statsample 0.12.0 → 0.13.0

data/lib/statsample/dominanceanalysis.rb

@@ -1,4 +1,3 @@
-
 module Statsample
   # Dominance Analysis is a procedure based on an examination of the R<sup>2</sup> values
   # for all possible subset models, to identify the relevance of one or more 
@@ -57,7 +56,7 @@ module Statsample
   # * Azen, R. & Budescu, D.V. (2006). Comparing predictors in Multivariate Regression Models: An extension of Dominance Analysis. <em>Journal of Educational and Behavioral Statistics, 31</em>(2), 157-180.
   #
   class DominanceAnalysis
-	include Summarizable
+    include Summarizable
     # Class to generate the regressions. Default to Statsample::Regression::Multiple::MatrixEngine
     attr_accessor :regression_class
     # Name of analysis

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -66,9 +66,8 @@ module Statsample
     #
     # * Azen, R. & Budescu, D.V. (2003). The dominance analysis approach for comparing predictors in multiple regression. <em>Psychological Methods, 8</em>(2), 129-148.
     class Bootstrap
-      include GetText
       include Writable
-      bindtextdomain("statsample")
+      include Summarizable
       # Total Dominance results
       attr_reader :samples_td
       # Conditional Dominance results
@@ -169,68 +168,61 @@ module Statsample
           }
         end
       end
-      # Summary of analysis
-      def summary
-        rp=ReportBuilder.new().add(self).to_text
-      end
-      
       def t
         Distribution::T.p_value(1-((1-@alpha) / 2), @n_samples - 1)
       end
-      def report_building(generator) # :nodoc:
+      def report_building(builder) # :nodoc:
         raise "You should bootstrap first" if @n_samples==0
-        anchor=generator.toc_entry(_("DAB: ")+@name)
-        generator.html "<div class='dominance-analysis-bootstrap'>#{@name}<a name='#{anchor}'></a>"
-        
-        generator.text _("Sample size: %d\n") % @n_samples
-        generator.text "t: #{t}\n"
-        generator.text _("Linear Regression Engine: %s") % @regression_class.name
-        
-        table=ReportBuilder::Table.new(:name=>"Bootstrap report", :header => [_("pairs"), "sD","Dij", _("SE(Dij)"), "Pij", "Pji", "Pno", _("Reproducibility")])
-        table.row([_("Complete dominance")])
-        table.hr
-        @pairs.each{|pair|
-          std=@samples_td[pair].to_vector(:scale)
-          ttd=da.total_dominance_pairwise(pair[0],pair[1])
-          table.row(summary_pairs(pair,std,ttd))
-        }
-        table.hr
-        table.row([_("Conditional dominance")])
-        table.hr
-        @pairs.each{|pair|
-          std=@samples_cd[pair].to_vector(:scale)
-          ttd=da.conditional_dominance_pairwise(pair[0],pair[1])
-          table.row(summary_pairs(pair,std,ttd))
-        
-        }
-        table.hr
-        table.row([_("General Dominance")])
-        table.hr
-        @pairs.each{|pair|
-          std=@samples_gd[pair].to_vector(:scale)
-          ttd=da.general_dominance_pairwise(pair[0],pair[1])
