statsample 0.7.0 → 0.8.0

data/test/test_dominance_analysis.rb

@@ -1,15 +1,13 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleCSVTestCase < Test::Unit::TestCase
+class StatsampleDominanceAnalysisTestCase < MiniTest::Unit::TestCase
   def aatest_dominance_univariate
     # Example from Budescu (1993)
     m=Matrix[[1, 0.683, 0.154, 0.460, 0.618],[0.683, 1, -0.050, 0.297, 0.461], [0.154, -0.050, 1, 0.006, 0.262],[0.460, 0.297, 0.006, 1, 0.507],[0.618, 0.461, 0.262, 0.507, 1]]
     m.extend Statsample::CovariateMatrix
     m.fields=%w{x1 x2 x3 x4 y}
     da=Statsample::DominanceAnalysis.new(m,'y')
-    
+
     contr_x1={'x2'=>0.003, 'x3'=>0.028, 'x4'=>0.063}
     contr_x1.each  do |k,v|
       assert_in_delta(v, da.models_data[['x1']].contributions[k], 0.001)
@@ -23,21 +21,21 @@ class StatsampleCSVTestCase < Test::Unit::TestCase
       assert_equal(expected_dominances[i], da.conditional_dominance_pairwise(a[0],a[1]))
       assert_equal(expected_g_dominances[i], da.general_dominance_pairwise(a[0],a[1]))
     end
-  end    
+  end
   def test_dominance_multivariate
     m=Matrix[[1.0, -0.19, -0.358, -0.343, 0.359, 0.257], [-0.19, 1.0, 0.26, 0.29, -0.11, -0.11], [-0.358, 0.26, 1.0, 0.54, -0.49, -0.23], [-0.343, 0.29, 0.54, 1.0, -0.22, -0.41], [0.359, -0.11, -0.49, -0.22, 1.0, 0.62], [0.257, -0.11, -0.23, -0.41, 0.62, 1]]
     m.extend Statsample::CovariateMatrix
     m.fields=%w{y1 y2 x1 x2 x3 x4}
     m2=m.submatrix(%w{y1 x1 x2 x3 x4})
-        
-    
+
+
     da=Statsample::DominanceAnalysis.new(m, ['y1','y2'], :cases=>683, :method_association=>:p2yx)
-    
+
     contr_x1={'x2'=>0.027, 'x3'=>0.024, 'x4'=>0.017}
     contr_x1.each  do |k,v|
       assert_in_delta(v, da.models_data[['x1']].contributions[k], 0.003)
     end
-    
-    
+
+
   end
-end
+end

data/test/test_factor.rb

@@ -1,98 +1,102 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
-class StatsampleFactorTestCase < Test::Unit::TestCase
-    # Tested with SPSS and R
-    def test_pca
-      if Statsample.has_gsl?
-        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_communality=[0.590, 0.694]
-        expected_communality.each_with_index{|ev,i|
-          assert_in_delta(ev,pca.communalities[i],0.001)
-        }
-        expected_cm=[0.768, 0.833]
-        
-        obs=pca.component_matrix(1).column(0).to_a
-        expected_cm.each_with_index{|ev,i|
-          assert_in_delta(ev,obs[i],0.001)
-        }
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-        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))
-        assert(pca.summary)
-      else
-        puts "PCA not tested. Requires GSL"
-      end
+class StatsampleFactorTestCase < MiniTest::Unit::TestCase
+  # Tested with SPSS and R
+  def test_pca
+    if Statsample.has_gsl?
+      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_communality=[0.590, 0.694]
+      expected_communality.each_with_index{|ev,i|
+        assert_in_delta(ev,pca.communalities[i],0.001)
+      }
+      expected_cm=[0.768, 0.833]
+
+      obs=pca.component_matrix(1).column(0).to_a
+      expected_cm.each_with_index{|ev,i|
+        assert_in_delta(ev,obs[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))
+      assert(pca.summary)
+    else
+      puts "PCA not tested. Requires GSL"
     end
-    
-    # Tested with R
-    def test_principalaxis
-      if Statsample.has_gsl?
-        require 'gsl'
-        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]]
-        fa=Statsample::Factor::PrincipalAxis.new(matrix,:m=>1)
-        cm=Matrix[[0.923],[0.912],[0.507],[0.483]].to_gsl
-        _test_matrix(cm,fa.component_matrix)
-        h2=[0.852,0.832,0.257,0.233]
-        h2.each_with_index{|ev,i|
-          assert_in_delta(ev,fa.communalities[i],0.001)
-        }
-        eigen1=2.175
-        assert_in_delta(eigen1, fa.eigenvalues[0],0.001)
-        
-        fa=Statsample::Factor::PrincipalAxis.new(matrix,:smc=>false)
-        assert_raise RuntimeError do
-          fa.iterate
-          
-        end
-        
-        
-        
-        assert(fa.summary)
-        
-      else
-        puts "Principal Axis not tested. Requires GSL"
+  end
+
+  # Tested with R
+  def test_principalaxis
+    if Statsample.has_gsl?
+      require 'gsl'
+      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]]
+      fa=Statsample::Factor::PrincipalAxis.new(matrix,:m=>1)
+      
+      cm=Matrix[[0.923],[0.912],[0.507],[0.483]].to_gsl
+      
+      _test_matrix(cm,fa.component_matrix)
+      
+      h2=[0.852,0.832,0.257,0.233]
+      h2.each_with_index{|ev,i|
+        assert_in_delta(ev,fa.communalities[i],0.001)
+      }
+      eigen1=2.175
+      assert_in_delta(eigen1, fa.eigenvalues[0],0.001)
+
+      fa=Statsample::Factor::PrincipalAxis.new(matrix,:smc=>false)
+      assert_raise RuntimeError do
+        fa.iterate
+
       end
+
+
+
+      assert(fa.summary)
+
+    else
+      puts "Principal Axis not tested. Requires GSL"
     end
-    
-    
-    def test_rotation_varimax
-      if Statsample.has_gsl?
-        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)
-      else
-        puts "Rotation not tested. Requires GSL"
-      end
+  end
+
+
+  def test_rotation_varimax
+    if Statsample.has_gsl?
+      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)
+      refute(varimax.rotated.nil?,"Rotated shouldn't be empty")
+      refute(varimax.component_transformation_matrix.nil?, "Component matrix shouldn't be empty")
+      refute(varimax.h2.nil?,"H2 shouldn't be empty")
+      _test_matrix(expected,varimax.rotated)
+    else
+      puts "Rotation not tested. Requires GSL"
     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
+  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
 end

