statsample 0.6.1 → 0.6.2

data/test/test_bivariate.rb

@@ -24,6 +24,24 @@ class StatsampleBivariateTestCase < Test::Unit::TestCase
         assert_in_delta(tcm_obs[i,j], tcm_exp[i,k], 0.00001)
       end
     end
+  end
+  def test_polychoric
+    # Should be the same results as Tetrachoric for 2x2 matrix
+    
+    matrix=Matrix[[rand(100)+10,rand(100)+10],[rand(100)+10,rand(100)+10]]
+    tetra = Statsample::Bivariate::Tetrachoric.new_with_matrix(matrix)
+    poly  = Statsample::Bivariate::Polychoric.new(matrix)
+    assert_in_delta(tetra.r,poly.r,0.0001)
+    
+    # Example for http://www.john-uebersax.com/stat/tetra.htm#exampl
+    
+    matrix=Matrix[[58,52,1],[26,58,3],[8,12,9]]
+    poly=Statsample::Bivariate::Polychoric.new(matrix)
+    assert_in_delta(0.4199, poly.r, 0.0001)
+    assert_in_delta(-0.2397, poly.threshold_y[0],0.001)
+    assert_in_delta(-0.0276, poly.threshold_x[0],0.001)
+    
+
   end
   def test_tetrachoric
     a,b,c,d=0,0,0,0
@@ -51,8 +69,9 @@ class StatsampleBivariateTestCase < Test::Unit::TestCase
     tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
     assert_in_delta(-0.53980,tc.r,0.0001)
     assert_in_delta(0.09940,tc.se,0.0001)
-    assert_in_delta(0.31864,tc.threshold_x,0.0001)
-    assert_in_delta(-0.15731,tc.threshold_y,0.0001)
+    assert_in_delta(-0.15731,tc.threshold_x, 0.0001)
+    assert_in_delta(0.31864,tc.threshold_y, 0.0001)
+
     x=%w{a a a a b b b a b b a a b b}.to_vector
     y=%w{0 0 1 1 0 0 1 1 1 1 0 0 1 1}.to_vector
     # crosstab

