statsample 1.5.0 → 2.0.0

data/lib/statsample/version.rb

@@ -1,3 +1,3 @@
 module Statsample
-  VERSION = '1.5.0'
+  VERSION = '2.0.0'
 end

data/statsample.gemspec

@@ -3,7 +3,7 @@ $:.unshift File.expand_path("../lib/", __FILE__)
 require 'statsample/version'
 require 'date'
 
-DESCRIPTION = <<MSG
+Statsample::DESCRIPTION = <<MSG
 A suite for basic and advanced statistics on Ruby. Tested on CRuby 1.9.3, 2.0.0
 and 2.1.1. See `.travis.yml` for more information.
 
@@ -11,7 +11,6 @@ Include:
 
 - Descriptive statistics: frequencies, median, mean,
 standard error, skew, kurtosis (and many others).
-- Imports and exports datasets from and to Excel, CSV and plain text files.
 - Correlations: Pearson's r, Spearman's rank correlation (rho), point biserial,
 tau a, tau b and  gamma. Tetrachoric and Polychoric correlation provides by
 statsample-bivariate-extension gem.
@@ -32,17 +31,11 @@ scales using factor analysis and correlations, if you want it.
 - Graphics: Histogram, Boxplot and Scatterplot.
 MSG
 
-POSTINSTALL = <<MSG
+Statsample::POSTINSTALL = <<MSG
 ***************************************************
 
 Thanks for installing statsample.
 
-On *nix, you could install statsample-optimization
-to retrieve gems gsl, statistics2 and a C extension
-to speed some methods.
-
-$ [sudo] gem install statsample-optimization
-
 *****************************************************
 MSG
 
@@ -56,8 +49,8 @@ Gem::Specification.new do |s|
   s.email = ["clbustos@gmail.com", "carlos@onox.com.br"]
 
   s.summary = "A suite for basic and advanced statistics on Ruby"
-  s.description = DESCRIPTION
-  s.post_install_message = POSTINSTALL
+  s.description = Statsample::DESCRIPTION
+  s.post_install_message = Statsample::POSTINSTALL
 
   s.rdoc_options = ["--main", "README.md"]
   s.extra_rdoc_files = ["History.txt", "LICENSE.txt", "README.md", "references.txt"]
@@ -67,22 +60,25 @@ Gem::Specification.new do |s|
   s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.executables = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }
 
-  s.add_runtime_dependency 'spreadsheet', '~> 0.6.5'
+  s.add_runtime_dependency 'daru', '~> 0.1'
+  s.add_runtime_dependency 'spreadsheet', '~> 1.0.3'
   s.add_runtime_dependency 'reportbuilder', '~> 1.4'
   s.add_runtime_dependency 'minimization', '~> 0.2'
   s.add_runtime_dependency 'dirty-memoize', '~> 0.0.4'
-  s.add_runtime_dependency 'extendmatrix', '~> 0.3'
+  s.add_runtime_dependency 'extendmatrix', '~> 0.4'
   s.add_runtime_dependency 'rserve-client', '~> 0.3'
-  s.add_runtime_dependency 'rubyvis', '~> 0.5.0'
+  s.add_runtime_dependency 'rubyvis', '~> 0.6.1'
   s.add_runtime_dependency 'distribution', '~> 0.7'
   s.add_runtime_dependency 'awesome_print', '~> 1.6'
 
-  s.add_development_dependency 'bundler', '~> 1.7'
+  s.add_development_dependency 'bundler', '~> 1.10'
   s.add_development_dependency 'rake', '~> 10.4'
   s.add_development_dependency 'rdoc', '~> 4.2'
   s.add_development_dependency 'shoulda', '~> 3.5'
   s.add_development_dependency 'shoulda-matchers', '~> 2.2'
-  s.add_development_dependency 'minitest', '~> 5.5'
+  s.add_development_dependency 'minitest', '~> 5.7'
   s.add_development_dependency 'gettext', '~> 3.1'
   s.add_development_dependency 'mocha', '~> 1.1'
+  s.add_development_dependency 'nmatrix', '~> 0.1.0'
+  s.add_development_dependency 'gsl-nmatrix', '~> 1.17.0'
 end

