statsample 0.5.1 → 0.6.0

data/test/test_bivariate.rb

@@ -3,144 +3,144 @@ require 'statsample'
 require 'test/unit'
 class StatsampleBivariateTestCase < Test::Unit::TestCase
   def test_sum_of_codeviated
-		v1=[1,2,3,4,5,6].to_vector(:scale)
-		v2=[6,2,4,10,12,8].to_vector(:scale)
-		assert_equal(23.0, Statsample::Bivariate.sum_of_codeviated(v1,v2))
-	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)
-        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)
-    end
-    def test_tetrachoric_matrix
-      ds=Statsample::PlainText.read(File.dirname(__FILE__)+"/../data/tetmat_test.txt", %w{a b c d e})
-      tcm_obs=Statsample::Bivariate.tetrachoric_correlation_matrix(ds)
-      tcm_exp=Statsample::PlainText.read(File.dirname(__FILE__)+"/../data/tetmat_matrix.txt", %w{a b c d e}).to_matrix
-      tcm_obs.row_size.times {|i|
-        tcm_obs.column_size {|j|
-          assert_in_delta(tcm_obs[i,j], tcm_exp[i,k], 0.00001)
-        }
-      }
-    end
-    def test_tetrachoric
-      a,b,c,d=0,0,0,0
-      assert_raise RuntimeError do
-        tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
-      end
-      a,b,c,d=10,10,0,0
-      assert_raise RuntimeError do
-        tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
-      end
-      a,b,c,d=10,0,10,0
-      assert_raise RuntimeError do
-        tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
+    v1=[1,2,3,4,5,6].to_vector(:scale)
+    v2=[6,2,4,10,12,8].to_vector(:scale)
+    assert_equal(23.0, Statsample::Bivariate.sum_of_codeviated(v1,v2))
+  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)
+    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)
+  end
+  def test_tetrachoric_matrix
+    ds=Statsample::PlainText.read(File.dirname(__FILE__)+"/../data/tetmat_test.txt", %w{a b c d e})
+    tcm_obs=Statsample::Bivariate.tetrachoric_correlation_matrix(ds)
+    tcm_exp=Statsample::PlainText.read(File.dirname(__FILE__)+"/../data/tetmat_matrix.txt", %w{a b c d e}).to_matrix
+    tcm_obs.row_size.times do |i|
+      tcm_obs.column_size do |j|
+        assert_in_delta(tcm_obs[i,j], tcm_exp[i,k], 0.00001)
       end
-      a,b,c,d=10,0,0,10
+    end
+  end
+  def test_tetrachoric
+    a,b,c,d=0,0,0,0
+    assert_raise RuntimeError do
       tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
-      assert_equal(1,tc.r)
-      assert_equal(0,tc.se)
-      a,b,c,d=0,10,10,0
+    end
+    a,b,c,d=10,10,0,0
+    assert_raise RuntimeError do
       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
+    end
+    a,b,c,d=10,0,10,0
+    assert_raise RuntimeError do
       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)
-      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
-      #    0    1
-      # a  4    3
-      # b  2    5
-      a,b,c,d=4,3,2,5
-      tc1  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
-      tc2  = Statsample::Bivariate::Tetrachoric.new_with_vectors(x,y)
-      assert_equal(tc1.r,tc2.r)
-      assert_equal(tc1.se,tc2.se)
-      
     end
-    def test_matrix_correlation
-        v1=[6,5,4,7,8,4,3,2].to_vector(:scale)
-        v2=[2,3,7,8,6,4,3,2].to_vector(:scale)
-        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)} 
-        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)]
-        ]
-	obt=Statsample::Bivariate.correlation_matrix(ds)
-	for i in 0...expected.row_size
-	for j in 0...expected.column_size
-		#puts expected[i,j].inspect
-		#puts obt[i,j].inspect
-		assert_in_delta(expected[i,j], obt[i,j],0.0001,"#{expected[i,j].class}!=#{obt[i,j].class}  ")
-	end
-	end
-#assert_equal(expected,obt)
+    a,b,c,d=10,0,0,10
+    tc  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
+    assert_equal(1,tc.r)
+    assert_equal(0,tc.se)
+    a,b,c,d=0,10,10,0
+    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)
+    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)
+    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
+    #    0    1
+    # a  4    3
+    # b  2    5
+    a,b,c,d=4,3,2,5
+    tc1  = Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
+    tc2  = Statsample::Bivariate::Tetrachoric.new_with_vectors(x,y)
+    assert_equal(tc1.r,tc2.r)
+    assert_equal(tc1.se,tc2.se)
+    
+  end
+  def test_matrix_correlation
+    v1=[6,5,4,7,8,4,3,2].to_vector(:scale)
+    v2=[2,3,7,8,6,4,3,2].to_vector(:scale)
+    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)} 
+    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)]
+    ]
+    obt=Statsample::Bivariate.correlation_matrix(ds)
+    for i in 0...expected.row_size
+      for j in 0...expected.column_size
+        #puts expected[i,j].inspect
+        #puts obt[i,j].inspect
+        assert_in_delta(expected[i,j], obt[i,j],0.0001,"#{expected[i,j].class}!=#{obt[i,j].class}  ")
+      end
     end
-    def test_prop_pearson
-        assert_in_delta(0.42, Statsample::Bivariate.prop_pearson(Statsample::Bivariate.t_r(0.084,94), 94),0.01)
-        assert_in_delta(0.65, Statsample::Bivariate.prop_pearson(Statsample::Bivariate.t_r(0.046,95), 95),0.01)
-        r=0.9
-        n=100
-        t=Statsample::Bivariate.t_r(r,n)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:both)<0.05)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:right)<0.05)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:left)>0.05)
+    #assert_equal(expected,obt)
+  end
+  def test_prop_pearson
+    assert_in_delta(0.42, Statsample::Bivariate.prop_pearson(Statsample::Bivariate.t_r(0.084,94), 94),0.01)
+    assert_in_delta(0.65, Statsample::Bivariate.prop_pearson(Statsample::Bivariate.t_r(0.046,95), 95),0.01)
+    r=0.9
+    n=100
+    t=Statsample::Bivariate.t_r(r,n)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:both)<0.05)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:right)<0.05)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:left)>0.05)
 
