statsample 0.3.2 → 0.3.3

data/History.txt

@@ -1,3 +1,9 @@
+=== 0.3.3 / 2009-08-11
+* Added i18n support. For now, only spanish translation available
+* Bug fix: Test now load libraries on ../lib path
+* Excel and CSV importers automatically modify type of vector to Scale when all data are numbers or nils values
+* 
+
 === 0.3.2 / 2009-08-04
 
 * Added Regression::Multiple::GslEngine

data/Manifest.txt

@@ -3,6 +3,7 @@ LICENSE.txt
 Manifest.txt
 README.txt
 bin/statsample
+data/locale/es/LC_MESSAGES/statsample.mo
 demo/benchmark.rb
 demo/chi-square.rb
 demo/crosstab.rb
@@ -47,6 +48,8 @@ lib/statsample/resample.rb
 lib/statsample/srs.rb
 lib/statsample/test.rb
 lib/statsample/vector.rb
+po/es/statsample.po
+po/statsample.pot
 setup.rb
 test/_test_chart.rb
 test/test_anova.rb

data/README.txt

@@ -1,11 +1,11 @@
 = Statsample
 
-* http://rubyforge.org/projects/ruby-statsample/
-* http://code.google.com/p/ruby-statsample/
+http://ruby-statsample.rubyforge.org/
+
 
 == DESCRIPTION:
 
-This package allows to process files and databases for statistical purposes, with focus on validation, recodification and estimation of parameters for several types of samples (simple random, stratified and multistage sampling).
+A suite for your basic and advanced statistics needs. Descriptive statistics, multiple regression, dominance analysis, scale's reliability analysis, bivariate statistics and others procedures.
 
 == FEATURES:
 
@@ -63,6 +63,10 @@ Optional:
 * Plotting: gnuplot and rbgnuplot, SVG::Graph
 * Advanced Statistical: gsl and rb-gsl (http://rb-gsl.rubyforge.org/)
 
+== DOWNLOAD
+* Gems and bugs report: http://rubyforge.org/projects/ruby-statsample/
+* SVN and Wiki: http://code.google.com/p/ruby-statsample/
+
 == INSTALL:
 
   sudo gem install ruby-statsample

data/demo/regression.rb

@@ -1,4 +1,5 @@
 require File.dirname(__FILE__)+'/../lib/statsample'
+require 'benchmark'
 tests=300
 include Statsample
 r = GSL::Rng.alloc(GSL::Rng::TAUS,Time.now.to_i)
@@ -24,9 +25,17 @@ if !File.exists? "regression.dab"
 else
     da=Statsample.load("regression.dab")
 end
-    
-da.lr_class=Regression::Multiple::AlglibEngine
-da.bootstrap(20)
+times=1
+Benchmark.bm(7) do |x|
+    x.report("GslEngine:") {
+        da.lr_class=Regression::Multiple::GslEngine
+        da.bootstrap(times)
+    }
+    x.report("AlglibEngine:") {
+        da.lr_class=Regression::Multiple::AlglibEngine
+        da.bootstrap(times)
+    }
+end
 
 puts da.summary
 da.save("regression.dab")