data/test/test_distribution.rb

@@ -8,51 +8,69 @@ rescue LoadError
     NOT_GSL=true
 end
 class DistributionTestCase < Test::Unit::TestCase
-    def test_chi
-        if !NOT_GSL
-        [2,3,4,5].each{|k|
-            chis=rand()*10
-            area=Distribution::ChiSquare.cdf(chis, k)
-            assert_in_delta(area, GSL::Cdf.chisq_P(chis,k),0.0001)
-            assert_in_delta(chis, Distribution::ChiSquare.p_value(area,k),0.0001,"Error on prob #{area} and k #{k}")
-        }
-        end
+  def test_chi
+    if !NOT_GSL
+    [2,3,4,5].each{|k|
+        chis=rand()*10
+        area=Distribution::ChiSquare.cdf(chis, k)
+        assert_in_delta(area, GSL::Cdf.chisq_P(chis,k),0.0001)
+        assert_in_delta(chis, Distribution::ChiSquare.p_value(area,k),0.0001,"Error on prob #{area} and k #{k}")
+    }
     end
-    def test_t
-        if !NOT_GSL
-            [-2,0.1,0.5,1,2].each{|t|
-                [2,5,10].each{|n|
-                    area=Distribution::T.cdf(t,n)
-                    assert_in_delta(area, GSL::Cdf.tdist_P(t,n),0.0001)
-                    assert_in_delta(Distribution::T.p_value(area,n), GSL::Cdf.tdist_Pinv(area,n),0.0001)
-                    
-                }
+  end
+  def test_t
+    if !NOT_GSL
+        [-2,0.1,0.5,1,2].each{|t|
+            [2,5,10].each{|n|
+                area=Distribution::T.cdf(t,n)
+                assert_in_delta(area, GSL::Cdf.tdist_P(t,n),0.0001)
+                assert_in_delta(Distribution::T.p_value(area,n), GSL::Cdf.tdist_Pinv(area,n),0.0001)
+                
             }
-        end
+        }
     end
-    def test_normal
-        if !NOT_GSL
-            [-2,0.1,0.5,1,2].each{|x|
-                area=Distribution::Normal.cdf(x)
-                assert_in_delta(area, GSL::Cdf.ugaussian_P(x),0.0001)
-                assert_in_delta(Distribution::Normal.p_value(area), GSL::Cdf.ugaussian_Pinv(area),0.0001)
-                assert_in_delta(Distribution::Normal.pdf(x), GSL::Ran::ugaussian_pdf(x),0.0001)
-            }
-        end
+  end
+  def test_normal
+    if !NOT_GSL
+        [-2,0.1,0.5,1,2].each{|x|
+            area=Distribution::Normal.cdf(x)
+            assert_in_delta(area, GSL::Cdf.ugaussian_P(x),0.0001)
+            assert_in_delta(Distribution::Normal.p_value(area), GSL::Cdf.ugaussian_Pinv(area),0.0001)
+            assert_in_delta(Distribution::Normal.pdf(x), GSL::Ran::ugaussian_pdf(x),0.0001)
+        }
     end
-    def test_f
-        if !NOT_GSL
-            [0.1,0.5,1,2,10,20,30].each{|f|
-                [2,5,10].each{|n2|
-                [2,5,10].each{|n1|
-                    area=Distribution::F.cdf(f,n1,n2)
-                    assert_in_delta(area, GSL::Cdf.fdist_P(f,n1,n2),0.0001)
-                    assert_in_delta(Distribution::F.p_value(area,n1,n2), GSL::Cdf.fdist_Pinv(area,n1,n2),0.0001)
-                    
-                }
-                }
+  end
+  def test_normal_bivariate
+    if !NOT_GSL
+      [0.2,0.4,0.6,0.8,0.9, 0.99,0.999,0.999999].each {|rho|
+        assert_equal(GSL::Ran::bivariate_gaussian_pdf(0, 0, 1,1,rho), Distribution::NormalBivariate.pdf(0,0, rho , 1,1))
+       
+      }
+    end
+    
+    [-3,-2,-1,0,1,1.5].each {|x|
+      assert_in_delta(Distribution::NormalBivariate.cdf_math(x,x,0.5), Distribution::NormalBivariate.cdf_iterate(x,x,0.5), 0.001)
+    }
+    
+    assert_in_delta(0.686, Distribution::NormalBivariate.cdf(2,0.5,0.5), 0.001)
+    assert_in_delta(0.498, Distribution::NormalBivariate.cdf(2,0.0,0.5), 0.001)
+    assert_in_delta(0.671, Distribution::NormalBivariate.cdf(1.5,0.5,0.5), 0.001)
+    
+    assert_in_delta(Distribution::Normal.cdf(0), Distribution::NormalBivariate.cdf(10,0,0.9), 0.001)
+  end
+  def test_f
+    if !NOT_GSL
+        [0.1,0.5,1,2,10,20,30].each{|f|
+            [2,5,10].each{|n2|
+            [2,5,10].each{|n1|
+                area=Distribution::F.cdf(f,n1,n2)
+                assert_in_delta(area, GSL::Cdf.fdist_P(f,n1,n2),0.0001)
+                assert_in_delta(Distribution::F.p_value(area,n1,n2), GSL::Cdf.fdist_Pinv(area,n1,n2),0.0001)
+                
+            }
             }
-        end
+        }
     end
+  end
 
 end

data/test/test_factor.rb

@@ -1,7 +1,6 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 require 'test/unit'
-require 'matrix_extension'
 class StatsampleFactorTestCase < Test::Unit::TestCase
     def test_pca
       require 'gsl'

