statsample 0.5.0 → 0.5.1

data/lib/statsample/vector.rb

@@ -182,6 +182,22 @@ module Statsample
         }
         set_valid_data
     end
+    # Dicotomize the vector with 0 and 1, based on lowest value
+    # If parameter if defined, this value and lower
+    # will be 0 and higher, 1
+    def dichotomize(low=nil)
+      fs=factors
+      low||=factors.min
+      @data_with_nils.collect{|x|
+        if x.nil?
+          nil
+        elsif x>low
+          1
+        else
+          0
+        end
+      }.to_scale
+    end
     # Iterate on each item.
     # Equivalent to
     #   @data.each{|x| yield x}
@@ -190,7 +206,6 @@ module Statsample
     end
     
     # Iterate on each item, retrieving index
-    
     def each_index
         (0...@data.size).each {|i|
             yield(i)
@@ -520,7 +535,6 @@ module Statsample
     # Retrieves uniques values for data.
     def factors
         if @type==:scale
-            
             @scale_data.uniq.sort
         else
             @valid_data.uniq.sort

data/test/test_anova.rb

@@ -4,24 +4,24 @@ require 'test/unit'
 
 class StatsampleAnovaTestCase < Test::Unit::TestCase
 	def initialize(*args)
-        @v1=[3,3,2,3,6].to_vector(:scale)
-        @v2=[7,6,5,6,7].to_vector(:scale)
-        @v3=[9,8,9,7,8].to_vector(:scale)
-        @anova=Statsample::Anova::OneWay.new([@v1,@v2,@v3])
+    @v1=[3,3,2,3,6].to_vector(:scale)
+    @v2=[7,6,5,6,7].to_vector(:scale)
+    @v3=[9,8,9,7,8].to_vector(:scale)
+    @anova=Statsample::Anova::OneWay.new([@v1,@v2,@v3])
 		super
 	end
-    def test_basic
-        assert_in_delta(72.933, @anova.sst,0.001)
-        assert_in_delta(14.8,@anova.sswg,0.001)
-        assert_in_delta(58.133,@anova.ssbg,0.001)
-        assert_in_delta(@anova.sst,@anova.sswg+@anova.ssbg,0.00001)
-        assert_equal(14,@anova.df_total)
-        assert_equal(12,@anova.df_wg)
-        assert_equal(2,@anova.df_bg)
-        assert_in_delta(23.568,@anova.f,0.001)
-        anova2=Statsample::Anova::OneWay.new([@v1,@v1,@v1,@v1,@v2])
-        assert_in_delta(3.960, anova2.f,0.001)
+  def test_basic
+    assert_in_delta(72.933, @anova.sst,0.001)
+    assert_in_delta(14.8,@anova.sswg,0.001)
+    assert_in_delta(58.133,@anova.ssbg,0.001)
+    assert_in_delta(@anova.sst,@anova.sswg+@anova.ssbg,0.00001)
+    assert_equal(14,@anova.df_total)
+    assert_equal(12,@anova.df_wg)
+    assert_equal(2,@anova.df_bg)
+    assert_in_delta(23.568,@anova.f,0.001)
+    anova2=Statsample::Anova::OneWay.new([@v1,@v1,@v1,@v1,@v2])
+    assert_in_delta(3.960, anova2.f,0.001)
 		assert(@anova.significance<0.01)
 		assert_in_delta(0.016, anova2.significance,0.001)
-    end
+  end
 end

data/test/test_bivariate.rb

@@ -0,0 +1,146 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+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)
+      end
+      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
+#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)
+    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
+end

data/test/test_csv.rb

@@ -26,6 +26,12 @@ class StatsampleCSVTestCase < Test::Unit::TestCase
     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=Dir::tmpdir+"/test_write.csv"
         Statsample::CSV.write(@ds,filename)

data/test/test_dataset.rb

@@ -13,10 +13,10 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
         assert_equal(%w{id name age city a1}, @ds.fields)
     end
     def test_saveload
-            outfile=Dir::tmpdir+"/dataset.ds"
-            @ds.save(outfile)
-            a=Statsample.load(outfile)
-            assert_equal(@ds,a)
+      outfile=Dir::tmpdir+"/dataset.ds"
+      @ds.save(outfile)
+      a=Statsample.load(outfile)
+      assert_equal(@ds,a)
     end
 
     def test_matrix
@@ -31,6 +31,24 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
         @ds.fields=%w{id name age}
         assert_equal(%w{id name age a1 city}, @ds.fields) 
     end
+    def test_merge
+      a=[1,2,3].to_scale
+       b=[3,4,5].to_vector
+       c=[4,5,6].to_scale
+       d=[7,8,9].to_vector
+       e=[10,20,30].to_vector
+       ds1={'a'=>a,'b'=>b}.to_dataset       
+       ds2={'c'=>c,'d'=>d}.to_dataset       
+       exp={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
+       
+       assert_equal(exp,ds1.merge(ds2))
+       exp.fields=%w{c d a b}
+       assert_equal(exp,ds2.merge(ds1))
+       ds3={'a'=>e}.to_dataset
+       exp={'a_1'=>a,'b'=>b,'a_2'=>e}.to_dataset
+       exp.fields=%w{a_1 b a_2}
+       assert_equal(exp,ds1.merge(ds3))
+     end
     def test_each_vector
         a=[1,2,3].to_vector
         b=[3,4,5].to_vector
@@ -185,7 +203,18 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
         assert_equal([1,1,0,nil,1],@ds.col('a1_b').to_a)
         assert_equal([0,1,0,nil,1],@ds.col('a1_c').to_a)
     end
-    
+    def test_percentiles
+      v1=(1..100).to_a.to_scale
+      assert_equal(50.5,v1.median)
+      assert_equal(25.5, v1.percentil(25))
+      v2=(1..99).to_a.to_scale
+      assert_equal(50,v2.median)
+      assert_equal(25,v2.percentil(25))
+      v3=(1..50).to_a.to_scale
+      assert_equal(25.5, v3.median)
+      assert_equal(13, v3.percentil(25))
+      
+    end
     def test_add_case
         ds=Statsample::Dataset.new({'a'=>[].to_vector, 'b'=>[].to_vector, 'c'=>[].to_vector})
         ds.add_case([1,2,3])
@@ -326,5 +355,20 @@ class StatsampleDatasetTestCase < Test::Unit::TestCase
         assert_equal(vsum,ds.compute("v1+v2+v3"))
         assert_equal(vmult,ds.compute("v1*v2"))
         
