statsample 0.18.0 → 1.0.0

metadata

@@ -3,10 +3,10 @@ name: statsample
 version: !ruby/object:Gem::Version 
   prerelease: false
   segments: 
+  - 1
   - 0
-  - 18
   - 0
-  version: 0.18.0
+  version: 1.0.0
 platform: ruby
 authors: 
 - Claudio Bustos
@@ -35,7 +35,7 @@ cert_chain:
   rpP0jjs0
   -----END CERTIFICATE-----
 
-date: 2011-01-07 00:00:00 -03:00
+date: 2011-01-27 00:00:00 -03:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -168,7 +168,7 @@ dependencies:
   type: :runtime
   version_requirements: *id009
 - !ruby/object:Gem::Dependency 
-  name: hoe
+  name: distribution
   prerelease: false
   requirement: &id010 !ruby/object:Gem::Requirement 
     none: false
@@ -177,11 +177,13 @@ dependencies:
       - !ruby/object:Gem::Version 
         segments: 
         - 0
-        version: "0"
-  type: :development
+        - 2
+        - 0
+        version: 0.2.0
+  type: :runtime
   version_requirements: *id010
 - !ruby/object:Gem::Dependency 
-  name: shoulda
+  name: hoe
   prerelease: false
   requirement: &id011 !ruby/object:Gem::Requirement 
     none: false
@@ -194,9 +196,22 @@ dependencies:
   type: :development
   version_requirements: *id011
 - !ruby/object:Gem::Dependency 
-  name: minitest
+  name: shoulda
   prerelease: false
   requirement: &id012 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id012
+- !ruby/object:Gem::Dependency 
+  name: minitest
+  prerelease: false
+  requirement: &id013 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -206,11 +221,63 @@ dependencies:
         - 0
         version: "2.0"
   type: :development
-  version_requirements: *id012
+  version_requirements: *id013
+- !ruby/object:Gem::Dependency 
+  name: rserve-client
+  prerelease: false
+  requirement: &id014 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id014
+- !ruby/object:Gem::Dependency 
+  name: gettext
+  prerelease: false
+  requirement: &id015 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id015
+- !ruby/object:Gem::Dependency 
+  name: mocha
+  prerelease: false
+  requirement: &id016 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id016
+- !ruby/object:Gem::Dependency 
+  name: hoe-git
+  prerelease: false
+  requirement: &id017 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id017
 - !ruby/object:Gem::Dependency 
   name: hoe
   prerelease: false
-  requirement: &id013 !ruby/object:Gem::Requirement 
+  requirement: &id018 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -221,7 +288,7 @@ dependencies:
         - 0
         version: 2.8.0
   type: :development
-  version_requirements: *id013
+  version_requirements: *id018
 description: |-
   A suite for basic and advanced statistics on Ruby. Tested on Ruby 1.8.7, 1.9.1, 1.9.2 (April, 2010) and JRuby 1.4 (Ruby 1.8.7 compatible).
   
