statsample 0.18.0 → 1.0.0

data/examples/correlation_matrix.rb

@@ -1,11 +1,19 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'benchmark'
 require 'statsample'
-a=1000.times.collect {rand}.to_scale
-b=1000.times.collect {rand}.to_scale
-c=1000.times.collect {rand}.to_scale
-d=1000.times.collect {rand}.to_scale
-ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-cm=Statsample::Bivariate.correlation_matrix(ds)
-puts cm.summary
+
+Statsample::Analysis.store("Statsample::Bivariate.correlation_matrix") do
+  samples=1000
+  ds=data_frame(
+    'a'=>rnorm(samples),
+    'b'=>rnorm(samples),
+    'c'=>rnorm(samples),
+    'd'=>rnorm(samples))
+  cm=cor(ds)
+  summary(cm)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
+

data/examples/dataset.rb

@@ -1,8 +1,17 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
-a=1000.times.collect {r=rand(5); r==4 ? nil: r;}.to_scale
-b=1000.times.collect {r=rand(5); r==4 ? nil: r;}.to_scale
 
-ds={'a'=>a,'b'=>b}.to_dataset
-puts ds.summary
+Statsample::Analysis.store(Statsample::Dataset) do
+  samples=1000
+  a=Statsample::Vector.new_scale(samples) {r=rand(5); r==4 ? nil: r}
+  b=Statsample::Vector.new_scale(samples) {r=rand(5); r==4 ? nil: r}
+
+  ds={'a'=>a,'b'=>b}.to_dataset
+  summary(ds)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
+

data/examples/dominance_analysis.rb

@@ -2,25 +2,31 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-sample=200
-a=sample.times.collect {rand}.to_scale
-b=sample.times.collect {rand}.to_scale
-c=sample.times.collect {rand}.to_scale
-d=sample.times.collect {rand}.to_scale
 
-ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-ds['y']=ds.collect{|row| row['a']*5 + row['b']*3 + row['c']*2 + row['d'] + rand()}
-rb=ReportBuilder.new(:name=>"Dominance Analysis")
 
-cm=Statsample::Bivariate.correlation_matrix(ds)
-rb.add(cm)
-lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y')
-rb.add(lr)
+Statsample::Analysis.store(Statsample::DominanceAnalysis) do
+  sample=300
+  a=rnorm(sample)
+  b=rnorm(sample)
+  c=rnorm(sample)
+  d=rnorm(sample)
+  
+  ds={'a'=>a,'b'=>b,'cc'=>c,'d'=>d}.to_dataset
+  attach(ds)
+  ds['y']=a*5+b*3+cc*2+d+rnorm(300)  
+  cm=cor(ds)
+  summary(cm)
+  lr=lr(ds,'y')
+  summary(lr)
+  da=dominance_analysis(ds,'y')
+  summary(da)
+  
+  da=dominance_analysis(ds,'y',:name=>"Dominance Analysis using group of predictors", :predictors=>['a', 'b', %w{cc d}])
+  summary(da)
+end
 
-#da=Statsample::DominanceAnalysis.new(ds,'y')
-#rb.add(da)
 
-da=Statsample::DominanceAnalysis.new(ds,'y',:name=>"Dominance Analysis using group of predictors", :predictors=>['a', 'b', %w{c d}])
-rb.add(da)
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
 
-puts rb.to_text

data/examples/dominance_analysis_bootstrap.rb

@@ -2,26 +2,32 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 
+Statsample::Analysis.store(Statsample::DominanceAnalysis::Bootstrap) do
+  
+  sample=300
+  a=rnorm(sample)
+  b=rnorm(sample)
+  c=rnorm(sample)
+  d=rnorm(sample)  
+  a.name="a"
+  b.name="b"
+  c.name="c"
+  d.name="d"
+  
+  ds={'a'=>a,'b'=>b,'cc'=>c,'d'=>d}.to_dataset
+  attach(ds)
+  ds['y1']=a*5+b*2+cc*2+d*2+rnorm(sample,0,10)
+  ds['y2']=a*10+rnorm(sample)
+  
+  dab=dominance_analysis_bootstrap(ds, ['y1','y2'], :debug=>true)
+  dab.bootstrap(100,nil)
+  summary(dab)
+  ds2=ds['a'..'y1']
+  dab2=dominance_analysis_bootstrap(ds2, 'y1', :debug=>true)
+  dab2.bootstrap(100,nil)
+  summary(dab2)
+end
 