data/test/helpers_tests.rb

@@ -33,7 +33,7 @@ module Minitest
     def assert_similar_vector(exp, obs, delta = 1e-10, msg = nil)
       msg ||= "Different vectors #{exp} - #{obs}"
       assert_equal(exp.size, obs.size)
-      exp.data_with_nils.each_with_index {|v, i|
+      exp.to_a.each_with_index {|v, i|
         assert_in_delta(v, obs[i], delta)
       }
     end

data/test/test_analysis.rb

@@ -39,7 +39,7 @@ class StatsampleAnalysisTestCase < Minitest::Test
     should 'to_text returns the same as a normal ReportBuilder object' do
       rb = ReportBuilder.new(name: :test)
       section = ReportBuilder::Section.new(name: 'first')
-      a = [1, 2, 3].to_numeric
+      a = Daru::Vector.new([1, 2, 3])
       section.add('first')
       section.add(a)
       rb.add(section)
@@ -98,8 +98,8 @@ class StatsampleAnalysisTestCase < Minitest::Test
       end
       should 'attach() allows to call objects on objects which respond to fields' do
         an = Statsample::Analysis::Suite.new(:summary)
-        ds = { 'x' => stub(mean: 10), 'y' => stub(mean: 12) }
-        ds.expects(:fields).returns(%w(x y)).at_least_once
+        ds = { :x => stub(mean: 10), :y => stub(mean: 12) }
+        ds.expects(:vectors).returns([:x, :y]).at_least_once
         an.attach(ds)
         assert_equal(10, an.x.mean)
         assert_equal(12, an.y.mean)
@@ -109,10 +109,10 @@ class StatsampleAnalysisTestCase < Minitest::Test
       end
       should 'attached objects should be called LIFO' do
         an = Statsample::Analysis::Suite.new(:summary)
-        ds1 = { 'x' => stub(mean: 100), 'y' => stub(mean: 120), 'z' => stub(mean: 13) }
-        ds1.expects(:fields).returns(%w(x y z)).at_least_once
-        ds2 = { 'x' => stub(mean: 10), 'y' => stub(mean: 12) }
-        ds2.expects(:fields).returns(%w(x y)).at_least_once
+        ds1 = { :x => stub(mean: 100), :y => stub(mean: 120), :z => stub(mean: 13) }
+        ds1.expects(:vectors).returns([:x, :y, :z]).at_least_once
+        ds2 = { :x => stub(mean: 10), :y => stub(mean: 12) }
+        ds2.expects(:vectors).returns([:x, :y]).at_least_once
         an.attach(ds1)
         an.attach(ds2)
         assert_equal(10, an.x.mean)
@@ -122,10 +122,10 @@ class StatsampleAnalysisTestCase < Minitest::Test
 
       should 'detach() without arguments drop latest object' do
         an = Statsample::Analysis::Suite.new(:summary)
-        ds1 = { 'x' => stub(mean: 100), 'y' => stub(mean: 120), 'z' => stub(mean: 13) }
-        ds1.expects(:fields).returns(%w(x y z)).at_least_once
-        ds2 = { 'x' => stub(mean: 10), 'y' => stub(mean: 12) }
-        ds2.expects(:fields).returns(%w(x y)).at_least_once
+        ds1 = { :x => stub(mean: 100), :y => stub(mean: 120), :z => stub(mean: 13) }
+        ds1.expects(:vectors).returns([:x, :y, :z]).at_least_once
+        ds2 = { :x => stub(mean: 10), :y => stub(mean: 12) }
+        ds2.expects(:vectors).returns([:x, :y]).at_least_once
         an.attach(ds1)
         an.attach(ds2)
         assert_equal(10, an.x.mean)
@@ -134,12 +134,12 @@ class StatsampleAnalysisTestCase < Minitest::Test
       end
       should 'detach() with argument drop select object' do
         an = Statsample::Analysis::Suite.new(:summary)
-        ds1 = { 'x' => 1 }
-        ds1.expects(:fields).returns(%w(x)).at_least_once
-        ds2 = { 'x' => 2, 'y' => 3 }
-        ds2.expects(:fields).returns(%w(x y)).at_least_once
-        ds3 = { 'y' => 4 }
-        ds3.expects(:fields).returns(%w(y)).at_least_once
+        ds1 = { :x => 1 }
+        ds1.expects(:vectors).returns([:x]).at_least_once
+        ds2 = { :x => 2, :y => 3 }
+        ds2.expects(:vectors).returns([:x, :y]).at_least_once
+        ds3 = { :y => 4 }
+        ds3.expects(:vectors).returns([:y]).at_least_once
 