-        r=-0.9
-        n=100
-        t=Statsample::Bivariate.t_r(r,n)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:both)<0.05)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:right)>0.05)
-        assert(Statsample::Bivariate.prop_pearson(t,n,:left)<0.05)
+    r=-0.9
+    n=100
+    t=Statsample::Bivariate.t_r(r,n)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:both)<0.05)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:right)>0.05)
+    assert(Statsample::Bivariate.prop_pearson(t,n,:left)<0.05)
+  end
+  def test_covariance
+  if HAS_GSL
+    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(Statsample::Bivariate.covariance(v1,v2), Statsample::Bivariate.covariance_slow(v1,v2), 0.001)
+    
+  end
+  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)
+    d=[1,1,1,1,1,0,0,0,0,0].to_vector(:scale)
+    assert_raise TypeError do
+      Statsample::Bivariate.point_biserial(c,d)
     end
-	def test_covariance
-		if HAS_GSL
-			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(Statsample::Bivariate.covariance(v1,v2), Statsample::Bivariate.covariance_slow(v1,v2), 0.001)
-			
-		end
-	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)
-		d=[1,1,1,1,1,0,0,0,0,0].to_vector(:scale)
-		assert_raise TypeError do
-			Statsample::Bivariate.point_biserial(c,d)
-		end
-		assert_in_delta(Statsample::Bivariate.point_biserial(d,c), Statsample::Bivariate.pearson(d,c), 0.0001)
-	end
-	def test_tau
-		v1=[1,2,3,4,5,6,7,8,9,10,11].to_vector(:ordinal)
-		v2=[1,3,4,5,7,8,2,9,10,6,11].to_vector(:ordinal)
-		assert_in_delta(0.6727,Statsample::Bivariate.tau_a(v1,v2),0.001)
-		assert_in_delta(0.6727,Statsample::Bivariate.tau_b((Statsample::Crosstab.new(v1,v2).to_matrix)),0.001)
-		v1=[12,14,14,17,19,19,19,19,19,20,21,21,21,21,21,22,23,24,24,24,26,26,27].to_vector(:ordinal)
-		v2=[11,4,4,2,0,0,0,0,0,0,4,0,4,0,0,0,0,4,0,0,0,0,0].to_vector(:ordinal)
-		assert_in_delta(-0.376201540231705, Statsample::Bivariate.tau_b(Statsample::Crosstab.new(v1,v2).to_matrix),0.001)
-	end
-	def test_gamma
-		m=Matrix[[10,5,2],[10,15,20]]
-		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
+    assert_in_delta(Statsample::Bivariate.point_biserial(d,c), Statsample::Bivariate.pearson(d,c), 0.0001)
+  end
+  def test_tau
+    v1=[1,2,3,4,5,6,7,8,9,10,11].to_vector(:ordinal)
+    v2=[1,3,4,5,7,8,2,9,10,6,11].to_vector(:ordinal)
+    assert_in_delta(0.6727,Statsample::Bivariate.tau_a(v1,v2),0.001)
+    assert_in_delta(0.6727,Statsample::Bivariate.tau_b((Statsample::Crosstab.new(v1,v2).to_matrix)),0.001)
+    v1=[12,14,14,17,19,19,19,19,19,20,21,21,21,21,21,22,23,24,24,24,26,26,27].to_vector(:ordinal)
+    v2=[11,4,4,2,0,0,0,0,0,0,4,0,4,0,0,0,0,4,0,0,0,0,0].to_vector(:ordinal)
+    assert_in_delta(-0.376201540231705, Statsample::Bivariate.tau_b(Statsample::Crosstab.new(v1,v2).to_matrix),0.001)
+  end
+  def test_gamma
+    m=Matrix[[10,5,2],[10,15,20]]
+    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

