statsample 0.7.0 → 0.8.0

data/History.txt

@@ -1,3 +1,10 @@
+=== 0.8.0 / 2010-03-29
+* New Statsample::Test::T module, with classes and methods to do Student's t tests for one and two samples. 
+* Statsample::PromiseAfter module to set a number of variables without explicitly call the compute or iterate method
+* All tests ported to MiniUnit
+* Directory 'demo' renamed to 'examples'
+* Bug fix on report_building on Statsample::Regression::Multiple classes
+
 === 0.7.0 / 2010-03-25
 * Ported to ReportBuilder 1.x series
 * Implementation of ruby based covariance and correlation changed to a clearer code

data/Manifest.txt

@@ -10,15 +10,16 @@ data/repeated_fields.csv
 data/test_binomial.csv
 data/tetmat_matrix.txt
 data/tetmat_test.txt
-demo/correlation_matrix.rb
-demo/dominance_analysis_bootstrap.rb
-demo/dominanceanalysis.rb
-demo/levene.rb
-demo/multiple_regression.rb
-demo/multivariate_correlation.rb
-demo/polychoric.rb
-demo/principal_axis.rb
-demo/tetrachoric.rb
+examples/correlation_matrix.rb
+examples/dominance_analysis.rb
+examples/dominance_analysis_bootstrap.rb
+examples/levene.rb
+examples/multiple_regression.rb
+examples/multivariate_correlation.rb
+examples/polychoric.rb
+examples/principal_axis.rb
+examples/t_test.rb
+examples/tetrachoric.rb
 lib/distribution.rb
 lib/distribution/chisquare.rb
 lib/distribution/f.rb
@@ -45,6 +46,7 @@ lib/statsample/factor.rb
 lib/statsample/factor/pca.rb
 lib/statsample/factor/principalaxis.rb
 lib/statsample/factor/rotation.rb
+lib/statsample/graph.rb
 lib/statsample/graph/gdchart.rb
 lib/statsample/graph/svgboxplot.rb
 lib/statsample/graph/svggraph.rb
@@ -74,6 +76,7 @@ lib/statsample/resample.rb
 lib/statsample/srs.rb
 lib/statsample/test.rb
 lib/statsample/test/levene.rb
+lib/statsample/test/t.rb
 lib/statsample/test/umannwhitney.rb
 lib/statsample/vector.rb
 po/es/statsample.mo
@@ -93,12 +96,14 @@ test/test_dominance_analysis.rb
 test/test_factor.rb
 test/test_ggobi.rb
 test/test_gsl.rb
+test/test_helpers.rb
 test/test_histogram.rb
 test/test_logit.rb
 test/test_matrix.rb
 test/test_mle.rb
 test/test_multiset.rb
 test/test_permutation.rb
+test/test_promise_after.rb
 test/test_regression.rb
 test/test_reliability.rb
 test/test_resample.rb
@@ -107,6 +112,7 @@ test/test_statistics.rb
 test/test_stest.rb
 test/test_stratified.rb
 test/test_svg_graph.rb
+test/test_test_t.rb
 test/test_umannwhitney.rb
 test/test_vector.rb
 test/test_xls.rb

data/README.txt

@@ -11,10 +11,12 @@ Includes:
 * 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), Tetrachoric, Polychoric
+* Tests: T, Levene, U-Mannwhitney, One-Way Anova
 * Regression: Simple, Multiple, Probit  and Logit
 * Factorial Analysis: Extraction (PCA and Principal Axis) and Rotation (Varimax and relatives)
 * Dominance Analysis, with multivariate dependent and bootstrap (Azen & Budescu)
 * Sample calculation related formulas
+* Creates reports on text, html and rtf, using ReportBuilder
 
 == FEATURES:
 
@@ -47,6 +49,10 @@ Includes:
 * Module Statsample::Crosstab provides function to create crosstab for categorical data
 * Reliability analysis provides functions to analyze scales. Class ItemAnalysis provides statistics like mean, standard deviation for a scale, Cronbach's alpha and standarized Cronbach's alpha, and for each item: mean, correlation with total scale, mean if deleted, Cronbach's alpha is deleted. With HtmlReport, graph the histogram of the scale and the Item Characteristic Curve for each item
 * Module Statsample::SRS (Simple Random Sampling) provides a lot of functions to estimate standard error for several type of samples
+* Module Statsample::Test provides several methods and classes to perform inferencial statistics
+  * Statsample::Test::Levene
+  * Statsample::Test::UMannWhitney
+  * Statsample::Test::T
 * Interfaces to gdchart, gnuplot and SVG::Graph 
 