+    end
+        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
+      ds=Statsample::Dataset.crosstab_by_asignation(v1,v2,v3)
+      assert_equal(:nominal, ds['_id'].type)
+      assert_equal(:scale, ds['a'].type)
+      assert_equal(:scale, ds['b'].type)
+      ev_id=%w{a b c}.to_vector
+      ev_a =%w{0 0 0}.to_scale
+      ev_b =%w{1 1 0}.to_scale
+      ev_c =%w{0 1 1}.to_scale
+      ds2={'_id'=>ev_id, 'a'=>ev_a, 'b'=>ev_b, 'c'=>ev_c}.to_dataset
+      assert_equal(ds, ds2)
     end
 end

data/test/test_statistics.rb

@@ -6,6 +6,11 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
 	def initialize(*args)
 		super
 	end
+  def test_recode_repeated
+    a=%w{a b c c d d d e}
+    exp=["a","b","c_1","c_2","d_1","d_2","d_3","e"]
+    assert_equal(exp,a.recode_repeated)
+  end
     def test_is_number
         assert("10".is_number?)
         assert("-10".is_number?)
@@ -30,96 +35,7 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
         chi=Statsample::Test.chi_square(real,expected)
         assert_in_delta(32.53,chi,0.1)
     end
-	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_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)
-    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)
-    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
+	
     def test_estimation_mean              
         v=([42]*23+[41]*4+[36]*1+[32]*1+[29]*1+[27]*2+[23]*1+[19]*1+[16]*2+[15]*2+[14,11,10,9,7]+ [6]*3+[5]*2+[4,3]).to_vector(:scale)
         assert_equal(50,v.size)

data/test/test_vector.rb

@@ -2,7 +2,9 @@ $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 require 'test/unit'
 require 'tmpdir'
-class StatsampleVectorTestCase < Test::Unit::TestCase
+class TestStatsample
+end
+class TestStatsample::TestVector < Test::Unit::TestCase
 
     def setup
 		@c = Statsample::Vector.new([5,5,5,5,5,6,6,7,8,9,10,1,2,3,4,nil,-99,-99], :nominal)
@@ -121,15 +123,15 @@ class StatsampleVectorTestCase < Test::Unit::TestCase
 		end
 	end
 	def test_nominal
-		assert_equal(@c[1],5)
-		assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c.frequencies)
-        assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c._frequencies)
-		assert_equal({ 1 => 1.quo(15) ,2=>1.quo(15), 3=>1.quo(15),4=>1.quo(15),5=>5.quo(15),6=>2.quo(15),7=>1.quo(15), 8=>1.quo(15), 9=>1.quo(15),10=>1.quo(15)}, @c.proportions)
-        assert_equal(@c.proportion, 1.quo(15))
-        assert_equal(@c.proportion(2), 1.quo(15))
-		assert_equal([1,2,3,4,5,6,7,8,9,10], @c.factors.sort)
-		assert_equal(@c.mode,5)
-		assert_equal(@c.n_valid,15)
+    assert_equal(@c[1],5)
+    assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c.frequencies)
+    assert_equal({ 1=>1,2=>1,3=>1,4=>1,5=>5,6=>2,7=>1,8=>1, 9=>1,10=>1},@c._frequencies)
+    assert_equal({ 1 => 1.quo(15) ,2=>1.quo(15), 3=>1.quo(15),4=>1.quo(15),5=>5.quo(15),6=>2.quo(15),7=>1.quo(15), 8=>1.quo(15), 9=>1.quo(15),10=>1.quo(15)}, @c.proportions)
+    assert_equal(@c.proportion, 1.quo(15))
+    assert_equal(@c.proportion(2), 1.quo(15))
+    assert_equal([1,2,3,4,5,6,7,8,9,10], @c.factors.sort)
+    assert_equal(@c.mode,5)
+    assert_equal(@c.n_valid,15)
 	end
     def test_equality
         v1=[1,2,3].to_vector
@@ -328,4 +330,19 @@ class StatsampleVectorTestCase < Test::Unit::TestCase
         expected=[2,2,2,4.5,4.5,6,7.5,7.5,10,10,10].to_vector(:ordinal)
         assert_equal(expected,a.ranked)
     end
+    def test_dichotomize
+      a=  [0,0,0,1,2,3,nil].to_vector
+      exp=[0,0,0,1,1,1,nil].to_scale
+      assert_equal(exp,a.dichotomize)
+      a=  [1,1,1,2,2,2,3].to_vector
+      exp=[0,0,0,1,1,1,1].to_scale
+      assert_equal(exp,a.dichotomize)      
+      a=  [0,0,0,1,2,3,nil].to_vector
+      exp=[0,0,0,0,1,1,nil].to_scale
+      assert_equal(exp,a.dichotomize(1))
+      a= %w{a a a b c d}.to_vector
+      exp=[0,0,0,1,1,1].to_scale
+      assert_equal(exp, a.dichotomize)
+    end
+
 end