@@ -1,60 +1,81 @@
 $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 require 'tempfile'
+require 'tmpdir'
 require 'test/unit'
 
 class StatsampleCodificationTestCase < Test::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
-	end
-    def test_create_yaml
-        assert_raise  ArgumentError do
-            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'])
-        h=YAML::load(yaml_hash)
-        assert_equal(['v1'],h.keys)
-        assert_equal(expected_keys_v1,h['v1'].keys.sort)
-        tf = Tempfile.new("test_codification")
-        yaml_hash=Statsample::Codification.create_yaml(@ds,['v1'],Statsample::SPLIT_TOKEN,tf)
-        tf.close
-        tf.open
-        h=YAML::load(tf)
-        assert_equal(['v1'],h.keys)
-        assert_equal(expected_keys_v1,h['v1'].keys.sort)
-        tf.close(true)
-    end
-    def test_recodification
-        expected=[['r'],['w','r'],['w'],['r'],['s'],['s','d'], ['s','d']]
-        assert_equal(expected,Statsample::Codification.recode_vector(@ds['v1'],@dict))
-        v2=['run','walk,dreaming',nil,'walk,dream,dreaming,walking'].to_vector
-        expected=[['r'],['w','d'],nil,['w','d']]
-        assert_equal(expected,Statsample::Codification.recode_vector(v2,@dict))
-    end
-    def test_recode_dataset_simple
-        yaml=YAML::dump({'v1'=>@dict})
-        Statsample::Codification.recode_dataset_simple!(@ds,yaml)
-        expected_vector=['r','w,r','w','r','s','s,d', 's,d'].to_vector
-        assert_not_equal(expected_vector,@ds['v1'])
-        assert_equal(expected_vector,@ds['v1_recoded'])
-    end
-    def test_recode_dataset_split
-        yaml=YAML::dump({'v1'=>@dict})
-        Statsample::Codification.recode_dataset_split!(@ds,yaml)
-        e={}
-        e['r']=[1,1,0,1,0,0,0].to_vector
-        e['w']=[0,1,1,0,0,0,0].to_vector
-        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}")
-
-        }
+  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
+  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(expected_keys_v1,hash['v1'].keys.sort)
+    assert_equal(expected_keys_v1,hash['v1'].values.sort)
+  end
+  def test_create_excel
+    filename=Dir::tmpdir+"/test_excel"+Time.now().to_s+".xls"
+    #filename = Tempfile.new("test_codification_"+Time.now().to_s)
+    Statsample::Codification.create_excel(@ds, ['v1'], filename)
+    field=(["v1"]*8).to_vector
+    keys=%w{dream dreaming run running sleep sleeping walk walking}.to_vector
+    ds=Statsample::Excel.read(filename)
+    assert_equal(field, ds['field'])
+    assert_equal(keys, ds['original'])
+    assert_equal(keys, ds['recoded'])
+    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,[])
     end
+    expected_keys_v1=%w{run walk walking running sleep sleeping dream dreaming}.sort
+    yaml_hash=Statsample::Codification.create_yaml(@ds,['v1'])
+    h=YAML::load(yaml_hash)
+    assert_equal(['v1'],h.keys)
+    assert_equal(expected_keys_v1,h['v1'].keys.sort)
+    tf = Tempfile.new("test_codification")
+    yaml_hash=Statsample::Codification.create_yaml(@ds,['v1'],tf, Statsample::SPLIT_TOKEN)
+    tf.close
+    tf.open
+    h=YAML::load(tf)
+    assert_equal(['v1'],h.keys)
+    assert_equal(expected_keys_v1,h['v1'].keys.sort)
+    tf.close(true)
+  end
+  def test_recodification
+    expected=[['r'],['w','r'],['w'],['r'],['s'],['s','d'], ['s','d']]
+    assert_equal(expected,Statsample::Codification.recode_vector(@ds['v1'],@dict))
+    v2=['run','walk,dreaming',nil,'walk,dream,dreaming,walking'].to_vector
+    expected=[['r'],['w','d'],nil,['w','d']]
+    assert_equal(expected,Statsample::Codification.recode_vector(v2,@dict))
+  end
+  def test_recode_dataset_simple
+    Statsample::Codification.recode_dataset_simple!(@ds,{'v1'=>@dict})
+    expected_vector=['r','w,r','w','r','s','s,d', 's,d'].to_vector
+    assert_not_equal(expected_vector,@ds['v1'])
+    assert_equal(expected_vector,@ds['v1_recoded'])
+  end
+  def test_recode_dataset_split
+    Statsample::Codification.recode_dataset_split!(@ds,{'v1'=>@dict})
+    e={}
+    e['r']=[1,1,0,1,0,0,0].to_vector
+    e['w']=[0,1,1,0,0,0,0].to_vector
+    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}")
+  
+    }
+  end
 
