statsample 0.5.1 → 0.6.0

data/test/test_histogram.rb

@@ -0,0 +1,26 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+require 'tmpdir'
+require 'test/unit'
+
+class StatsampleHistogramTestCase < Test::Unit::TestCase
+  def test_control
+    h = Statsample::Histogram.alloc(4)
+    assert_equal([0.0]*4, h.bin)
+    assert_equal([0.0]*5, h.range)
+    h = Statsample::Histogram.alloc([1, 3, 7, 9, 20])
+    assert_equal([0.0]*4, h.bin)
+    assert_equal([1,3,7,9,20], h.range)
+    h = Statsample::Histogram.alloc(5, [0, 5])
+    assert_equal([0.0,1.0,2.0,3.0,4.0,5.0], h.range)
+    assert_equal([0.0]*5,h.bin)
+    h.increment(2.5)
+    assert_equal([0.0,0.0,1.0,0.0,0.0], h.bin)
+    h.increment([0.5,0.5,3.5,3.5])
+    assert_equal([2.0,0.0,1.0,2.0,0.0], h.bin)
+    h.increment(0)
+    assert_equal([3.0,0.0,1.0,2.0,0.0], h.bin)
+    h.increment(5)
+    assert_equal([3.0,0.0,1.0,2.0,0.0], h.bin)
+  end
+end

data/test/test_permutation.rb

@@ -0,0 +1,37 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+require 'test/unit'
+
+class StatsamplePermutationTestCase < Test::Unit::TestCase
+    def initialize(*args)
+          super
+    end
+    def test_number_of_permutations
+      per1=Statsample::Permutation.new(4)
+      assert_equal(24,per1.permutation_number)
+      per2=Statsample::Permutation.new([1,1,1,0,0,0])
+      assert_equal(20,per2.permutation_number)
+    end
+    def test_permutation_with_number
+      per1=Statsample::Permutation.new(2)
+      exp1=[[0,1],[1,0]]
+      assert_equal(exp1,per1.permutations)
+      per2=Statsample::Permutation.new(3)
+      exp2=[[0,1,2],[0,2,1],[1,0,2],[1,2,0],[2,0,1],[2,1,0]]
+      assert_equal(exp2,per2.permutations)
+      
+    end
+    def test_permutation_with_array_simple
+      per1=Statsample::Permutation.new(%w{a b})
+      exp1=[['a','b'],['b','a']]
+      assert_equal(exp1,per1.permutations)
+      per2=Statsample::Permutation.new(%w{a b c})
+      exp2=[%w{a b c},%w{a c b},%w{b a c} ,%w{b c a},%w{c a b},%w{c b a}]
+      assert_equal(exp2,per2.permutations)
+    end
+    def test_permutation_with_array_repeated
+      per1=Statsample::Permutation.new([0,0,1,1])
+      exp1=[[0,0,1,1],[0,1,0,1],[0,1,1,0],[1,0,0,1],[1,0,1,0],[1,1,0,0]]
+      assert_equal(exp1,per1.permutations)
+    end
+end

