statsample 0.6.2 → 0.6.3

data/lib/statsample/bivariate/tetrachoric.rb

@@ -107,13 +107,14 @@ module Statsample
       def threshold_y
         @zac
       end
+      # Summary of the analysis
       def summary
         rp=ReportBuilder.new()
         rp.add(self)
         rp.to_text
       end
       
-      def to_reportbuilder(generator)
+      def to_reportbuilder(generator) # :nodoc:
         section=ReportBuilder::Section.new(:name=>@name)
         t=ReportBuilder::Table.new(:name=>_("Contingence Table"),:header=>["","Y=0","Y=1", "T"])
         t.add_row(["X=0", @a,@b,@a+@b])
@@ -129,6 +130,7 @@ module Statsample
         generator.parse_element(section)
       end
       
+      # Creates a new tetrachoric object for analysis 
       def initialize(a,b,c,d)
         @a,@b,@c,@d=a,b,c,d
         @name=_("Tetrachoric correlation")
@@ -138,7 +140,9 @@ module Statsample
         raise "All frequencies should be positive" if  (@a < 0 or @b < 0 or @c < 0  or @d < 0)        
         compute
       end
-      
+      # Compute the tetrachoric correlation.
+      # Called on object creation.
+      #
       def compute
       
       #
@@ -412,7 +416,7 @@ module Statsample
       end
       
       
-      def calculate_sdr
+      def calculate_sdr # :nodoc:
         #
         # COMPUTE SDR
         #
@@ -442,7 +446,7 @@ module Statsample
         @sdzero = Math::sqrt(((@aa + @bb) * (@aa + @cc) * (@bb + @dd) * (@cc + @dd)).quo(@tot)).quo(@tot ** 2 * @ss)
         @sdr = @sdzero if (@r == 0)
       end
-      private :calculate_cosine, :calculate_sdr, :compute, :gaussian_quadrature
+      private :calculate_cosine, :calculate_sdr, :compute_sdzero, :compute, :gaussian_quadrature
     end
   end
 end

data/lib/statsample/combination.rb

@@ -40,7 +40,7 @@ module Statsample
     def next_value
         @d.next_value
     end
-    class CombinationRuby
+    class CombinationRuby # :nodoc:
       attr_reader :data
       def initialize(k,n)
           raise "k<=n" if k>n
@@ -83,7 +83,7 @@ module Statsample
     end
     
     # rb-gsl engine for Combinations
-    class CombinationGsl
+    class CombinationGsl # :nodoc:
       def initialize(k,n)
           require 'gsl'
           raise "k<=n" if k>n

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -23,13 +23,16 @@ module Statsample
       attr_accessor :ds
       # Name of analysis
       attr_accessor :name
-      # Alpha level of confidence
+      # Alpha level of confidence. Default: ALPHA
       attr_accessor :alpha
+      # Debug?
+      attr_accessor :debug
       # Create a new Dominance Analysis Bootstrap Object
       # 
       # * ds: A Dataset object
       # * y_var: Name of dependent variable
       # * opts: Any other attribute of the class 
+      ALPHA=0.95
       def initialize(ds,y_var, opts=Hash.new)
         @ds=ds
         @y_var=y_var
@@ -37,7 +40,8 @@ module Statsample
         @fields=ds.fields-[y_var]
         @samples_ga=@fields.inject({}){|a,v| a[v]=[];a}
         @n_samples=0
-        @alpha=0.95
+        @alpha=ALPHA
+        @debug=false
         @regression_class=Regression::Multiple::RubyEngine
         @name=_("Bootstrap dominance Analysis:  %s over %s") % [ ds.fields.join(",") , @y_var]
         opts.each{|k,v|
@@ -58,11 +62,11 @@ module Statsample
       # 
       # * 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)
+      
+      def bootstrap(number_samples,n=nil)
         number_samples.times{ |t|
           @n_samples+=1
-          puts _("Bootstrap %d of %d") % [t+1, number_samples] if report
+          puts _("Bootstrap %d of %d") % [t+1, number_samples] if @debug
           ds_boot=@ds.bootstrap(n)
           da_1=DominanceAnalysis.new(ds_boot, @y_var, :regression_class => @regression_class)
           da_1.total_dominance.each{|k,v|
@@ -93,6 +97,7 @@ module Statsample
           }
         end
       end
+      # Summary of analysis
       def summary
         rp=ReportBuilder.new()
         rp.add(self)
@@ -101,7 +106,7 @@ module Statsample
       def t
         Distribution::T.p_value(1-((1-@alpha) / 2), @n_samples - 1)
       end
-      def to_reportbuilder(generator)
+      def to_reportbuilder(generator) # :nodoc:
         raise "You should bootstrap first" if @n_samples==0
         anchor=generator.add_toc_entry(_("DAB: ")+@name)
         generator.add_html "<div class='dominance-analysis-bootstrap'>#{@name}<a name='#{anchor}'></a>"

