statsample 0.5.1 → 0.6.0

data/lib/statsample/dataset.rb

@@ -23,8 +23,8 @@ module Statsample
       @exp=e
     end
     def to_s
-      m="Error: "+@exp.message+"\n"+@exp.backtrace.join("\n")+"\nOn Dataset:"+@ds.inspect
-      m+="\nRow: #{@i}" unless @i.nil?
+      m="Error on iteration: "+@exp.message+"\n"+@exp.backtrace.join("\n")
+      m+="\nRow: #{@ds.i}" unless @ds.i.nil?
       m
     end
   end
@@ -120,7 +120,7 @@ module Statsample
       end
       matrix
     end
-    def vector_label(v_id)
+    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
@@ -334,7 +334,7 @@ module Statsample
       a=[]
       fields=check_fields(fields)
       size=fields.size
-      each_with_index do |i, row|
+      each_with_index do |row, i |
         # numero de invalidos
         sum=0
         invalids=0
@@ -407,21 +407,21 @@ module Statsample
         }
         @i=nil
       rescue =>e
-        raise DatasetException.new(self,e)
+        raise DatasetException.new(self, e)
       end
     end
-    # Returns each case as index and hash
+    # Returns each case as hash and index
     def each_with_index
       begin
         @i=0
         @cases.times{|i|
           @i=i
           row=case_as_hash(i)
-          yield i,row
+          yield row, i
         }
         @i=nil
       rescue =>e
-        raise DatasetException.new(self,e)
+        raise DatasetException.new(self, e)
       end
     end
     # Returns each case as an array, coding missing values as nils
@@ -473,26 +473,28 @@ module Statsample
     def collect(type=:scale)
       data=[]
       each {|row|
-        data.push(yield(row))
+        data.push yield(row)
       }
       Statsample::Vector.new(data,type)
     end
     def collect_with_index(type=:scale)
       data=[]
-      each_with_index {|i,row|
+      each_with_index {|row, i|
         data.push(yield(i,row))
       }
       Statsample::Vector.new(data,type)
     end
     # Recode a vector based on a block
     def recode!(vector_name)
+      
       0.upto(@cases-1) {|i|
         @vectors[vector_name].data[i]=yield case_as_hash(i)
       }
       @vectors[vector_name].set_valid_data
     end
-    def crosstab(v1,v2)
-      Statsample::Crosstab.new(@vectors[v1],@vectors[v2])
+    
+    def crosstab(v1,v2,opts={})
+      Statsample::Crosstab.new(@vectors[v1], @vectors[v2],opts)
     end
     def[]=(i,v)
       if v.instance_of? Statsample::Vector
@@ -508,6 +510,15 @@ module Statsample
         rows.push(c)
       }
       Matrix.rows(rows)
+    end
+    if HAS_GSL
+      def to_matrix_gsl
+      rows=[]
+      self.each_array{|c|
+        rows.push(c)
+      }
+      GSL::Matrix.alloc(*rows)
+      end
     end
 		def to_multiset_by_split(*fields)
 			require 'statsample/multiset'
@@ -640,6 +651,77 @@ module Statsample
     def inspect
       self.to_s
     end
+    # Creates a new dataset for one to many relations
+    # on a dataset, based on pattern of field names.
+    # for example, you have a survey for number of children
+    # with this structure:
+    #   id, name, child_name_1, child_age_1, child_name_2, child_age_2
+    # with 
+    #   ds.one_to_many(%w{id}, "child_%v_%n"
+    # the field of first parameters will be copied verbatim
+    # to new dataset, and fields which responds to second 
+    # pattern will be added one case for each different %n.
+    # For example
+    #   cases=[
+    #     ['1','george','red',10,'blue',20,nil,nil],
+    #     ['2','fred','green',15,'orange',30,'white',20],
+    #     ['3','alfred',nil,nil,nil,nil,nil,nil]
+    #   ]
+    #   ds=Statsample::Dataset.new(%w{id name car_color1 car_value1 car_color2 car_value2 car_color3 car_value3})
+    #   cases.each {|c| ds.add_case_array c }
+    #   ds.one_to_many(['id'],'car_%v%n').to_matrix
+    #   => Matrix[
+    #      ["red", "1", 10], 
+    #      ["blue", "1", 20],
+    #      ["green", "2", 15],
+    #      ["orange", "2", 30],
+    #      ["white", "2", 20]
+    #      ]
+    # 
+    def one_to_many(parent_fields, pattern)
+      base_pattern=pattern.gsub(/%v|%n/,"")
+      re=Regexp.new pattern.gsub("%v","(.+?)").gsub("%n","(\\d+?)")
+      ds_vars=parent_fields
+      vars=[]
+      max_n=0
+      h=parent_fields.inject({}) {|a,v| a[v]=Statsample::Vector.new([], @vectors[v].type);a }
+      # Adding _row_id
+      h['_col_id']=[].to_scale
+      ds_vars.push("_col_id")
+      @fields.each do |f|
+        if f=~re
+          if !vars.include? $1
+            vars.push($1) 
+            h[$1]=Statsample::Vector.new([], @vectors[f].type)
+          end
+          max_n=$2.to_i if max_n < $2.to_i
+        end
+      end
+      ds=Dataset.new(h,ds_vars+vars)
+      each do |row|
+        row_out={}
+        parent_fields.each do |f|
+          row_out[f]=row[f]
+        end
+        max_n.times do |n1|
+          n=n1+1
+          any_data=false
+          vars.each do |v|
+            data=row[pattern.gsub("%v",v.to_s).gsub("%n",n.to_s)]
+            row_out[v]=data
+            any_data=true if !data.nil?
+          end
+          if any_data
+            row_out["_col_id"]=n
+            ds.add_case(row_out,false)
+          end
+          
+        end
+      end
+      ds.update_valid_data
+      ds
+    end
+   
 		def summary
 			out=""
 			out << "Summary for dataset\n"