data/test/test_statistics.rb

@@ -11,72 +11,83 @@ class StatsampleStatisicsTestCase < Test::Unit::TestCase
     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?)
-        assert("0.1".is_number?)
-        assert("-0.1".is_number?)
-        assert("10e3".is_number?)
-        assert("10e-3".is_number?)
-        assert(!"1212-1212-1".is_number?)
-        assert(!"a10".is_number?)
-        assert(!"".is_number?)
-
+  def test_is_number
+    assert("10".is_number?)
+    assert("-10".is_number?)
+    assert("0.1".is_number?)
+    assert("-0.1".is_number?)
+    assert("10e3".is_number?)
+    assert("10e-3".is_number?)
+    assert(!"1212-1212-1".is_number?)
+    assert(!"a10".is_number?)
+    assert(!"".is_number?)
+  
+  end
+  def test_chi_square
+    assert_raise TypeError do
+        Statsample::Test.chi_square(1,1)
     end
-    def test_chi_square
-        assert_raise TypeError do
-            Statsample::Test.chi_square(1,1)
-        end
-        real=Matrix[[95,95],[45,155]]
-        expected=Matrix[[68,122],[72,128]]
-        assert_nothing_raised do
-            chi=Statsample::Test.chi_square(real,expected)
-        end
+    real=Matrix[[95,95],[45,155]]
+    expected=Matrix[[68,122],[72,128]]
+    assert_nothing_raised do
         chi=Statsample::Test.chi_square(real,expected)
-        assert_in_delta(32.53,chi,0.1)
     end
+    chi=Statsample::Test.chi_square(real,expected)
+    assert_in_delta(32.53,chi,0.1)
+  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)
-        assert_equal(1471,v.sum())
-        limits=Statsample::SRS.mean_confidence_interval_z(v.mean(), v.sds(), v.size,676,0.80)
-    end
-    def test_estimation_proportion
-        # total
-        pop=3042
-        sam=200
-        prop=0.19
-        assert_in_delta(81.8, Statsample::SRS.proportion_total_sd_ep_wor(prop, sam, pop), 0.1)
-        
-        # confidence limits
-        pop=500
-        sam=100
-        prop=0.37
-        a=0.95
-        l= Statsample::SRS.proportion_confidence_interval_z(prop, sam, pop, a)
-        assert_in_delta(0.28,l[0],0.01)
-        assert_in_delta(0.46,l[1],0.01)
-    end
-    def test_ml
-        if(true)
-		real=[1,1,1,1].to_vector(:scale)
-		
-		pred=[0.0001,0.0001,0.0001,0.0001].to_vector(:scale)
-        # puts  Statsample::Bivariate.maximum_likehood_dichotomic(pred,real)
-
-        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)
+    assert_equal(1471,v.sum())
+    limits=Statsample::SRS.mean_confidence_interval_z(v.mean(), v.sds(), v.size,676,0.80)
+  end
+  def test_estimation_proportion
+    # total
+    pop=3042
+    sam=200
+    prop=0.19
+    assert_in_delta(81.8, Statsample::SRS.proportion_total_sd_ep_wor(prop, sam, pop), 0.1)
+    
+    # confidence limits
+    pop=500
+    sam=100
+    prop=0.37
+    a=0.95
+    l= Statsample::SRS.proportion_confidence_interval_z(prop, sam, pop, a)
+    assert_in_delta(0.28,l[0],0.01)
+    assert_in_delta(0.46,l[1],0.01)
+  end
+  def test_ml
+    if(true)
+    real=[1,1,1,1].to_vector(:scale)
+    
+    pred=[0.0001,0.0001,0.0001,0.0001].to_vector(:scale)
+    # puts  Statsample::Bivariate.maximum_likehood_dichotomic(pred,real)
+    
     end
-    def test_simple_linear_regression
-		a=[1,2,3,4,5,6].to_vector(:scale)
-		b=[6,2,4,10,12,8].to_vector(:scale)
-		reg = Statsample::Regression::Simple.new_from_vectors(a,b)
-        assert_in_delta((reg.ssr+reg.sse).to_f,reg.sst,0.001)
-        assert_in_delta(Statsample::Bivariate.pearson(a,b),reg.r,0.001)
-		assert_in_delta(2.4,reg.a,0.01)
-		assert_in_delta(1.314,reg.b,0.001)
-		assert_in_delta(0.657,reg.r,0.001)
-		assert_in_delta(0.432,reg.r2,0.001)
-        
-	end    
+  end
+  def test_simple_linear_regression
+    a=[1,2,3,4,5,6].to_vector(:scale)
+    b=[6,2,4,10,12,8].to_vector(:scale)
+    reg = Statsample::Regression::Simple.new_from_vectors(a,b)
+    assert_in_delta((reg.ssr+reg.sse).to_f,reg.sst,0.001)
+    assert_in_delta(Statsample::Bivariate.pearson(a,b),reg.r,0.001)
+    assert_in_delta(2.4,reg.a,0.01)
+    assert_in_delta(1.314,reg.b,0.001)
+    assert_in_delta(0.657,reg.r,0.001)
+    assert_in_delta(0.432,reg.r2,0.001)
+	end
+  def test_u_mannwhitney
+    a=[1,2,3,4,5,6].to_scale
+    b=[0,5,7,9,10,11].to_scale
+    assert_equal(7.5, Statsample::Test.u_mannwhitney(a,b).u)
+    assert_equal(7.5, Statsample::Test.u_mannwhitney(b,a).u)
+    a=[1, 7,8,9,10,11].to_scale
+    b=[2,3,4,5,6,12].to_scale
+    assert_equal(11, Statsample::Test.u_mannwhitney(a,b).u)
+    
+    
+    
+  end
 end

data/test/test_umannwhitney.rb

@@ -0,0 +1,17 @@
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+require 'test/unit'
+
+class StatsampleSrsTestCase < Test::Unit::TestCase
+    def test_u_mannwhitney
+      v1=[1,2,3,4,7,8,9,10,14,15].to_scale
+      v2=[5,6,11,12,13,16,17,18,19].to_scale
+      u=Statsample::Test::UMannWhitney.new(v1,v2)
+      assert_equal(73,u.r1)
+      assert_equal(117,u.r2)
+      assert_equal(18,u.u)
+      assert_in_delta(-2.205,u.z,0.001)
+      assert_in_delta(0.027,u.z_probability,0.001)
+      assert_in_delta(0.028,u.exact_probability,0.001)
+    end
+end

