statsample 1.5.0 → 2.0.0

data/lib/statsample/dominanceanalysis.rb

@@ -7,13 +7,13 @@ module Statsample
   #
   # == Use
   #
-  #  a=1000.times.collect {rand}.to_numeric
-  #  b=1000.times.collect {rand}.to_numeric
-  #  c=1000.times.collect {rand}.to_numeric
-  #  ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
-  #  ds['y']=ds.collect{|row| row['a']*5+row['b']*3+row['c']*2+rand()}
-  #  da=Statsample::DominanceAnalysis.new(ds,'y')
-  #  puts da.summary
+  # a = Daru::Vector.new(1000.times.collect {rand})
+  # b = Daru::Vector.new(1000.times.collect {rand})
+  # c = Daru::Vector.new(1000.times.collect {rand})
+  # ds= Daru::DataFrame.new({:a => a,:b => b,:c => c})
+  # ds[:y] = ds.collect_rows {|row| row[:a]*5 + row[:b]*3 + row[:c]*2 + rand()}
+  # da=Statsample::DominanceAnalysis.new(ds, :y)
+  # puts da.summary
   # 
   # === Output:
   #
@@ -115,21 +115,21 @@ module Statsample
       }
       @dependent=dependent
       @dependent=[@dependent] unless @dependent.is_a? Array
-      
-      @predictors ||= input.fields-@dependent
-      
-      @name=_("Dominance Analysis:  %s over %s") % [ @predictors.flatten.join(",") , @dependent.join(",")] if @name.nil?
-      
-      if input.is_a? Statsample::Dataset
+
+      if input.kind_of? Daru::DataFrame
+        @predictors ||= input.vectors.to_a - @dependent
         @ds=input
         @matrix=Statsample::Bivariate.correlation_matrix(input)
         @cases=Statsample::Bivariate.min_n_valid(input)
       elsif input.is_a? ::Matrix
+        @predictors ||= input.fields-@dependent
         @ds=nil
         @matrix=input
       else
         raise ArgumentError.new("You should use a Matrix or a Dataset")
       end
+
+      @name=_("Dominance Analysis:  %s over %s") % [ @predictors.flatten.join(",") , @dependent.join(",")] if @name.nil?
       @models=nil
       @models_data=nil
       @general_averages=nil
@@ -264,22 +264,21 @@ module Statsample
     end
     
     def md(m)
-      models_data[m.sort {|a,b| a.to_s<=>b.to_s}]
+      models_data[m.sort {|a,b| a.to_s <=> b.to_s}]
     end
     # Get all model of size k
     def md_k(k)
       out=[]
-      @models.each{|m| out.push(md(m)) if m.size==k }
+      @models.each{ |m| out.push(md(m)) if m.size==k }
       out
     end
     
     # For a hash with arrays of numbers as values
     # Returns a hash with same keys and 
     # value as the mean of values of original hash
-    
     def get_averages(averages)
       out={}
-      averages.each{|key,val| out[key]=val.to_vector(:numeric).mean }
+      averages.each{ |key,val| out[key] = Daru::Vector.new(val).mean }
       out
     end
     # Hash with average for each k size model.

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -5,16 +5,16 @@ module Statsample
     #
     # == Usage
     # 
-    #  require 'statsample'
-    #  a=100.times.collect {rand}.to_numeric
-    #  b=100.times.collect {rand}.to_numeric
-    #  c=100.times.collect {rand}.to_numeric
-    #  d=100.times.collect {rand}.to_numeric
-    #  ds={'a'=>a,'b'=>b,'c'=>c,'d'=>d}.to_dataset
-    #  ds['y']=ds.collect{|row| row['a']*5+row['b']*2+row['c']*2+row['d']*2+10*rand()}
-    #  dab=Statsample::DominanceAnalysis::Bootstrap.new(ds2, 'y', :debug=>true)
-    #  dab.bootstrap(100,nil)
-    #  puts dab.summary
+    # require 'statsample'
+    # a = Daru::Vector.new(100.times.collect {rand})
+    # b = Daru::Vector.new(100.times.collect {rand})
+    # c = Daru::Vector.new(100.times.collect {rand})
+    # d = Daru::Vector.new(100.times.collect {rand})
+    # ds = Daru::DataFrame.new({:a => a,:b => b,:c => c,:d => d})
+    # ds[:y] = ds.collect_rows { |row| row[:a]*5+row[:b]*2+row[:c]*2+row[:d]*2+10*rand() }
+    # dab=Statsample::DominanceAnalysis::Bootstrap.new(ds, :y, :debug=>true)
+    # dab.bootstrap(100,nil)
+    # puts dab.summary
     # <strong>Output</strong>
     #   Sample size: 100
     #  t: 1.98421693632958
@@ -91,28 +91,28 @@ module Statsample
       ALPHA=0.95
       # Create a new Dominance Analysis Bootstrap Object
       # 
-      # * ds: A Dataset object
+      # * ds: A Daru::DataFrame object
       # * y_var: Name of dependent variable
       # * opts: Any other attribute of the class 
       def initialize(ds,y_var, opts=Hash.new)
-        @ds=ds
-        @y_var=y_var
-        @n=ds.cases
+        @ds    = ds
+        @y_var = y_var.respond_to?(:to_sym) ? y_var.to_sym : y_var
+        @n     = ds.nrows
         
