statsample 1.4.3 → 1.5.0

data/lib/statsample/factor.rb

@@ -34,7 +34,7 @@ module Statsample
     #   matrix is not appropriate for factor analysis."
     # 
     def self.anti_image_covariance_matrix(matrix)
-      s2=Matrix.diag(*(matrix.inverse.diagonal)).inverse
+      s2=Matrix.diagonal(*(matrix.inverse.diagonal)).inverse
       aicm=(s2)*matrix.inverse*(s2)
       aicm.extend(Statsample::CovariateMatrix)
       aicm.fields=matrix.fields if matrix.respond_to? :fields
@@ -42,13 +42,12 @@ module Statsample
     end
     def self.anti_image_correlation_matrix(matrix)
       matrix=matrix.to_matrix
-      s=Matrix.diag(*(matrix.inverse.diagonal)).sqrt.inverse
+      s=Matrix.diagonal(*(matrix.inverse.diagonal)).sqrt.inverse
       aicm=s*matrix.inverse*s
       
       aicm.extend(Statsample::CovariateMatrix)
       aicm.fields=matrix.fields if matrix.respond_to? :fields
       aicm
-      
     end
       
     # Kaiser-Meyer-Olkin measure of sampling adequacy for correlation matrix.
@@ -101,6 +100,5 @@ module Statsample
       end
       sum_r.quo(sum_r+sum_q)
     end
-    
   end
 end

data/lib/statsample/factor/map.rb

@@ -75,7 +75,8 @@ module Statsample
         
         (ncol-1).times do |m|
           puts "MAP:Eigenvalue #{m+1}" if $DEBUG
-          a=loadings[0..(loadings.row_size-1),0..m]
+          a=use_gsl ? loadings[0..(loadings.row_size-1),0..m] : 
+            loadings.minor(0..(loadings.row_size-1),0..m)
           partcov= gsl_m - (a*a.transpose)
           
           d=klass_m.diagonal(*(partcov.diagonal.collect {|v| Math::sqrt(1/v)}))

data/lib/statsample/factor/parallelanalysis.rb

@@ -124,7 +124,7 @@ module Statsample
         
         @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=:scale}
+        @ds_eigenvalues.fields.each {|f| @ds_eigenvalues[f].type=:numeric}
         if bootstrap_method==:parameter or bootstrap_method==:random
           rng = Distribution::Normal.rng
         end
@@ -137,7 +137,7 @@ module Statsample
             
             @fields.each do |f|
               if bootstrap_method==:random
-                ds_bootstrap[f]=@n_cases.times.map {|c| rng.call}.to_scale
+                ds_bootstrap[f]=@n_cases.times.map {|c| rng.call}.to_numeric
               elsif bootstrap_method==:data
                 ds_bootstrap[f]=ds[f].sample_with_replacement(@n_cases)
               else

data/lib/statsample/factor/pca.rb

@@ -13,8 +13,8 @@ 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_scale
-  #   b=[2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9].to_scale
+  #   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)

data/lib/statsample/factor/principalaxis.rb

@@ -6,8 +6,8 @@ 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_scale
-  #   b=[2.4,0.7,2.9,2.2,3.0,2.7,1.6,1.1,1.6,0.9].to_scale
+  #   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)
   #   pa=Statsample::Factor::PrincipalAxis.new(cor_matrix)

data/lib/statsample/graph/boxplot.rb

@@ -8,12 +8,12 @@ module Statsample
     # 
     # == Usage
     # === Svg output
-    #  a=[1,2,3,4].to_scale
-    #  b=[3,4,5,6].to_scale
+    #  a=[1,2,3,4].to_numeric
+    #  b=[3,4,5,6].to_numeric
     #  puts Statsample::Graph::Boxplot.new(:vectors=>[a,b]).to_svg
     # === Using ReportBuilder
-    #  a=[1,2,3,4].to_scale
-    #  b=[3,4,5,6].to_scale
+    #  a=[1,2,3,4].to_numeric
+    #  b=[3,4,5,6].to_numeric
     #  rb=ReportBuilder.new
     #  rb.add(Statsample::Graph::Boxplot.new(:vectors=>[a,b]))
     #  rb.save_html('boxplot.html')

