statsample 0.12.0 → 0.13.0

data.tar.gz.sig

@@ -1 +1,2 @@
-�HG��@��^��uH�
+�2�����׌��Ab���Է����;P�
+��m��Iƚ��Xr�(ηV����:Pd�Y�����L���ϡ���-R���'��;�2l�n'40XH���!�(�l=�,�gX�|�N���{L�--�sWtr/b��^L�-tB?�I%�H�o�fk#HI��
uc�V��c�0 ��T���x��)����v�(�f<0$�Zev��S��^�t*F̞�@�U�2d���8���(v��JUs�Q6�Ǐ/�#���S�;

data/History.txt

@@ -1,3 +1,14 @@
+=== 0.13.0 / 2010-06-13
+
+* Polychoric and Tetrachoric moved to gem statsample-bivariate-extension
+* All classes left with summary method include Summarizable now. Every method which return localizable string is now parsed with _()
+* Correct implementation of Reliability::MultiScaleAnalysis. 
+* Spanish translation for Mann-Whitney's U
+* Added example for Mann-Whitney's U test
+* Better summary for Mann-Whitney's U Test
+* Added Statsample::Bivariate::Pearson class to retrieve complete analysis for r correlations
+* Bug fix on DominanceAnalysis::Bootstrap
+
 === 0.12.0 / 2010-06-09
 
 * Modified Rakefile to remove dependencies based on C extensions. These are moved to statsample-optimization

data/Manifest.txt

@@ -25,6 +25,7 @@ examples/principal_axis.rb
 examples/reliability.rb
 examples/t_test.rb
 examples/tetrachoric.rb
+examples/u_test.rb
 examples/vector.rb
 lib/distribution.rb
 lib/distribution/chisquare.rb
@@ -39,8 +40,7 @@ lib/statsample/anova.rb
 lib/statsample/anova/oneway.rb
 lib/statsample/anova/twoway.rb
 lib/statsample/bivariate.rb
-lib/statsample/bivariate/polychoric.rb
-lib/statsample/bivariate/tetrachoric.rb
+lib/statsample/bivariate/pearson.rb
 lib/statsample/codification.rb
 lib/statsample/combination.rb
 lib/statsample/converter/csv.rb
@@ -101,7 +101,6 @@ test/test_anovatwoway.rb
 test/test_anovatwowaywithdataset.rb
 test/test_anovawithvectors.rb
 test/test_bivariate.rb
-test/test_bivariate_polychoric.rb
 test/test_codification.rb
 test/test_combination.rb
 test/test_crosstab.rb

data/README.txt

@@ -76,23 +76,6 @@ Include:
     cm=Statsample::Bivariate.correlation_matrix(ds)
     puts cm.summary
 
-=== Tetrachoric correlation
-
-    require 'statsample'
-    a=40
-    b=10
-    c=20
-    d=30
-    tetra=Statsample::Bivariate::Tetrachoric.new(a,b,c,d)
-    puts tetra.summary
-    
-=== Polychoric correlation
-
-    require 'statsample'
-    ct=Matrix[[58,52,1],[26,58,3],[8,12,9]]
-    
-    poly=Statsample::Bivariate::Polychoric.new(ct)
-    puts poly.summary
 
 == REQUIREMENTS:
 

data/Rakefile

@@ -23,13 +23,13 @@ task :release do
 system %{git push origin master}
 end
 desc "Update pot/po files."
-task :updatepo do
+task "gettext:updatepo" do
   require 'gettext/tools'
   GetText.update_pofiles("statsample", Dir.glob("{lib,bin}/**/*.{rb,rhtml}"), "statsample #{Statsample::VERSION}")
 end
 