         an.attach(ds3)
         an.attach(ds2)

data/test/test_anova_contrast.rb

@@ -2,12 +2,12 @@ require(File.expand_path(File.dirname(__FILE__) + '/helpers_tests.rb'))
 class StatsampleAnovaContrastTestCase < Minitest::Test
   context(Statsample::Anova::Contrast) do
     setup do
-      constant = [12, 13, 11, 12, 12].to_numeric
-      frequent = [9, 10, 9, 13, 14].to_numeric
-      infrequent = [15, 16, 17, 16, 16].to_numeric
-      never = [17, 18, 12, 18, 20].to_numeric
-      @vectors = [constant, frequent, infrequent, never]
-      @c = Statsample::Anova::Contrast.new(vectors: @vectors)
+      constant   = Daru::Vector.new([12, 13, 11, 12, 12])
+      frequent   = Daru::Vector.new([9, 10, 9, 13, 14])
+      infrequent = Daru::Vector.new([15, 16, 17, 16, 16])
+      never      = Daru::Vector.new([17, 18, 12, 18, 20])
+      @vectors   = [constant, frequent, infrequent, never]
+      @c         = Statsample::Anova::Contrast.new(vectors: @vectors)
     end
     should 'return correct value using c' do
       @c.c([1, -1.quo(3), -1.quo(3), -1.quo(3)])

data/test/test_anovatwowaywithdataset.rb

@@ -4,14 +4,14 @@ require(File.expand_path(File.dirname(__FILE__) + '/helpers_tests.rb'))
 class StatsampleAnovaTwoWayWithVectorsTestCase < Minitest::Test
   context(Statsample::Anova::TwoWayWithVectors) do
     setup do
-      @pa = [5, 4, 3, 4, 2, 18, 19, 14, 12, 15, 6, 7, 5, 8, 4, 6, 9, 5, 9, 3].to_numeric
-      @pa.name = 'Passive Avoidance'
-      @a = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1].to_vector
-      @a.labels = { 0 => '0%', 1 => '35%' }
-      @a.name = 'Diet'
-      @b = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1].to_vector
-      @b.labels = { 0 => 'Young', 1 => 'Older' }
-      @b.name = 'Age'
+      @pa = Daru::Vector.new [5, 4, 3, 4, 2, 18, 19, 14, 12, 15, 6, 7, 5, 8, 4, 6, 9, 5, 9, 3]
+      @pa.rename 'Passive Avoidance'
+      @a = Daru::Vector.new [0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
+      # @a.labels = { 0 => '0%', 1 => '35%' }
+      @a.rename 'Diet'
+      @b = Daru::Vector.new [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
+      # @b.labels = { 0 => 'Young', 1 => 'Older' }
+      @b.rename 'Age'
       @anova = Statsample::Anova::TwoWayWithVectors.new(a: @a, b: @b, dependent: @pa)
     end
     should 'Statsample::Anova respond to #twoway_with_vectors' do

data/test/test_anovawithvectors.rb

@@ -3,9 +3,9 @@ class StatsampleAnovaOneWayWithVectorsTestCase < Minitest::Test
   context(Statsample::Anova::OneWayWithVectors) do
     context('when initializing') do
       setup do
-        @v1 = 10.times.map { rand(100) }.to_numeric
-        @v2 = 10.times.map { rand(100) }.to_numeric
-        @v3 = 10.times.map { rand(100) }.to_numeric
+        @v1 = Daru::Vector.new(10.times.map { rand(100) })
+        @v2 = Daru::Vector.new(10.times.map { rand(100) })
+        @v3 = Daru::Vector.new(10.times.map { rand(100) })
       end
       should 'be the same using [] or args*' do
         a1 = Statsample::Anova::OneWayWithVectors.new(@v1, @v2, @v3)
@@ -28,9 +28,9 @@ class StatsampleAnovaOneWayWithVectorsTestCase < Minitest::Test
       end
     end
     setup do
-      @v1 = [3, 3, 2, 3, 6].to_vector(:numeric)
-      @v2 = [7, 6, 5, 6, 7].to_vector(:numeric)
-      @v3 = [9, 8, 9, 7, 8].to_vector(:numeric)
+      @v1 = Daru::Vector.new([3, 3, 2, 3, 6])
+      @v2 = Daru::Vector.new([7, 6, 5, 6, 7])
+      @v3 = Daru::Vector.new([9, 8, 9, 7, 8])
       @name = 'Anova testing'
       @anova = Statsample::Anova::OneWayWithVectors.new(@v1, @v2, @v3, name: @name)
     end
@@ -66,10 +66,10 @@ class StatsampleAnovaOneWayWithVectorsTestCase < Minitest::Test
       assert_in_delta(@anova.sst, @anova.sswg + @anova.ssbg, 0.00001)
     end
     should 'df total equal to number of n-1' do
-      assert_equal(@v1.n + @v2.n + @v3.n - 1, @anova.df_total)
+      assert_equal(@v1.size + @v2.size + @v3.size - 1, @anova.df_total)
     end
     should 'df wg equal to number of n-k' do
-      assert_equal(@v1.n + @v2.n + @v3.n - 3, @anova.df_wg)
+      assert_equal(@v1.size + @v2.size + @v3.size - 3, @anova.df_wg)
     end
     should 'df bg equal to number of k-1' do
       assert_equal(2, @anova.df_bg)