data/test/test_gsl.rb

@@ -1,22 +1,21 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 require 'test/unit'
-require 'matrix_extension'
 class StatsampleGSLTestCase < Test::Unit::TestCase
-    def test_matrix_to_gsl
-        if HAS_GSL
-        a=[1,2,3,4,20].to_vector(:scale)
-        b=[3,2,3,4,50].to_vector(:scale)
-        c=[6,2,3,4,3].to_vector(:scale)
-        ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
-        gsl=ds.to_matrix.to_gsl
-        assert_equal(5,gsl.size1)
-        assert_equal(3,gsl.size2)
-        matrix=gsl.to_matrix
-        assert_equal(5,matrix.row_size)
-        assert_equal(3,matrix.column_size)
-        end
+  def test_matrix_to_gsl
+    if HAS_GSL
+      a=[1,2,3,4,20].to_vector(:scale)
+      b=[3,2,3,4,50].to_vector(:scale)
+      c=[6,2,3,4,3].to_vector(:scale)
+      ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
+      gsl=ds.to_matrix.to_gsl
+      assert_equal(5,gsl.size1)
+      assert_equal(3,gsl.size2)
+      matrix=gsl.to_matrix
+      assert_equal(5,matrix.row_size)
+      assert_equal(3,matrix.column_size)
     end
+  end
 end
 
 

data/test/test_regression.rb

@@ -50,7 +50,7 @@ class StatsampleRegressionTestCase < Test::Unit::TestCase
             assert_in_delta(residuals[i],c_residuals[i],0.001)
         }
 	else
-		puts "Regression::Multiple::AlglibEngine not tested (no Alglib)"
+		puts "Regression::Multiple::GslEngine not tested (no Gsl)"
 	end
     end
 

data/test/test_statistics.rb

@@ -24,13 +24,10 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
   
   end
   def test_chi_square
-    assert_raise TypeError do
-        Statsample::Test.chi_square(1,1)
-    end
     real=Matrix[[95,95],[45,155]]
     expected=Matrix[[68,122],[72,128]]
     assert_nothing_raised do
-        chi=Statsample::Test.chi_square(real,expected)
+      chi=Statsample::Test.chi_square(real,expected)
     end
     chi=Statsample::Test.chi_square(real,expected)
     assert_in_delta(32.53,chi,0.1)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: statsample
 version: !ruby/object:Gem::Version 
-  version: 0.6.1
+  version: 0.6.2
 platform: ruby
 authors: 
 - Claudio Bustos
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-08 00:00:00 -03:00
+date: 2010-02-11 00:00:00 -03:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -76,35 +76,23 @@ files:
 - data/test_binomial.csv
 - data/tetmat_matrix.txt
 - data/tetmat_test.txt
-- 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/pca.rb
-- demo/proportion.rb
-- demo/regression.rb
-- demo/sample_test.csv
-- demo/spss_matrix.rb
-- demo/strata_proportion.rb
-- demo/stratum.rb
-- demo/t-student.rb
-- demo/umann.rb
+- demo/dominance_analysis_bootstrap.rb
+- demo/dominanceanalysis.rb
+- demo/multiple_regression.rb
+- demo/polychoric.rb
+- demo/tetrachoric.rb
 - lib/distribution.rb
 - lib/distribution/chisquare.rb
 - lib/distribution/f.rb
 - lib/distribution/normal.rb
+- lib/distribution/normalbivariate.rb
 - lib/distribution/t.rb
-- lib/matrix_extension.rb
 - lib/spss.rb
 - lib/statistics2.rb
 - lib/statsample.rb
 - lib/statsample/anova.rb
 - lib/statsample/bivariate.rb
+- lib/statsample/bivariate/polychoric.rb
 - lib/statsample/bivariate/tetrachoric.rb
 - lib/statsample/codification.rb
 - lib/statsample/combination.rb
@@ -127,6 +115,7 @@ files:
 - lib/statsample/graph/svgscatterplot.rb
 - lib/statsample/histogram.rb
 - lib/statsample/htmlreport.rb
+- lib/statsample/matrix.rb
 - lib/statsample/mle.rb
 - lib/statsample/mle/logit.rb
 - lib/statsample/mle/normal.rb