 desc "Create mo-files"
-task :makemo do
+task "gettext:makemo" do
   require 'gettext/tools'
   GetText.create_mofiles()
   # GetText.create_mofiles(true, "po", "locale")  # This is for "Ruby on Rails".
@@ -40,7 +40,8 @@ h=Hoe.spec('statsample') do
   #self.testlib=:minitest
 	self.rubyforge_name = "ruby-statsample"
 	self.developer('Claudio Bustos', 'clbustos@gmail.com')
-	self.extra_deps << ["spreadsheet","~>0.6.0"] << ["svg-graph", "~>1.0"] << ["reportbuilder", "~>1.0"] << ["minimization", "~>0.2.0"] << ["fastercsv"] << ["dirty-memoize", "~>0.0"] << ["extendmatrix","~>0.2.0"]
+	self.extra_deps << ["spreadsheet","~>0.6.0"] << ["svg-graph", "~>1.0"] << ["reportbuilder", "~>1.0"] << ["minimization", "~>0.2.0"] << ["fastercsv"] << ["dirty-memoize", "~>0.0"] << ["extendmatrix","~>0.2.0"] << ["statsample-bivariate-extension", "~>0.13.0"]
+  
 	self.extra_dev_deps << ["shoulda"]
   self.clean_globs << "test/images/*" << "demo/item_analysis/*" << "demo/Regression"
   self.post_install_message = <<-EOF
@@ -51,13 +52,13 @@ On *nix, you should install statsample-optimization
 to retrieve gems gsl, statistics2 and a C extension
 to speed some methods.
 
-  $sudo gem install statsample-optimization
+  $ sudo gem install statsample-optimization
 
-To use it, on Ubuntu I recommend install 
-build-essential and libgsl0-dev using apt-get and 
-compile ruby 1.8 or 1.9 from source code first.
+On Ubuntu, install  build-essential and libgsl0-dev 
+using apt-get and  compile ruby 1.8 or 1.9 from 
+source code first.
 
-  $sudo apt-get install build-essential libgsl0-dev
+  $ sudo apt-get install build-essential libgsl0-dev
 
 
 *****************************************************
@@ -90,7 +91,7 @@ Rake::RDocTask.new(:docs) do |rd|
 end
 
 
-desc 'publicar a rdocs con analytics'
+desc 'Publish rdocs with analytics support'
 task :publicar_docs => [:clean, :docs] do
   ruby %{agregar_adsense_a_doc.rb}
   path = File.expand_path("~/.rubyforge/user-config.yml")

data/examples/principal_axis.rb

@@ -4,5 +4,7 @@ $:.unshift(File.dirname(__FILE__)+'/../lib/')
 require 'statsample'
 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]]
+matrix.extend Statsample::CovariateMatrix
+#matrix.fields=%w{a b c d}
 fa=Statsample::Factor::PrincipalAxis.new(matrix,:m=>1,:smc=>false)
 puts fa.summary

data/examples/u_test.rb

@@ -0,0 +1,8 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib')
+require 'statsample'
+a=10.times.map {rand(100)}.to_scale
+b=20.times.map {(rand(20))**2+50}.to_scale
+
+u=Statsample::Test::UMannWhitney.new(a,b)
+puts u.summary

data/lib/distribution.rb

@@ -1,7 +1,7 @@
 begin
     require 'statistics2'
 rescue LoadError
-        puts "You should install statistics2"
+    puts "You should install statistics2"
 end
 # Several distributions modules to calculate cdf, inverse cdf and pdf
 # See Distribution::Pdf for interface.

data/lib/statsample.rb

@@ -31,9 +31,9 @@ end
 class String
   def is_number?
     if self =~ /^-?\d+[,.]?\d*(e-?\d+)?$/
-        true
+      true
     else
-        false
+      false
     end
   end
 end
@@ -112,7 +112,7 @@ module Statsample
       false
     end
   end
-  VERSION = '0.12.0'
+  VERSION = '0.13.0'
   SPLIT_TOKEN = ","
   autoload(:Database, 'statsample/converters')
   autoload(:Anova, 'statsample/anova')
@@ -201,19 +201,19 @@ module Statsample
   
   
   
-	module Util
+  module Util
     # Reference: http://www.itl.nist.gov/div898/handbook/eda/section3/normprpl.htm
     def normal_order_statistic_medians(i,n)
       if i==1
-          u= 1.0 - normal_order_statistic_medians(n,n)
+        u= 1.0 - normal_order_statistic_medians(n,n)
       elsif i==n
-          u=0.5**(1 / n.to_f)
+        u=0.5**(1 / n.to_f)
       else
-          u= (i - 0.3175) / (n + 0.365)
+        u= (i - 0.3175) / (n + 0.365)
       end
       u
     end
-	end
+  end
   
