statsample 0.9.0 → 0.10.0

data/lib/statsample/bivariate.rb

@@ -6,7 +6,7 @@ module Statsample
     class << self
       # Covariance between two vectors
       def covariance(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         return nil if v1a.size==0
         if Statsample.has_gsl?
           GSL::Stats::covariance(v1a.gsl, v2a.gsl)
@@ -16,7 +16,7 @@ module Statsample
       end
       # Estimate the ML between two dichotomic vectors
       def maximum_likehood_dichotomic(pred,real)
-        preda,reala=Statsample.only_valid(pred,real)                
+        preda,reala=Statsample.only_valid_clone(pred,real)                
         sum=0
         pred.each_index{|i|
            sum+=(real[i]*Math::log(pred[i])) + ((1-real[i])*Math::log(1-pred[i]))
@@ -29,14 +29,14 @@ module Statsample
         sum_of_squares(v1a,v2a) / (v1a.size-1)
       end
       def sum_of_squares(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)        
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)        
         m1=v1a.mean
         m2=v2a.mean
         (v1a.size).times.inject(0) {|ac,i| ac+(v1a[i]-m1)*(v2a[i]-m2)}
       end
       # Calculate Pearson correlation coefficient (r) between 2 vectors
       def pearson(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         return nil if v1a.size ==0
         if Statsample.has_gsl?
           GSL::Stats::correlation(v1a.gsl, v2a.gsl)
@@ -45,7 +45,7 @@ module Statsample
         end
       end
       def pearson_slow(v1,v2) # :nodoc:
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         # Calculate sum of squares
         ss=sum_of_squares(v1a,v2a)
         ss.quo(Math::sqrt(v1a.sum_of_squares) * Math::sqrt(v2a.sum_of_squares))
@@ -60,7 +60,7 @@ module Statsample
       # Retrieves the value for t test for a pearson correlation
       # between two vectors to test the null hipothesis of r=0
       def t_pearson(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         r=pearson(v1a,v2a)
         if(r==1.0) 
           0
@@ -117,7 +117,7 @@ module Statsample
       # Correlation between v1 and v2, controling the effect of
       # control on both.
       def partial_correlation(v1,v2,control)
-        v1a,v2a,cona=Statsample.only_valid(v1,v2,control)
+        v1a,v2a,cona=Statsample.only_valid_clone(v1,v2,control)
         rv1v2=pearson(v1a,v2a)
         rv1con=pearson(v1a,cona)
         rv2con=pearson(v2a,cona)        
@@ -129,13 +129,20 @@ module Statsample
       # Order of rows and columns depends on Dataset#fields order
       
       def covariance_matrix(ds)
+        cache={}
         matrix=ds.collect_matrix do |row,col|
           if (ds[row].type!=:scale or ds[col].type!=:scale)
             nil
           elsif row==col
             ds[row].variance
           else
-            covariance(ds[row], ds[col])
+            if cache[[col,row]].nil?
+              cov=covariance(ds[row],ds[col])
+              cache[[row,col]]=cov
+              cov
+            else
+               cache[[col,row]]
+            end
           end
         end
         matrix.extend CovariateMatrix
@@ -147,13 +154,20 @@ module Statsample
       # Order of rows and columns depends on Dataset#fields order
       
       def correlation_matrix(ds)
+        cache={}
         cm=ds.collect_matrix do |row,col|
           if row==col
             1.0
           elsif (ds[row].type!=:scale or ds[col].type!=:scale)
             nil
           else
-            pearson(ds[row],ds[col])
+            if cache[[col,row]].nil?
+              r=pearson(ds[row],ds[col])
+              cache[[row,col]]=r
+              r
+            else
+              cache[[col,row]]
+            end 
           end
         end
         cm.extend(Statsample::CovariateMatrix)
@@ -167,7 +181,7 @@ module Statsample
           if row==col
             ds[row].valid_data.size
           else
-            rowa,rowb=Statsample.only_valid(ds[row],ds[col])
+            rowa,rowb=Statsample.only_valid_clone(ds[row],ds[col])
             rowa.size
           end
         end
@@ -179,7 +193,7 @@ module Statsample
       def correlation_probability_matrix(ds, tails=:both)
         rows=ds.fields.collect do |row|
           ds.fields.collect do |col|
-            v1a,v2a=Statsample.only_valid(ds[row],ds[col])
+            v1a,v2a=Statsample.only_valid_clone(ds[row],ds[col])
             (row==col or ds[row].type!=:scale or ds[col].type!=:scale) ? nil : prop_pearson(t_pearson(ds[row],ds[col]), v1a.size, tails)
           end
         end
@@ -188,7 +202,7 @@ module Statsample
       