data/lib/statsample/graph/histogram.rb

@@ -6,10 +6,10 @@ module Statsample
     # 
     # == Usage
     # === Svg output
-    #  a=[1,2,3,4].to_scale
+    #  a=[1,2,3,4].to_numeric
     #  puts Statsample::Graph::Histogram.new(a).to_svg
     # === Using ReportBuilder
-    #  a=[1,2,3,4].to_scale
+    #  a=[1,2,3,4].to_numeric
     #  rb=ReportBuilder.new
     #  rb.add(Statsample::Graph::Histogram.new(a))
     #  rb.save_html('histogram.html')

data/lib/statsample/graph/scatterplot.rb

@@ -10,12 +10,12 @@ module Statsample
     # The data is displayed as a collection of points, each having the value of one variable determining the position on the horizontal axis and the value of the other variable determining the position on the vertical axis.[2] This kind of plot is also called a scatter chart, scatter diagram and scatter graph.
     # == Usage
     # === Svg output
-    #  a=[1,2,3,4].to_scale
-    #  b=[3,4,5,6].to_scale
+    #  a=[1,2,3,4].to_numeric
+    #  b=[3,4,5,6].to_numeric
     #  puts Statsample::Graph::Scatterplot.new(a,b).to_svg
     # === Using ReportBuilder
-    #  a=[1,2,3,4].to_scale
-    #  b=[3,4,5,6].to_scale
+    #  a=[1,2,3,4].to_numeric
+    #  b=[3,4,5,6].to_numeric
     #  rb=ReportBuilder.new
     #  rb.add(Statsample::Graph::Scatterplot.new(a,b))
     #  rb.save_html('scatter.html')

data/lib/statsample/matrix.rb

@@ -10,11 +10,12 @@ class ::Matrix
   def to_matrix
     self
   end
+
   def to_dataset
     f = (self.respond_to? :fields_y) ? fields_y : column_size.times.map {|i| _("VAR_%d") % (i+1) }
     ds=Statsample::Dataset.new(f)
     f.each do |ff|
-      ds[ff].type=:scale
+      ds[ff].type=:numeric
       ds[ff].name=ff
     end
     row_size.times {|i|
@@ -24,6 +25,7 @@ class ::Matrix
     ds.name=self.name if self.respond_to? :name
     ds
   end
+
   if defined? :eigenpairs
     alias_method :eigenpairs_ruby, :eigenpairs
   end
@@ -38,17 +40,15 @@ class ::Matrix
   def eigenvalues
     eigenpairs.collect {|v| v[0]}
   end
+
   def eigenvectors
     eigenpairs.collect {|v| v[1]}
   end
+
   def eigenvectors_matrix
     Matrix.columns(eigenvectors)
   end
 
-
-
-
-
   def to_gsl
     out=[]
     self.row_size.times{|i|
@@ -56,6 +56,10 @@ class ::Matrix
     }
     GSL::Matrix[*out]
   end
+
+  def []=(i, j, x)
+    @rows[i][j] = x
+  end
 end
 
 module GSL
@@ -64,9 +68,11 @@ module GSL
       def to_matrix
       ::Matrix.columns([self.size.times.map {|i| self[i]}])
       end
+
       def to_ary
         to_a
       end
+
       def to_gsl
         self
       end
@@ -81,7 +87,7 @@ module GSL
       f = (self.respond_to? :fields_y) ? fields_y : column_size.times.map {|i| _("VAR_%d") % (i+1) }
       ds=Statsample::Dataset.new(f)
       f.each do |ff|
-        ds[ff].type=:scale
+        ds[ff].type=:numeric
         ds[ff].name=ff
       end
       row_size.times {|i|
@@ -95,18 +101,23 @@ module GSL
     def row_size
       size1
     end
+
     def column_size
       size2
     end
+
     def determinant
       det
     end
+
     def inverse
       GSL::Linalg::LU.invert(self)
     end
+
     def eigenvalues
       eigenpairs.collect {|v| v[0]}
     end
+
     def eigenvectors
       eigenpairs.collect {|v| v[1]}
     end
@@ -123,6 +134,7 @@ module GSL
       GSL::Eigen::symmv_sort(eigval, eigvec, GSL::Eigen::SORT_VAL_DESC)
       eigvec
     end
+
     def eigenpairs
       eigval, eigvec= GSL::Eigen.symmv(self)
       GSL::Eigen::symmv_sort(eigval, eigvec, GSL::Eigen::SORT_VAL_DESC)
@@ -137,12 +149,14 @@ module GSL
     def square?
       size1==size2
     end
+
     def to_matrix
       rows=self.size1
       cols=self.size2
       out=(0...rows).collect{|i| (0...cols).collect {|j| self[i,j]} }
       ::Matrix.rows(out)
     end
+    
     def total_sum
       sum=0
       size1.times {|i|