 

data/Rakefile

@@ -88,4 +88,12 @@ task :publicar_docs => [:clean, :docs] do
   sh %{rsync #{h.rsync_args} #{local_dir}/ #{host}:#{remote_dir}}
 end
     
+task :release => [:tag] do 
+end
+
+task :tag do	
+  sh %(svn commit -m "Version bump: #{Statsample::VERSION}")
+	sh %(svn cp https://ruby-statsample.googlecode.com/svn/reportbuilder/trunk https://ruby-statsample.googlecode.com/svn/statsample/tags/v#{Statsample::VERSION} -m "ReportBuilder #{Statsample::VERSION} tagged")
+end
+
 # vim: syntax=Ruby

data/{demo → examples}/multiple_regression.rb

@@ -3,7 +3,7 @@ $:.unshift(File.dirname(__FILE__)+'/../lib/')
 
 require 'statsample'
 require 'benchmark'
-samples=10000
+samples=1000
 a=samples.times.collect {rand}.to_scale
 b=samples.times.collect {rand}.to_scale
 c=samples.times.collect {rand}.to_scale
@@ -15,7 +15,7 @@ ds['y']=ds.collect{|row| row['a']*5+row['b']*3+row['c']*2+row['d']*1+rand()}
 Benchmark.bm(7) do |x|
 
 
-rb=ReportBuilder.new("Multiple Regression Engines")
+rb=ReportBuilder.new(:name=>"Multiple Regression Engines")
 
 if Statsample.has_gsl?
   x.report("GSL:") {
@@ -29,6 +29,8 @@ end
   lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y',:name=>"Multiple Regression using RubyEngine")
   rb.add(lr.summary)
   }
-
   puts rb.to_text
 end
+
+
+

data/examples/t_test.rb

@@ -0,0 +1,11 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib')
+require 'statsample'
+a=10.times.map {rand(100)}.to_scale
+t_1=Statsample::Test.t_one_sample(a,{:u=>50})
+puts t_1.summary
+
+b=20.times.map {(rand(20))**2+50}.to_scale
+
+t_2=Statsample::Test.t_two_samples_independent(a,b)
+puts t_2.summary

data/lib/statistics2.rb

@@ -229,7 +229,7 @@ module Statistics2  # :nodoc:
       s *= (i - 1) * c2 / i
       i += 2
     end
-    if df & 1 != 0
+    if df.is_a? Float or df & 1 != 0
       0.5+(p*Math.sqrt(c2)+Math.atan(t/Math.sqrt(df)))/Math::PI
     else
       (1.0 + p) / 2.0

data/lib/statsample.rb

@@ -18,12 +18,10 @@
 #
 
 
-$:.unshift(File.dirname(__FILE__))
-$:.unshift(File.expand_path(File.dirname(__FILE__)+"/../ext"))
-
+#$:.unshift(File.dirname(__FILE__))
 require 'matrix'
 require 'distribution'
-raise "Install reportbuilder ~>1.0" unless gem 'reportbuilder','~>1.0'
+gem 'reportbuilder','~>1.0'
 require 'reportbuilder'
 class Numeric
   def square ; self * self ; end
@@ -113,7 +111,7 @@ module Statsample
       false
     end
   end
-  VERSION = '0.7.0'
+  VERSION = '0.8.0'
   SPLIT_TOKEN = ","
   autoload(:Database, 'statsample/converters')
   autoload(:Anova, 'statsample/anova')
@@ -140,7 +138,7 @@ module Statsample
   autoload(:Regression, 'statsample/regression')
   autoload(:Test, 'statsample/test')
   autoload(:Factor, 'statsample/factor')
-  
+  autoload(:Graph, 'statsample/graph')
   