       # Spearman ranked correlation coefficient (rho) between 2 vectors
       def spearman(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         v1r,v2r=v1a.ranked(:scale),v2a.ranked(:scale)
         pearson(v1r,v2r)
       end
@@ -206,7 +220,7 @@ module Statsample
       # Kendall Rank Correlation Coefficient.
       # Based on Hervé Adbi article
       def tau_a(v1,v2)
-        v1a,v2a=Statsample.only_valid(v1,v2)
+        v1a,v2a=Statsample.only_valid_clone(v1,v2)
         n=v1.size
         v1r,v2r=v1a.ranked(:scale),v2a.ranked(:scale)
         o1=ordered_pairs(v1r)

data/lib/statsample/bivariate/polychoric.rb

@@ -10,18 +10,29 @@ module Statsample
     # Polychoric correlation matrix.
     # Order of rows and columns depends on Dataset#fields order
     def self.polychoric_correlation_matrix(ds)
-      ds.collect_matrix do |row,col|
+      cache={}
+      matrix=ds.collect_matrix do |row,col|
         if row==col
           1.0
         else
           begin
-            polychoric(ds[row],ds[col])
+            if cache[[col,row]].nil?
+              poly=polychoric(ds[row],ds[col])
+              cache[[row,col]]=poly
+              poly
+            else
+              cache[[col,row]]
+            end
           rescue RuntimeError
             nil
           end
         end
       end
+      matrix.extend CovariateMatrix
+      matrix.fields=ds.fields
+      matrix
     end
+    
     # = Polychoric correlation.
     #
     # The <em>polychoric</em> correlation is a measure of 
@@ -83,6 +94,7 @@ module Statsample
       
       
       # Method of calculation of polychoric series. 
+      # <tt>:two_step</tt> used by default.
       # 
       # :two_step:: two-step ML, based on code by Gegenfurtner(1992).
       # :polychoric_series:: polychoric series estimate, using 
@@ -107,7 +119,7 @@ module Statsample
       EPSILON=1e-6
       MINIMIZER_TYPE_TWO_STEP="brent"
       MINIMIZER_TYPE_JOINT="nmsimplex"
-      def new_with_vectors(v1,v2)
+      def self.new_with_vectors(v1,v2)
         Polychoric.new(Crosstab.new(v1,v2).to_matrix)
       end
       # Params:
@@ -249,6 +261,7 @@ module Statsample
               b=(j==@nc-1) ? 100: beta[j]
               #puts "a:#{a} b:#{b}"
               pd[i][j]=Distribution::NormalBivariate.cdf(a, b, rho)
+              
             end
             pc[i][j] = pd[i][j]
             pd[i][j] = pd[i][j] - pc[i-1][j] if i>0
@@ -256,7 +269,7 @@ module Statsample
             pd[i][j] = pd[i][j] + pc[i-1][j-1] if (i>0 and j>0)
             res= pd[i][j]
              #puts "i:#{i} | j:#{j} | ac: #{sprintf("%0.4f", pc[i][j])} | pd: #{sprintf("%0.4f", pd[i][j])} | res:#{sprintf("%0.4f", res)}"
-          if (res==0)
+          if (res<=0)
            #    puts "Correccion"
             res=1e-16
           end
@@ -328,7 +341,7 @@ module Statsample
         min.epsilon=@epsilon
         min.expected=0
         min.iterate
-        @log+=min.log
+        @log+=min.log.to_table.to_s
         @r=min.x_minimum
         @loglike_model=-min.f_minimum
         puts @log if @debug