-          table.row(summary_pairs(pair,std,ttd))
-        }
-        generator.parse_element(table)
-        
-        table=ReportBuilder::Table.new(:name=>_("General averages"), :header=>[_("var"), _("mean"), _("se"), _("p.5"), _("p.95")])
-        
-        @fields.each{|f|
-          v=@samples_ga[f].to_vector(:scale)
-          row=[@ds.label(f), sprintf("%0.3f",v.mean), sprintf("%0.3f",v.sd), sprintf("%0.3f",v.percentil(5)),sprintf("%0.3f",v.percentil(95))]
-          table.row(row)
-        
-        }
-        
-        generator.parse_element(table)
-        generator.html("</div>")
+        builder.section(:name=>@name) do |generator|
+          generator.text _("Sample size: %d\n") % @n_samples
+          generator.text "t: #{t}\n"
+          generator.text _("Linear Regression Engine: %s") % @regression_class.name
+          
+          table=ReportBuilder::Table.new(:name=>"Bootstrap report", :header => [_("pairs"), "sD","Dij", _("SE(Dij)"), "Pij", "Pji", "Pno", _("Reproducibility")])
+          table.row([_("Complete dominance"),"","","","","","",""])
+          table.hr
+          @pairs.each{|pair|
+            std=@samples_td[pair].to_vector(:scale)
+            ttd=da.total_dominance_pairwise(pair[0],pair[1])
+            table.row(summary_pairs(pair,std,ttd))
+          }
+          table.hr
+          table.row([_("Conditional dominance"),"","","","","","",""])
+          table.hr
+          @pairs.each{|pair|
+            std=@samples_cd[pair].to_vector(:scale)
+            ttd=da.conditional_dominance_pairwise(pair[0],pair[1])
+            table.row(summary_pairs(pair,std,ttd))
+          
+          }
+          table.hr
+          table.row([_("General Dominance"),"","","","","","",""])
+          table.hr
+          @pairs.each{|pair|
+            std=@samples_gd[pair].to_vector(:scale)
+            ttd=da.general_dominance_pairwise(pair[0],pair[1])
+            table.row(summary_pairs(pair,std,ttd))
+          }
+          generator.parse_element(table)
+          
+          table=ReportBuilder::Table.new(:name=>_("General averages"), :header=>[_("var"), _("mean"), _("se"), _("p.5"), _("p.95")])
+          
+          @fields.each{|f|
+            v=@samples_ga[f].to_vector(:scale)
+            row=[@ds[f].name, sprintf("%0.3f",v.mean), sprintf("%0.3f",v.sd), sprintf("%0.3f",v.percentil(5)),sprintf("%0.3f",v.percentil(95))]
+            table.row(row)
+          
+          }
+          
+          generator.parse_element(table)
+        end
       end
       def summary_pairs(pair,std,ttd)
           freqs=std.proportions
           [0, 0.5, 1].each{|n|
               freqs[n]=0 if freqs[n].nil?
           }
-          name=@ds.label(pair[0])+" - "+@ds.label(pair[1])
+          name="%s - %s" % [@ds[pair[0]].name, @ds[pair[1]].name]
           [name,f(ttd,1),f(std.mean,4),f(std.sd),f(freqs[1]), f(freqs[0]), f(freqs[0.5]), f(freqs[ttd])]
       end
       def f(v,n=3)