data/lib/statsample/regression.rb

@@ -25,8 +25,8 @@ module Statsample
       # * x: independent Vector
       # * y: dependent Vector
       # <b>Usage:</b>
-      #   x=100.times.collect {|i| rand(100)}.to_scale
-      #   y=100.times.collect {|i| 2+x[i]*2+rand()}.to_scale
+      #   x=100.times.collect {|i| rand(100)}.to_numeric
+      #   y=100.times.collect {|i| 2+x[i]*2+rand()}.to_numeric
       #   sr=Statsample::Regression.simple(x,y)
       #   sr.a
       #   => 2.51763295177808

data/lib/statsample/regression/multiple.rb

@@ -6,9 +6,9 @@ module Statsample
     #  Use:.
     #
     #  require 'statsample'
-    #  a=1000.times.collect {rand}.to_scale
-    #  b=1000.times.collect {rand}.to_scale
-    #  c=1000.times.collect {rand}.to_scale
+    #  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()}
     #  lr=Statsample::Regression.multiple(ds,'y')

data/lib/statsample/regression/multiple/alglibengine.rb

@@ -9,10 +9,10 @@ module Multiple
 # If you need pairwise, use RubyEngine
 # Example:
 #
-#   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:scale)
-#   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:scale)
-#   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:scale)
-#   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:scale)
+#   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:numeric)
+#   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:numeric)
+#   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:numeric)
+#   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:numeric)
 #   ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
 #   lr=Statsample::Regression::Multiple::AlglibEngine.new(ds,'y')
 #            
@@ -109,7 +109,7 @@ class AlglibEngine < BaseEngine
         red_sd=residuals.sds
         res.collect {|v|
             v.quo(red_sd)
-        }.to_vector(:scale)
+        }.to_vector(:numeric)
     end
 end
 end

data/lib/statsample/regression/multiple/baseengine.rb

@@ -53,7 +53,7 @@ module Statsample
             else
               process(vect)
             end
-          }.to_vector(:scale)
+          }.to_vector(:numeric)
         end
         # Retrieves a vector with standarized values for y
         def standarized_predicted
@@ -69,7 +69,7 @@ module Statsample
             else
               @ds[@y_var][i] - process(vect)
             end
-          }.to_vector(:scale)
+          }.to_vector(:numeric)
         end
         # R Multiple
         def r
@@ -133,7 +133,7 @@ module Statsample
         def tolerance(var)
           ds=assign_names(@dep_columns)
           ds.each{|k,v|
-          ds[k]=v.to_vector(:scale)
+          ds[k]=v.to_vector(:numeric)
           }
           lr=self.class.new(ds.to_dataset,var)
           1-lr.r2

data/lib/statsample/regression/multiple/gslengine.rb

@@ -9,10 +9,10 @@ if Statsample.has_gsl?
         # If you need pairwise, use RubyEngine
         # Example:
         #
-        #   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:scale)
-        #   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:scale)
-        #   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:scale)
-        #   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:scale)
+        #   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:numeric)
+        #   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:numeric)
+        #   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:numeric)
+        #   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:numeric)
         #   ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
         #   lr=Statsample::Regression::Multiple::GslEngine.new(ds,'y')
         #
@@ -109,7 +109,7 @@ if Statsample.has_gsl?
             red_sd=residuals.sds
             res.collect {|v|
               v.quo(red_sd)
-            }.to_vector(:scale)
+            }.to_vector(:numeric)
           end
 
