatrix(@fields)
-           @matrix_cor_yy = @matrix_cor.submatrix(y_var, y_var)
-           
-           @sxx = @matrix.submatrix(@fields)
-           @syy = @matrix.submatrix(y_var, y_var)
-           @sxy = @matrix.submatrix(@fields, y_var)
-           @syx = @sxy.t
-           
-           
+          matrix.extend Statsample::CovariateMatrix
+          @matrix=matrix
+          @fields=matrix.fields-y_var
+          @y_var=y_var
+          @q=@y_var.size
+          @matrix_cor=matrix.correlation
+          @matrix_cor_xx = @matrix_cor.submatrix(@fields)
+          @matrix_cor_yy = @matrix_cor.submatrix(y_var, y_var)
+          
+          @sxx = @matrix.submatrix(@fields)
+          @syy = @matrix.submatrix(y_var, y_var)
+          @sxy = @matrix.submatrix(@fields, y_var)
+          @syx = @sxy.t
         end
         
         def r2yx

data/lib/statsample/regression/simple.rb

@@ -1,81 +1,96 @@
 module Statsample
-    module Regression
-        # Class for calculation of linear regressions with form
-        # y = a+bx
-		# To create a SimpleRegression object:
-		# * <tt> SimpleRegression.new_from_vectors(vx,vy)</tt>
-		# * <tt> SimpleRegression.new_from_gsl(gsl) </tt>
-		#
-		class Simple
-			attr_accessor :a,:b,:cov00, :cov01, :covx1, :chisq, :status
-			private_class_method :new
-			def initialize(init_method, *argv)
-				self.send(init_method, *argv)
-			end
-			def y(val_x)
-				@a+@b*val_x
-			end
-			def x(val_y)
-				(val_y-@a) / @b.to_f
-			end
-            # Sum of square error
-			def sse
-				(0...@vx.size).inject(0) {|acum,i|
-                    acum+((@vy[i]-y(@vx[i]))**2)
-				}				
-			end                   
-			def standard_error
-				Math::sqrt(sse / (@vx.size-2).to_f)
-			end
-            # Sum of square regression
-            def ssr
-                vy_mean=@vy.mean
-				(0...@vx.size).inject(0) {|a,i|
-                    a+((y(@vx[i])-vy_mean)**2)
-				}				
-                
-            end
-            # Sum of square total
-            def sst
-                @vy.sum_of_squared_deviation
-            end
-            # Value of r
-            def r
-                @b * (@vx.sds / @vy.sds)
-            end
-            # Value of r^2
-            def r2
-                r**2
-            end
-            class << self
-				def new_from_gsl(ar)
-					new(:init_gsl, *ar)
-				end
-				def new_from_vectors(vx,vy)
-                    new(:init_vectors,vx,vy)
-				end
-			end
-            def init_vectors(vx,vy)
-                @vx,@vy=Statsample.only_valid(vx,vy)
-                x_m=@vx.mean
-                y_m=@vy.mean
-                num=den=0
-                (0...@vx.size).each {|i|
-                    num+=(@vx[i]-x_m)*(@vy[i]-y_m)
-                    den+=(@vx[i]-x_m)**2
-                }
-                @b=num.to_f/den
-                @a=y_m - @b*x_m
-            end
-			def init_gsl(a,b,cov00, cov01, covx1, chisq, status)
-				@a=a
-				@b=b
-				@cov00=cov00
-				@cov01=cov01
-				@covx1=covx1
-				@chisq=chisq
-				@status=status
-			end
-		end
+  module Regression
+    # Class for calculation of linear regressions with form
+    #   y = a+bx
+    # To create a SimpleRegression object:
+    # * <tt> SimpleRegression.new_from_dataset(ds,x,y)</tt>
+    # * <tt> SimpleRegression.new_from_vectors(vx,vy)</tt>
+    # * <tt> SimpleRegression.new_from_gsl(gsl) </tt>
+    #
+    class Simple
+      attr_accessor :a,:b,:cov00, :cov01, :covx1, :chisq, :status
+
+      def initialize(init_method, *argv)
+        self.send(init_method, *argv)
+      end
+      private_class_method :new
+      # Obtain y value given x value
+      # x=a+bx
+
+      def y(val_x)
+        @a+@b*val_x
+      end
+      # Obtain x value given y value
+      # x=(y-a)/b
+      def x(val_y)
+        (val_y-@a) / @b.to_f
+      end
+      # Sum of square error
+      def sse
+        (0...@vx.size).inject(0) {|acum,i| acum+((@vy[i]-y(@vx[i]))**2)
+        }
+      end
+      def standard_error
+        Math::sqrt(sse / (@vx.size-2).to_f)
+      end
+      # Sum of square regression
+      def ssr
+        vy_mean=@vy.mean
+        (0...@vx.size).inject(0) {|a,i|
+          a+((y(@vx[i])-vy_mean)**2)
+        }
+
+      end
+      # Sum of square total
+      def sst
+        @vy.sum_of_squared_deviation
+      end
+      # Value of r
+      def r
+        @b * (@vx.sds / @vy.sds)
+      end
+      # Value of r^2
+      def r2
+        r**2
+      end
+      class << self
+        # Create a regression object giving an array with following parameters:
+        # <tt>a,b,cov00, cov01, covx1, chisq, status</tt>
+        # Useful to obtain x and y values with a and b values.
+        def new_from_gsl(ar)
+          new(:init_gsl, *ar)
+        end
+        # Create a simple regression using two vectors
+        def new_from_vectors(vx,vy)
+          new(:init_vectors,vx,vy)
+        end
+        # Create a simple regression using a dataset and two vector names.
+        def new_from_dataset(ds,x,y)
+          new(:init_vectors,ds[x],ds[y])
+        end
+      end
+      def init_vectors(vx,vy)
+        @vx,@vy=Statsample.only_valid(vx,vy)
+        x_m=@vx.mean
+        y_m=@vy.mean
+        num=den=0
+        (0...@vx.size).each {|i|
+          num+=(@vx[i]-x_m)*(@vy[i]-y_m)
+          den+=(@vx[i]-x_m)**2
+        }
+        @b=num.to_f/den
+        @a=y_m - @b*x_m
+      end
+      def init_gsl(a,b,cov00, cov01, covx1, chisq, status)
+        @a=a
+        @b=b
+        @cov00=cov00
+        @cov01=cov01
+        @covx1=covx1
+        @chisq=chisq
+        @status=status
+      end
+      private :init_vectors, :init_gsl
     end
+  end
 end