data/lib/statsample/factor.rb

@@ -11,7 +11,6 @@ module Statsample
   #   * Statsample::Factor::Varimax
   #   * Statsample::Factor::Equimax
   #   * Statsample::Factor::Quartimax
-  # 
   # See documentation of each class to use it
   module Factor
   end

data/lib/statsample/factor/parallelanalysis.rb

@@ -15,7 +15,7 @@ module Factor
 class ParallelAnalysis
   
   include DirtyMemoize
-  
+  include Summarizable
   # Number of random sets to produce. 50 by default
   attr_accessor :iterations
   # Name of analysis
@@ -47,7 +47,7 @@ class ParallelAnalysis
     @n_variables=@fields.size
     @n_cases=ds.cases
     opts_default={
-      :name=>"Parallel Analysis",
+      :name=>_("Parallel Analysis"),
       :iterations=>50,
       :bootstrap_method => :raw_data,
       :factor_class => Statsample::Factor::PCA,
@@ -59,10 +59,6 @@ class ParallelAnalysis
     @opts[:matrix_method]==:correlation_matrix if @opts[:bootstrap_method]==:parameters
     opts_default.keys.each {|k| send("#{k}=", @opts[k]) }
   end
-  # Summary of results
-  def summary
-    ReportBuilder.new(:no_title=>true).add(self).to_text
-  end
   # Number of factor to retent
   def number_of_factors
     total=0
@@ -73,13 +69,13 @@ class ParallelAnalysis
   end
   def report_building(g) #:nodoc:
     g.section(:name=>@name) do |s|
-      s.text "Bootstrap Method: #{bootstrap_method}"
-      s.text "Correlation Matrix type : #{matrix_method}"
-      s.text "Number of variables: #{@n_variables}"
-      s.text "Number of cases: #{@n_cases}"
-      s.text "Number of iterations: #{@iterations}"
-      s.text "Number or factors to preserve: #{number_of_factors}"
-      s.table(:name=>"Eigenvalues", :header=>["Eigenvalue", "actual", "mean","p.#{percentil}","preserve?"]) do |t|
+      s.text _("Bootstrap Method: %s") % bootstrap_method
+      s.text _("Correlation Matrix type : %s") % matrix_method
+      s.text _("Number of variables: %d") % @n_variables
+      s.text _("Number of cases: %d") % @n_cases
+      s.text _("Number of iterations: %d") % @iterations
+      s.text _("Number or factors to preserve: %d") % number_of_factors
+      s.table(:name=>_("Eigenvalues"), :header=>[_("Eigenvalue"), _("actual"), _("mean"),"p.#{percentil}",_("preserve?")]) do |t|
         ds_eigenvalues.fields.each_with_index do |f,i|
           v=ds_eigenvalues[f]
           t.row [i+1, "%0.4f" % @original[i], "%0.4f" %  v.mean, "%0.4f" %  v.percentil(percentil), (v.percentil(percentil)>0 and @original[i] > v.percentil(percentil)) ? "Yes":""]

data/lib/statsample/factor/pca.rb

@@ -36,8 +36,7 @@ module Factor
     attr_accessor :m
     # Use GSL if available
     attr_accessor :use_gsl
-    include GetText
-    bindtextdomain("statsample")
+    include Summarizable
     
     def initialize(matrix, opts=Hash.new)
 	@use_gsl=nil
@@ -139,25 +138,21 @@ module Factor
         @eigenpairs=@eigenpairs.sort.reverse
     end
     
-    def summary
-      ReportBuilder.new(:no_title=>true).add(self).to_text
-    end
     def report_building(builder) # :nodoc:
       builder.section(:name=>@name) do |generator|
-      generator.text "Number of factors: #{m}"
-      generator.table(:name=>_("Communalities"), :header=>["Variable","Initial","Extraction"]) do |t|
+      generator.text _("Number of factors: %d") % m
+      generator.table(:name=>_("Communalities"), :header=>[_("Variable"),_("Initial"),_("Extraction")]) do |t|
         communalities(m).each_with_index {|com,i|
           t.row([i, 1.0, sprintf("%0.3f", com)])
         }
       end      
-      generator.table(:name=>_("Eigenvalues"), :header=>["Variable","Value"]) do |t|
+      generator.table(:name=>_("Eigenvalues"), :header=>[_("Variable"),_("Value")]) do |t|
         eigenvalues.each_with_index {|eigenvalue,i|
           t.row([i, sprintf("%0.3f",eigenvalue)])
         }
       end
       
-      generator.table(:name=>_("Component Matrix"), :header=>["Variable"]+m.times.collect {|c| c+1}) do |t|
-        
+      generator.table(:name=>_("Component Matrix"), :header=>[_("Variable")]+m.times.collect {|c| c+1}) do |t|
         i=0
         component_matrix(m).to_a.each do |row|
           t.row([i]+row.collect {|c| sprintf("%0.3f",c)})

data/lib/statsample/factor/principalaxis.rb

@@ -28,12 +28,11 @@ module Factor
   #   
   class PrincipalAxis
     include DirtyMemoize
+    include Summarizable
     # Minimum difference between succesive iterations on sum of communalities
     DELTA=1e-3
     # Maximum number of iterations
     MAX_ITERATIONS=50
-    include GetText
-    bindtextdomain("statsample")
     # Number of factors. Set by default to the number of factors
     # with eigen values > 1 on PCA over data
     attr_accessor :m
@@ -58,6 +57,12 @@ module Factor
     