data/test/test_vector.rb

@@ -149,6 +149,10 @@ class TestStatsample::TestVector < Test::Unit::TestCase
 		assert_equal(5,@c.median)
 		assert_equal(4,@c.percentil(25))
 		assert_equal(7,@c.percentil(75))
+    
+    v=[200000, 200000, 210000, 220000, 230000, 250000, 250000, 250000, 270000, 300000, 450000, 130000, 140000, 140000, 140000, 145000, 148000, 165000, 170000, 180000, 180000, 180000, 180000, 180000, 180000 ].to_scale
+    assert_equal(180000,v.median)
+
 	end
 	def test_ranked
 		v1=[0.8,1.2,1.2,2.3,18].to_vector(:ordinal)
@@ -254,36 +258,28 @@ class TestStatsample::TestVector < Test::Unit::TestCase
         assert_equal(expected.data,@c.data)
     end
     def test_gsl
-		if HAS_GSL
-			a=Statsample::Vector.new([1,2,3,4,"STRING"], :scale)
-			assert_equal(2,a.mean)
-			assert_equal(a.variance_sample_slow,a.variance_sample)
-			assert_equal(a.standard_deviation_sample_slow,a.sds)
-			assert_equal(a.variance_population_slow,a.variance_population)
-			assert_equal(a.standard_deviation_population_slow,a.standard_deviation_population)
-            assert_nothing_raised do
-                a=[].to_vector(:scale)
-            end
-            a.add(1,false)
-            a.add(2,false)
-            a.set_valid_data
-            assert_equal(3,a.sum)
-            b=[1,2,nil,3,4,5,nil,6].to_vector(:scale)
-            assert_equal(21, b.sum)
-            
-            assert_equal(3.5, b.mean)
-            assert_equal(6,b.gsl.size)
-            # histogram
-            a=[11,12,13,15,21,22,23,32,33].to_vector(:scale)
-            h=a.histogram(3)
-            assert_equal(4,h[0])
-            assert_equal(3,h[1])
-            assert_equal(2,h[2])
-            h=a.histogram([10,20,30,40])
-            assert_equal(4,h[0])
-            assert_equal(3,h[1])
-            assert_equal(2,h[2])
-            
+      if HAS_GSL
+        a=Statsample::Vector.new([1,2,3,4,"STRING"], :scale)
+        assert_equal(2,a.mean)
+        assert_equal(a.variance_sample_slow,a.variance_sample)
+        assert_equal(a.standard_deviation_sample_slow,a.sds)
+        assert_equal(a.variance_population_slow,a.variance_population)
+        assert_equal(a.standard_deviation_population_slow,a.standard_deviation_population)
+        assert_nothing_raised do
+          a=[].to_vector(:scale)
+        end
+        a.add(1,false)
+        a.add(2,false)
+        a.set_valid_data
+        assert_equal(3,a.sum)
+        b=[1,2,nil,3,4,5,nil,6].to_vector(:scale)
+        assert_equal(21, b.sum)        
+        assert_equal(3.5, b.mean)
+        assert_equal(6,b.gsl.size)
+        c=[10,20,30,40,50,100,1000,2000,5000].to_scale
+        assert_in_delta(c.skew,     c.skew_slow     ,0.0001)
+        assert_in_delta(c.kurtosis, c.kurtosis_slow ,0.0001)
+        
 		end
 	end
 	def test_vector_matrix        
@@ -344,5 +340,25 @@ class TestStatsample::TestVector < Test::Unit::TestCase
       exp=[0,0,0,1,1,1].to_scale
       assert_equal(exp, a.dichotomize)
     end
+    def test_can_be_methods
+      a=  [0,0,0,1,2,3,nil].to_vector
+      assert(a.can_be_scale?)
+      a=[0,"s",0,1,2,3,nil].to_vector
+      assert(!a.can_be_scale?)
+      a.missing_values=["s"]
+      assert(a.can_be_scale?)
+      
+      a=[Date.new(2009,10,10), Date.today(), "2009-10-10", "2009-1-1", nil, "NOW"].to_vector
+      assert(a.can_be_date?)
+      a=[Date.new(2009,10,10), Date.today(),nil,"sss"].to_vector
+      assert(!a.can_be_date?)      
+    end
+    def test_date_vector
+      a=[Date.new(2009,10,10), :NOW, "2009-10-10", "2009-1-1", nil, "NOW","MISSING"].to_vector(:date, :missing_values=>["MISSING"])
+      
+      assert(a.type==:date)
+      expected=[Date.new(2009,10,10), Date.today(), Date.new(2009,10,10), Date.new(2009,1,1), nil, Date.today(), nil ]
+      assert_equal(expected, a.date_data_with_nils)
 