data/lib/statsample/factor/pca.rb

@@ -95,7 +95,7 @@ module Factor
       }
       @eigenpairs=@eigenpairs.sort.reverse
     end
-    def to_reportbuilder(generator)
+    def to_reportbuilder(generator) # :nodoc:
       anchor=generator.add_toc_entry(_("PCA: ")+name)
       generator.add_html "<div class='pca'>"+_("PCA")+" #{@name}<a name='#{anchor}'></a>"
 

data/lib/statsample/graph/gdchart.rb

@@ -1,6 +1,6 @@
 require 'GDChart'
 module Statsample
-	module Util
+	module Util # :nodoc:
 	class << self
 		def chart_gdchart(file,width,height,chart_type, labels, options,num_datasets,data)
 				require 'GDChart'
@@ -18,7 +18,7 @@ module Statsample
 		end
 		end
 	end
-	class Vector
+	class Vector # :nodoc:
 		# Creates a barchart using ruby-gdchart
 		def gdchart_frequencies(file, width=300, height=150, chart_type=GDChart::BAR, options={})
 			labels,data=[],[]

data/lib/statsample/graph/svgboxplot.rb

@@ -1,108 +1,108 @@
 module Statsample
-    module Graph
-        class SvgBoxplot < SVG::Graph::Bar
-            def initialize(config={})
-                config[:fields]=["dummy"]
-                super(config)
-            end
-            def get_x_labels
-                @data.collect{|d|
-                    d[:title]
-                }
-            end
-            
-            def min_value
-                min = 0
-                if min_scale_value.nil? 
-                    min = @data.collect{|x| x[:data].min}.min
-                    if min > 0
-                        if min > 10
-                            min=min-2
-                        else
-                            min=0
-                        end
+  module Graph
+    class SvgBoxplot < SVG::Graph::Bar # :nodoc:
+        def initialize(config={})
+            config[:fields]=["dummy"]
+            super(config)
+        end
+        def get_x_labels
+            @data.collect{|d|
+                d[:title]
+            }
+        end
+        
+        def min_value
+            min = 0
+            if min_scale_value.nil? 
+                min = @data.collect{|x| x[:data].min}.min
+                if min > 0
+                    if min > 10
+                        min=min-2
+                    else
+                        min=0
                     end
-                else
-                    min = min_scale_value
                 end
-                return min
-            end
-            def draw_data
-            minvalue = min_value
-            fieldwidth = field_width
-            unit_size =  (@graph_height.to_f - font_size*2*top_font) / 
-                          (get_y_labels.max - get_y_labels.min)
-            bargap = bar_gap ? (fieldwidth < 10 ? fieldwidth / 2 : 10) : 0
-            
-            bar_width = fieldwidth - bargap
-            bar_width /= @data.length if stack == :side
-            x_mod = (@graph_width-bargap) / 2 - (stack==:side ? bar_width/2 : 0)
-            
-            bottom = @graph_height
-            
-            field_count = 0
-            for dataset in @data
-            
-            # cases (assume 0 = +ve):
-            #   value  min  length
-            #    +ve   +ve  value - min
-            #    +ve   -ve  value - 0
-            #    -ve   -ve  value.abs - 0
-            
-            min=dataset[:data].min
-            max=dataset[:data].max
-            median=dataset[:vector].median
-            q1=dataset[:vector].percentil(25)
-            q3=dataset[:vector].percentil(75)
-            iqr=q3-q1
-            left = (fieldwidth * field_count)
-            #length = (value.abs - (minvalue > 0 ? minvalue : 0)) * unit_size
-            # top is 0 if value is negative
-            top_wisk=(q3+iqr*1.5 < max) ? q3+iqr*1.5 : max
-            down_wisk= (q1-iqr*1.5 > min) ? q1-iqr*1.5 : min
-            
-            top=@graph_height-((top_wisk-minvalue)*unit_size)
-            down=@graph_height-((down_wisk-minvalue)*unit_size)
-            
-            median_bar=@graph_height-((median-minvalue)*unit_size)
-            middle= left+(bar_width / 2)
-            left_whis=left+(bar_width * 0.4)
-            rigth_whis=left+(bar_width*0.6)
-            left_rect= left+(bar_width * 0.25)
-            rigth_rect = left+ (bar_width * 0.75)
-            top_rect=@graph_height-((q3-minvalue)*unit_size)
-            height_rect=iqr*unit_size