     def initialize(matrix, opts=Hash.new)
       @matrix=matrix
+      if @matrix.respond_to? :fields
+        @fields=@matrix.fields
+      else
+        @fields=@matrix.row_size.times.map {|i| _("Variable %d") % (i+1)}
+      end
+      
       @name=""
       @m=nil
       @initial_eigenvalues=nil
@@ -167,40 +172,29 @@ module Factor
       rxx=Matrix.rows(rows)
       [rxx,rxy]
     end
-    def summary
-      rp=ReportBuilder.new()
-      rp.add(self)
-      rp.to_text
-    end
     def report_building(generator)
       iterate if @clean
-      anchor=generator.toc_entry(_("Factor Analysis: ")+name)
-      generator.html "<div class='pca'>"+_("Factor Analysis")+" #{@name}<a name='#{anchor}'></a>"
-     
-      generator.text "Number of factors: #{m}"
-      generator.text "Iterations: #{@iterations}"
-      
-      t=ReportBuilder::Table.new(:name=>_("Communalities"), :header=>["Variable","Initial","Extraction"])
-      communalities(m).each_with_index {|com,i|
-        t.row([i, sprintf("%0.4f", initial_communalities[i]), sprintf("%0.3f", com)])
-      }
-      generator.parse_element(t)
-      
-      t=ReportBuilder::Table.new(:name=>_("Eigenvalues"), :header=>["Variable","Value"])
-      @initial_eigenvalues.each_with_index {|eigenvalue,i|
-        t.row([i, sprintf("%0.3f",eigenvalue)])
-      }
-      generator.parse_element(t)
-      
-      t=ReportBuilder::Table.new(:name=>_("Component Matrix"), :header=>["Variable"]+m.times.collect {|c| c+1})
-      
-      i=0
-      component_matrix(m).to_a.each do |row|
-        t.row([i]+row.collect {|c| sprintf("%0.3f",c)})
-        i+=1
+      generator.section(:name=>@name) do |s|
+        s.text _("Number of factors: %d") % m
+        s.text _("Iterations: %d") % @iterations
+        s.table(:name=>_("Communalities"), :header=>[_("Variable"),_("Initial"),_("Extraction")]) do |t|
+          communalities(m).each_with_index {|com,i|
+            t.row([@fields[i], sprintf("%0.4f", initial_communalities[i]), sprintf("%0.3f", com)])
+          }
+        end
+        s.table(:name=>_("Eigenvalues"), :header=>[_("Variable"),_("Value")]) do |t|
+          @initial_eigenvalues.each_with_index {|eigenvalue,i|
+            t.row([@fields[i], sprintf("%0.3f",eigenvalue)])
+          }
+        end
+        s.table(:name=>_("Component Matrix"), :header=>["Variable"]+m.times.collect {|c| c+1}) do |t|
+          i=0
+          component_matrix(m).to_a.each do |row|
+            t.row([@fields[i]]+row.collect {|c| sprintf("%0.3f",c)})
+            i+=1
+          end
+        end
       end
-      generator.parse_element(t)
-      generator.html("</div>")
     end
     
     dirty_writer :max_iterations, :epsilon, :smc

data/lib/statsample/matrix.rb

@@ -37,12 +37,8 @@ module Statsample
   # 
   module CovariateMatrix
     include Summarizable
-    # Gives a nice summary
-    def summary
-      rp=ReportBuilder.new()
-      rp.add(self)
-      rp.to_text
-    end
+    @@covariatematrix=0
+
     # Get type of covariate matrix. Could be :covariance or :correlation
     def type
       if row_size==column_size
@@ -81,7 +77,7 @@ module Statsample
     end
     def fields
       raise "Should be square" if !square?
-      @fields_x
+      fields_x
     end
     def fields=(v)
       raise "Matrix should be square" if !square?
@@ -97,17 +93,21 @@ module Statsample
       @fields_y=v
     end
     def fields_x
-      @fields_x||=row_size.times.collect {|i| i} 
+      @fields_x||=row_size.times.collect {|i| _("X%d") % i} 
     end
     def fields_y
-      @fields_y||=column_size.times.collect {|i| i} 
+      @fields_y||=column_size.times.collect {|i| _("Y%d") % i} 
     end
     