data/lib/statsample/converters.rb

@@ -78,7 +78,46 @@ module Statsample
         end
         end
     end
-    module Excel
+    class SpreadsheetBase
+        class << self
+            def extract_fields(row)
+                fields=row.to_a.collect{|c| c.downcase}
+                if fields.size!=fields.uniq.size
+                    repeated=fields.inject({}) {|a,v|
+                    (a[v].nil? ? a[v]=1 : a[v]+=1); a }.find_all{|k,v| v>1}.collect{|k,v|k}.join(",")
+                    raise "There are some repeated fields on the header:#{repeated}. Please, fix" 
+                end
+                fields
+            end
+            
+            def process_row(row,empty)
+                row.to_a.collect do |c|
+                    if empty.include?(c)
+                        nil
+                    else
+                        if c.is_a? String and c.is_number?
+                            if c=~/^\d+$/
+                                c.to_i
+                            else
+                                c.gsub(",",".").to_f
+                            end
+                        else
+                            c
+                        end
+                    end
+                end
+            end
+            def convert_to_scale(ds,fields)
+                fields.each do |f|
+                    if ds[f].can_be_scale?
+                        ds[f].type=:scale
+                    end
+                end
+            end
+                
+        end
+    end
+    class Excel < SpreadsheetBase 
         class << self
             def write(dataset,filename)
                 require 'spreadsheet'
@@ -101,7 +140,6 @@ module Statsample
             #
             def read(filename, worksheet_id=0, ignore_lines=0, empty=[''])
             require 'spreadsheet'
-                
                 first_row=true
                 fields=[]
                 fields_data={}
@@ -121,35 +159,28 @@ module Statsample
                         if c.is_a? Spreadsheet::Formula
                             nil
                         else
-                            c.to_s
+                            c
                         end
                     }
                     if first_row
-                        fields=row.to_a.collect{|c| c.downcase}
-                        if fields.size!=fields.uniq.size
-                            repeated=fields.inject({}) {|a,v|
-                                (a[v].nil? ? a[v]=1 : a[v]+=1); a }.find_all{|k,v| v>1}.collect{|k,v|k}.join(",")
-                                raise "There are some repeated fields on the header:#{repeated}. Please, fix" 
-                        end
+                        fields=extract_fields(row)
                         ds=Statsample::Dataset.new(fields)
                         first_row=false
                     else
-                        rowa=row.to_a.collect{|c|
-                            
-                            empty.include?(c) ? nil: c
-                        }
+                        rowa=process_row(row,empty)
                         (fields.size - rowa.size).times {|i|
                             rowa << nil
                         }
                         ds.add_case(rowa,false)
                     end
                 end
+                convert_to_scale(ds,fields)
                 ds.update_valid_data
                 ds
             end
         end
     end
-    module CSV
+    class CSV < SpreadsheetBase
 		class << self
         # Returns a Dataset  based on a csv file
         #
@@ -157,7 +188,6 @@ module Statsample
         #     ds=Statsample::CSV.read("test_csv.csv")
         def read(filename, empty=[''],ignore_lines=0,fs=nil,rs=nil)
         require 'csv'
-            
                 first_row=true
                 fields=[]
                 fields_data={}
@@ -173,23 +203,15 @@ module Statsample
                         c.to_s
                     }
                     if first_row
-                        fields=row.to_a.collect{|c| c.downcase}
-                        if fields.size!=fields.uniq.size
-                            repeated=fields.inject({}) {|a,v|
-                                (a[v].nil? ? a[v]=1 : a[v]+=1); a }.find_all{|k,v| v>1}.collect{|k,v|k}.join(",")
-                           
-                                raise "There are some repeated fields on the header:#{repeated}. Please, fix" 
-                        end
+                        fields=extract_fields(row)
                         ds=Statsample::Dataset.new(fields)
                         first_row=false
                     else
-                        rowa=row.to_a.collect{|c|
-                            empty.include?(c) ? nil: c
-                        }
-                        
+                        rowa=process_row(row,empty)
                         ds.add_case(rowa,false)
                     end
                 end
+                convert_to_scale(ds,fields)
                 ds.update_valid_data
                 ds
             end

data/lib/statsample/crosstab.rb

@@ -4,6 +4,8 @@ module Statsample
 	# The first vector will be at rows and the second will the the columns
 	#
     class Crosstab
+        include GetText
+        bindtextdomain("statsample")
 		attr_reader :v_rows, :v_cols
         attr_accessor :row_label, :column_label
 		def initialize(v1,v2)
@@ -88,10 +90,10 @@ module Statsample
             total=0
             total_cols=cn.inject({}) {|a,x| a[x]=0;a}
             out.add "Chi Square: #{chi_square}\n"
-            out.add "Rows: #{@row_label}\n" unless @row_label.nil?
-            out.add "Columns: #{@column_label}\n" unless @column_label.nil?
+            out.add(_("Rows: %s\n") % @row_label) unless @row_label.nil?
+            out.add(_("Columns: %s\n") % @column_label) unless @column_label.nil?
             
-            t=Statsample::ReportTable.new([""]+cols_names+["Total"])
+            t=Statsample::ReportTable.new([""]+cols_names+[_("Total")])
             rn.each{|row|
                 total_row=0
                 t_row=[@v_rows.labeling(row)]
@@ -106,7 +108,7 @@ module Statsample
                 t.add_row(t_row)
             }
             t.add_horizontal_line
-            t_row=["Total"]
+            t_row=[_("Total")]
             cn.each{|v|
                 t_row.push(total_cols[v])
             }

