statsample 0.7.0 → 0.8.0

data/test/test_bivariate.rb

@@ -1,7 +1,5 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'minitest/unit'
-MiniTest::Unit.autorun
+require(File.dirname(__FILE__)+'/test_helpers.rb')
+
 class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
   def test_sum_of_squares
     v1=[1,2,3,4,5,6].to_vector(:scale)
@@ -16,25 +14,25 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     else
       puts "Bivariate::covariance not tested (needs GSL)"
     end
-  
+
   end
 
   def test_gsl_pearson
-     if Statsample.has_gsl?
-       v1=100.times.collect {|a| rand()}.to_scale
-       v2=100.times.collect {|a| rand()}.to_scale
-
-       assert_in_delta(GSL::Stats::correlation(v1.gsl, v2.gsl), Statsample::Bivariate.pearson_slow(v1,v2), 1e-10)
-     else
-       puts "Not tested gsl versus ruby correlation (needs GSL)"
-     end
+    if Statsample.has_gsl?
+      v1=100.times.collect {|a| rand()}.to_scale
+      v2=100.times.collect {|a| rand()}.to_scale
+
+      assert_in_delta(GSL::Stats::correlation(v1.gsl, v2.gsl), Statsample::Bivariate.pearson_slow(v1,v2), 1e-10)
+    else
+      puts "Not tested gsl versus ruby correlation (needs GSL)"
+    end
   end
   def test_pearson
     v1=[6,5,4,7,8,4,3,2].to_vector(:scale)
     v2=[2,3,7,8,6,4,3,2].to_vector(:scale)
     assert_in_delta(0.525,Statsample::Bivariate.pearson(v1,v2), 0.001)
     assert_in_delta(0.525,Statsample::Bivariate.pearson_slow(v1,v2), 0.001)
-    
+
     v3=[6,2,  1000,1000,5,4,7,8,4,3,2,nil].to_vector(:scale)
     v4=[2,nil,nil,nil,  3,7,8,6,4,3,2,500].to_vector(:scale)
     assert_in_delta(0.525,Statsample::Bivariate.pearson(v3,v4),0.001)
@@ -53,6 +51,11 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
       end
     end
   end
+  def test_polychoric_summary
+      matrix=Matrix[[150+rand(2),150+rand(2)],[150+rand(2),150+rand(2)],[200,300]]
+      poly  = Statsample::Bivariate::Polychoric.new(matrix)
+      assert(poly.summary.size>0)
+  end
   def test_poly_vs_tetra
     5.times {
       # Should be the same results as Tetrachoric for 2x2 matrix
@@ -68,19 +71,19 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     }
   end
   def test_polychoric
-    
-      matrix=Matrix[[58,52,1],[26,58,3],[8,12,9]]
-      poly=Statsample::Bivariate::Polychoric.new(matrix)
-      poly.compute_two_step_mle_drasgow_ruby
-      assert_in_delta(0.420, poly.r, 0.001)
-      assert_in_delta(-0.240, poly.threshold_y[0],0.001)
-      assert_in_delta(-0.027, poly.threshold_x[0],0.001)
-      assert_in_delta(1.578, poly.threshold_y[1],0.001)
-      assert_in_delta(1.137, poly.threshold_x[1],0.001)
-    if Statsample.has_gsl?  
+
+    matrix=Matrix[[58,52,1],[26,58,3],[8,12,9]]
+    poly=Statsample::Bivariate::Polychoric.new(matrix)
+    poly.compute_two_step_mle_drasgow_ruby
+    assert_in_delta(0.420, poly.r, 0.001)
+    assert_in_delta(-0.240, poly.threshold_y[0],0.001)
+    assert_in_delta(-0.027, poly.threshold_x[0],0.001)
+    assert_in_delta(1.578, poly.threshold_y[1],0.001)
+    assert_in_delta(1.137, poly.threshold_x[1],0.001)
+    if Statsample.has_gsl?
       poly.method=:polychoric_series
       poly.compute
-      
+
       assert_in_delta(0.556, poly.r, 0.001)
       assert_in_delta(-0.240, poly.threshold_y[0],0.001)
       assert_in_delta(-0.027, poly.threshold_x[0],0.001)
@@ -88,7 +91,7 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
       assert_in_delta(1.137, poly.threshold_x[1],0.001)
 