     def name=(v)
       @name=v
     end
     def name
-      @name
+      @name||=get_new_name
+    end
+    def get_new_name
+      @@covariatematrix+=1
+      _("Covariate matrix %d") % @@covariatematrix
     end
     # Select a submatrix of factors. If you have a correlation matrix
     # with a, b and c, you could obtain a submatrix of correlations of
@@ -149,7 +149,7 @@ module Statsample
       matrix
     end
     def report_building(generator)
-      @name||= (type==:correlation ? "Correlation":"Covariance")+" Matrix"
+      @name||= (type==:correlation ? _("Correlation"):_("Covariance"))+_(" Matrix")
       generator.table(:name=>@name, :header=>[""]+fields_y) do |t|
         row_size.times {|i|
           t.row([fields_x[i]]+@rows[i].collect {|i1| sprintf("%0.3f",i1).gsub("0.",".")})

data/lib/statsample/mle.rb

@@ -134,7 +134,6 @@ module Statsample
     end
   end
 end
-
 require 'statsample/mle/normal'
 require 'statsample/mle/logit'
 require 'statsample/mle/probit'

data/lib/statsample/regression.rb

@@ -35,7 +35,6 @@ module Statsample
       #   => 1.99973746599856
       #   sr.r
       #   => 0.999987881153254
-
       def self.simple(x,y)
         Statsample::Regression::Simple.new_from_vectors(x,y)
       end

data/lib/statsample/reliability.rb

@@ -108,7 +108,7 @@ module Statsample
         out
       end # def
     end # self
-   end # Reliability
- end # Statsample
+  end # Reliability
+end # Statsample
 require 'statsample/reliability/scaleanalysis.rb'
 require 'statsample/reliability/multiscaleanalysis.rb'