-a=100.times.collect {rand}.to_scale
-b=100.times.collect {rand}.to_scale
-c=100.times.collect {rand}.to_scale
-d=100.times.collect {rand}.to_scale
-
-a.name="a"
-b.name="b"
-c.name="c"
-d.name="d"
-
-ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-
-ds['y1']=ds.collect{|row| row['a']*5+row['b']*2+row['c']*2+row['d']*2+10*rand()}
-ds['y2']=ds.collect{|row| row['a']*10+rand()}
-
-dab=Statsample::DominanceAnalysis::Bootstrap.new(ds, ['y1','y2'], :debug=>true)
-dab.bootstrap(100,nil)
-puts dab.summary
-ds2=ds['a'..'y1']
-dab=Statsample::DominanceAnalysis::Bootstrap.new(ds2, 'y1', :debug=>true)
-dab.bootstrap(100,nil)
-puts dab.summary
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/histogram.rb

@@ -1,13 +1,12 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
-$:.unshift('/home/cdx/dev/reportbuilder/lib/')
 require 'statsample'
-n=3000
-rng=Distribution::Normal.rng_ugaussian
-a=n.times.map {|i| rng.call()*20}.to_scale
-hg=Statsample::Graph::Histogram.new(a, :bins=>20, :line_normal_distribution=>true )
 
-rb=ReportBuilder.new
-#rb.add(a.histogram)
-rb.add(hg)
-rb.save_html('histogram.html')
+Statsample::Analysis.store(Statsample::Graph::Histogram) do
+  histogram(rnorm(3000,0,20))
+end
+
+
+if __FILE__==$0
+   Statsample::Analysis.run
+end

data/examples/icc.rb

@@ -2,25 +2,24 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-size=1000
-a=size.times.map {rand(10)}.to_scale
-b=a.recode{|i|i+rand(4)-2}
-c=a.recode{|i|i+rand(4)-2}
-d=a.recode{|i|i+rand(4)-2}
-@ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-
-
-
-@icc=Statsample::Reliability::ICC.new(@ds)
-
-puts @icc.summary
-
-@icc.type=:icc_3_1
-
-puts @icc.summary
-
-
-@icc.type=:icc_a_k
-
-puts @icc.summary
 
+Statsample::Analysis.store(Statsample::Reliability::ICC) do
+
+  size=1000
+  a=Statsample::Vector.new_scale(size) {rand(10)}
+  b=a.recode{|i|i+rand(4)-2}
+  c=a.recode{|i|i+rand(4)-2}
+  d=a.recode{|i|i+rand(4)-2}
+  @ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
+  @icc=Statsample::Reliability::ICC.new(@ds)
+  summary(@icc)
+  @icc.type=:icc_3_1
+  summary(@icc)
+  @icc.type=:icc_a_k
+  summary(@icc)
+  
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/levene.rb

@@ -2,8 +2,14 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-a=[1,2,3,4,5,6,7,8,100,10].to_scale
-b=[30,40,50,60,70,80,90,100,110,120].to_scale
 
-levene=Statsample::Test::Levene.new([a,b])
-puts levene.summary
+Statsample::Analysis.store(Statsample::Test::Levene) do
+
+  a=[1,2,3,4,5,6,7,8,100,10].to_scale
+  b=[30,40,50,60,70,80,90,100,110,120].to_scale
+  summary(levene([a,b]))
+end
+
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end

data/examples/multiple_regression.rb

@@ -1,36 +1,17 @@
 #!/usr/bin/ruby
-#$:.unshift(File.dirname(__FILE__)+'/../lib/')
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-require 'benchmark'
-samples=1000
-a=samples.times.collect {rand}.to_scale
-b=samples.times.collect {rand}.to_scale
-c=samples.times.collect {rand}.to_scale
-d=samples.times.collect {rand}.to_scale
 
-ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-ds['y']=ds.collect{|row| row['a']*5+row['b']*3+row['c']*2+row['d']*1+rand()}
+Statsample::Analysis.store(Statsample::Regression::Multiple) do
 