data/lib/statsample/crosstab.rb

@@ -4,50 +4,44 @@ module Statsample
 	# The first vector will be at rows and the second will the the columns
 	#
   class Crosstab
-    include GetText
-    bindtextdomain("statsample")
+    include Summarizable
     attr_reader :v_rows, :v_cols
     attr_accessor :row_label, :column_label, :name, :percentage_row, :percentage_column, :percentage_total
     def initialize(v1, v2, opts=Hash.new)
-    raise ArgumentError, "Both arguments should be Vectors" unless v1.is_a? Statsample::Vector and v2.is_a? Statsample::Vector
-    raise ArgumentError, "Vectors should be the same size" unless v1.size==v2.size
-    @v_rows, @v_cols=Statsample.only_valid(v1,v2)
-    @cases=@v_rows.size
-    @row_label=nil
-    @column_label=nil
-    @name=nil
-    @percentage_row=@percentage_column=@percentage_total=false
-    opts.each{|k,v|
-      self.send("#{k}=",v) if self.respond_to? k
-    }
-    if(@name.nil?)
-      if (!@row_label.nil? and !@column_label.nil?)
-        @name=_("Crosstab %s - %s") % [@row_label, @column_label]
-      else
-        @name=_("Crosstab")
-      end
-    end
+      raise ArgumentError, "Both arguments should be Vectors" unless v1.is_a? Statsample::Vector and v2.is_a? Statsample::Vector
+      raise ArgumentError, "Vectors should be the same size" unless v1.size==v2.size
+      @v_rows, @v_cols=Statsample.only_valid_clone(v1,v2)
+      @cases=@v_rows.size
+      @row_label=v1.name
+      @column_label=v2.name
+      @name=nil
+      @percentage_row=@percentage_column=@percentage_total=false
+      opts.each{|k,v|
+        self.send("#{k}=",v) if self.respond_to? k
+      }
+      @name||=_("Crosstab %s - %s") % [@row_label, @column_label]
     end	
     def rows_names
-    @v_rows.factors.sort
+      @v_rows.factors.sort
     end
     def cols_names
-    @v_cols.factors.sort
+      @v_cols.factors.sort
     end
     def rows_total
-    @v_rows.frequencies
+      @v_rows.frequencies
     end
     def cols_total
-    @v_cols.frequencies
+      @v_cols.frequencies
     end
+    
     def frequencies
-    base=rows_names.inject([]){|s,row| 
-      s+=cols_names.collect{|col| [row,col]}
-    }.inject({}) {|s,par|
-      s[par]=0
-      s
-    }
-    base.update(Statsample::vector_cols_matrix(@v_rows,@v_cols).to_a.to_vector.frequencies)
+      base=rows_names.inject([]){|s,row| 
+        s+=cols_names.collect{|col| [row,col]}
+      }.inject({}) {|s,par|
+        s[par]=0
+        s
+      }
+      base.update(Statsample::vector_cols_matrix(@v_rows,@v_cols).to_a.to_vector.frequencies)
     end
     def to_matrix
       f=frequencies
@@ -93,52 +87,50 @@ module Statsample
     def cols_empty_hash
       cols_names.inject({}) {|a,x| a[x]=0;a}
     end
-    def report_building(generator)
-      anchor=generator.toc_entry(_("Crosstab: ")+name)
-      generator.html "<div class='crosstab'>"+_("Crosstab")+" #{@name}<a name='#{anchor}'></a>"
-      fq=frequencies
-      rn=rows_names
-      cn=cols_names
-      total=0
-      total_cols=cols_empty_hash
-      generator.text "Chi Square: #{chi_square}"
-      generator.text(_("Rows: %s") % @row_label) unless @row_label.nil?
-      generator.text(_("Columns: %s") % @column_label) unless @column_label.nil?
-      
-      t=ReportBuilder::Table.new(:name=>@name+" - "+_("Raw"), :header=>[""]+cols_names.collect {|c| @v_cols.labeling(c)}+[_("Total")])
-      rn.each do |row|
-        total_row=0
-        t_row=[@v_rows.labeling(row)]
-        cn.each do |col|
-          data=fq[[row,col]]
-          total_row+=fq[[row,col]]
-          total+=fq[[row,col]]                    
-          total_cols[col]+=fq[[row,col]]                    
-          t_row.push(data)
+    def report_building(builder)
+      builder.section(:name=>@name) do |generator|
+        fq=frequencies
+        rn=rows_names
+        cn=cols_names
+        total=0
+        total_cols=cols_empty_hash
+        generator.text "Chi Square: #{chi_square}"
+        generator.text(_("Rows: %s") % @row_label) unless @row_label.nil?
+        generator.text(_("Columns: %s") % @column_label) unless @column_label.nil?
+        
+        t=ReportBuilder::Table.new(:name=>@name+" - "+_("Raw"), :header=>[""]+cols_names.collect {|c| @v_cols.labeling(c)}+[_("Total")])
+        rn.each do |row|
+          total_row=0
+          t_row=[@v_rows.labeling(row)]
+          cn.each do |col|
+            data=fq[[row,col]]
+            total_row+=fq[[row,col]]
+            total+=fq[[row,col]]                    
+            total_cols[col]+=fq[[row,col]]                    
+            t_row.push(data)
+          end
+          t_row.push(total_row)
+          t.row(t_row)
+        end
+        t.hr
+        t_row=[_("Total")]
+        cn.each do |v|
+          t_row.push(total_cols[v])
         end
-        t_row.push(total_row)
+        t_row.push(total)
         t.row(t_row)
+        generator.parse_element(t)
+        
+        if(@percentage_row)
+          table_percentage(generator,:row)
+        end
+        if(@percentage_column)
+        table_percentage(generator,:column)
+        end
+        if(@percentage_total)
+        table_percentage(generator,:total)
+        end
       end
-      t.hr
-      t_row=[_("Total")]
-      cn.each do |v|
-        t_row.push(total_cols[v])
-      end
-      t_row.push(total)
-      t.row(t_row)
-      generator.parse_element(t)
-      
-      if(@percentage_row)
-        table_percentage(generator,:row)
-      end
-      if(@percentage_column)
-      table_percentage(generator,:column)
-      end
-      if(@percentage_total)
-      table_percentage(generator,:total)
-      end
-      
-      generator.html("</div>")
     end
       