-            path="M #{left_whis} #{top} H #{rigth_whis} M #{middle} #{top} V #{down} M #{left_whis} #{down} H #{rigth_whis} M #{left_rect} #{median_bar} H #{rigth_rect}"
-            
-            
-            # Marcamos Outliers
-            if top_wisk!=max or down_wisk!=min
-                dataset[:vector].valid_data.each{|d|
-                    if(d<down_wisk) or (d>top_wisk)
-                    y_out=(@graph_height - (d -minvalue)*unit_size).to_s
-                        @graph.add_element( "circle", {
-                         "cx" => (middle).to_s,
-                         "cy" => y_out,
-                        "r" => "3",
-                        "class" => "dataPoint#{field_count+1}"
-                        })
-                        @graph.add_element( "text", {
-                        "x" => (middle+20).to_s,
-                        "y" => y_out,
-                        "class" => "dataPointLabel",
-                        "style" => "#{style} stroke: #000;"
-                        }).text = d.to_s                    end
-                }
+            else
+                min = min_scale_value
             end
-            
-            @graph.add_element( "rect", { "x" => left_rect.to_s, "y" => top_rect.to_s, "width" => (bar_width / 2).to_s, "height" => (height_rect).to_s, "class" => "fill#{field_count+1}"})
+            return min
+        end
+        def draw_data
+        minvalue = min_value
+        fieldwidth = field_width
+        unit_size =  (@graph_height.to_f - font_size*2*top_font) / 
+                      (get_y_labels.max - get_y_labels.min)
+        bargap = bar_gap ? (fieldwidth < 10 ? fieldwidth / 2 : 10) : 0
+        
+        bar_width = fieldwidth - bargap
+        bar_width /= @data.length if stack == :side
+        x_mod = (@graph_width-bargap) / 2 - (stack==:side ? bar_width/2 : 0)
+        
+        bottom = @graph_height
+        
+        field_count = 0
+        for dataset in @data
+        
+        # cases (assume 0 = +ve):
+        #   value  min  length
+        #    +ve   +ve  value - min
+        #    +ve   -ve  value - 0
+        #    -ve   -ve  value.abs - 0
+        
+        min=dataset[:data].min
+        max=dataset[:data].max
+        median=dataset[:vector].median
+        q1=dataset[:vector].percentil(25)
+        q3=dataset[:vector].percentil(75)
+        iqr=q3-q1
+        left = (fieldwidth * field_count)
+        #length = (value.abs - (minvalue > 0 ? minvalue : 0)) * unit_size
+        # top is 0 if value is negative
+        top_wisk=(q3+iqr*1.5 < max) ? q3+iqr*1.5 : max
+        down_wisk= (q1-iqr*1.5 > min) ? q1-iqr*1.5 : min
+        
+        top=@graph_height-((top_wisk-minvalue)*unit_size)
+        down=@graph_height-((down_wisk-minvalue)*unit_size)
+        
+        median_bar=@graph_height-((median-minvalue)*unit_size)
+        middle= left+(bar_width / 2)
+        left_whis=left+(bar_width * 0.4)
+        rigth_whis=left+(bar_width*0.6)
+        left_rect= left+(bar_width * 0.25)
+        rigth_rect = left+ (bar_width * 0.75)
+        top_rect=@graph_height-((q3-minvalue)*unit_size)
+        height_rect=iqr*unit_size
+        path="M #{left_whis} #{top} H #{rigth_whis} M #{middle} #{top} V #{down} M #{left_whis} #{down} H #{rigth_whis} M #{left_rect} #{median_bar} H #{rigth_rect}"
+        
+        
+        # Marcamos Outliers
+        if top_wisk!=max or down_wisk!=min
+            dataset[:vector].valid_data.each{|d|
+                if(d<down_wisk) or (d>top_wisk)
+                y_out=(@graph_height - (d -minvalue)*unit_size).to_s
+                    @graph.add_element( "circle", {
+                     "cx" => (middle).to_s,
+                     "cy" => y_out,
+                    "r" => "3",
+                    "class" => "dataPoint#{field_count+1}"
+                    })
+                    @graph.add_element( "text", {
+                    "x" => (middle+20).to_s,
+                    "y" => y_out,
+                    "class" => "dataPointLabel",
+                    "style" => "#{style} stroke: #000;"
+                    }).text = d.to_s                    end
+            }
+        end
+        
+        @graph.add_element( "rect", { "x" => left_rect.to_s, "y" => top_rect.to_s, "width" => (bar_width / 2).to_s, "height" => (height_rect).to_s, "class" => "fill#{field_count+1}"})
 