data/lib/statsample/dominanceanalysis.rb

@@ -38,15 +38,16 @@ module Statsample
             return 0.5 if dm==0.5
             dominances=[dm]
             @models_data.each{|k,m|
-                if !m.contributions[i].nil? and !m.contributions[j].nil?
-                    if m.contributions[i]>m.contributions[j]
-                        dominances.push(1)
-                    elsif m.contributions[i]<m.contributions[j]
-                        dominances.push(0)
-                    else
-                        dominances.push(0.5)
-                    end
+              if !m.contributions[i].nil? and !m.contributions[j].nil?
+                if m.contributions[i]>m.contributions[j]
+                    dominances.push(1)
+                elsif m.contributions[i]<m.contributions[j]
+                    dominances.push(0)
+                else
+                  return 0.5
+                    #dominances.push(0.5)
                 end
+              end
             }
             final=dominances.uniq
             final.size>1 ? 0.5 : final[0]
@@ -64,7 +65,8 @@ module Statsample
                 elsif a[i]<a[j]
                     dominances.push(0)
                 else
-                    a(0.5)
+                  return 0.5
+                    dominances.push(0.5)
                 end                 
             end
             final=dominances.uniq
@@ -72,34 +74,34 @@ module Statsample
         end
         # Returns 1 if i gD k, 0 if j gD i and 0.5 if undetermined        
         def general_dominance_pairwise(i,j)
-            ga=general_averages
-            if ga[i]>ga[j]
-                1
-            elsif ga[i]<ga[j]
-                0
-            else
-                0.5
-            end                 
+          ga=general_averages
+          if ga[i]>ga[j]
+              1
+          elsif ga[i]<ga[j]
+              0
+          else
+              0.5
+          end                 
         end
         def pairs
-            @models.find_all{|m| m.size==2}
+          @models.find_all{|m| m.size==2}
         end
         def total_dominance
             pairs.inject({}){|a,pair|
-                a[pair]=total_dominance_pairwise(pair[0], pair[1])
-                a
+              a[pair]=total_dominance_pairwise(pair[0], pair[1])
+              a
             }
         end
         def conditional_dominance
             pairs.inject({}){|a,pair|
-                a[pair]=conditional_dominance_pairwise(pair[0], pair[1])
-                a
+              a[pair]=conditional_dominance_pairwise(pair[0], pair[1])
+              a
             }
         end
         def general_dominance
             pairs.inject({}){|a,pair|
-                a[pair]=general_dominance_pairwise(pair[0], pair[1])
-                a
+              a[pair]=general_dominance_pairwise(pair[0], pair[1])
+              a
             }
         end
         