data/test/test_awesome_print_bug.rb

@@ -5,7 +5,7 @@ class StatsampleAwesomePrintBug < Minitest::Test
       require 'awesome_print'
     end
     should 'should be flawless' do
-      a = [1, 2, 3].to_numeric
+      a = Daru::Vector.new([1, 2, 3])
 
       assert(a != [1, 2, 3])
       assert_nothing_raised do

data/test/test_bartlettsphericity.rb

@@ -4,11 +4,11 @@ class StatsampleBartlettSphericityTestCase < Minitest::Test
   include Statsample::Test
   context Statsample::Test::BartlettSphericity do
     setup do
-      @v1 = [1, 2, 3, 4, 7, 8, 9, 10, 14, 15, 20, 50, 60, 70].to_numeric
-      @v2 = [5, 6, 11, 12, 13, 16, 17, 18, 19, 20, 30, 0, 0, 0].to_numeric
-      @v3 = [10, 3, 20, 30, 40, 50, 80, 10, 20, 30, 40, 2, 3, 4].to_numeric
+      @v1 = Daru::Vector.new([1, 2, 3, 4, 7, 8, 9, 10, 14, 15, 20, 50, 60, 70])
+      @v2 = Daru::Vector.new([5, 6, 11, 12, 13, 16, 17, 18, 19, 20, 30, 0, 0, 0])
+      @v3 = Daru::Vector.new([10, 3, 20, 30, 40, 50, 80, 10, 20, 30, 40, 2, 3, 4])
       # KMO: 0.490
-      ds = { 'v1' => @v1, 'v2' => @v2, 'v3' => @v3 }.to_dataset
+      ds = Daru::DataFrame.new({ :v1 => @v1, :v2 => @v2, :v3 => @v3 })
       cor = Statsample::Bivariate.correlation_matrix(ds)
       @bs = Statsample::Test::BartlettSphericity.new(cor, 14)
     end

data/test/test_bivariate.rb

@@ -1,38 +1,38 @@
 require(File.expand_path(File.dirname(__FILE__) + '/helpers_tests.rb'))
 class StatsampleBivariateTestCase < Minitest::Test
   should 'method sum of squares should be correct' do
-    v1 = [1, 2, 3, 4, 5, 6].to_vector(:numeric)
-    v2 = [6, 2, 4, 10, 12, 8].to_vector(:numeric)
+    v1 = Daru::Vector.new([1, 2, 3, 4, 5, 6])
+    v2 = Daru::Vector.new([6, 2, 4, 10, 12, 8])
     assert_equal(23.0, Statsample::Bivariate.sum_of_squares(v1, v2))
   end
   should_with_gsl 'return same covariance with ruby and gls implementation' do
-    v1 = 20.times.collect { |_a| rand }.to_numeric
-    v2 = 20.times.collect { |_a| rand }.to_numeric
+    v1 = Daru::Vector.new(20.times.collect { |_a| rand })
+    v2 = Daru::Vector.new(20.times.collect { |_a| rand })
     assert_in_delta(Statsample::Bivariate.covariance(v1, v2), Statsample::Bivariate.covariance_slow(v1, v2), 0.001)
   end
 
   should_with_gsl 'return same correlation with ruby and gls implementation' do
-    v1 = 20.times.collect { |_a| rand }.to_numeric
-    v2 = 20.times.collect { |_a| rand }.to_numeric
+    v1 = Daru::Vector.new(20.times.collect { |_a| rand })
+    v2 = Daru::Vector.new(20.times.collect { |_a| rand })
 