-            @graph.add_element("path",{"d"=>path, "style"=>"stroke:black;stroke-width:2"})
-            
-            field_count += 1
-            end
-           
-            end
+        @graph.add_element("path",{"d"=>path, "style"=>"stroke:black;stroke-width:2"})
+        
+        field_count += 1
+        end
+       
         end
     end
+  end
 end

data/lib/statsample/graph/svggraph.rb

@@ -92,7 +92,7 @@ end
 # this allows rendering of svg and png on rox and gqview without problems
 module SVG #:nodoc:
 	module Graph 
-		class BarNoOp < Bar
+		class BarNoOp < Bar # :nodoc:
 			def get_css; SVG::Graph.get_css_standard; end
 		end
 		class BarHorizontalNoOp < BarHorizontal

data/lib/statsample/graph/svghistogram.rb

@@ -1,6 +1,6 @@
 module Statsample
   module Graph
-    class SvgHistogram < SVG::Graph::BarBase
+    class SvgHistogram < SVG::Graph::BarBase # :nodoc:
       attr_accessor :inner_margin, :mean, :sigma, :show_normal
       def initialize(config)
         config[:fields]=[:dummy]

data/lib/statsample/graph/svgscatterplot.rb

@@ -1,111 +1,109 @@
 module Statsample
-    module Graph
-        class SvgScatterplot < SVG::Graph::Plot
-            attr_accessor :draw_path
-            def initialize(ds,config={})
-                super(config)
-                @ds=ds
-                set_x(@ds.fields[0])
-            end
-            def set_defaults
-                super
-                init_with(
-                    :show_data_values => false,
-                    :draw_path => false
-                    )
-            end
-            def set_x(x)
-                @x=x
-                @y=@ds.fields - [x]
-            end
-            def parse
-                data=@y.inject({}){|a,v| a[v]=[];a}
-                @ds.each{|row|
-                    @y.each{|y|
-                        data[y]+=[row[@x],row[y]] unless row[@x].nil? or row[y].nil?
-                    }
-                }
-                data.each{|y,d|
-                    add_data({
-                            :data=>d, :title=>@ds.vector_label(y)
-                    })
-                }
-            end
-            def get_x_labels
-                values=super
-                values.collect{|x|
-                    if x.is_a? Integer
-                        x 
-                    else
-                        sprintf("%0.2f",x).to_f
-                    end
-                }
-            end
-            def get_y_labels
-                values=super
-                values.collect{|x|
-                    if x.is_a? Integer
-                        x 
-                    else
-                        sprintf("%0.2f",x).to_f
-                    end
-                }
-            end
-            def draw_data
+  module Graph
+    class SvgScatterplot < SVG::Graph::Plot # :nodoc:
+      attr_accessor :draw_path
+      def initialize(ds,config={})
+          super(config)
+          @ds=ds
+          set_x(@ds.fields[0])
+      end
+      def set_defaults
+          super
+          init_with(
+              :show_data_values => false,
+              :draw_path => false
+              )
+      end
+      def set_x(x)
+          @x=x
+          @y=@ds.fields - [x]
+      end
+      def parse
+        data=@y.inject({}){|a,v| a[v]=[];a}
+        @ds.each{|row|
+          @y.each{|y|
+              data[y]+=[row[@x],row[y]] unless row[@x].nil? or row[y].nil?
+          }
+        }
+        data.each{|y,d|
+          add_data({
+                  :data=>d, :title=>@ds.vector_label(y)
+          })
+        }
+      end
+      def get_x_labels
+        values=super