data/test/test_ggobi.rb

@@ -1,27 +1,24 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
+require 'ostruct'
+class StatsampleGGobiTestCase < MiniTest::Unit::TestCase
 
-class StatsampleGGobiTestCase < Test::Unit::TestCase
-
-	def initialize(*args)
-		super
-		v1=([10.2,20.3,10,20,30,40,30,20,30,40]*10).to_vector(:scale)
-		@v2=(%w{a b c a a a b b c d}*10).to_vector(:nominal)
-		@v2.labels={"a"=>"letter a","d"=>"letter d"}
-		v3=([1,2,3,4,5,4,3,2,1,2]*10).to_vector(:ordinal)
-		@ds={'v1'=>v1,'v2'=>@v2,'v3'=>v3}.to_dataset
-	end
-	def test_values_definition
-		a=[1.0,2,"a",nil]
-		assert_equal("1.0 2 a NA", Statsample::GGobi.values_definition(a,"NA"))
-	end
-	def test_variable_definition
-		carrier=OpenStruct.new
-		carrier.categorials=[]
-		carrier.conversions={}
-		real_var_definition=Statsample::GGobi.variable_definition(carrier,@v2,'variable 2',"v2")
-		expected=<<EOS
+  def setup
+    v1=([10.2,20.3,10,20,30,40,30,20,30,40]*10).to_vector(:scale)
+    @v2=(%w{a b c a a a b b c d}*10).to_vector(:nominal)
+    @v2.labels={"a"=>"letter a","d"=>"letter d"}
+    v3=([1,2,3,4,5,4,3,2,1,2]*10).to_vector(:ordinal)
+    @ds={'v1'=>v1,'v2'=>@v2,'v3'=>v3}.to_dataset
+  end
+  def test_values_definition
+    a=[1.0,2,"a",nil]
+    assert_equal("1.0 2 a NA", Statsample::GGobi.values_definition(a,"NA"))
+  end
+  def test_variable_definition
+    carrier=OpenStruct.new
+    carrier.categorials=[]
+    carrier.conversions={}
+    real_var_definition=Statsample::GGobi.variable_definition(carrier,@v2,'variable 2',"v2")
+		expected=<<-EOS
 <categoricalvariable name="variable 2" nickname="v2">
 <levels count="4">
 <level value="1">letter a</level>
@@ -29,14 +26,14 @@ class StatsampleGGobiTestCase < Test::Unit::TestCase
 <level value="3">c</level>
 <level value="4">letter d</level></levels>
 </categoricalvariable>
-EOS
-assert_equal(expected.gsub(/\s/," "),real_var_definition.gsub(/\s/," "))
-assert_equal({'variable 2'=>{'a'=>1,'b'=>2,'c'=>3,'d'=>4}},carrier.conversions)
-	assert_equal(['variable 2'],carrier.categorials)
-	end
-	def test_out
-		filename="/tmp/test_statsample_ggobi.xml"
-		go=Statsample::GGobi.out(@ds)
-		
-	end
+    EOS
+    assert_equal(expected.gsub(/\s/," "),real_var_definition.gsub(/\s/," "))
+    assert_equal({'variable 2'=>{'a'=>1,'b'=>2,'c'=>3,'d'=>4}},carrier.conversions)
+    assert_equal(['variable 2'],carrier.categorials)
+  end
+  def test_out
+    filename="/tmp/test_statsample_ggobi.xml"
+    go=Statsample::GGobi.out(@ds)
+
+  end
 end