     

data/lib/statsample/dataset.rb

@@ -56,16 +56,17 @@ module Statsample
   
   class Dataset
     include Writable
+    include Summarizable
     # Hash of Statsample::Vector
     attr_reader :vectors
     # Ordered names of vectors
     attr_reader :fields
+    # Name of dataset
+    attr_accessor:name
     # Number of cases
     attr_reader :cases
     # Location of pointer on enumerations methods (like #each)
     attr_reader :i
-    # Deprecated: Label of vectors
-    attr_accessor :labels
     
     # Generates a new dataset, using three vectors
     # - Rows
@@ -122,10 +123,12 @@ 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
-    # [labels]  Hash to set names for fields.
 
     #
-    def initialize(vectors={}, fields=[], labels={})
+    def initialize(vectors={}, fields=[])
+      @@n_dataset||=0
+      @@n_dataset+=1
+      @name=_("Dataset %d") % @@n_dataset
       if vectors.instance_of? Array
         @fields=vectors.dup
         @vectors=vectors.inject({}){|a,x| a[x]=Statsample::Vector.new(); a}
@@ -137,7 +140,6 @@ module Statsample
         check_length
       end
       @i=nil
-      @labels=labels
     end
     def to_gsl_matrix
       matrix=GSL::Matrix.alloc(cases,@vectors.size)
@@ -146,11 +148,7 @@ module Statsample
       end
       matrix
     end
-    # Retrieves label for a vector, giving a field name.
-    def label(v_id) 
-      raise "Vector #{v} doesn't exists" unless @fields.include? v_id
-      @labels[v_id].nil? ? v_id : @labels[v_id]
-    end
+
     # Creates a copy of the given dataset, deleting all the cases with
     # missing data on one of the vectors
     def dup_only_valid
@@ -172,7 +170,8 @@ module Statsample
       @fields.slice(@fields.index(from)..@fields.index(to))
     end
     # Returns a duplicate of the Database
-    # If fields given, only include those vectors
+    # If fields given, only include those vectors.
+    # 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]
@@ -180,14 +179,27 @@ module Statsample
       fields_to_include=@fields if fields_to_include.size==0
       vectors={}
       fields=[]
-      new_labels={}
       fields_to_include.each{|f|
         raise "Vector #{f} doesn't exists" unless @vectors.has_key? f
         vectors[f]=@vectors[f].dup
-        new_labels[f]=@labels[f]
         fields.push(f)
       }
-      Dataset.new(vectors,fields,new_labels)
+      Dataset.new(vectors,fields)
+    end
+    # Returns a shallow copy of Dataset.
+    # Object id will be distinct, but @vectors will be the same.
+    def clone(*fields_to_include)
+      if fields_to_include.size==1 and fields_to_include[0].is_a? Array
+        fields_to_include=fields_to_include[0]
+      end
+      fields_to_include=@fields.dup if fields_to_include.size==0
+      ds=Dataset.new
+      fields_to_include.each{|f|
+        raise "Vector #{f} doesn't exists" unless @vectors.has_key? f
+        ds[f]=@vectors[f]
+      }
+      ds.fields=fields_to_include
+      ds
     end
     # Creates a copy of the given dataset, without data on vectors
     def dup_empty
@@ -195,7 +207,7 @@ module Statsample
         a[v[0]]=v[1].dup_empty
         a
       }
-      Dataset.new(vectors,@fields.dup,@labels.dup)
+      Dataset.new(vectors,@fields.dup)
     end
     # Merge vectors from two datasets
     # In case of name collition, the vectors names are changed to 
@@ -216,14 +228,14 @@ module Statsample
       ds_new.update_valid_data
       ds_new
     end
-    # Returns a dataset with standarized data
-	def standarize
-	  ds=dup()
-	  ds.fields.each {|f|
-		ds[f]=ds[f].vector_standarized
-	  }
-	  ds
-	end
+      # Returns a dataset with standarized data
+    def standarize
+      ds=dup()
+      ds.fields.each do |f|
+        ds[f]=ds[f].vector_standarized
+      end
+      ds
+    end
     # Generate a matrix, based on fields of dataset
     def collect_matrix
       rows=@fields.collect{|row|
@@ -233,7 +245,7 @@ module Statsample
       }
       Matrix.rows(rows)
     end
-    # We have the same datasets if the labels and vectors are the same
+    # We have the same datasets if vectors and fields are the same
     def ==(d2)
       @vectors==d2.vectors and @fields==d2.fields
     end
@@ -305,12 +317,12 @@ module Statsample
       @vectors.delete(name)
     end
     