+        values.collect{|x|
+          if x.is_a? Integer
+              x 
+          else
+              sprintf("%0.2f",x).to_f
+          end
+        }
+      end
+      def get_y_labels
+        values=super
+        values.collect{|x|
+          if x.is_a? Integer
+              x 
+          else
+              sprintf("%0.2f",x).to_f
+          end
+        }
+      end
+      def draw_data
         line = 1
-
+        
         x_min, x_max, x_div = x_range
         y_min, y_max, y_div = y_range
         x_step = (@graph_width.to_f - font_size*2) / (x_max-x_min)
         y_step = (@graph_height.to_f -  font_size*2) / (y_max-y_min)
-
+        
         for data in @data
-          x_points = data[:data][X]
-          y_points = data[:data][Y]
-
-          lpath = "L"
-          x_start = 0
-          y_start = 0
-          x_points.each_index { |idx|
-            x = (x_points[idx] -  x_min) * x_step
-            y = @graph_height - (y_points[idx] -  y_min) * y_step
-            x_start, y_start = x,y if idx == 0
-            lpath << "#{x} #{y} "
-          }
-
-          if area_fill
-            @graph.add_element( "path", {
-              "d" => "M#{x_start} #@graph_height #{lpath} V#@graph_height Z",
-              "class" => "fill#{line}"
+        x_points = data[:data][X]
+        y_points = data[:data][Y]
+        
+        lpath = "L"
+        x_start = 0
+        y_start = 0
+        x_points.each_index { |idx|
+        x = (x_points[idx] -  x_min) * x_step
+        y = @graph_height - (y_points[idx] -  y_min) * y_step
+        x_start, y_start = x,y if idx == 0
+        lpath << "#{x} #{y} "
+        }
+        
+        if area_fill
+        @graph.add_element( "path", {
+          "d" => "M#{x_start} #@graph_height #{lpath} V#@graph_height Z",
+          "class" => "fill#{line}"
+        })
+        end
+        if draw_path
+        @graph.add_element( "path", {
+        "d" => "M#{x_start} #{y_start} #{lpath}",
+        "class" => "line#{line}"
+        })
+        end
+        if show_data_points || show_data_values
+        x_points.each_index { |idx|
+          x = (x_points[idx] -  x_min) * x_step
+          y = @graph_height - (y_points[idx] -  y_min) * y_step
+          if show_data_points
+            @graph.add_element( "circle", {
+              "cx" => x.to_s,
+              "cy" => y.to_s,
+              "r" => "2.5",
+              "class" => "dataPoint#{line}"
             })
+            add_popup(x, y, format( x_points[idx], y_points[idx] )) if add_popups
           end
-          if draw_path
-          @graph.add_element( "path", {
-            "d" => "M#{x_start} #{y_start} #{lpath}",
-            "class" => "line#{line}"
-          })
-          end
-          if show_data_points || show_data_values
-            x_points.each_index { |idx|
-              x = (x_points[idx] -  x_min) * x_step
-              y = @graph_height - (y_points[idx] -  y_min) * y_step
-              if show_data_points
-                @graph.add_element( "circle", {
-                  "cx" => x.to_s,
-                  "cy" => y.to_s,
-                  "r" => "2.5",
-                  "class" => "dataPoint#{line}"
-                })
-                add_popup(x, y, format( x_points[idx], y_points[idx] )) if add_popups
-              end
-              make_datapoint_text( x, y-6, y_points[idx] ) if show_data_values
-            }
-          end
-          line += 1
+          make_datapoint_text( x, y-6, y_points[idx] ) if show_data_values
+        }
         end
-      end
-            
-            
+        line += 1
         end
+      end
     end
+  end
 end