data/test/test_gsl.rb

@@ -1,7 +1,7 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
-class StatsampleGSLTestCase < Test::Unit::TestCase
+require(File.dirname(__FILE__)+'/test_helpers.rb')
+
+
+class StatsampleGSLTestCase < MiniTest::Unit::TestCase
   def test_matrix_to_gsl
     if Statsample.has_gsl?
       a=[1,2,3,4,20].to_vector(:scale)

data/test/test_helpers.rb

@@ -0,0 +1,26 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+require 'minitest/unit'
+require 'tempfile'
+require 'tmpdir'
+
+module MiniTest::Assertions
+  alias :assert_raise :assert_raises unless method_defined? :assert_raise
+  alias :assert_not_equal :refute_equal unless method_defined? :assert_not_equal
+  alias :assert_not_same :refute_same unless method_defined? :assert_not_same
+  unless method_defined? :assert_nothing_raised
+    def assert_nothing_raised(msg=nil)
+      msg||="Nothing should be raised, but raised %s"
+      begin
+        yield
+        not_raised=true
+      rescue Exception => e
+        not_raised=false
+        msg=sprintf(msg,e)
+      end
+      assert(not_raised,msg)
+    end
+  end
+end
+
+MiniTest::Unit.autorun

data/test/test_histogram.rb

@@ -1,9 +1,8 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'tmpdir'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleHistogramTestCase < Test::Unit::TestCase
+
+
+class StatsampleHistogramTestCase < MiniTest::Unit::TestCase
   def test_control
     h = Statsample::Histogram.alloc(4)
     assert_equal([0.0]*4, h.bin)
@@ -23,4 +22,4 @@ class StatsampleHistogramTestCase < Test::Unit::TestCase
     h.increment(5)
     assert_equal([3.0,0.0,1.0,2.0,0.0], h.bin)
   end
-end
+end

data/test/test_logit.rb

@@ -1,22 +1,21 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
-class StatsampleLogitTestCase < Test::Unit::TestCase
-    def test_logit_1
-        crime=File.dirname(__FILE__)+'/../data/test_binomial.csv'
-        ds=Statsample::CSV.read(crime)
-        lr=Statsample::Regression::Binomial::Logit.new(ds,'y')
-        assert_in_delta(-38.8669,lr.log_likehood,0.001)
-        assert_in_delta(-5.3658,lr.constant,0.001)
-        
-        exp_coeffs={"a"=>0.3270,"b"=>0.8147, "c"=>-0.4031}
-        exp_coeffs.each{|k,v|
-            assert_in_delta(v,lr.coeffs[k],0.001)
-        }
-        exp_errors={'a'=>0.4390,'b'=>0.4270,'c'=>0.3819}
-        exp_errors.each{|k,v|
-            assert_in_delta(v,lr.coeffs_se[k],0.001)
-        }
-        assert_equal(7,lr.iterations)               
-    end
+require(File.dirname(__FILE__)+'/test_helpers.rb')
+
+class StatsampleLogitTestCase < MiniTest::Unit::TestCase
+  def test_logit_1
+    crime=File.dirname(__FILE__)+'/../data/test_binomial.csv'
+    ds=Statsample::CSV.read(crime)
+    lr=Statsample::Regression::Binomial::Logit.new(ds,'y')
+    assert_in_delta(-38.8669,lr.log_likehood,0.001)
+    assert_in_delta(-5.3658,lr.constant,0.001)
+
+    exp_coeffs={"a"=>0.3270,"b"=>0.8147, "c"=>-0.4031}
+    exp_coeffs.each{|k,v|
+      assert_in_delta(v,lr.coeffs[k],0.001)
+    }
+    exp_errors={'a'=>0.4390,'b'=>0.4270,'c'=>0.3819}
+    exp_errors.each{|k,v|
+      assert_in_delta(v,lr.coeffs_se[k],0.001)
+    }
+    assert_equal(7,lr.iterations)
+  end
 end