         @n_samples=0
         @alpha=ALPHA
         @debug=false
         if y_var.is_a? Array
-          @fields=ds.fields-y_var
+          @fields=ds.vectors.to_a - y_var
           @regression_class=Regression::Multiple::MultipleDependent
           
         else
-          @fields=ds.fields-[y_var]
+          @fields=ds.vectors.to_a - [y_var]
           @regression_class=Regression::Multiple::MatrixEngine
         end
-        @samples_ga=@fields.inject({}){|a,v| a[v]=[];a}
+        @samples_ga=@fields.inject({}) { |a,v| a[v]=[]; a }
 
-        @name=_("Bootstrap dominance Analysis:  %s over %s") % [ ds.fields.join(",") , @y_var]
+        @name=_("Bootstrap dominance Analysis:  %s over %s") % [ ds.vectors.to_a.join(",") , @y_var]
         opts.each{|k,v|
           self.send("#{k}=",v) if self.respond_to? k
         }
@@ -130,15 +130,14 @@ module Statsample
       # each sample on @samples_td, @samples_cd, @samples_gd, @samples_ga
       # 
       # * number_samples: Number of new samples to add
-      # * n: size of each new sample. If nil, equal to original sample size
-      
+      # * n: size of each new sample. If nil, equal to original sample size     
       def bootstrap(number_samples,n=nil)
         number_samples.times{ |t|
           @n_samples+=1
           puts _("Bootstrap %d of %d") % [t+1, number_samples] if @debug
-          ds_boot=@ds.bootstrap(n)
+          ds_boot=@ds.bootstrap(n)                 
           da_1=DominanceAnalysis.new(ds_boot, @y_var, :regression_class => @regression_class)
-          
+
           da_1.total_dominance.each{|k,v|
             @samples_td[k].push(v)
           }
@@ -182,7 +181,7 @@ module Statsample
           table.row([_("Complete dominance"),"","","","","","",""])
           table.hr
           @pairs.each{|pair|
-            std=@samples_td[pair].to_vector(:numeric)
+            std=Daru::Vector.new(@samples_td[pair])
             ttd=da.total_dominance_pairwise(pair[0],pair[1])
             table.row(summary_pairs(pair,std,ttd))
           }
@@ -190,7 +189,7 @@ module Statsample
           table.row([_("Conditional dominance"),"","","","","","",""])
           table.hr
           @pairs.each{|pair|
-            std=@samples_cd[pair].to_vector(:numeric)
+            std=Daru::Vector.new(@samples_cd[pair])
             ttd=da.conditional_dominance_pairwise(pair[0],pair[1])
             table.row(summary_pairs(pair,std,ttd))
           
@@ -199,7 +198,7 @@ module Statsample
           table.row([_("General Dominance"),"","","","","","",""])
           table.hr
           @pairs.each{|pair|
-            std=@samples_gd[pair].to_vector(:numeric)
+            std=Daru::Vector.new(@samples_gd[pair])
             ttd=da.general_dominance_pairwise(pair[0],pair[1])
             table.row(summary_pairs(pair,std,ttd))
           }
@@ -208,10 +207,9 @@ module Statsample
           table=ReportBuilder::Table.new(:name=>_("General averages"), :header=>[_("var"), _("mean"), _("se"), _("p.5"), _("p.95")])
           