-Benchmark.bm(7) do |x|
-
-
-rb=ReportBuilder.new(:name=>"Multiple Regression Engines")
-
-if Statsample.has_gsl?
-  x.report("GSL:") {
-  lr=Statsample::Regression::Multiple::GslEngine.new(ds,'y',:name=>"Multiple Regression using GSL")
-  rb.add(lr.summary)
-  }
+  samples=2000
+  ds=dataset('a'=>rnorm(samples),'b'=>rnorm(samples),'cc'=>rnorm(samples),'d'=>rnorm(samples))
+  attach(ds)
+  ds['y']=a*5+b*3+cc*2+d+rnorm(samples)
+  summary lr(ds,'y')
 end
 
-
-  x.report("Ruby:") {
-  lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y',:name=>"Multiple Regression using RubyEngine")
-  rb.add(lr.summary)
-  }
-  puts rb.to_text
+if __FILE__==$0
+   Statsample::Analysis.run_batch
 end
-
-
-

data/examples/multivariate_correlation.rb

@@ -5,7 +5,8 @@ require 'statsample'
 require 'mathn'
 
 
-
+Statsample::Analysis.store(Statsample::Regression::Multiple::MultipleDependent) do
+  
   complete=Matrix[
   [1,0.53,0.62,0.19,-0.09,0.08,0.02,-0.12,0.08],
   [0.53,1,0.61,0.23,0.1,0.18,0.02,-0.1,0.15],
@@ -22,6 +23,11 @@ require 'mathn'
   
   lr=Statsample::Regression::Multiple::MultipleDependent.new(complete, %w{adhd cd odd})
   
-  puts "R^2_yx #{lr.r2yx}"
-  puts "P^2_yx #{lr.p2yx}"
+  echo "R^2_yx #{lr.r2yx}"
+  echo "P^2_yx #{lr.p2yx}"
+end
+
 
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end

data/examples/parallel_analysis.rb

@@ -2,30 +2,34 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-samples=100
+samples=150
 variables=30
 iterations=50
-rng = GSL::Rng.alloc()
-f1=samples.times.collect {rng.ugaussian()}.to_scale
-f2=samples.times.collect {rng.ugaussian()}.to_scale
-f3=samples.times.collect {rng.ugaussian()}.to_scale
+Statsample::Analysis.store(Statsample::Factor::ParallelAnalysis) do 
+  
+rng = Distribution::Normal.rng()
+f1=rnorm(samples)
+f2=rnorm(samples)
+f3=rnorm(samples)
 
 vectors={}
 
 variables.times do |i|
-  vectors["v#{i}"]=samples.times.collect {|nv| f1[nv]*i+(f2[nv]*(15-i))+((f3[nv]*(30-i))*1.5)*rng.ugaussian()}.to_scale
+  vectors["v#{i}"]=samples.times.collect {|nv| f1[nv]*i+(f2[nv]*(15-i))+((f3[nv]*(30-i))*1.5)*rng.call}.to_scale
   vectors["v#{i}"].name="Vector #{i}"
 end
-ds=vectors.to_dataset
 
-pa=Statsample::Factor::ParallelAnalysis.new(ds, :iterations=>iterations, :debug=>true)
-pca=Statsample::Factor::PCA.new(Statsample::Bivariate.correlation_matrix(ds))
-rb=ReportBuilder.new(:name=>"Parallel Analysis with simulation") do
-  text "There are 3 real factors on data"
-  parse_element pca
-  text "Traditional Kaiser criterion (k>1) returns #{pca.m} factors"
-  parse_element pa
-  text "Parallel Analysis returns #{pa.number_of_factors} factors to preserve"
+  ds=vectors.to_dataset
+
+  pa=Statsample::Factor::ParallelAnalysis.new(ds, :iterations=>iterations, :debug=>true)
+  pca=pca(cor(ds))
+  echo "There are 3 real factors on data"
+  summary pca
+  echo "Traditional Kaiser criterion (k>1) returns #{pca.m} factors"
+  summary pa
+  echo "Parallel Analysis returns #{pa.number_of_factors} factors to preserve"
 end
 
-puts rb.to_text
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end

data/examples/polychoric.rb

@@ -1,21 +1,27 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
+$:.unshift("/home/cdx/usr/lib/statsample-bivariate-extension/lib/")
 
 require 'statsample'
-ct=Matrix[[58,52,1],[26,58,3],[8,12,9]]
+Statsample::Analysis.store(Statsample::Bivariate::Polychoric) do 
+ct=Matrix[[rand(10)+50, rand(10)+50,  rand(10)+1],
+          [rand(20)+5,  rand(50)+4,   rand(10)+1],
+          [rand(8)+1,   rand(12)+1,   rand(10)+1]]
 