-    assert_in_delta(GSL::Stats.correlation(v1.gsl, v2.gsl), Statsample::Bivariate.pearson_slow(v1, v2), 1e-10)
+    assert_in_delta(GSL::Stats.correlation(v1.to_gsl, v2.to_gsl), Statsample::Bivariate.pearson_slow(v1, v2), 1e-10)
   end
   should 'return correct pearson correlation' do
-    v1 = [6, 5, 4, 7, 8, 4, 3, 2].to_vector(:numeric)
-    v2 = [2, 3, 7, 8, 6, 4, 3, 2].to_vector(:numeric)
+    v1 = Daru::Vector.new([6, 5, 4, 7, 8, 4, 3, 2])
+    v2 = Daru::Vector.new([2, 3, 7, 8, 6, 4, 3, 2])
     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(:numeric)
-    v4 = [2, nil, nil, nil,  3, 7, 8, 6, 4, 3, 2, 500].to_vector(:numeric)
+    v3 = Daru::Vector.new([6, 2,  1000, 1000, 5, 4, 7, 8, 4, 3, 2, nil])
+    v4 = Daru::Vector.new([2, nil, nil, nil,  3, 7, 8, 6, 4, 3, 2, 500])
     assert_in_delta(0.525, Statsample::Bivariate.pearson(v3, v4), 0.001)
     # Test ruby method
     v3a, v4a = Statsample.only_valid v3, v4
     assert_in_delta(0.525, Statsample::Bivariate.pearson_slow(v3a, v4a), 0.001)
   end
   should 'return correct values for t_pearson and prop_pearson' do
-    v1 = [6, 5, 4, 7, 8, 4, 3, 2].to_vector(:numeric)
-    v2 = [2, 3, 7, 8, 6, 4, 3, 2].to_vector(:numeric)
+    v1 = Daru::Vector.new([6, 5, 4, 7, 8, 4, 3, 2])
+    v2 = Daru::Vector.new([2, 3, 7, 8, 6, 4, 3, 2])
     r = Statsample::Bivariate::Pearson.new(v1, v2)
     assert_in_delta(0.525, r.r, 0.001)
     assert_in_delta(Statsample::Bivariate.t_pearson(v1, v2), r.t, 0.001)
@@ -40,11 +40,11 @@ class StatsampleBivariateTestCase < Minitest::Test
     assert(r.summary.size > 0)
   end
   should 'return correct correlation_matrix with nils values' do
-    v1 = [6, 5, 4, 7, 8, 4, 3, 2].to_vector(:numeric)
-    v2 = [2, 3, 7, 8, 6, 4, 3, 2].to_vector(:numeric)
-    v3 = [6, 2,  1000, 1000, 5, 4, 7, 8].to_vector(:numeric)
-    v4 = [2, nil, nil, nil,  3, 7, 8, 6].to_vector(:numeric)
-    ds = { 'v1' => v1, 'v2' => v2, 'v3' => v3, 'v4' => v4 }.to_dataset
+    v1 = Daru::Vector.new([6, 5, 4, 7, 8, 4, 3, 2])
+    v2 = Daru::Vector.new([2, 3, 7, 8, 6, 4, 3, 2])
+    v3 = Daru::Vector.new([6, 2,  1000, 1000, 5, 4, 7, 8])
+    v4 = Daru::Vector.new([2, nil, nil, nil,  3, 7, 8, 6])
+    ds = Daru::DataFrame.new({ :v1 => v1, :v2 => v2, :v3 => v3, :v4 => v4 })
     c = proc { |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)]
@@ -61,13 +61,13 @@ class StatsampleBivariateTestCase < Minitest::Test
   end
   should_with_gsl 'return same values for optimized and pairwise covariance matrix' do
     cases = 100
-    v1 = Statsample::Vector.new_numeric(cases) { rand }
-    v2 = Statsample::Vector.new_numeric(cases) { rand }
-    v3 = Statsample::Vector.new_numeric(cases) { rand }
-    v4 = Statsample::Vector.new_numeric(cases) { rand }
-    v5 = Statsample::Vector.new_numeric(cases) { rand }
+    v1 = Daru::Vector.new_with_size(cases) { rand }
+    v2 = Daru::Vector.new_with_size(cases) { rand }
+    v3 = Daru::Vector.new_with_size(cases) { rand }
+    v4 = Daru::Vector.new_with_size(cases) { rand }
+    v5 = Daru::Vector.new_with_size(cases) { rand }
 