           @fields.each{|f|
-            v=@samples_ga[f].to_vector(:numeric)
+            v=Daru::Vector.new(@samples_ga[f])
             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)
-          
+            table.row(row)          
           }
           
           generator.parse_element(table)

data/lib/statsample/factor/parallelanalysis.rb

@@ -22,13 +22,13 @@ module Statsample
 
     class ParallelAnalysis
       def self.with_random_data(cases,vars,opts=Hash.new)
-        require 'ostruct'
-        ds=OpenStruct.new
-        ds.fields=vars.times.map {|i| "v#{i+1}"}
-        ds.cases=cases
+        ds= Daru::DataFrame.new({}, 
+          order: vars.times.map {|i| "v#{i+1}".to_sym},
+          index: cases )
         opts=opts.merge({:bootstrap_method=> :random, :no_data=>true})
         new(ds, opts)
       end
+
       include DirtyMemoize
       include Summarizable
       # Number of random sets to produce. 50 by default
@@ -61,9 +61,9 @@ module Statsample
       attr_accessor :use_gsl
       def initialize(ds, opts=Hash.new)
         @ds=ds
-        @fields=@ds.fields
+        @fields=@ds.vectors.to_a
         @n_variables=@fields.size
-        @n_cases=ds.cases
+        @n_cases=ds.nrows
         opts_default={
           :name=>_("Parallel Analysis"),
           :iterations=>50, # See Liu and Rijmen (2008)
@@ -82,7 +82,7 @@ module Statsample
       # Number of factor to retent
       def number_of_factors
         total=0
-        ds_eigenvalues.fields.each_with_index do |f,i|
+        ds_eigenvalues.vectors.to_a.each_with_index do |f,i|
           if (@original[i]>0 and @original[i]>ds_eigenvalues[f].percentil(percentil))
             total+=1
           else
@@ -101,7 +101,7 @@ module Statsample
           s.text _("Number of iterations: %d") % @iterations
           if @no_data
             s.table(:name=>_("Eigenvalues"), :header=>[_("n"), _("generated eigenvalue"), "p.#{percentil}"]) do |t|
-              ds_eigenvalues.fields.each_with_index do |f,i|
+              ds_eigenvalues.vectors.to_a.each_with_index do |f,i|
                 v=ds_eigenvalues[f]
                 t.row [i+1, "%0.4f" %  v.mean, "%0.4f" %  v.percentil(percentil), ]
               end
@@ -109,7 +109,7 @@ module Statsample
           else
             s.text _("Number or factors to preserve: %d") % number_of_factors 
             s.table(:name=>_("Eigenvalues"), :header=>[_("n"), _("data eigenvalue"), _("generated eigenvalue"),"p.#{percentil}",_("preserve?")]) do |t|
-              ds_eigenvalues.fields.each_with_index do |f,i|
+              ds_eigenvalues.vectors.to_a.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":""]
               end
@@ -120,11 +120,9 @@ module Statsample
       end
       # Perform calculation. Shouldn't be called directly for the user
       def compute
+        @original=Statsample::Bivariate.send(matrix_method, @ds).eigenvalues unless no_data
+        @ds_eigenvalues=Daru::DataFrame.new({}, order: (1..@n_variables).map{|v| ("ev_%05d" % v).to_sym})
         
-        
-        @original=Statsample::Bivariate.send(matrix_method, @ds).eigenvalues unless no_data        
-        @ds_eigenvalues=Statsample::Dataset.new((1..@n_variables).map{|v| "ev_%05d" % v})
-        @ds_eigenvalues.fields.each {|f| @ds_eigenvalues[f].type=:numeric}
         if bootstrap_method==:parameter or bootstrap_method==:random
           rng = Distribution::Normal.rng
         end
@@ -133,18 +131,18 @@ module Statsample
           begin
             puts "#{@name}: Iteration #{i}" if $DEBUG or debug
             # Create a dataset of dummy values
-            ds_bootstrap=Statsample::Dataset.new(@ds.fields)
+            ds_bootstrap = Daru::DataFrame.new({}, order: @ds.vectors, index: @n_cases)
             
             @fields.each do |f|
               if bootstrap_method==:random
-                ds_bootstrap[f]=@n_cases.times.map {|c| rng.call}.to_numeric
+                ds_bootstrap[f] = Daru::Vector.new(@n_cases.times.map {|c| rng.call})
               elsif bootstrap_method==:data
-                ds_bootstrap[f]=ds[f].sample_with_replacement(@n_cases)
+                ds_bootstrap[f] = ds[f].sample_with_replacement(@n_cases)
               else
                 raise "bootstrap_method doesn't recogniced"
               end
             end
-            ds_bootstrap.update_valid_data
+            ds_bootstrap.update
             