   
   
@@ -224,7 +224,7 @@ module Statsample
       fp.close
     end        
   end
-  # Provides basic method to generate summaries
+  # Provides method summary to generate summaries and include GetText
   module Summarizable
     include GetText
     bindtextdomain("statsample")
@@ -242,12 +242,12 @@ end
 begin 
   require 'statsamplert'
 rescue LoadError
-  module Statsample 
-      OPTIMIZED=false
+  module Statsample
+    OPTIMIZED=false
   end
 end
 
 require 'statsample/vector'
 require 'statsample/dataset'
 require 'statsample/crosstab'
-require 'statsample/matrix'
+require 'statsample/matrix'

data/lib/statsample/anova/oneway.rb

@@ -32,8 +32,8 @@ module Statsample
         @ss_total=@ss_num+@ss_den
         @ms_total=@ms_num+@ms_den
         opts_default={:name=>"ANOVA",
-                      :name_denominator=>"Explained variance",
-                      :name_numerator=>"Unexplained variance"}
+                      :name_denominator=>_("Explained variance"),
+                      :name_numerator=>_("Unexplained variance")}
         @opts=opts_default.merge(opts)
         opts_default.keys.each {|k|
           send("#{k}=", @opts[k])
@@ -89,8 +89,8 @@ module Statsample
         end
         opts||=Hash.new
         opts_default={:name=>_("Anova One-Way"), 
-                      :name_numerator=>"Between Groups",
-                      :name_denominator=>"Within Groups",
+                      :name_numerator=>_("Between Groups"),
+                      :name_denominator=>_("Within Groups"),
                       :summary_descriptives=>false,
                       :summary_levene=>false}
         @opts=opts_default.merge(opts).merge(:ss_num=>ssbg, :ss_den=>sswg, :df_num=>df_bg, :df_den=>df_wg)

data/lib/statsample/bivariate.rb

@@ -1,8 +1,15 @@
-require 'statsample/bivariate/tetrachoric'
-require 'statsample/bivariate/polychoric'
+require 'statsample/bivariate/pearson'
+
 module Statsample
-  # Diverse bivariate methods, including #covariance, #pearson correlation (r), #spearman ranked correlation (rho), #tetrachoric correlation and #polychoric correlation.
+  # Diverse methods and classes to calculate bivariate relations
+  # Specific classes: 
+  # * Statsample::Bivariate::Pearson : Pearson correlation coefficient (r)
+  # * Statsample::Bivariate::Tetrachoric : Tetrachoric correlation
+  # * Statsample::Bivariate::Polychoric  : Polychoric correlation (using joint, two-step and polychoric series)
   module Bivariate
+    autoload(:Polychoric, "statsample/bivariate/polychoric")
+    autoload(:Tetrachoric, "statsample/bivariate/tetrachoric")
+    
     class << self
       # Covariance between two vectors
       def covariance(v1,v2)

data/lib/statsample/bivariate/pearson.rb

@@ -0,0 +1,55 @@
+module Statsample
+  module Bivariate
+    # = Pearson correlation coefficient (r) 
+    # 
+    # The moment-product Pearson's correlation coefficient, known as 'r'
+    # is a measure of bivariate associate between two continous
+    # variables.
+    # 
+    # == Usage
+    #   a = [1,2,3,4,5,6].to_scale
+    #   b = [2,3,4,5,6,7].to_scale
+    #   pearson = Statsample::Bivariate::Pearson.new(a,b)
+    #   puts pearson.r
+    #   puts pearson.t
+    #   puts pearson.probability
+    # 
+    #   puts pearson.summary
+    # 
+    class Pearson
+      
+      include Statsample::Test
+      include Summarizable
+      # Name of correlation
+      attr_accessor :name
+      # Tails for probability (:both, :left or :right)
+      attr_accessor :tails     
+      attr_accessor :n      
+      def initialize(v1,v2,opts=Hash.new)
+        @v1_name,@v2_name = v1.name,v2.name
+        @v1,@v2           = Statsample.only_valid_clone(v1,v2)
+        @n=@v1.size
+        opts_default={
+          :name=>_("Correlation (%s - %s)") % [@v1_name, @v2_name],
+          :tails=>:both
+        }
+        @opts=opts.merge(opts_default)
+        @opts.each{|k,v|
+          self.send("#{k}=",v) if self.respond_to? k
+        }
+      end
+      def r
+        Statsample::Bivariate.pearson(@v1,@v2)
+      end
+      def t
+        Statsample::Bivariate.t_pearson(@v1,@v2)
+      end
+      def probability
+        p_using_cdf(Distribution::T.cdf(t, @v1.size-2), tails)
+      end
+      def report_building(builder)
+        builder.text(_("%s : r=%0.3f (t:%0.3f, g.l.=%d, p:%0.3f / %s tails)") % [@name, r,t, (n-2), probability, tails])
+      end
+    end
+  end
+end