 # Estimation of polychoric correlation using two-step (default)
-poly=Statsample::Bivariate::Polychoric.new(ct, :name=>"Polychoric with two-step", :debug=>true)
-
-puts poly.summary
+poly=polychoric(ct, :name=>"Polychoric with two-step", :debug=>false)
+summary poly
 
 # Estimation of polychoric correlation using joint method (slow)
-poly=Statsample::Bivariate::Polychoric.new(ct, :method=>:joint, :name=>"Polychoric with joint")
-puts poly.summary
-
+poly=polychoric(ct, :method=>:joint, :name=>"Polychoric with joint")
+summary poly
 
 # Uses polychoric series (not recomended)
 
-poly=Statsample::Bivariate::Polychoric.new(ct, :method=>:polychoric_series, :name=>"Polychoric with polychoric series")
-puts poly.summary
+poly=polychoric(ct, :method=>:polychoric_series, :name=>"Polychoric with polychoric series")
+summary poly
+end
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end
 

data/examples/principal_axis.rb

@@ -2,9 +2,21 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
-matrix=Matrix[
-[1.0, 0.709501601093587, 0.877596585880047, 0.272219316266807],  [0.709501601093587, 1.0, 0.291633797330304, 0.871141831433844], [0.877596585880047, 0.291633797330304, 1.0, -0.213373722977167], [0.272219316266807, 0.871141831433844, -0.213373722977167, 1.0]]
-matrix.extend Statsample::CovariateMatrix
-#matrix.fields=%w{a b c d}
-fa=Statsample::Factor::PrincipalAxis.new(matrix,:m=>1,:smc=>false)
-puts fa.summary
+
+Statsample::Analysis.store(Statsample::Factor::PrincipalAxis) do
+
+  matrix=Matrix[
+  [1.0, 0.709501601093587, 0.877596585880047, 0.272219316266807],  [0.709501601093587, 1.0, 0.291633797330304, 0.871141831433844], [0.877596585880047, 0.291633797330304, 1.0, -0.213373722977167], [0.272219316266807, 0.871141831433844, -0.213373722977167, 1.0]]
+  
+  matrix.extend Statsample::CovariateMatrix
+  
+  #matrix.fields=%w{a b c d}
+  fa=principal_axis(matrix,:m=>1,:smc=>false)
+  
+  summary fa
+end
+
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end
+

data/examples/reliability.rb

@@ -1,20 +1,33 @@
 #!/usr/bin/ruby
 $:.unshift(File.dirname(__FILE__)+'/../lib')
 require 'statsample'
-samples=100
-a=samples.times.map {rand(100)}.to_scale
-ds=Statsample::Dataset.new
-20.times do |i|
-        ds["v#{i}"]=a.collect {|v| v+rand(20)}.to_scale
-end
-ds.update_valid_data
-rel=Statsample::Reliability::ScaleAnalysis.new(ds)
-puts rel.summary
 
+Statsample::Analysis.store(Statsample::Reliability) do
+  
+  samples=100
+  a=rnorm(samples)
+  
+  ds=Statsample::Dataset.new
+  
+  20.times do |i|
+    ds["v#{i}"]=a+rnorm(samples,0,0.2)
+  end
+  
+  ds.update_valid_data
+  
+  rel=Statsample::Reliability::ScaleAnalysis.new(ds)
+  summary rel
+  
+  
+  ms=Statsample::Reliability::MultiScaleAnalysis.new(:name=>"Multi Scale analyss") do |m|
+    m.scale "Scale 1", ds.clone(%w{v1 v2 v3 v4 v5 v6 v7 v8 v9 v10})
+    m.scale "Scale 2", ds.clone(%w{v11 v12 v13 v14 v15 v16 v17 v18 v19})
+  end
+  
+  summary ms
+end
 
-ms=Statsample::Reliability::MultiScaleAnalysis.new(:name=>"Multi Scale analyss") do |m|
-  m.scale "Scale 1", ds.clone(%w{v1 v2 v3 v4 v5 v6 v7 v8 v9 v10})
-  m.scale "Scale 2", ds.clone(%w{v11 v12 v13 v14 v15 v16 v17 v18 v19})
+if __FILE__==$0
+   Statsample::Analysis.run_batch
 end
 
-puts ms.summary