   
   class << self
@@ -154,6 +152,7 @@ module Statsample
         false
       end
     end
+    
     # Create a matrix using vectors as columns.
     # Use:
     #
@@ -204,6 +203,58 @@ module Statsample
       u
     end
 	end
+  
+  module PromiseAfter
+    # Like memoizable module (http://promise.rubyforge.org/Promise.html)
+    # but this applies to set a lot or variables with one expensive method
+    # with a direct calling of dependent methods.
+    # If one of the dependent methods returns nil or false, the main method 
+    # is called.
+    #
+    # Use when
+    # 1. You have one expensive operation which set many internal variables
+    # 2. This expensive operations depends on values which can set
+    #    anytime BEFORE calculation of main function
+    # 
+    # I use for classes which requires a iteration to set several variables,
+    # hiding to user the need to explicitily call the iterate method.
+    # 
+    # Example:
+    #  class ExpensiveCalculation
+    #   include PromiseAfter
+    #   attr_accessor :y, :z
+    #   def initialize(y=nil,z=nil)
+    #     @y=y
+    #     @z=z
+    #   def compute
+    #     @a=@y*1000+@z*1000
+    #   end
+    #   def a
+    #      @a.nil? nil : "This is the value: #{@a}"
+    #   end
+    #   promise_after :compute, :a, :b
+    #  end
+    #  puts ExpensiveCalculation.new(1,2).a
+    
+    def promise_after(function, *syms)
+      syms.each do |sym|
+        # You should doc the method!
+        raise NoMethodError, "Method `#{sym}' doesn't exists! Create it first " unless method_defined? sym
+        alias_method((sym.to_s+"_without_promise_after").intern, sym)
+        define_method(sym) {
+          #sym_to_iv="@#{sym.to_s.gsub(":","")}".intern
+          #if !instance_variable_defined?(sym_to_iv) or instance_variable_get(sym_to_iv).nil?
+          if(!send(sym.to_s+"_without_promise_after"))
+            send(function)
+          end
+          send(sym.to_s+"_without_promise_after")
+        }
+
+      end
+    end
+  end
+  
+  
   module Writable
     def save(filename)
       fp=File.open(filename,"w")

data/lib/statsample/bivariate/polychoric.rb

@@ -65,6 +65,7 @@ module Statsample
     
     class Polychoric
       include GetText
+      extend Statsample::PromiseAfter
       bindtextdomain("statsample")
       # Name of the analysis
       attr_accessor :name
@@ -135,28 +136,16 @@ module Statsample
         compute_basic_parameters
       end
       # Returns the polychoric correlation
-      def r
-        if @r.nil?
-          compute
-        end
-        @r
-      end
+      attr_reader :r
       # Returns the rows thresholds
+      attr_reader :alpha
+      # Returns the columns thresholds
+      attr_reader :beta
       
-      def threshold_x
-        if @alpha.nil?
-          compute
-        end
-        @alpha
-      end
-      # Returns the column thresholds
+      promise_after :compute, :r, :alpha, :beta
       
-      def threshold_y
-        if @beta.nil?
-          compute
-        end
-        @beta
-      end
+      alias :threshold_x :alpha
+      alias :threshold_y :beta
       
       
       # Start the computation of polychoric correlation
@@ -739,22 +728,20 @@ module Statsample
       end
       
       def summary
-        rp=ReportBuilder.new()
-        rp.add(self)
-        rp.to_text
+        rp=ReportBuilder.new(:no_title=>true).add(self).to_text
       end
+     
       
       def report_building(generator) # :nodoc: 
-        compute if @r.nil?
+        #compute if r.nil?
         section=ReportBuilder::Section.new(:name=>@name)
-        t=ReportBuilder::Table.new(:name=>_("Contingence Table"),:header=>[""]+(@n.times.collect {|i| "Y=#{i}"})+["Total"])
+        t=ReportBuilder::Table.new(:name=>_("Contingence Table"), :header=>[""]+(@n.times.collect {|i| "Y=#{i}"})+["Total"])
         @m.times do |i|
           t.row(["X = #{i}"]+(@n.times.collect {|j| @matrix[i,j]}) + [@sumr[i]])
         end
         t.hr
         t.row(["T"]+(@n.times.collect {|j| @sumc[j]})+[@total])
         section.add(t)
-        #generator.parse_element(t)
         section.add(sprintf("r: %0.4f",r))
         t=ReportBuilder::Table.new(:name=>_("Thresholds"), :header=>["","Value"])
         threshold_x.each_with_index {|val,i|

data/lib/statsample/bivariate/tetrachoric.rb

@@ -114,9 +114,7 @@ module Statsample
       end
       # Summary of the analysis
       def summary
-        rp=ReportBuilder.new(:name=>@name)
-        rp.add(self)
-        rp.to_text
+        ReportBuilder.new(:name=>@name).add(self).to_text
       end
 