@@ -258,14 +325,19 @@ files:
 - Manifest.txt
 - README.txt
 - Rakefile
+- benchmarks/correlation_matrix_15_variables.rb
+- benchmarks/correlation_matrix_5_variables.rb
+- benchmarks/correlation_matrix_methods/correlation_matrix.ds
+- benchmarks/correlation_matrix_methods/correlation_matrix.html
+- benchmarks/correlation_matrix_methods/correlation_matrix.rb
+- benchmarks/correlation_matrix_methods/correlation_matrix.xls
+- benchmarks/correlation_matrix_methods/correlation_matrix_gsl_ruby.ods
+- benchmarks/correlation_matrix_methods/correlation_matrix_with_graphics.ods
+- benchmarks/correlation_matrix_methods/results.ds
+- benchmarks/factor_map.rb
+- benchmarks/helpers_benchmark.rb
 - bin/statsample
-- data/crime.txt
-- data/hartman_23.matrix
 - data/locale/es/LC_MESSAGES/statsample.mo
-- data/repeated_fields.csv
-- data/test_binomial.csv
-- data/tetmat_matrix.txt
-- data/tetmat_test.txt
 - doc_latex/manual/equations.tex
 - examples/boxplot.rb
 - examples/correlation_matrix.rb
@@ -278,7 +350,6 @@ files:
 - examples/multiple_regression.rb
 - examples/multivariate_correlation.rb
 - examples/parallel_analysis.rb
-- examples/parallel_analysis_tetrachoric.rb
 - examples/polychoric.rb
 - examples/principal_axis.rb
 - examples/reliability.rb
@@ -289,15 +360,11 @@ files:
 - examples/vector.rb
 - examples/velicer_map_test.rb
 - grab_references.rb
-- lib/distribution.rb
-- lib/distribution/chisquare.rb
-- lib/distribution/f.rb
-- lib/distribution/normal.rb
-- lib/distribution/normalbivariate.rb
-- lib/distribution/normalmultivariate.rb
-- lib/distribution/t.rb
 - lib/spss.rb
 - lib/statsample.rb
+- lib/statsample/analysis.rb
+- lib/statsample/analysis/suite.rb
+- lib/statsample/analysis/suitereportbuilder.rb
 - lib/statsample/anova.rb
 - lib/statsample/anova/oneway.rb
 - lib/statsample/anova/twoway.rb
@@ -346,6 +413,7 @@ files:
 - lib/statsample/reliability/skillscaleanalysis.rb
 - lib/statsample/resample.rb
 - lib/statsample/rserve_extension.rb
+- lib/statsample/shorthand.rb
 - lib/statsample/srs.rb
 - lib/statsample/test.rb
 - lib/statsample/test/bartlettsphericity.rb
@@ -355,6 +423,7 @@ files:
 - lib/statsample/test/t.rb
 - lib/statsample/test/umannwhitney.rb
 - lib/statsample/vector.rb
+- lib/statsample/vector/gsl.rb
 - po/es/statsample.mo
 - po/es/statsample.po
 - po/statsample.pot
@@ -362,7 +431,16 @@ files:
 - setup.rb
 - test/fixtures/bank2.dat
 - test/fixtures/correlation_matrix.rb
+- test/fixtures/crime.txt
+- test/fixtures/hartman_23.matrix
+- test/fixtures/repeated_fields.csv
+- test/fixtures/test_binomial.csv
+- test/fixtures/test_csv.csv
+- test/fixtures/test_xls.xls
+- test/fixtures/tetmat_matrix.txt
+- test/fixtures/tetmat_test.txt
 - test/helpers_tests.rb
+- test/test_analysis.rb
 - test/test_anovaoneway.rb
 - test/test_anovatwoway.rb
 - test/test_anovatwowaywithdataset.rb
@@ -371,12 +449,12 @@ files:
 - test/test_bivariate.rb
 - test/test_codification.rb
 - test/test_crosstab.rb
-- test/test_csv.csv
 - test/test_csv.rb
 - test/test_dataset.rb
-- test/test_distribution.rb
 - test/test_dominance_analysis.rb
 - test/test_factor.rb
+- test/test_factor_map.rb
+- test/test_factor_pa.rb
 - test/test_ggobi.rb
 - test/test_gsl.rb
 - test/test_histogram.rb
@@ -399,7 +477,7 @@ files:
 - test/test_umannwhitney.rb
 - test/test_vector.rb
 - test/test_xls.rb
-- test/test_xls.xls
+- web/Rakefile
 has_rdoc: true
 homepage: http://ruby-statsample.rubyforge.org/
 licenses: []
@@ -453,16 +531,18 @@ specification_version: 3
 summary: A suite for basic and advanced statistics on Ruby
 test_files: 
 - test/test_bivariate.rb
+- test/test_factor_pa.rb
 - test/test_dominance_analysis.rb
 - test/test_factor.rb
 - test/test_codification.rb
 - test/test_anovatwowaywithdataset.rb
 - test/test_umannwhitney.rb
+- test/test_factor_map.rb
 - test/test_anovawithvectors.rb
 - test/test_crosstab.rb
-- test/test_distribution.rb
 - test/test_rserve_extension.rb
 - test/test_csv.rb
+- test/test_analysis.rb
 - test/test_matrix.rb
 - test/test_gsl.rb
 - test/test_bartlettsphericity.rb

data/examples/parallel_analysis_tetrachoric.rb

@@ -1,31 +0,0 @@
-#!/usr/bin/ruby
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-
-require 'statsample'
-require 'statsample/bivariate/tetrachoric'
-samples=1000
-variables=10
-rng = GSL::Rng.alloc()
-f1=samples.times.collect {rng.ugaussian()}.to_scale
-f2=samples.times.collect {rng.ugaussian()}.to_scale
-f3=samples.times.collect {rng.ugaussian()}.to_scale
-
-vectors={}
-
-variables.times do |i|
-  vectors["v#{i}"]=samples.times.collect {|nv|  f1[nv]*(i-30)+f2[nv]*(i+30)+f3[nv]*(i+15) + rng.ugaussian() > 0 ? 1 : 0}.to_scale
-end
-ds=vectors.to_dataset
-
-pa=Statsample::Factor::ParallelAnalysis.new(ds, :iterations=>10, :matrix_method=>:tetrachoric_correlation_matrix, :debug=>true)
-
-pca=Statsample::Factor::PCA.new(Statsample::Bivariate.tetrachoric_correlation_matrix(ds))
-rb=ReportBuilder.new(:name=>"Parallel Analysis with simulation") do |g|
-  g.text("There are 3 real factors on data")
-  g.parse_element(pca)
-  g.text("Traditional Kaiser criterion (k>1) returns #{pca.m} factors")
-  g.parse_element(pa)
-  g.text("Parallel Analysis returns #{pa.number_of_factors} factors to preserve")
-end
-
-puts rb.to_text