data/demo/benchmark.rb

@@ -1,76 +0,0 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'benchmark'
-v=(0..10000).collect{|n|
-	r=rand(100)
-    if(r<90)
-    r 
-    else
-        nil
-    end
-}.to_vector
-v.missing_values=[5,10,20]
-v.type=:scale
-a=[]
-b=[]
-c=[]
-(0..1000).each{|i|
-    a.push(rand())
-    b.push(rand())
-    c.push(rand())
-}
-ds=Statsample::Dataset.new({'a'=>a.to_vector(:scale),'b'=>b.to_vector(:scale), 'c'=>c.to_vector(:scale)})
-    
-
- n = 300
- if (false)
-     Benchmark.bm(7) do |bench|
-         bench.report("missing or")   { for i in 1..n; v.each {|x|             !(x.nil? or v.missing_values.include? x) }; end }
-         bench.report("missing and")   { for i in 1..n;v.each {|x|             !x.nil? and !v.missing_values.include? x } ; end }
-    end
- end
- if (false)
-     Benchmark.bm(7) do |bench|
-         bench.report("true")   { Statsample::OPTIMIZED=true; for i in 1..n; v.set_valid_data ; end }
-         bench.report("false")   { Statsample::OPTIMIZED=false; for i in 1..n; v.set_valid_data ; end }
-    end
- end
-
- if (true)
-     Benchmark.bm(7) do |x|
-         x.report("Alglib coeffs")   { for i in 1..n; lr=Statsample::Regression::Multiple::AlglibEngine.new(ds,"c"); lr.coeffs;          lr=nil;end }
-
-         x.report("GslEngine coeffs")   { for i in 1..n; lr=Statsample::Regression::Multiple::GslEngine.new(ds,"c"); lr.coeffs;lr=nil; end }
-     end
- end
- if(true)
-     Benchmark.bm(7) do |x|
-         x.report("Alglib process")   { for i in 1..n; lr=Statsample::Regression::Multiple::AlglibEngine.new(ds,"c"); lr.process([rand(10),rand(10)]); end }
-         x.report("GslEngine process")   { for i in 1..n; lr=Statsample::Regression::Multiple::GslEngine.new(ds,"c"); lr.process([rand(10),rand(10)]); end }
-
-    end
- end
- if (false)
-    Benchmark.bm(7) do |x|
-		x.report("mean")   { for i in 1..n; v.mean; end }
-		x.report("slow_mean")   { for i in 1..n; v.mean_slow; end }
-
-    end
-
-    Benchmark.bm(7) do |x|
-		x.report("variance_sample")   { for i in 1..n; v.variance_sample; end }
-		x.report("variance_slow")   { for i in 1..n; v.slow_variance_sample; end }
-
-    end
-
-
-    Benchmark.bm(7) do |x|
-		
-		x.report("Nominal.frequencies")   { for i in 1..n; v.frequencies; end }
-		x.report("Nominal.frequencies_slow")   { for i in 1..n; v.frequencies_slow; end }
-
-		x.report("_frequencies")   { for i in 1..n; Statsample._frequencies(v.valid_data); end }
-
-    end
-
-end

data/demo/chi-square.rb

@@ -1,44 +0,0 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
-require 'rbgsl'
-require 'statsample/resample'
-require 'statsample/test'
-require 'matrix'
-ideal=Matrix[[30,30,40]]
-tests=10000
-monte=Statsample::Resample.repeat_and_save(tests) {
-	observed=[0,0,0]
-	(1..100).each{|i|
-		r=rand(100)
-		if r<30
-			observed[0]+=1
-		elsif r<60
-			observed[1]+=1
-		else
-			observed[2]+=1
-		end
-	}
-	Statsample::Test::chi_square(Matrix[observed],ideal)
-}
-
-
-
-v=monte.to_vector(:scale)
-
-x=[]
-y=[]
-y2=[]
-y3=[]
-y4=[]
-prev=0
-prev_chi=0
-v.frequencies.sort.each{|k,v1|
-	x.push(k)
-	y.push(prev+v1)
-	prev=prev+v1
-	cdf_chi=GSL::Cdf.chisq_P(k,2)
-	y2.push(cdf_chi)
-	y4.push(prev.quo(tests))
-}
-
-
-GSL::graph(GSL::Vector.alloc(x), GSL::Vector.alloc(y2), GSL::Vector.alloc(y4))

data/demo/crosstab.rb

@@ -1,7 +0,0 @@
-require './../lib/statsample'
-a=[1,1,1,1,1,1,1,2,2,2,2,2,3,3,3].to_vector
-b=[1,2,3,2,2,2,1,1,1,2,2,1,2,2,3].to_vector
-
-ct=Statsample::Crosstab.new(a,b)
-puts ct.summary
-