data/lib/statsample/reliability/multiscaleanalysis.rb

@@ -1,33 +1,62 @@
 module Statsample
   module Reliability
-    # DSL for analysis of multiple scales analysis. Analoge of Scale Reliability analysis on SPSS.
-    # Returns several statistics for complete scale and each item
+    # DSL for analysis of multiple scales analysis. 
+    # Retrieves reliability analysis for each scale and
+    # provides fast accessors to correlations matrix,
+    # PCA and Factor Analysis.
+    # 
     # == Usage
     #  @x1=[1,1,1,1,2,2,2,2,3,3,3,30].to_vector(:scale)
     #  @x2=[1,1,1,2,2,3,3,3,3,4,4,50].to_vector(:scale)
     #  @x3=[2,2,1,1,1,2,2,2,3,4,5,40].to_vector(:scale)
     #  @x4=[1,2,3,4,4,4,4,3,4,4,5,30].to_vector(:scale)
     #  ds={'x1'=>@x1,'x2'=>@x2,'x3'=>@x3,'x4'=>@x4}.to_dataset
-    #  msa=Statsample::Reliability::MultiScaleAnalysis.new(:name=>"Scales") do |m|
-    #    m.scale :s1, "Section 1", ds.clone(%w{x1 x2})
-    #    m.scale :s2, "Section 2", ds.clone(%w{x3 x4})
-    #    m.correlation_matrix
-    #    m.factor_analysis
+    #  opts={:name=>"Scales", # Name of analysis
+    #        :summary_correlation_matrix=>true, # Add correlation matrix
+    #        :summary_pca } # Add PCA between scales
+    #  msa=Statsample::Reliability::MultiScaleAnalysis.new(opts) do |m|
+    #    m.scale :s1, ds.clone(%w{x1 x2})
+    #    m.scale :s2, ds.clone(%w{x3 x4}), {:name=>"Scale 2"}
     #  end
-    #  puts msa.summary
+    #  # Retrieve summary
+    #  puts msa.summary 
     class MultiScaleAnalysis
       include Statsample::Summarizable
+      # Hash with scales
       attr_reader :scales
+      # Name of analysis
       attr_accessor :name
+      # Add a correlation matrix on summary
       attr_accessor :summary_correlation_matrix
+      # Add PCA to summary
       attr_accessor :summary_pca
+      # Add Principal Axis to summary
+      attr_accessor :summary_principal_axis
+      # Options for Factor::PCA object
       attr_accessor :pca_options
+      # Options for Factor::PrincipalAxis 
+      attr_accessor :principal_axis_options
+      # Generates a new MultiScaleAnalysis
+      # Opts could be any accessor of the class 
+      # * :name, 
+      # * :summary_correlation_matrix
+      # * :summary_pca
+      # * :summary_principal_axis
+      # * :pca_options
+      # * :factor_analysis_options
+      #
+      # If block given, all methods should be called
+      # inside object environment.
+      # 
       def initialize(opts=Hash.new, &block)
         @scales=Hash.new
         opts_default={  :name=>_("Multiple Scale analysis"),
                         :summary_correlation_matrix=>false,
                         :summary_pca=>false,
-                        :pca_options=>Hash.new}
+                        :summary_principal_axis=>false,
+                        :pca_options=>Hash.new,
+                        :principal_axis_options=>Hash.new
+        }
         @opts=opts_default.merge(opts)
         @opts.each{|k,v|
           self.send("#{k}=",v) if self.respond_to? k
@@ -37,6 +66,12 @@ module Statsample
           block.arity<1 ? instance_eval(&block) : block.call(self)
         end
       end
+      # Add or retrieve a scale to analysis.
+      # If second parameters is a dataset, generates a ScaleAnalysis 
+      # for <tt>ds</tt>, named <tt>code</tt> with options <tt>opts</tt>.
+      # 
+      # If second parameters is empty, returns the ScaleAnalysis
+      # <tt>code</tt>.
       def scale(code,ds=nil, opts=nil)
         if ds.nil?
           @scales[code]
@@ -45,17 +80,24 @@ module Statsample
           @scales[code]=ScaleAnalysis.new(ds, opts)
         end
       end
+      # Delete ScaleAnalysis named <tt>code</tt>
       def delete_scale(code)
         @scales.delete code
       end
-      def pca(opts=Hash.new)
+      # Retrieves a Principal Component Analysis (Factor::PCA)
+      # using all scales, using <tt>opts</tt> a options.
+      def pca(opts=nil)
+        opts||=pca_options        
         Statsample::Factor::PCA.new(correlation_matrix,opts)
       end
-      def factor_analysis(opts=nil)
-        opts||=pca_options
-        Statsample::Factor::FactorAnalysis.new(correlation_matrix,opts)
+      # Retrieves a PrincipalAxis Analysis (Factor::PrincipalAxis)
+      # using all scales, using <tt>opts</tt> a options.
+      def principal_axis_analysis(opts=nil)
+        opts||=principal_axis_options
+        Statsample::Factor::PrincipalAxis.new(correlation_matrix,opts)
       end
-      
+      # Retrieves a Correlation Matrix between scales.
+      # 
       def correlation_matrix
         vectors=Hash.new
         @scales.each_pair do |code,scale|
@@ -63,7 +105,7 @@ module Statsample
         end
         Statsample::Bivariate.correlation_matrix(vectors.to_dataset)
       end
-      def report_building(b)
+      def report_building(b) # :nodoc:
         b.section(:name=>name) do |s|
           s.section(:name=>_("Reliability analysis of scales")) do |s2|
             @scales.each_pair do |k,scale|
@@ -80,6 +122,11 @@ module Statsample
               s2.parse_element(pca)
             end
           end
+          if summary_principal_axis
+            s.section(:name=>_("Principal Axis for %s") % name) do |s2|
+              s2.parse_element(principal_axis_analysis)
+            end
+          end          
         end
       end
     end