             matrix=Statsample::Bivariate.send(matrix_method, ds_bootstrap)
             matrix=matrix.to_gsl if @use_gsl
@@ -155,13 +153,13 @@ module Statsample
                 end
             end
             ev=matrix.eigenvalues
-            @ds_eigenvalues.add_case_array(ev)
+            @ds_eigenvalues.add_row(ev)
           rescue Statsample::Bivariate::Tetrachoric::RequerimentNotMeet => e
             puts "Error: #{e}" if $DEBUG
             redo
           end
         end
-        @ds_eigenvalues.update_valid_data
+        @ds_eigenvalues.update
       end
       dirty_memoize :number_of_factors, :ds_eigenvalues
       dirty_writer :iterations, :bootstrap_method, :percentil, :smc

data/lib/statsample/factor/pca.rb

@@ -13,11 +13,11 @@ module Factor
   # 
   # == Usage:
   #   require 'statsample'
-  #   a=[2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1].to_numeric
-  #   b=[2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9].to_numeric
-  #   ds={'a'=>a,'b'=>b}.to_dataset
-  #   cor_matrix=Statsample::Bivariate.correlation_matrix(ds)
-  #   pca=Statsample::Factor::PCA.new(cor_matrix)
+  #   a = Daru::Vector.new([2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1])
+  #   b = Daru::Vector.new([2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9])
+  #   ds = Daru::DataFrame.new({:a => a,:b => b})
+  #   cor_matrix = Statsample::Bivariate.correlation_matrix(ds)
+  #   pca=  Statsample::Factor::PCA.new(cor_matrix)
   #   pca.m
   #   => 1
   #   pca.eigenvalues
@@ -52,11 +52,13 @@ module Factor
     attr_accessor :rotation_type
     attr_accessor :matrix_type
     def initialize(matrix, opts=Hash.new)
-      @use_gsl=nil
+      @use_gsl = opts[:use_gsl]
+      opts.delete :use_gsl
+
       @name=_("Principal Component Analysis")
       @matrix=matrix
       @n_variables=@matrix.column_size      
-      @variables_names=(@matrix.respond_to? :fields) ? @matrix.fields : @n_variables.times.map {|i| _("VAR_%d") % (i+1)}
+      @variables_names=(@matrix.respond_to? :fields) ? @matrix.fields : @n_variables.times.map {|i| "VAR_#{i+1}".to_sym }
       
       @matrix_type = @matrix.respond_to?(:_type) ? @matrix._type : :correlation
       
@@ -67,13 +69,14 @@ module Factor
       opts.each{|k,v|
         self.send("#{k}=",v) if self.respond_to? k
       }
+
       if @use_gsl.nil?
         @use_gsl=Statsample.has_gsl?
       end
       if @matrix.respond_to? :fields
         @variables_names=@matrix.fields
       else
-        @variables_names=@n_variables.times.map {|i| "V#{i+1}"}
+        @variables_names=@n_variables.times.map {|i| "V#{i+1}".to_sym}
       end
       calculate_eigenpairs
       
@@ -81,7 +84,6 @@ module Factor
         # Set number of factors with eigenvalues > 1
         @m=@eigenpairs.find_all {|ev,ec| ev>=1.0}.size
       end
-      
     end
     def rotation
       @rotation_type.new(component_matrix)
@@ -92,10 +94,10 @@ module Factor
     def create_centered_ds
       h={}
       @original_ds.factors.each {|f|
-        mean=@original_ds[f].mean
-        h[f]=@original_ds[f].recode {|c| c-mean}
+        mean = @original_ds[f].mean
+        h[f] = @original_ds[f].recode {|c| c-mean}
       }
-      @ds=h.to_dataset
+      @ds = Daru::DataFrame.new(h)
     end
     
     # Feature matrix for +m+ factors
@@ -137,8 +139,8 @@ module Factor
       pcs=(fv.transpose*data_matrix.transpose).transpose
       
       pcs.extend Statsample::NamedMatrix
-      pcs.fields_y=m.times.map {|i| "PC_%d" % (i+1)}
-      pcs.to_dataset
+      pcs.fields_y = m.times.map { |i| "PC_#{i+1}".to_sym }
+      pcs.to_dataframe
     end
     def component_matrix(m=nil)
       var="component_matrix_#{matrix_type}"
@@ -159,7 +161,7 @@ module Factor
       cm.extend NamedMatrix
       cm.name=_("Component matrix (from covariance)")
       cm.fields_x = @variables_names
-      cm.fields_y = m.times.map {|i| "PC_%d" % (i+1)}
+      cm.fields_y = m.times.map {|i| "PC_#{i+1}".to_sym }
       