           # Standard error for coeffs

data/lib/statsample/regression/multiple/rubyengine.rb

@@ -8,10 +8,10 @@ module Multiple
 # 
 # Example:
 #
-#   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:scale)
-#   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:scale)
-#   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:scale)
-#   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:scale)
+#   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:numeric)
+#   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:numeric)
+#   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:numeric)
+#   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:numeric)
 #   ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
 #   lr=Statsample::Regression::Multiple::RubyEngine.new(ds,'y')
 

data/lib/statsample/reliability/icc.rb

@@ -7,7 +7,7 @@ module Statsample
     # == Usage
     #   require 'statsample'
     #   size=1000
-    #   a = size.times.map {rand(10)}.to_scale
+    #   a = size.times.map {rand(10)}.to_numeric
     #   b = a.recode{|i|i+rand(4)-2}
     #   c  =a.recode{|i|i+rand(4)-2}
     #   d = a.recode{|i|i+rand(4)-2}

data/lib/statsample/reliability/multiscaleanalysis.rb

@@ -6,10 +6,10 @@ module Statsample
     # 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)
+    #  @x1=[1,1,1,1,2,2,2,2,3,3,3,30].to_vector(:numeric)
+    #  @x2=[1,1,1,2,2,3,3,3,3,4,4,50].to_vector(:numeric)
+    #  @x3=[2,2,1,1,1,2,2,2,3,4,5,40].to_vector(:numeric)
+    #  @x4=[1,2,3,4,4,4,4,3,4,4,5,30].to_vector(:numeric)
     #  ds={'x1'=>@x1,'x2'=>@x2,'x3'=>@x3,'x4'=>@x4}.to_dataset
     #  opts={:name=>"Scales", # Name of analysis
     #        :summary_correlation_matrix=>true, # Add correlation matrix

data/lib/statsample/reliability/scaleanalysis.rb

@@ -3,10 +3,10 @@ module Statsample
     # Analysis of a Scale. Analoge of Scale Reliability analysis on SPSS.
     # Returns several statistics for complete scale and each item
     # == 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)
+    #  @x1=[1,1,1,1,2,2,2,2,3,3,3,30].to_vector(:numeric)
+    #  @x2=[1,1,1,2,2,3,3,3,3,4,4,50].to_vector(:numeric)
+    #  @x3=[2,2,1,1,1,2,2,2,3,4,5,40].to_vector(:numeric)
+    #  @x4=[1,2,3,4,4,4,4,3,4,4,5,30].to_vector(:numeric)
     #  ds={'x1'=>@x1,'x2'=>@x2,'x3'=>@x3,'x4'=>@x4}.to_dataset
     #  ia=Statsample::Reliability::ScaleAnalysis.new(ds)
     #  puts ia.summary
@@ -49,7 +49,7 @@ module Statsample
         
         @cov_m=Statsample::Bivariate.covariance_matrix(@ds)
         # Mean for covariances and variances
-        @variances=@k.times.map {|i| @cov_m[i,i]}.to_scale
+        @variances=@k.times.map {|i| @cov_m[i,i]}.to_numeric
         @variances_mean=@variances.mean
         @covariances_mean=(@variance-@variances.sum).quo(@k**2-@k)
         #begin
@@ -97,7 +97,7 @@ module Statsample
         end
       end
       def mean_rpb
-        item_total_correlation.values.to_scale.mean
+        item_total_correlation.values.to_numeric.mean
       end
       def item_statistics
           @is||=@ds.fields.inject({}) do |a,v|

data/lib/statsample/reliability/skillscaleanalysis.rb

@@ -54,7 +54,7 @@ module Statsample
       def corrected_dataset
         if @cds.nil?
           @cds=@ds.dup_empty
-          @key.keys.each {|k| @cds[k].type=:scale; @cds[k].name=@ds[k].name}
+          @key.keys.each {|k| @cds[k].type=:numeric; @cds[k].name=@ds[k].name}
           @ds.each do |row|
             out={}
             row.each do |k,v|

data/lib/statsample/resample.rb

@@ -7,7 +7,7 @@ module Statsample
       
       def generate (size,low,upper)
         range=upper-low+1
-        Vector.new((0...size).collect {|x| rand(range)+low },:scale)
+        Vector.new((0...size).collect {|x| rand(range)+low },:numeric)
       end
               
     end

data/lib/statsample/shorthand.rb

@@ -52,7 +52,7 @@ module Statsample
     # Random generation for the normal distribution
     def rnorm(n,mean=0,sd=1)
       rng=Distribution::Normal.rng(mean,sd)
-      Statsample::Vector.new_scale(n) { rng.call}
+      Statsample::Vector.new_numeric(n) { rng.call}
     end
     # Creates a new Statsample::Dataset
     # Each key is transformed into string