 end

data/test/test_dataset.rb

@@ -356,7 +356,7 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
         assert_equal(vmult,ds.compute("v1*v2"))
         
     end
-        def test_crosstab_with_asignation
+    def test_crosstab_with_asignation
       v1=%w{a a a b b b c c c}.to_vector
       v2=%w{a b c a b c a b c}.to_vector
       v3=%w{0 1 0 0 1 1 0 0 1}.to_scale
@@ -371,4 +371,22 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
       ds2={'_id'=>ev_id, 'a'=>ev_a, 'b'=>ev_b, 'c'=>ev_c}.to_dataset
       assert_equal(ds, ds2)
     end
+    def test_one_to_many
+      cases=[
+        ['1','george','red',10,'blue',20,nil,nil],
+        ['2','fred','green',15,'orange',30,'white',20],
+        ['3','alfred',nil,nil,nil,nil,nil,nil]
+      ]
+      ds=Statsample::Dataset.new(%w{id name car_color1 car_value1 car_color2 car_value2 car_color3 car_value3})
+      cases.each {|c| ds.add_case_array c }
+      ds.update_valid_data
+      ids=%w{1 1 2 2 2}.to_vector
+      colors=%w{red blue green orange white}.to_vector
+      values=[10,20,15,30,20].to_vector
+      col_ids=[1,2,1,2,3].to_scale
+      ds_expected={'id'=>ids, '_col_id'=>col_ids, 'color'=>colors, 'value'=>values}.to_dataset(['id','_col_id', 'color','value'])
+      assert_equal(ds_expected, ds.one_to_many(%w{id}, "car_%v%n"))
+      
+    end
+    
 end

data/test/test_factor.rb

@@ -0,0 +1,44 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+require 'test/unit'
+require 'matrix_extension'
+class StatsampleFactorTestCase < Test::Unit::TestCase
+    def test_pca
+      require 'gsl'
+      a=[2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1].to_scale
+      b=[2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9].to_scale
+      a.recode! {|c| c-a.mean}
+      b.recode! {|c| c-b.mean}
+      ds={'a'=>a,'b'=>b}.to_dataset
+      cov_matrix=Statsample::Bivariate.covariance_matrix(ds)
+      pca=Statsample::Factor::PCA.new(cov_matrix)
+      expected_eigenvalues=[1.284, 0.0490]
+      expected_eigenvalues.each_with_index{|ev,i|
+        assert_in_delta(ev,pca.eigenvalues[i],0.001)
+      }
+      expected_fm_1=GSL::Matrix[[0.677], [0.735]]
+      expected_fm_2=GSL::Matrix[[0.677,0.735], [0.735, -0.677]]
+      _test_matrix(expected_fm_1,pca.feature_vector(1))
+      _test_matrix(expected_fm_2,pca.feature_vector(2))
+    end
+    def test_rotation_varimax
+      a = Matrix[ [ 0.4320,  0.8129,  0.3872]  ,
+       [0.7950, -0.5416,  0.2565]  ,
+       [0.5944,  0.7234, -0.3441],
+       [0.8945, -0.3921, -0.1863] ]
+       expected= Matrix[[-0.0204423,     0.938674,    -0.340334],
+       [0.983662, 0.0730206, 0.134997],
+       [0.0826106, 0.435975, -0.893379],
+       [0.939901, -0.0965213, -0.309596]].to_gsl
+       varimax=Statsample::Factor::Varimax.new(a)
+       varimax.iterate
+       _test_matrix(expected,varimax.rotated)
+    end
+    def _test_matrix(a,b)
+      a.size1.times {|i|
+        a.size2.times {|j|
+          assert_in_delta(a[i,j], b[i,j],0.001)
+        }
+      }
+    end
+end