statsample 0.3.0 → 0.3.1

data/lib/statsample/regression/simple.rb

@@ -0,0 +1,81 @@
+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
+    end
+end

data/test/test_regression.rb

@@ -4,7 +4,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
 	def initialize(*args)
 		@x=[13,20,10,33,15].to_vector(:scale)
 		@y=[23,18,35,10,27	].to_vector(:scale)
-		@reg=Statsample::Regression::SimpleRegression.new_from_vectors(@x,@y)
+		@reg=Statsample::Regression::Simple.new_from_vectors(@x,@y)
 		super
 	end
 	def test_parameters
@@ -18,7 +18,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
         @c=[11,22,30,40,50,65,78,79,99,100,nil,3,7,nil,7].to_vector(:scale)
         @y=[3,4,5,6,7,8,9,10,20,30,30,40,nil,50,nil].to_vector(:scale)
         ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
-        lr=Statsample::Regression::MultipleRegressionPairwise.new(ds,'y')
+        lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y')
         assert_in_delta(2407.436,lr.sst,0.001)
         assert_in_delta(0.752,lr.r,0.001)
         assert_in_delta(0.565,lr.r2,0.001)
@@ -34,7 +34,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
         @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:scale)
         @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:scale)
         ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
-        lr=Statsample::Regression::MultipleRegressionAlglib.new(ds,'y')
+        lr=Statsample::Regression::Multiple::AlglibEngine.new(ds,'y')
         model_test(lr)
         predicted=[1.7857, 6.0989, 3.2433, 7.2908, 4.9667, 10.3428, 8.8158, 10.4717, 23.6639, 25.3198]
         c_predicted=lr.predicted
@@ -47,7 +47,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
             assert_in_delta(residuals[i],c_residuals[i],0.001)
         }
 	else
-		puts "Regression::MultipleRegressionAlglib not tested (no Alglib)"
+		puts "Regression::Multiple::AlglibEngine not tested (no Alglib)"
 	end
     end
     def model_test(lr)
@@ -92,7 +92,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
         @c=[nil,11,22,30,40,50,65,78,79,99,100].to_vector(:scale)
         @y=[nil,3,4,5,6,7,8,9,10,20,30].to_vector(:scale)
         ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
-        lr=Statsample::Regression::MultipleRegressionPairwise.new(ds,'y')
+        lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y')
         model_test(lr)
         predicted=[nil,1.7857, 6.0989, 3.2433, 7.2908, 4.9667, 10.3428, 8.8158, 10.4717, 23.6639, 25.3198]
         c_predicted = lr.predicted

data/test/test_statistics.rb

@@ -1,6 +1,5 @@
 require File.dirname(__FILE__)+'/../lib/statsample'
 require 'test/unit'
-
 class StatsampleStatisicsTestCase < Test::Unit::TestCase
 
 	def initialize(*args)
@@ -131,7 +130,7 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
     def test_simple_linear_regression
 		a=[1,2,3,4,5,6].to_vector(:scale)
 		b=[6,2,4,10,12,8].to_vector(:scale)
-		reg = Statsample::Regression::SimpleRegression.new_from_vectors(a,b)
+		reg = Statsample::Regression::Simple.new_from_vectors(a,b)
         assert_in_delta((reg.ssr+reg.sse).to_f,reg.sst,0.001)
         assert_in_delta(Statsample::Bivariate.pearson(a,b),reg.r,0.001)
 		assert_in_delta(2.4,reg.a,0.01)
@@ -139,14 +138,5 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
 		assert_in_delta(0.657,reg.r,0.001)
 		assert_in_delta(0.432,reg.r2,0.001)
         
-	end
-    def a_test_multiple_regression
-        x1=[1,2,3,4,5,6].to_vector(:scale)
-        x2=[3,5,8,9,10,20].to_vector(:scale)
-        x3=[100,90,50,30,50,10].to_vector(:scale)
-		y=[6,2,4,10,12,8].to_vector(:scale)
-        reg=Statsample::Regression::MultipleRegression.new_from_vectors([x1,x2,x3],y)
-        # p reg
-    end
-    
+	end    
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: statsample
 version: !ruby/object:Gem::Version 
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors: 
 - Claudio Bustos
@@ -61,15 +61,20 @@ files:
 - bin/statsample
 - demo/benchmark.rb
 - demo/chi-square.rb
+- demo/crosstab.rb
 - demo/dice.rb
 - demo/distribution_t.rb
 - demo/graph.rb
 - demo/item_analysis.rb
 - demo/mean.rb
+- demo/nunnally_6.rb
 - demo/proportion.rb
+- demo/regression.rb
 - demo/sample_test.csv
 - demo/strata_proportion.rb
 - demo/stratum.rb
+- demo/t-student.rb
+- lib/spss.rb
 - lib/statsample.rb
 - lib/statsample/anova.rb
 - lib/statsample/bivariate.rb
@@ -81,19 +86,22 @@ files:
 - lib/statsample/dominanceanalysis.rb
 - lib/statsample/dominanceanalysis/bootstrap.rb
 - lib/statsample/graph/gdchart.rb
-- lib/statsample/graph/svggraph.rb
 - lib/statsample/graph/svgboxplot.rb
+- lib/statsample/graph/svggraph.rb
 - lib/statsample/graph/svghistogram.rb
 - lib/statsample/graph/svgscatterplot.rb
 - lib/statsample/htmlreport.rb
 - lib/statsample/multiset.rb
 - lib/statsample/regression.rb
+- lib/statsample/regression/multiple.rb
+- lib/statsample/regression/multiple/alglibengine.rb
+- lib/statsample/regression/multiple/rubyengine.rb
+- lib/statsample/regression/simple.rb
 - lib/statsample/reliability.rb
 - lib/statsample/resample.rb
 - lib/statsample/srs.rb
 - lib/statsample/test.rb
 - lib/statsample/vector.rb
-- lib/spss.rb
 - test/_test_chart.rb
 - test/test_anova.rb
 - test/test_codification.rb
@@ -106,10 +114,13 @@ files:
 - test/test_regression.rb
 - test/test_reliability.rb
 - test/test_resample.rb
+- test/test_srs.rb
 - test/test_statistics.rb
 - test/test_stratified.rb
 - test/test_svg_graph.rb
 - test/test_vector.rb
+- test/test_xls.rb
+- test/test_xls.xls
 has_rdoc: true
 homepage: http://rubyforge.org/projects/ruby-statsample/
 licenses: []