       def report_building(generator) # :nodoc:

data/lib/statsample/converter/csv.rb

@@ -1,21 +1,20 @@
-if RUBY_VERSION<"1.9"
-  require 'fastercsv'
-  Statsample::CSV_klass=FasterCSV  
-else
-  require 'csv'
-  Statsample::CSV_klass=CSV  
-  
-end
+
 
 module Statsample
   class CSV < SpreadsheetBase
+    if RUBY_VERSION<"1.9"
+      require 'fastercsv'
+      CSV_klass=::FasterCSV  
+    else
+      require 'csv'
+      CSV_klass=::CSV  
+    end    
     class << self
       # Returns a Dataset  based on a csv file
       #
       # USE:
       #     ds=Statsample::CSV.read("test_csv.csv")
-      def read(filename, empty=[''],ignore_lines=0,fs=nil,rs=nil)
-        
+      def read(filename, empty=[''],ignore_lines=0,fs=nil,rs=nil)        
         first_row=true
         fields=[]
         fields_data={}
@@ -24,7 +23,7 @@ module Statsample
         opts={}
         opts[:col_sep]=fs unless fs.nil?
         opts[:row_sep]=rs unless rs.nil?
-        csv=Statsample::CSV_klass.send(:open, filename,'r',opts)
+        csv=CSV_klass.open(filename,'r',opts)
         csv.each do |row|
           line_number+=1
           if(line_number<=ignore_lines)
@@ -51,7 +50,7 @@ module Statsample
       #     Statsample::CSV.write(ds,"test_csv.csv")
       def write(dataset,filename, convert_comma=false,*opts)
         
-        writer=Statsample::CSV_klass.send(:open, filename,'w',*opts)
+        writer=CSV_klass.open(filename,'w',*opts)
         writer << dataset.fields
         dataset.each_array do|row|
           if(convert_comma)

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -171,10 +171,9 @@ module Statsample
       end
       # Summary of analysis
       def summary
-        rp=ReportBuilder.new()
-        rp.add(self)
-        rp.to_text
+        rp=ReportBuilder.new().add(self).to_text
       end
+      
       def t
         Distribution::T.p_value(1-((1-@alpha) / 2), @n_samples - 1)
       end

data/lib/statsample/factor/principalaxis.rb

@@ -90,8 +90,6 @@ module Factor
       @component_matrix
     end
     # Iterate to find the factors
-    # Parameters
-    # * m: Number of factors
     def iterate(m=nil)
       @clean=false
       m||=@m

data/lib/statsample/factor/rotation.rb

@@ -18,13 +18,14 @@ module Factor
   class Rotation
     EPSILON=1e-15
     MAX_ITERATIONS=25
-    
+    extend Statsample::PromiseAfter
     attr_reader :iterations, :rotated, :component_transformation_matrix, :h2
     # Maximum number of iterations    
     attr_accessor :max_iterations
     # Maximum precision    
     attr_accessor :epsilon
     
+    promise_after :iterate, :iterations, :rotated, :component_transformation_matrix, :h2
     
     def initialize(matrix, opts=Hash.new)
       @matrix=matrix
@@ -33,19 +34,16 @@ module Factor
       @component_transformation_matrix=nil
       @max_iterations=MAX_ITERATIONS
       @epsilon=EPSILON
+      @rotated=nil
       @h2=(@matrix.collect {|c| c**2} * Matrix.column_vector([1]*@m)).column(0).to_a
       opts.each{|k,v|
         self.send("#{k}=",v) if self.respond_to? k
       }
-      
-      
     end
     alias_method :communalities, :h2
     alias_method :rotated_component_matrix, :rotated
-    # Start iteration of 
-    def iterate(max_i=nil)
-      max_i||=@max_iterations
-      @max_iterations=max_i
+    # Start iteration 
+    def iterate
       t=Matrix.identity(@m)
       b=@matrix.dup
       h=Matrix.diagonal(*@h2).collect {|c| Math::sqrt(c)}
@@ -54,7 +52,7 @@ module Factor
       @not_converged=true
       @iterations=0
       while @not_converged
-        break if iterations>max_i 
+        break if iterations>@max_iterations
         @iterations+=1
         #puts "Iteration #{iterations}"
         num_pairs=@m*(@m-1).quo(2)