data/lib/distribution.rb

@@ -1,25 +0,0 @@
-begin
-  require 'statistics2'
-rescue LoadError
-  puts "You should install statistics2"
-end
-# Several distributions modules to calculate cdf, inverse cdf and pdf
-# See Distribution::Pdf for interface.
-# 
-# Usage:
-#    Distribution::Normal.cdf(1.96)
-#    => 0.97500210485178
-#    Distribution::Normal.p_value(0.95)
-#    => 1.64485364660836
-module Distribution
-  def self.has_gsl?
-    Statsample.has_gsl?
-  end
-  
-  autoload(:ChiSquare, 'distribution/chisquare')
-  autoload(:T, 'distribution/t')
-  autoload(:F, 'distribution/f')
-  autoload(:Normal, 'distribution/normal')
-  autoload(:NormalBivariate, 'distribution/normalbivariate')
-  # autoload(:NormalMultivariate, 'distribution/normalmultivariate')
-end

data/lib/distribution/chisquare.rb

@@ -1,23 +0,0 @@
-module Distribution
-    # Calculate cdf and inverse cdf for Chi Square Distribution.
-    # 
-    # Based on Statistics2 module
-    # 
-    module ChiSquare
-        class << self
-            # Return the P-value of the corresponding integral with 
-            # k degrees of freedom
-            def p_value(pr,k)
-                Statistics2.pchi2X_(k.to_i, pr)
-            end
-            # Chi-square cumulative distribution function (cdf).
-            # 
-            # Returns the integral of Chi-squared distribution 
-            # with k degrees of freedom over [0, x]
-            # 
-            def cdf(x, k)
-                Statistics2.chi2dist(k.to_i,x)
-            end
-        end
-    end
-end

data/lib/distribution/f.rb

@@ -1,35 +0,0 @@
-module Distribution
-  # Calculate cdf and inverse cdf for Fisher Distribution.
-  # Uses Statistics2 module
-  module F
-    class << self
-      # Return the P-value of the corresponding integral with 
-      # k degrees of freedom
-      #
-      #   Distribution::F.p_value(0.95,1,2)
-      def p_value(pr,k1,k2)
-        # Statistics2 has some troubles with extreme f values
-        if Distribution.has_gsl?
-          GSL::Cdf.fdist_Pinv(pr,k1,k2)
-        else
-          #puts "F:#{k1}, #{k2},#{pr}"
-          Statistics2.pfdist(k1,k2, pr)
-        end
-      end
-      # F cumulative distribution function (cdf).
-      # 
-      # Returns the integral of F-distribution 
-      # with k1 and k2 degrees of freedom
-      # over [0, x].
-      #   Distribution::F.cdf(20,3,2)
-      # 
-      def cdf(x, k1, k2)
-        if Distribution.has_gsl?
-          GSL::Cdf.fdist_P(x.to_f,k1,k2)
-        else
-          Statistics2.fdist(k1, k2,x)
-        end
-      end
-    end
-  end
-end

data/lib/distribution/normal.rb

@@ -1,60 +0,0 @@
-module Distribution
-  # Calculate cdf and inverse cdf for Normal Distribution.
-  # Uses Statistics2 module
-  module Normal
-    class << self
-      # Return a proc which return a random number within a gaussian distribution -> N(0,1)
-      # == Reference:
-      # * http://www.taygeta.com/random/gaussian.html
-      def rng_ugaussian
-        if Distribution.has_gsl?
-          rng=GSL::Rng.alloc()
-          lambda { rng.ugaussian()}
-        else
-          returned,y1,y2=0,0,0
-          lambda {
-            if returned==0
-              begin
-                x1 = 2.0 * rand - 1.0
-                x2 = 2.0 * rand - 1.0
-                w = x1 * x1 + x2 * x2
-              end while ( w >= 1.0 )
-              w = Math::sqrt( (-2.0 * Math::log( w ) ) / w )
-              y1 = x1 * w
-              y2 = x2 * w
-              returned=1
-              y1
-            else
-              returned=0
-              y2
-            end
-          }
-        end
-      end
-      # Return the P-value of the corresponding integral
-      def p_value(pr)
-          Statistics2.pnormaldist(pr)
-      end
-      # Normal cumulative distribution function (cdf).
-      # 
-      # Returns the integral of  normal distribution 
-      # over (-Infty, x].
-      # 
-      def cdf(x)
-        Statistics2.normaldist(x)
-      end
-
-      if Distribution.has_gsl?
-        alias :cdf_ruby :cdf 
-        def cdf(x) # :nodoc:
-          GSL::Cdf::gaussian_P(x)
-        end
-      end
-      # Normal probability density function (pdf)
-      # With x=0 and sigma=1
-      def pdf(x)
-          (1.0/Math::sqrt(2*Math::PI))*Math::exp(-(x**2/2.0))
-      end
-    end
-  end
-end