       # Example for Tallis(1962, cited by Drasgow, 2006)
-      
+
       matrix=Matrix[[58,52,1],[26,58,3],[8,12,9]]
       poly=Statsample::Bivariate::Polychoric.new(matrix)
       poly.compute_two_step_mle_drasgow_gsl
@@ -98,11 +101,11 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
       assert_in_delta(1.578, poly.threshold_y[1],0.001)
       assert_in_delta(1.137, poly.threshold_x[1],0.001)
 
-      
+
       poly.method=:joint
       poly.compute
-      
-      
+
+
       assert_in_delta(0.4192, poly.r, 0.0001)
       assert_in_delta(-0.2421, poly.threshold_y[0],0.0001)
       assert_in_delta(-0.0297, poly.threshold_x[0],0.0001)
@@ -113,7 +116,7 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     end
     assert(poly.summary)
   end
-  
+
   def test_tetrachoric
     a,b,c,d=0,0,0,0
     assert_raises RuntimeError do
@@ -135,7 +138,7 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
     assert_equal(-1,tc.r)
     assert_equal(0,tc.se)
-    
+
     a,b,c,d = 30,40,70,20
     tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
     assert_in_delta(-0.53980,tc.r,0.0001)
@@ -162,9 +165,9 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     v3=[6,2,  1000,1000,5,4,7,8].to_vector(:scale)
     v4=[2,nil,nil,nil,  3,7,8,6].to_vector(:scale)
     ds={'v1'=>v1,'v2'=>v2,'v3'=>v3,'v4'=>v4}.to_dataset
-    c=Proc.new {|n1,n2|Statsample::Bivariate.pearson(n1,n2)} 
+    c=Proc.new {|n1,n2|Statsample::Bivariate.pearson(n1,n2)}
     expected=Matrix[ [c.call(v1,v1),c.call(v1,v2),c.call(v1,v3),c.call(v1,v4)], [c.call(v2,v1),c.call(v2,v2),c.call(v2,v3),c.call(v2,v4)], [c.call(v3,v1),c.call(v3,v2),c.call(v3,v3),c.call(v3,v4)],
-    [c.call(v4,v1),c.call(v4,v2),c.call(v4,v3),c.call(v4,v4)]
+      [c.call(v4,v1),c.call(v4,v2),c.call(v4,v3),c.call(v4,v4)]
     ]
     obt=Statsample::Bivariate.correlation_matrix(ds)
     for i in 0...expected.row_size
@@ -193,12 +196,12 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     assert(Statsample::Bivariate.prop_pearson(t,n,:right)>0.05)
     assert(Statsample::Bivariate.prop_pearson(t,n,:left)<0.05)
   end
-  
+
   def test_spearman
     v1=[86,97,99,100,101,103,106,110,112,113].to_vector(:scale)
     v2=[0,20,28,27,50,29,7,17,6,12].to_vector(:scale)
     assert_in_delta(-0.175758,Statsample::Bivariate.spearman(v1,v2),0.0001)
-      
+
   end
   def test_point_biserial
     c=[1,3,5,6,7,100,200,300,400,300].to_vector(:scale)
@@ -222,7 +225,7 @@ class StatsampleBivariateTestCase < MiniTest::Unit::TestCase
     assert_in_delta(0.636,Statsample::Bivariate.gamma(m),0.001)
     m2=Matrix[[15,12,6,5],[12,8,10,8],[4,6,9,10]]
     assert_in_delta(0.349,Statsample::Bivariate.gamma(m2),0.001)
-  
-  
+
+
   end
 end

data/test/test_codification.rb

@@ -1,21 +1,17 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'tempfile'
-require 'tmpdir'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleCodificationTestCase < Test::Unit::TestCase
+class StatsampleCodificationTestCase < MiniTest::Unit::TestCase
 