+    end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: statsample
 version: !ruby/object:Gem::Version 
-  version: 0.5.1
+  version: 0.6.0
 platform: ruby
 authors: 
 - Claudio Bustos
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-11-22 00:00:00 -03:00
+date: 2010-02-06 00:00:00 -03:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -32,6 +32,16 @@ dependencies:
       - !ruby/object:Gem::Version 
         version: 1.0.0
     version: 
+- !ruby/object:Gem::Dependency 
+  name: reportbuilder
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.0
+    version: 
 - !ruby/object:Gem::Dependency 
   name: hoe
   type: :development
@@ -40,9 +50,9 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 2.3.3
+        version: 2.4.0
     version: 
-description: A suite for your basic and advanced statistics needs. Descriptive statistics, multiple regression, dominance analysis, scale's reliability analysis, bivariate statistics and others procedures.
+description: A suite for your basic and advanced statistics needs. Descriptive statistics, multiple regression, factorial analysis, dominance analysis, scale's reliability analysis, bivariate statistics and others procedures.
 email: 
 - clbustos@gmail.com
 executables: 
@@ -75,6 +85,7 @@ files:
 - demo/item_analysis.rb
 - demo/mean.rb
 - demo/nunnally_6.rb
+- demo/pca.rb
 - demo/proportion.rb
 - demo/regression.rb
 - demo/sample_test.csv
@@ -82,6 +93,7 @@ files:
 - demo/strata_proportion.rb
 - demo/stratum.rb
 - demo/t-student.rb
+- demo/umann.rb
 - lib/distribution.rb
 - lib/distribution/chisquare.rb
 - lib/distribution/f.rb
@@ -104,17 +116,23 @@ files:
 - lib/statsample/dataset.rb
 - lib/statsample/dominanceanalysis.rb
 - lib/statsample/dominanceanalysis/bootstrap.rb
+- lib/statsample/factor.rb
+- lib/statsample/factor/pca.rb
+- lib/statsample/factor/principalaxis.rb
+- lib/statsample/factor/rotation.rb
 - lib/statsample/graph/gdchart.rb
 - lib/statsample/graph/svgboxplot.rb
 - lib/statsample/graph/svggraph.rb
 - lib/statsample/graph/svghistogram.rb
 - lib/statsample/graph/svgscatterplot.rb
+- lib/statsample/histogram.rb
 - lib/statsample/htmlreport.rb
 - lib/statsample/mle.rb
 - lib/statsample/mle/logit.rb
 - lib/statsample/mle/normal.rb
 - lib/statsample/mle/probit.rb
 - lib/statsample/multiset.rb
+- lib/statsample/permutation.rb
 - lib/statsample/regression.rb
 - lib/statsample/regression/binomial.rb
 - lib/statsample/regression/binomial/logit.rb
@@ -129,6 +147,7 @@ files:
 - lib/statsample/resample.rb
 - lib/statsample/srs.rb
 - lib/statsample/test.rb
+- lib/statsample/test/umannwhitney.rb
 - lib/statsample/vector.rb
 - po/es/statsample.po
 - po/statsample.pot
@@ -142,11 +161,14 @@ files:
 - test/test_csv.rb
 - test/test_dataset.rb
 - test/test_distribution.rb
+- test/test_factor.rb
 - test/test_ggobi.rb
 - test/test_gsl.rb
+- test/test_histogram.rb
 - test/test_logit.rb
 - test/test_mle.rb
 - test/test_multiset.rb
+- test/test_permutation.rb
 - test/test_regression.rb
 - test/test_reliability.rb
 - test/test_resample.rb
@@ -154,6 +176,7 @@ files:
 - test/test_statistics.rb
 - test/test_stratified.rb
 - test/test_svg_graph.rb
+- test/test_umannwhitney.rb
 - test/test_vector.rb
 - test/test_xls.rb
 - test/test_xls.xls
@@ -188,8 +211,11 @@ specification_version: 3
 summary: A suite for your basic and advanced statistics needs
 test_files: 
 - test/test_bivariate.rb
+- test/test_factor.rb
 - test/test_anova.rb
+- test/test_permutation.rb
 - test/test_codification.rb
+- test/test_umannwhitney.rb
 - test/test_crosstab.rb
 - test/test_distribution.rb
 - test/test_svg_graph.rb
@@ -206,6 +232,7 @@ test_files:
 - test/test_logit.rb
 - test/test_statistics.rb
 - test/test_reliability.rb
+- test/test_histogram.rb
 - test/test_dataset.rb
 - test/test_regression.rb
 - test/test_multiset.rb