       cm
     end
@@ -180,17 +182,16 @@ module Factor
       cm.extend CovariateMatrix
       cm.name=_("Component matrix")
       cm.fields_x = @variables_names
-      cm.fields_y = m.times.map {|i| "PC_%d" % (i+1)}
+      cm.fields_y = m.times.map { |i| "PC_#{i+1}".to_sym }
       cm
     end
     def communalities(m=nil)
-      
       m||=@m
       h=[]
       @n_variables.times do |i|
         sum=0
         m.times do |j|
-          sum+=(@eigenpairs[j][0].abs*@eigenpairs[j][1][i]**2)
+          sum += (@eigenpairs[j][0].abs*@eigenpairs[j][1][i]**2)
         end
         h.push(sum)
       end
@@ -202,11 +203,11 @@ module Factor
     end
     def eigenvectors
       @eigenpairs.collect {|c| 
-        @use_gsl ? c[1].to_gsl : c[1].to_vector
+        @use_gsl ? c[1].to_gsl : Daru::Vector.new(c[1])
       }
     end
     def calculate_eigenpairs
-      @eigenpairs= @use_gsl ? @matrix.to_gsl.eigenpairs : @matrix.to_matrix.eigenpairs_ruby 
+      @eigenpairs= @use_gsl ? @matrix.to_gsl.eigenpairs : @matrix.to_matrix.eigenpairs_ruby
     end
   
     

data/lib/statsample/factor/principalaxis.rb

@@ -6,9 +6,9 @@ module Factor
   # 
   # == Usage:
   #   require 'statsample'
-  #   a=[2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1].to_numeric
-  #   b=[2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9].to_numeric
-  #   ds={'a'=>a,'b'=>b}.to_dataset
+  #   a = Daru::Vector.new([2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1])
+  #   b = Daru::Vector.new([2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9])
+  #   ds= Daru::DataFrame.new({:a => a,:b => b})
   #   cor_matrix=Statsample::Bivariate.correlation_matrix(ds)
   #   pa=Statsample::Factor::PrincipalAxis.new(cor_matrix)
   #   pa.iterate(1)

data/lib/statsample/graph/boxplot.rb

@@ -8,12 +8,12 @@ module Statsample
     # 
     # == Usage
     # === Svg output
-    #  a=[1,2,3,4].to_numeric
-    #  b=[3,4,5,6].to_numeric
-    #  puts Statsample::Graph::Boxplot.new(:vectors=>[a,b]).to_svg
+    #  a = Daru::Vector.new([1,2,3,4])
+    #  b = Daru::Vector.new([3,4,5,6])
+    # puts Statsample::Graph::Boxplot.new(:vectors=>[a,b]).to_svg
     # === Using ReportBuilder
-    #  a=[1,2,3,4].to_numeric
-    #  b=[3,4,5,6].to_numeric
+    #  a = Daru::Vector.new([1,2,3,4])
+    #  b = Daru::Vector.new([3,4,5,6])
     #  rb=ReportBuilder.new
     #  rb.add(Statsample::Graph::Boxplot.new(:vectors=>[a,b]))
     #  rb.save_html('boxplot.html')
@@ -85,8 +85,6 @@ module Statsample
         min||=@vectors.map {|v| v.min}.min
         max||=@vectors.map {|v| v.max}.max
         
-        
-        
         margin_hor=margin_left + margin_right
         margin_vert=margin_top  + margin_bottom
         x_scale = pv.Scale.ordinal(@vectors.size.times.map.to_a).split_banded(0, width-margin_hor, 4.0/5)
@@ -115,12 +113,10 @@ module Statsample
           out[:low_whisker]=min
           out[:high_whisker]=max
           # And now, data outside whiskers
-          out[:outliers]=v.data_with_nils.find_all {|d| d < min or d > max }
+          out[:outliers]=v.to_a.find_all {|d| d < min or d > max }
           out
         }
-        
-
-        
+               
         vis=Rubyvis::Panel.new do |pan| 
           pan.width  width  - margin_hor
           pan.height height - margin_vert
@@ -157,7 +153,6 @@ module Statsample
             bp.left {|v|  x_scale[index]}
             bp.width x_scale.range_band
             
-            
             # Bar
             bp.bar do |b|
               b.bottom {|v| y_scale[v[:percentil_25]]}
@@ -168,9 +163,7 @@ module Statsample
                   colors.scale(that.groups[parent.index]).darker
                 else
                   colors.scale(index).darker
-                end
-              
-              
+                end  
               }
               b.fill_style {|v| 
                 if that.groups
@@ -237,7 +230,6 @@ module Statsample
         builder.section(:name=>name) do |b|
           b.image(to_svg, :type=>'svg', :width=>width, :height=>height)
         end
-        
       end
     end
   end