   def initialize(*args)
     v1=%w{run walk,run walking running sleep sleeping,dreaming sleep,dream}.to_vector
     @dict={'run'=>'r','walk'=>'w','walking'=>'w','running'=>'r','sleep'=>'s', 'sleeping'=>'s', 'dream'=>'d', 'dreaming'=>'d'}
     @ds={"v1"=>v1}.to_dataset
-  super
+    super
   end
   def test_create_hash
     expected_keys_v1=%w{run walk walking running sleep sleeping dream dreaming}.sort
     hash=Statsample::Codification.create_hash(@ds,['v1'])
-    assert_equal(['v1'],hash.keys)                 
+    assert_equal(['v1'],hash.keys)
     assert_equal(expected_keys_v1,hash['v1'].keys.sort)
     assert_equal(expected_keys_v1,hash['v1'].values.sort)
   end
@@ -32,11 +28,11 @@ class StatsampleCodificationTestCase < Test::Unit::TestCase
     hash=Statsample::Codification.excel_to_recoded_hash(filename)
     assert_equal(keys.data, hash['v1'].keys.sort)
     assert_equal(keys.data, hash['v1'].values.sort)
-    
+
   end
   def test_create_yaml
     assert_raise  ArgumentError do
-        Statsample::Codification.create_yaml(@ds,[])
+      Statsample::Codification.create_yaml(@ds,[])
     end
     expected_keys_v1=%w{run walk walking running sleep sleeping dream dreaming}.sort
     yaml_hash=Statsample::Codification.create_yaml(@ds,['v1'])
@@ -73,9 +69,9 @@ class StatsampleCodificationTestCase < Test::Unit::TestCase
     e['s']=[0,0,0,0,1,1,1].to_vector
     e['d']=[0,0,0,0,0,1,1].to_vector
     e.each{|k,expected|
-        assert_equal(expected,@ds['v1_'+k],"Error on key #{k}")
-  
+      assert_equal(expected,@ds['v1_'+k],"Error on key #{k}")
+
     }
   end
 
-end
+end

data/test/test_combination.rb

@@ -1,42 +1,40 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleCombinationTestCase < Test::Unit::TestCase
-	def initialize(*args)
-        super
-	end
-    def test_basic
-        k=3
-        n=5
-        expected=[[0,1,2],[0,1,3],[0,1,4],[0,2,3],[0,2,4],[0,3,4],[1,2,3],[1,2,4],[1,3,4],[2,3,4]]
-        comb=Statsample::Combination.new(k,n)
-        a=[]
-        comb.each{|y|
-            a.push(y)
-        }
-        assert_equal(expected,a)
-    end
-    def test_gsl_versus_ruby
-        if Statsample.has_gsl?
-        k=3
-        n=10
-        gsl=Statsample::Combination.new(k,n,false)
-        gsl_array=[]
-        gsl.each{|y|
-            gsl_array.push(y)
-        }
-        rb=Statsample::Combination.new(k,n,true)
-        rb_array=[]
-        rb.each{|y|
-            rb_array.push(y)
-        }
-        assert(gsl.d.is_a?(Statsample::Combination::CombinationGsl))
-        assert(rb.d.is_a?(Statsample::Combination::CombinationRuby))
-        
-        assert_equal(rb_array,gsl_array)
+class StatsampleCombinationTestCase < MiniTest::Unit::TestCase
+  def initialize(*args)
+    super
+  end
+  def test_basic
+    k=3
+    n=5
+    expected=[[0,1,2],[0,1,3],[0,1,4],[0,2,3],[0,2,4],[0,3,4],[1,2,3],[1,2,4],[1,3,4],[2,3,4]]
+    comb=Statsample::Combination.new(k,n)
+    a=[]
+    comb.each{|y|
+      a.push(y)
+    }
+    assert_equal(expected,a)
+  end
+  def test_gsl_versus_ruby
+    if Statsample.has_gsl?
+      k=3
+      n=10
+      gsl=Statsample::Combination.new(k,n,false)
+      gsl_array=[]
+      gsl.each{|y|
+        gsl_array.push(y)
+      }
+      rb=Statsample::Combination.new(k,n,true)
+      rb_array=[]
+      rb.each{|y|
+        rb_array.push(y)
+      }
+      assert(gsl.d.is_a?(Statsample::Combination::CombinationGsl))
+      assert(rb.d.is_a?(Statsample::Combination::CombinationRuby))
+
+      assert_equal(rb_array,gsl_array)
     else
-            puts "Not CombinationRuby vs CombinationGSL (no gsl)"
-        end
+      puts "Not CombinationRuby vs CombinationGSL (no gsl)"
     end
-end
+  end
+end

data/test/test_crosstab.rb

@@ -1,52 +1,50 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleCrosstabTestCase < Test::Unit::TestCase
+class StatsampleCrosstabTestCase < MiniTest::Unit::TestCase
 