-    def add_vectors_by_split_recode(name,join='-',sep=Statsample::SPLIT_TOKEN)
-      split=@vectors[name].split_by_separator(sep)
+    def add_vectors_by_split_recode(name_,join='-',sep=Statsample::SPLIT_TOKEN)
+      split=@vectors[name_].split_by_separator(sep)
       i=1
       split.each{|k,v|
-        new_field=name+join+i.to_s
-        @labels[new_field]=name+":"+k
+        new_field=name_+join+i.to_s
+        v.name=name_+":"+k
         add_vector(new_field,v)
         i+=1
       }
@@ -505,15 +517,13 @@ module Statsample
     end
     # Returns the vector named i
     def[](i)
-      if i.is_a? String
-        raise Exception,"Vector '#{i}' doesn't exists on dataset" unless @vectors.has_key?(i)
-        @vectors[i]
-      elsif i.is_a? Range
+      if i.is_a? Range
         fields=from_to(i.begin,i.end)
         vectors=fields.inject({}) {|a,v| a[v]=@vectors[v];a}
         ds=Dataset.new(vectors,fields)
       else
-        raise ArgumentError, "You need a String or a Range"
+        raise Exception,"Vector '#{i}' doesn't exists on dataset" unless @vectors.has_key?(i)
+        @vectors[i]
       end
     end
     # Retrieves a Statsample::Vector, based on the result
@@ -702,7 +712,7 @@ module Statsample
       vr
     end
     def to_s
-      "#<"+self.class.to_s+":"+self.object_id.to_s+" @fields=["+@fields.join(",")+"] labels="+@labels.inspect+" cases="+@vectors[@fields[0]].size.to_s
+      "#<"+self.class.to_s+":"+self.object_id.to_s+" @fields=["+@fields.join(",")+"] cases="+@vectors[@fields[0]].size.to_s
     end
     def inspect
       self.to_s
@@ -779,17 +789,14 @@ module Statsample
       ds
     end
    
-		def summary
-			out=""
-			out << "Summary for dataset\n"
-			@vectors.each{|k,v|
-				out << "###############\n"
-				out << "Vector #{k}:\n"
-				out << v.summary
-				out << "###############\n"
-				
-			}
-			out 
+		def report_building(b)
+      b.section(:name=>@name) do |g|
+        g.text _"Cases: %d"  % cases
+        
+        @fields.each do |f|
+          g.parse_element(@vectors[f])
+        end
+      end
 		end
     def as_r
       require 'rsruby/dataframe'