data/demo/dice.rb

@@ -1,13 +0,0 @@
-require File.dirname(__FILE__)+"/../lib/statsample"
-require 'statsample/srs'
-require 'statsample/resample'
-require 'gnuplot'
-
-tests=3000
-# rand a 50%
-monte_with=Statsample::Resample.repeat_and_save(tests) {
-    (1+rand(6))+(1+rand(6))
-}.to_vector(:scale)
-
-p monte_with.mean
-

data/demo/distribution_t.rb

@@ -1,95 +0,0 @@
-#!/usr/bin/ruby
-
-require File.dirname(__FILE__)+"/../lib/statsample"
-require 'statsample/resample'
-require 'gnuplot'
-r = GSL::Rng.alloc(GSL::Rng::TAUS, 1)
-v=[]
-population_size=10000
-population_size.times{|i|
-    v.push(r.ugaussian)
-}
-
-v=v.to_vector(:scale)
-vm=v.mean
-vsd=v.sdp
-puts "Population sd:#{v.sdp}"
-tests=3000
-Gnuplot.open do |gp|
-			Gnuplot::Plot.new( gp ) do |plot|
-			plot.boxwidth("0.9 absolute")
-			plot.xrange("[-3:3]")
-			plot.yrange("[0:1.1]")
-			plot.style("fill  solid 1.00 border -1")
-[2].each {|ss|
-    puts "Sample size:#{ss}"
-    ee=v.sdp.quo(Math::sqrt(ss))
-    puts "SE: #{ee}"
-
-    puts "Expected variance with replacement: #{v.variance_population.quo(ss)*(v.size-1).quo(v.size)}"
-    puts "Expected variance without replacement: #{v.variance_population.quo(ss)*(1-ss.quo(v.size))}"
-    
-	sample_size=ss
-    sds_prom=[]
-    sds_prom_wo=[]
-	monte_wr=Statsample::Resample.repeat_and_save(tests) {
-		sample=v.sample_with_replacement(sample_size)
-        sds_prom.push(sample.sds)
-		sample.mean
-	}
-    monte_wor=Statsample::Resample.repeat_and_save(tests) {
-		sample=v.sample_without_replacement(sample_size)
-        sds_prom_wo.push(sample.sds)
-		sample.mean
-	}
-    xxz=[]
-    xxt=[]
-	xa=[]
-	xy=[]
-	xt=[]
-	xz=[]
-    
-    s_wr=sds_prom.to_vector(:scale).mean
-    s_wor=sds_prom_wo.to_vector(:scale).mean
-
-	mw=monte_wr.to_vector(:scale)
-    mwo=monte_wor.to_vector(:scale)
-    puts "Sample variance with replacement: #{mw.variance_population}"
-    puts "Sample variance without replacement: #{monte_wor.to_vector(:scale).variance_population}"
-    puts "Mean sd estimadet :#{vsd*Math::sqrt(ss-1)}"
-    puts "Mean Sd W/R: #{s_wr}" 
-    puts "Mean Sd WO/R: #{s_wor}" 
-
-	mx=mw.mean
-    er=mw.sds
-
-	prev=0
-	mw.frequencies.sort.each{|x,y|
-        t=(x-vm).quo(s_wr.quo(Math::sqrt(ss))*s_wr.quo(ss-1))
-        z=(x-vm).quo(vsd.quo(Math::sqrt(ss)))
-		xxz.push(z)
-        xxt.push(t)
-		prev+=y
-		xy.push(prev.to_f/tests)
-		xt.push(Distribution::T.cdf(t, ss-1))
-		xz.push(Distribution::Normal.cdf(z))
-
-	}
-	plot.data << Gnuplot::DataSet.new( [xxt,xy] ) do |ds|
-		ds.with="lines"
-		ds.title = "sim #{sample_size}"
-	end
-	plot.data << Gnuplot::DataSet.new( [xxt,xt] ) do |ds|
-		ds.with="lines"
-		ds.title = "t #{sample_size}"
-	end
-	plot.data << Gnuplot::DataSet.new( [xxz,xz] ) do |ds|
-		ds.with="lines"
-		ds.title = "z"
-	end
-	
-}
-
-end
-end
-