@@ -108,56 +110,61 @@ module Statsample
         end
         # Get all model of size k
         def md_k(k)
-            out=[]
-            models=@models.each{|m|
-                out.push(md(m)) if m.size==k
-            }
-            out
+          out=[]
+          models=@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(:scale).mean }
           out
         end
+        # Hash with average for each k size 
+        # model
         def average_k(k)
-            return nil if k==@fields.size
-            models=md_k(k)
-            averages=@fields.inject({}) {|a,v| a[v]=[];a}
-            models.each{|m|
-                @fields.each{|f|
-                    averages[f].push(m.contributions[f]) unless m.contributions[f].nil?
-                }
-            }
-            get_averages(averages)
+          return nil if k==@fields.size
+          models=md_k(k)
+          averages=@fields.inject({}) {|a,v| a[v]=[];a}
+          models.each do |m|
+            @fields.each do |f|
+              averages[f].push(m.contributions[f]) unless m.contributions[f].nil?
+            end
+          end
+          get_averages(averages)
         end
         def general_averages
-            if @general_averages.nil?
-                averages=@fields.inject({}) {|a,v| a[v]=[md(v).r2];a}
-                for k in 1...@fields.size
-                    ak=average_k(k)
-                    @fields.each{|f|
-                        averages[f].push(ak[f])
-                    }
-                end
-                @general_averages=get_averages(averages)
+          if @general_averages.nil?
+            averages=@fields.inject({}) {|a,v| a[v]=[md(v).r2];a}
+            for k in 1...@fields.size
+                ak=average_k(k)
+                @fields.each{|f|
+                    averages[f].push(ak[f])
+                }
             end
-            @general_averages
+            @general_averages=get_averages(averages)
+          end
+          @general_averages
         end
         def create_models
-            @models=[]
-            @models_data={}
-            for i in 1..@fields.size
-                c=Statsample::Combination.new(i,@fields.size)
-                c.each{|data|
-                    convert=data.collect {|i1|
-                        @fields[i1]
-                    }
-                    @models.push(convert)
-                    ds_prev=@ds.dup(convert+[@y_var])
-                    modeldata=ModelData.new(convert,ds_prev, @y_var, @fields, @r_class)
-                    @models_data[convert.sort]=modeldata
-                }
-            end
+          @models=[]
+          @models_data={}
+          for i in 1..@fields.size
+              c=Statsample::Combination.new(i,@fields.size)
+              c.each{|data|
+                  convert=data.collect {|i1|
+                      @fields[i1]
+                  }
+                  @models.push(convert)
+                  ds_prev=@ds.dup(convert+[@y_var])
+                  modeldata=ModelData.new(convert,ds_prev, @y_var, @fields, @r_class)
+                  @models_data[convert.sort]=modeldata
+              }
+          end
         end
         def summary(report_type=ConsoleSummary)
             out=""

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -26,25 +26,29 @@ class DominanceAnalysis
             end
             @da
         end
+        # Creates re-samples from original dataset.
+        # * number_samples: Number of new samples to add
+        # * n: size of each new sample. If nil, equal to original sample size
+        # * report: if true, echo number of current resample and total
         def bootstrap(number_samples,n=nil,report=false)
-                number_samples.times{ |t|
-                    @n_samples+=1
-                    puts _("Bootstrap %d of %d") % [t+1, number_samples] if report
-                    ds_boot=@ds.bootstrap(n)
-                    da_1=DominanceAnalysis.new(ds_boot,@y_var,@lr_class)
-                    da_1.total_dominance.each{|k,v|
-                        @samples_td[k].push(v)
-                    }
-                    da_1.conditional_dominance.each{|k,v|
-                        @samples_cd[k].push(v)
-                    }
-                    da_1.general_dominance.each{|k,v|
-                        @samples_gd[k].push(v)
-                    }
-                    da_1.general_averages.each{|k,v|
-                        @samples_ga[k].push(v)
-                    }
-                }
+          number_samples.times{ |t|
+            @n_samples+=1
+            puts _("Bootstrap %d of %d") % [t+1, number_samples] if report
+            ds_boot=@ds.bootstrap(n)
+            da_1=DominanceAnalysis.new(ds_boot,@y_var,@lr_class)
+            da_1.total_dominance.each{|k,v|
+                @samples_td[k].push(v)
+            }
+            da_1.conditional_dominance.each{|k,v|
+                @samples_cd[k].push(v)
+            }
+            da_1.general_dominance.each{|k,v|
+                @samples_gd[k].push(v)
+            }
+            da_1.general_averages.each{|k,v|
+                @samples_ga[k].push(v)
+            }
+          }
         end
         def create_samples_pairs
             @samples_td={}
@@ -106,7 +110,7 @@ class DominanceAnalysis
             table.header=[_("var"),_("mean"),_("se"),_("p.5"),_("p.95")]
             @fields.each{|f|
                 v=@samples_ga[f].to_vector(:scale)
-                row=[@ds.vector_label(f), sprintf("%0.3f",v.mean), sprintf("%0.3f",v.sd), sprintf("%0.3f",v.percentil(5)),sprintf("%0.3f",v.percentil(95))]
+                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.add_row(row)
 
             }
@@ -115,10 +119,10 @@ class DominanceAnalysis
         end
         def summary_pairs(pair,std,ttd)
             freqs=std.proportions
-            [0,0.5,1].each{|n|
+            [0, 0.5, 1].each{|n|
                 freqs[n]=0 if freqs[n].nil?
             }
-            name=@ds.vector_label(pair[0])+" - "+@ds.vector_label(pair[1])
+            name=@ds.label(pair[0])+" - "+@ds.label(pair[1])
             [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

@@ -0,0 +1,18 @@
+require 'statsample/factor/pca'
+require 'statsample/factor/principalaxis'
+require 'statsample/factor/rotation'
+
+module Statsample
+  # = Factor Analysis toolbox
+  # * Classes for Extraction of factors: 
+  #   * Statsample::Factor::PCA
+  #   * Statsample::Factor::PrincipalAxis
+  # * Classes for Rotation of factors: 
+  #   * Statsample::Factor::Varimax
+  #   * Statsample::Factor::Equimax
+  #   * Statsample::Factor::Quartimax
+  # 
+  # See documentation of each class to use it
+  module Factor
+  end
+end