data/lib/statsample/dataset.rb

@@ -39,13 +39,15 @@ module Statsample
   # 
   # 
   # ==Usage
-  # Create a empty dataset
+  # Create a empty dataset:
   #   Dataset.new()
-  # Create a dataset with three empty vectors, called <tt>v1</tt>, <tt>v2</tt> and <tt>v3</tt>
+  # Create a dataset with three empty vectors, called <tt>v1</tt>, <tt>v2</tt> and <tt>v3</tt>:
   #   Dataset.new(%w{v1 v2 v3})
-  # Create a dataset with two vectors
+  # Create a dataset with two vectors, called <tt>v1</tt>
+  # and <tt>v2</tt>:
   #   Dataset.new({'v1'=>%w{1 2 3}.to_vector, 'v2'=>%w{4 5 6}.to_vector})
-  # Create a dataset with two given vectors (v1 and v2), with vectors on inverted order
+  # Create a dataset with two given vectors (v1 and v2), 
+  # with vectors on inverted order:
   #   Dataset.new({'v2'=>v2,'v1'=>v1},['v2','v1'])
   #
   # The fast way to create a dataset uses Hash#to_dataset, with
@@ -59,7 +61,7 @@ module Statsample
     include Summarizable
     # Hash of Statsample::Vector
     attr_reader :vectors
-    # Ordered names of vectors
+    # Ordered ids of vectors
     attr_reader :fields
     # Name of dataset
     attr_accessor:name
@@ -67,7 +69,7 @@ module Statsample
     attr_reader :cases
     # Location of pointer on enumerations methods (like #each)
     attr_reader :i
-    
+
     # Generates a new dataset, using three vectors
     # - Rows
     # - Columns
@@ -87,7 +89,8 @@ module Statsample
     #    b  1   0
     #
     # Useful to process outputs from databases
-    #    
+    #
+    
     def self.crosstab_by_asignation(rows,columns,values)
       raise "Three vectors should be equal size" if rows.size!=columns.size or rows.size!=values.size
       cols_values=columns.factors
@@ -123,7 +126,6 @@ module Statsample
     # [fields]  Array of names for vectors. Is only used for set the
     # order of variables. If empty, vectors keys on alfabethic order as
     # used as fields
-
     #
     def initialize(vectors={}, fields=[])
       @@n_dataset||=0
@@ -141,6 +143,10 @@ module Statsample
       end
       @i=nil
     end
+    
+    #
+    # Returns a GSL::matrix
+    #
     def to_gsl_matrix
       matrix=GSL::Matrix.alloc(cases,@vectors.size)
       each_array do |row|
@@ -171,7 +177,7 @@ module Statsample
     end
     # Returns a duplicate of the Database
     # If fields given, only include those vectors.
-    # Every vector will be dup
+    # Every vector will be dup.
     def dup(*fields_to_include)
       if fields_to_include.size==1 and fields_to_include[0].is_a? Array
         fields_to_include=fields_to_include[0]
@@ -186,6 +192,10 @@ module Statsample
       }
       Dataset.new(vectors,fields)
     end
+    # Returns (when possible) a cheap copy of dataset.
+    # If no vector have missing values, returns original vectors.
+    # If missing values presents, uses Dataset.dup_only_valid
+    #
     def clone_only_valid(*fields_to_include)
       if fields_to_include.size==1 and fields_to_include[0].is_a? Array
         fields_to_include=fields_to_include[0]
@@ -240,7 +250,7 @@ module Statsample
       ds_new.update_valid_data
       ds_new
     end
-      # Returns a dataset with standarized data
+    # Returns a dataset with standarized data
     def standarize
       ds=dup()
       ds.fields.each do |f|
@@ -261,15 +271,18 @@ module Statsample
     def ==(d2)
       @vectors==d2.vectors and @fields==d2.fields
     end
+    # Returns vector <tt>c</tt>
     def col(c)
       @vectors[c]
     end
     alias_method :vector, :col
-    def add_vector(name,vector)
+    # Equal to Dataset[<tt>name</tt>]=<tt>vector</tt>
+    def add_vector(name, vector)
       raise ArgumentError, "Vector have different size" if vector.size!=@cases
       @vectors[name]=vector
       check_order
     end
+    # Returns true if dataset have vector <tt>v</tt>
     def has_vector? (v)
       return @vectors.has_key?(v)
     end
@@ -295,8 +308,8 @@ module Statsample
     # * Hash: keys equal to fields
     # If uvd is false, #update_valid_data is not executed after 
     # inserting a case. This is very useful if you want to increase the 
-    # performance on inserting many cases, 
-    # because #update_valid_data performs check on vectors and on the dataset
+    # performance on inserting many cases,  because #update_valid_data 
+    # performs check on vectors and on the dataset
     