data/test/test_matrix.rb

@@ -1,51 +1,50 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'test/unit'
-require 'statsample'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleMatrixTestCase < Test::Unit::TestCase
-        
-    def setup
-    end
-    def test_subindex
-      matrix=Matrix[[1,2,3],[4,5,6],[7,8,9]]
-      assert_equal(5, matrix[1,1])
-      assert_equal(Matrix[[1,2,3]], matrix[0,:*])
-      assert_equal(Matrix[[1],[4],[7]], matrix[:*,0])
-      assert_equal(Matrix[[1,2],[4,5],[7,8]], matrix[:*,0..1])
-      assert_equal(Matrix[[1,2],[4,5]], matrix[0..1,0..1])
-    end
-    def test_sums
-      matrix=Matrix[[1,2,3],[4,5,6],[7,8,9]]
-      assert_equal(6,matrix.row_sum[0])
-      assert_equal(12,matrix.column_sum[0])
-      assert_equal(45,matrix.total_sum)
-    end
-    def test_covariate
-      a=Matrix[[1.0, 0.3, 0.2], [0.3, 1.0, 0.5], [0.2, 0.5, 1.0]]
-      a.extend Statsample::CovariateMatrix
-      a.fields=%w{a b c}
-      assert_equal(:correlation, a.type)
-      
-      assert_equal(Matrix[[0.5],[0.3]], a.submatrix(%w{c a}, %w{b}))
-      assert_equal(Matrix[[1.0, 0.2] , [0.2, 1.0]], a.submatrix(%w{c a}))
-      assert_equal(:correlation, a.submatrix(%w{c a}).type)
-      
-      a=Matrix[[20,30,10], [30,60,50], [10,50,50]]
-      
-      a.extend Statsample::CovariateMatrix
-      
-      assert_equal(:covariance, a.type)
-      
-      a=100.times.collect {rand()}.to_scale
-      b=100.times.collect {rand()}.to_scale
-      c=100.times.collect {rand()}.to_scale
-      ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
-      corr=Statsample::Bivariate.correlation_matrix(ds)
-      real=Statsample::Bivariate.covariance_matrix(ds).correlation
-      corr.row_size.times do |i|
-        corr.column_size.times do |j|
-          assert_in_delta(corr[i,j], real[i,j],1e-15)
-        end
+
+class StatsampleMatrixTestCase < MiniTest::Unit::TestCase
+
+  def setup
+  end
+  def test_subindex
+    matrix=Matrix[[1,2,3],[4,5,6],[7,8,9]]
+    assert_equal(5, matrix[1,1])
+    assert_equal(Matrix[[1,2,3]], matrix[0,:*])
+    assert_equal(Matrix[[1],[4],[7]], matrix[:*,0])
+    assert_equal(Matrix[[1,2],[4,5],[7,8]], matrix[:*,0..1])
+    assert_equal(Matrix[[1,2],[4,5]], matrix[0..1,0..1])
+  end
+  def test_sums
+    matrix=Matrix[[1,2,3],[4,5,6],[7,8,9]]
+    assert_equal(6,matrix.row_sum[0])
+    assert_equal(12,matrix.column_sum[0])
+    assert_equal(45,matrix.total_sum)
+  end
+  def test_covariate
+    a=Matrix[[1.0, 0.3, 0.2], [0.3, 1.0, 0.5], [0.2, 0.5, 1.0]]
+    a.extend Statsample::CovariateMatrix
+    a.fields=%w{a b c}
+    assert_equal(:correlation, a.type)
+
+    assert_equal(Matrix[[0.5],[0.3]], a.submatrix(%w{c a}, %w{b}))
+    assert_equal(Matrix[[1.0, 0.2] , [0.2, 1.0]], a.submatrix(%w{c a}))
+    assert_equal(:correlation, a.submatrix(%w{c a}).type)
+
+    a=Matrix[[20,30,10], [30,60,50], [10,50,50]]
+
+    a.extend Statsample::CovariateMatrix
+
+    assert_equal(:covariance, a.type)
+
+    a=100.times.collect {rand()}.to_scale
+    b=100.times.collect {rand()}.to_scale
+    c=100.times.collect {rand()}.to_scale
+    ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
+    corr=Statsample::Bivariate.correlation_matrix(ds)
+    real=Statsample::Bivariate.covariance_matrix(ds).correlation
+    corr.row_size.times do |i|
+      corr.column_size.times do |j|
+        assert_in_delta(corr[i,j], real[i,j],1e-15)
       end
     end
-end
+  end
+end