data/lib/statsample/regression.rb

@@ -2,7 +2,6 @@ require 'statsample/regression/simple'
 require 'statsample/regression/multiple'
 
 require 'statsample/regression/multiple/matrixengine'
-require 'statsample/regression/multiple/alglibengine'
 require 'statsample/regression/multiple/rubyengine'
 require 'statsample/regression/multiple/gslengine'
 
@@ -11,7 +10,80 @@ require 'statsample/regression/binomial/logit'
 require 'statsample/regression/binomial/probit'
 
 module Statsample
-    # Module for regression procedures.
+    # = Module for regression procedures.
+    # Use the method on this class to generate
+    # analysis.
+    # If you need more control, you can
+    # create and control directly the objects who computes
+    # the regressions.
+    # 
+    # * Simple Regression :  Statsample::Regression::Simple
+    # * Multiple Regression: Statsample::Regression::Multiple
+    # * Logit Regression:    Statsample::Regression::Binomial::Logit
+    # * Probit Regression:    Statsample::Regression::Binomial::Probit
     module Regression
+      # Create a Statsample::Regression::Simple object, for simple regression
+      # * x: independent Vector
+      # * y: dependent Vector
+      # <b>Usage:</b>
+      #   x=100.times.collect {|i| rand(100)}.to_scale
+      #   y=100.times.collect {|i| 2+x[i]*2+rand()}.to_scale
+      #   sr=Statsample::Regression.simple(x,y)
+      #   sr.a
+      #   => 2.51763295177808
+      #   sr.b
+      #   => 1.99973746599856
+      #   sr.r
+      #   => 0.999987881153254
+
+      def self.simple(x,y)
+        Statsample::Regression::Simple.new_from_vectors(x,y)
+      end
+      # Create a Binomial::Logit object, for logit regression.
+      # * ds:: Dataset
+      # * y::  Name of dependent vector
+      # <b>Usage</b>
+      #   dataset=Statsample::CSV.read("data.csv")
+      #   lr=Statsample::Regression.logit(dataset,'y')
+      #   
+      def self.logit(ds,y_var)
+        Statsample::Regression::Binomial::Logit.new(ds,y_var)                
+      end
+      # Create a Binomial::Probit object, for probit regression
+      # * ds:: Dataset
+      # * y::  Name of dependent vector
+      # <b>Usage</b>
+      #   dataset=Statsample::CSV.read("data.csv")
+      #   lr=Statsample::Regression.probit(dataset,'y')
+      #   
+      
+      def self.probit(ds,y_var)
+        Statsample::Regression::Binomial::Probit.new(ds,y_var)                
+      end
+      
+      
+      # Creates one of the Statsample::Regression::Multiple object,
+      # for OLS multiple regression.
+      # Parameters:
+      # * ds: Dataset.
+      # * y: Name of dependent variable.
+      # * missing_data: Could be
+      #   * :listwise: delete cases with one or more empty data (default).
+      #   * :pairwise: uses correlation matrix. Use with caution.
+      # 
+      # <b>Usage:</b>
+      #   lr=Statsample::Regression::multiple(ds,'y')
+      def self.multiple(ds,y_var, missing_data=:listwise)
+        if missing_data==:pairwise
+           RubyEngine.new(ds,y_var)
+        else
+          if Statsample.has_gsl?
+            Statsample::Regression::Multiple::GslEngine.new(ds,y_var)
+          else
+            ds2=ds.dup_only_valid
+            Statsample::Regression::Multiple::RubyEngine.new(ds2,y_var)
+          end
+        end
+      end
     end
 end