-	def initialize(*args)
-		@v1=%w{black blonde black black red black brown black blonde black red black blonde}.to_vector
-		@v2=%w{woman man man woman man man man woman man woman woman man man}.to_vector
-		@ct=Statsample::Crosstab.new(@v1,@v2)
-		super
-	end
-	def test_crosstab_errors
-		e1=%w{black blonde black black red black brown black blonde black}
-		assert_raise ArgumentError do
-			Statsample::Crosstab.new(e1,@v2)
-		end
-		e2=%w{black blonde black black red black brown black blonde black black}.to_vector
-		
-		assert_raise ArgumentError do
-			Statsample::Crosstab.new(e2,@v2)
-		end
-		assert_nothing_raised do
-			Statsample::Crosstab.new(@v1,@v2)
-		end
-	end
-	def test_crosstab_basic
-		assert_equal(%w{black blonde brown red}, @ct.rows_names)
-		assert_equal(%w{man woman}, @ct.cols_names)
-		assert_equal({'black'=>7,'blonde'=>3,'red'=>2,'brown'=>1}, @ct.rows_total)
-		assert_equal({'man'=>8,'woman'=>5}, @ct.cols_total)
-	end
-	def test_crosstab_frequencies
-		fq=@ct.frequencies
-        assert_equal(8,fq.size)
-        sum=fq.inject(0) {|s,x| s+x[1]}
-        assert_equal(13,sum)
-        fr=@ct.frequencies_by_row
-        assert_equal(4,fr.size)
-        assert_equal(%w{black blonde brown red},fr.keys.sort)
-        fc=@ct.frequencies_by_col
-        assert_equal(2,fc.size)
-        assert_equal(%w{man woman},fc.keys.sort)
-        assert_equal(Matrix.rows([[3,4],[3,0],[1,0],[1,1]]),@ct.to_matrix)
-	end
-    def test_expected
-        v1=%w{1 1 1 1 1 0 0 0 0 0}.to_vector
-        v2=%w{0 0 0 0 0 1 1 1 1 1}.to_vector
-        ct=Statsample::Crosstab.new(v1,v2)
-        assert_equal(Matrix[[2.5,2.5],[2.5,2.5]],ct.matrix_expected)
+  def initialize(*args)
+    @v1=%w{black blonde black black red black brown black blonde black red black blonde}.to_vector
+    @v2=%w{woman man man woman man man man woman man woman woman man man}.to_vector
+    @ct=Statsample::Crosstab.new(@v1,@v2)
+    super
+  end
+  def test_crosstab_errors
+    e1=%w{black blonde black black red black brown black blonde black}
+    assert_raise ArgumentError do
+      Statsample::Crosstab.new(e1,@v2)
     end
+    e2=%w{black blonde black black red black brown black blonde black black}.to_vector
+
+    assert_raise ArgumentError do
+      Statsample::Crosstab.new(e2,@v2)
+    end
+    assert_nothing_raised do
+      Statsample::Crosstab.new(@v1,@v2)
+    end
+  end
+  def test_crosstab_basic
+    assert_equal(%w{black blonde brown red}, @ct.rows_names)
+    assert_equal(%w{man woman}, @ct.cols_names)
+    assert_equal({'black'=>7,'blonde'=>3,'red'=>2,'brown'=>1}, @ct.rows_total)
+    assert_equal({'man'=>8,'woman'=>5}, @ct.cols_total)
+  end
+  def test_crosstab_frequencies
+    fq=@ct.frequencies
+    assert_equal(8,fq.size)
+    sum=fq.inject(0) {|s,x| s+x[1]}
+    assert_equal(13,sum)
+    fr=@ct.frequencies_by_row
+    assert_equal(4,fr.size)
+    assert_equal(%w{black blonde brown red},fr.keys.sort)
+    fc=@ct.frequencies_by_col
+    assert_equal(2,fc.size)
+    assert_equal(%w{man woman},fc.keys.sort)
+    assert_equal(Matrix.rows([[3,4],[3,0],[1,0],[1,1]]),@ct.to_matrix)
+  end
+  def test_expected
+    v1=%w{1 1 1 1 1 0 0 0 0 0}.to_vector
+    v2=%w{0 0 0 0 0 1 1 1 1 1}.to_vector
+    ct=Statsample::Crosstab.new(v1,v2)
+    assert_equal(Matrix[[2.5,2.5],[2.5,2.5]],ct.matrix_expected)
+  end
 end