-    ds = { 'v1' => v1, 'v2' => v2, 'v3' => v3, 'v4' => v4, 'v5' => v5 }.to_dataset
+    ds = Daru::DataFrame.new({ :v1 => v1, :v2 => v2, :v3 => v3, :v4 => v4, :v5 => v5 })
 
     cor_opt = Statsample::Bivariate.covariance_matrix_optimized(ds)
 
@@ -76,13 +76,14 @@ class StatsampleBivariateTestCase < Minitest::Test
   end
   should_with_gsl 'return same values for optimized and pairwise correlation matrix' do
     cases = 100
-    v1 = Statsample::Vector.new_numeric(cases) { rand }
-    v2 = Statsample::Vector.new_numeric(cases) { rand }
-    v3 = Statsample::Vector.new_numeric(cases) { rand }
-    v4 = Statsample::Vector.new_numeric(cases) { rand }
-    v5 = Statsample::Vector.new_numeric(cases) { rand }
+    v1 = Daru::Vector.new_with_size(cases) { rand }
+    v2 = Daru::Vector.new_with_size(cases) { rand }
+    v3 = Daru::Vector.new_with_size(cases) { rand }
+    v4 = Daru::Vector.new_with_size(cases) { rand }
+    v5 = Daru::Vector.new_with_size(cases) { rand }
 
-    ds = { 'v1' => v1, 'v2' => v2, 'v3' => v3, 'v4' => v4, 'v5' => v5 }.to_dataset
+    ds = Daru::DataFrame.new({ 
+      :v1 => v1, :v2 => v2, :v3 => v3, :v4 => v4, :v5 => v5 })
 
     cor_opt = Statsample::Bivariate.correlation_matrix_optimized(ds)
 
@@ -90,11 +91,11 @@ class StatsampleBivariateTestCase < Minitest::Test
     assert_equal_matrix(cor_opt, cor_pw, 1e-15)
   end
   should 'return correct correlation_matrix without nils values' do
-    v1 = [6, 5, 4, 7, 8, 4, 3, 2].to_vector(:numeric)
-    v2 = [2, 3, 7, 8, 6, 4, 3, 2].to_vector(:numeric)
-    v3 = [6, 2,  1000, 1000, 5, 4, 7, 8].to_vector(:numeric)
-    v4 = [2, 4, 6, 7,  3, 7, 8, 6].to_vector(:numeric)
-    ds = { 'v1' => v1, 'v2' => v2, 'v3' => v3, 'v4' => v4 }.to_dataset
+    v1 = Daru::Vector.new([6, 5, 4, 7, 8, 4, 3, 2])
+    v2 = Daru::Vector.new([2, 3, 7, 8, 6, 4, 3, 2])
+    v3 = Daru::Vector.new([6, 2,  1000, 1000, 5, 4, 7, 8])
+    v4 = Daru::Vector.new([2, 4, 6, 7,  3, 7, 8, 6])
+    ds = Daru::DataFrame.new({ :v1 => v1, :v2 => v2, :v3 => v3, :v4 => v4 })
     c = proc { |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)]
@@ -129,25 +130,25 @@ class StatsampleBivariateTestCase < Minitest::Test
   end
 