     def add_case(v,uvd=true)
       case v
@@ -323,7 +336,7 @@ module Statsample
       @fields.each{|f| @vectors[f].set_valid_data}
       check_length
     end
-    # Delete a vector
+    # Delete vector named <tt>name</tt>.
     def delete_vector(name)
       @fields.delete(name)
       @vectors.delete(name)
@@ -345,26 +358,27 @@ module Statsample
         add_vector(name+join+k,v)
       }
     end
-		def vector_by_calculation(type=:scale)
-			a=[]
-			each {|row|
-				a.push(yield(row))
-			}
-			a.to_vector(type)
-		end
-		# Returns a vector with sumatory of fields
-		# if fields parameter is empty, sum all fields 
-		def vector_sum(fields=nil)
-			a=[]
-			fields||=@fields
-			collect_with_index do |row, i|
-				if(fields.find{|f| !@vectors[f].data_with_nils[i]})
-					nil
-				else
-					fields.inject(0) {|ac,v| ac + row[v].to_f}
-				end
-      end
-		end
+    
+    def vector_by_calculation(type=:scale)
+      a=[]
+      each do |row|
+        a.push(yield(row))
+      end
+      a.to_vector(type)
+    end
+    # Returns a vector with sumatory of fields
+    # if fields parameter is empty, sum all fields 
+    def vector_sum(fields=nil)
+      a=[]
+      fields||=@fields
+      collect_with_index do |row, i|
+        if(fields.find{|f| !@vectors[f].data_with_nils[i]})
+          nil
+        else
+          fields.inject(0) {|ac,v| ac + row[v].to_f}
+        end
+      end
+    end
     # Check if #fields attribute is correct, after inserting or deleting vectors
     def check_fields(fields)
       fields||=@fields
@@ -614,14 +628,14 @@ module Statsample
       ds
     end
     
-		# creates a new vector with the data of a given field which the block returns true
-		def filter_field(field)
-			a=[]
-			each {|c|
-				a.push(c[field]) if yield c
-			}
-			a.to_vector(@vectors[field].type)
-		end
+    # creates a new vector with the data of a given field which the block returns true
+    def filter_field(field)
+      a=[]
+      each do |c|
+        a.push(c[field]) if yield c
+      end
+      a.to_vector(@vectors[field].type)
+    end
     
     def to_multiset_by_split_one_field(field)
       raise ArgumentError,"Should use a correct field name" if !@fields.include? field
@@ -802,8 +816,7 @@ module Statsample
       ds.update_valid_data
       ds
     end
-   
-		def report_building(b)
+    def report_building(b)
       b.section(:name=>@name) do |g|
         g.text _"Cases: %d"  % cases
         @fields.each do |f|
@@ -811,11 +824,6 @@ module Statsample
           g.parse_element(@vectors[f])
         end
       end
-		end
-    def as_r
-      require 'rsruby/dataframe'
-      r=RSRuby.instance
-
     end
   end
 end