data/test/test_csv.rb

@@ -1,46 +1,41 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require "tempfile"
-require 'minitest/unit'
-MiniTest::Unit.autorun
-class StatsampleCSVTestCase < MiniTest::Unit::TestCase
-    def setup
-        @ds=Statsample::CSV.read(File.dirname(__FILE__)+"/test_csv.csv")
-    end
-    def test_read
-        assert_equal(6,@ds.cases)
-        assert_equal(%w{id name age city a1}, @ds.fields)
-        id=[1,2,3,4,5,6].to_vector(:scale)
-        name=["Alex","Claude","Peter","Franz","George","Fernand"].to_vector(:nominal)
-        age=[20,23,25,27,5.5,nil].to_vector(:scale)
-        city=["New York","London","London","Paris","Tome",nil].to_vector(:nominal)
-        a1=["a,b","b,c","a",nil,"a,b,c",nil].to_vector(:nominal)
-        ds_exp=Statsample::Dataset.new({'id'=>id,'name'=>name,'age'=>age,'city'=>city,'a1'=>a1}, %w{id name age city a1})
-        ds_exp.fields.each{|f|
-            assert_equal(ds_exp[f],@ds[f])
-        }
-        assert_equal(ds_exp,@ds)
-        
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-    end
-    def test_nil
-        assert_equal(nil,@ds['age'][5])
-    end
-    def test_repeated
-      ds=Statsample::CSV.read(File.dirname(__FILE__)+"/../data/repeated_fields.csv")
-      assert_equal(%w{id name_1 age_1 city a1 name_2 age_2},ds.fields)
-      age=[3,4,5,6,nil,8].to_vector(:scale)
-      assert_equal(age,ds['age_2'])
-    end
-    def test_write
-      filename=Tempfile.new("afile")
-      #  filename=Dir::tmpdir+"/test_write.csv"
-        Statsample::CSV.write(@ds, filename.path)
-        ds2=Statsample::CSV.read(filename.path)
-        i=0
-        ds2.each_array{|row|
-            assert_equal(@ds.case_as_array(i),row)
-               i+=1
-        }
-    end
-end
+class StatsampleCSVTestCase < MiniTest::Unit::TestCase
+  def setup
+    @ds=Statsample::CSV.read(File.dirname(__FILE__)+"/test_csv.csv")
+  end
+  def test_read
+    assert_equal(6,@ds.cases)
+    assert_equal(%w{id name age city a1}, @ds.fields)
+    id=[1,2,3,4,5,6].to_vector(:scale)
+    name=["Alex","Claude","Peter","Franz","George","Fernand"].to_vector(:nominal)
+    age=[20,23,25,27,5.5,nil].to_vector(:scale)
+    city=["New York","London","London","Paris","Tome",nil].to_vector(:nominal)
+    a1=["a,b","b,c","a",nil,"a,b,c",nil].to_vector(:nominal)
+    ds_exp=Statsample::Dataset.new({'id'=>id,'name'=>name,'age'=>age,'city'=>city,'a1'=>a1}, %w{id name age city a1})
+    ds_exp.fields.each{|f|
+      assert_equal(ds_exp[f],@ds[f])
+    }
+    assert_equal(ds_exp,@ds)
+  end
+  def test_nil
+    assert_equal(nil,@ds['age'][5])
+  end
+  def test_repeated
+    ds=Statsample::CSV.read(File.dirname(__FILE__)+"/../data/repeated_fields.csv")
+    assert_equal(%w{id name_1 age_1 city a1 name_2 age_2},ds.fields)
+    age=[3,4,5,6,nil,8].to_vector(:scale)
+    assert_equal(age,ds['age_2'])
+  end
+  def test_write
+    filename=Tempfile.new("afile")
+    #  filename=Dir::tmpdir+"/test_write.csv"
+    Statsample::CSV.write(@ds, filename.path)
+    ds2=Statsample::CSV.read(filename.path)
+    i=0
+    ds2.each_array{|row|
+      assert_equal(@ds.case_as_array(i),row)
+      i+=1
+    }
+  end
+end