   should "return correct value for Spearman's rho" do
-    v1 = [86, 97, 99, 100, 101, 103, 106, 110, 112, 113].to_vector(:numeric)
-    v2 = [0, 20, 28, 27, 50, 29, 7, 17, 6, 12].to_vector(:numeric)
+    v1 =Daru::Vector.new( [86, 97, 99, 100, 101, 103, 106, 110, 112, 113])
+    v2 =Daru::Vector.new( [0, 20, 28, 27, 50, 29, 7, 17, 6, 12])
     assert_in_delta(-0.175758, Statsample::Bivariate.spearman(v1, v2), 0.0001)
   end
   should 'return correct value for point_biserial correlation' do
-    c = [1, 3, 5, 6, 7, 100, 200, 300, 400, 300].to_vector(:numeric)
-    d = [1, 1, 1, 1, 1, 0, 0, 0, 0, 0].to_vector(:numeric)
+    c = Daru::Vector.new([1, 3, 5, 6, 7, 100, 200, 300, 400, 300])
+    d = Daru::Vector.new([1, 1, 1, 1, 1, 0, 0, 0, 0, 0])
     assert_raises 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
   should 'return correct value for tau_a and tau_b' do
-    v1 = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11].to_vector(:numeric)
-    v2 = [1, 3, 4, 5, 7, 8, 2, 9, 10, 6, 11].to_vector(:numeric)
+    v1 = Daru::Vector.new([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11])
+    v2 = Daru::Vector.new([1, 3, 4, 5, 7, 8, 2, 9, 10, 6, 11])
     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(:numeric)
-    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(:numeric)
+    v1 = Daru::Vector.new([12, 14, 14, 17, 19, 19, 19, 19, 19, 20, 21, 21, 21, 21, 21, 22, 23, 24, 24, 24, 26, 26, 27])
+    v2 = Daru::Vector.new([11, 4, 4, 2, 0, 0, 0, 0, 0, 0, 4, 0, 4, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0])
     assert_in_delta(-0.376201540231705, Statsample::Bivariate.tau_b(Statsample::Crosstab.new(v1, v2).to_matrix), 0.001)
   end
   should 'return correct value for gamma correlation' do
@@ -156,4 +157,8 @@ class StatsampleBivariateTestCase < Minitest::Test
     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
+
+  should 'return correct residuals' do
+    # TODO: test Statsample::Bivariate.residuals
+  end
 end

data/test/test_codification.rb

@@ -1,33 +1,33 @@
 require(File.expand_path(File.dirname(__FILE__) + '/helpers_tests.rb'))
 class StatsampleCodificationTestCase < Minitest::Test
   def initialize(*args)
-    v1 = %w(run walk,run walking running sleep sleeping,dreaming sleep,dream).to_vector
+    v1 = Daru::Vector.new(%w(run walk,run walking running sleep sleeping,dreaming sleep,dream))
     @dict = { 'run' => 'r', 'walk' => 'w', 'walking' => 'w', 'running' => 'r', 'sleep' => 's', 'sleeping' => 's', 'dream' => 'd', 'dreaming' => 'd' }
-    @ds = { 'v1' => v1 }.to_dataset
+    @ds = Daru::DataFrame.new({ :v1 => v1 })
     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)
+    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'])
+    field = Daru::Vector.new(['v1'] * 8, name: :field)
+    keys = Daru::Vector.new(%w(dream dreaming run running sleep sleeping walk walking))
+    ds = Daru::DataFrame.from_excel(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)
+    assert_equal(keys.to_a, hash[:v1].keys.sort)
+    assert_equal(keys.to_a, hash[:v1].values.sort)
   end
 
   def test_create_yaml
@@ -35,44 +35,44 @@ class StatsampleCodificationTestCase < Minitest::Test
       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'])
+    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)
+    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)
+    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)
+    assert_equal([:v1], h.keys)
+    assert_equal(expected_keys_v1, h[:v1].keys.sort)
     tf.close(true)
   end
 
   def test_recodification
     expected = [['r'], %w(w r), ['w'], ['r'], ['s'], %w(s d), %w(s d)]
-    assert_equal(expected, Statsample::Codification.recode_vector(@ds['v1'], @dict))
-    v2 = ['run', 'walk,dreaming', nil, 'walk,dream,dreaming,walking'].to_vector
+    assert_equal(expected, Statsample::Codification.recode_vector(@ds[:v1], @dict))
+    v2 = Daru::Vector.new(['run', 'walk,dreaming', nil, 'walk,dream,dreaming,walking'])
     expected = [['r'], %w(w d), nil, %w(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'])
+    Statsample::Codification.recode_dataset_simple!(@ds, :v1 => @dict)
+    expected_vector = Daru::Vector.new(['r', 'w,r', 'w', 'r', 's', 's,d', 's,d'])
+    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)
+    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}")
+    e['r'] = Daru::Vector.new([1, 1, 0, 1, 0, 0, 0])
+    e['w'] = Daru::Vector.new([0, 1, 1, 0, 0, 0, 0])
+    e['s'] = Daru::Vector.new([0, 0, 0, 0, 1, 1, 1])
+    e['d'] = Daru::Vector.new([0, 0, 0, 0, 0, 1, 1])
+    e.each { |k, expected|
+      assert_equal(expected, @ds[('v1_' + k).to_sym], "Error on key #{k}")
     }
   end
 end