data/lib/statsample/dominanceanalysis/bootstrap.rb

@@ -1,7 +1,9 @@
 module Statsample
 class DominanceAnalysis
     class Bootstrap
+        include GetText
         include Writable
+        bindtextdomain("statsample")
         attr_reader :samples_td,:samples_cd,:samples_gd,:samples_ga, :fields
         attr_writer :lr_class
         attr_accessor :ds
@@ -24,10 +26,10 @@ class DominanceAnalysis
             end
             @da
         end
-        def bootstrap(number_samples,n=nil)
+        def bootstrap(number_samples,n=nil,report=false)
                 number_samples.times{ |t|
                     @n_samples+=1
-                    puts "Bootstrap #{t+1} of #{number_samples}"
+                    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|
@@ -66,15 +68,15 @@ class DominanceAnalysis
             alfa=0.95
             t=GSL::Cdf.tdist_Pinv(1-((1-alfa) / 2),@n_samples - 1)
             out.extend report_type
-            out.add "Summary for Bootstrap Dominance Analysis of "+@fields.join(", ")+" over "+@y_var+"\n"
-            out.add "Size of sample: #{@n_samples}\n"
+            out.add _("Summary for Bootstrap Dominance Analysis of %s on %s\n") % [@fields.join(", "), @y_var]
+            out.add _("Sample size: %d\n") % @n_samples
             out.add "t:#{t}\n"
             out.add "Linear Regression Engine: #{@lr_class.name}"
             out.nl
             table=ReportTable.new
-            header=["pairs","sD","Dij","SE(Dij)","Pij","Pji","Pno","Reprod"]
+            header=[_("pairs"),"sD","Dij",_("SE(Dij)"),"Pij","Pji","Pno",_("Reproducibility")]
             table.header=header
-            table.add_row(["Complete dominance"])
+            table.add_row([_("Complete dominance")])
             table.add_horizontal_line
             @pairs.each{|pair|
                 std=@samples_td[pair].to_vector(:scale)
@@ -82,7 +84,7 @@ class DominanceAnalysis
                 table.add_row(summary_pairs(pair,std,ttd))
             }
             table.add_horizontal_line
-            table.add_row(["Conditional dominance"])
+            table.add_row([_("Conditional dominance")])
             table.add_horizontal_line
             @pairs.each{|pair|
                 std=@samples_cd[pair].to_vector(:scale)
@@ -91,7 +93,7 @@ class DominanceAnalysis
 
             }
             table.add_horizontal_line
-            table.add_row(["General Dominance"])
+            table.add_row([_("General Dominance")])
             table.add_horizontal_line
             @pairs.each{|pair|
                 std=@samples_gd[pair].to_vector(:scale)
@@ -99,9 +101,9 @@ class DominanceAnalysis
                 table.add_row(summary_pairs(pair,std,ttd))
             }
             out.parse_table(table)
-            out.add("General averages")
+            out.add(_("General averages"))
             table=Statsample::ReportTable.new
-            table.header=["var","mean","se","p.5","p.95"]
+            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))]

data/lib/statsample/dominanceanalysis.rb

@@ -1,6 +1,8 @@
 require 'statsample/dominanceanalysis/bootstrap'
 module Statsample
     class DominanceAnalysis
+        include GetText
+        bindtextdomain("statsample")
         def initialize(ds,y_var, r_class = Regression::Multiple::RubyEngine)
             @y_var=y_var
             @dy=ds[@y_var]
@@ -164,10 +166,10 @@ module Statsample
         def summary(report_type=ConsoleSummary)
             out=""
             out.extend report_type
-            out << "Summary for Dominance Analysis of "+@fields.join(", ")+" over "+@y_var+"\n"
+            out << _("Summary for Dominance Analysis of %s on %s\n") % [@fields.join(", "),@y_var]
                 t=Statsample::ReportTable.new
                 t.header=["","r2","sign"]+@fields
-                row=["Model 0","",""]+@fields.collect{|f|
+                row=[_("Model 0"),"",""]+@fields.collect{|f|
                     sprintf("%0.3f",md(f).r2)
                 }
                 t.add_row(row)
@@ -181,7 +183,7 @@ module Statsample
                 a=average_k(i)
                 if !a.nil?
                     t.add_horizontal_line
-                    row=["k=#{i} Average","",""] + @fields.collect{|f|
+                    row=[_("k=%d Average") % i,"",""] + @fields.collect{|f|
                         sprintf("%0.3f",a[f])
                     }
                     t.add_row(row)
@@ -194,18 +196,18 @@ module Statsample
             g=general_averages
                     t.add_horizontal_line
             
-            row=["Overall averages","",""]+@fields.collect{|f|
+            row=[_("Overall averages"),"",""]+@fields.collect{|f|
                         sprintf("%0.3f",g[f])
             }
             t.add_row(row)
             out.parse_table(t)
                     
             out.nl
-            out << "Pairwise\n"
+            out << _("Pairwise")+"\n"
             td=total_dominance
             cd=conditional_dominance
             gd=general_dominance
-            t=Statsample::ReportTable.new(["Pairs","T","C","G"])
+            t=Statsample::ReportTable.new([_("Pairs"),"T","C","G"])
             pairs.each{|p|
                 name=p.join(" - ")
                 row=[name, sprintf("%0.1f",td[p]), sprintf("%0.1f",cd[p]), sprintf("%0.1f",gd[p])]

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

@@ -4,6 +4,8 @@ module Regression
 module Multiple
 # Class for Multiple Regression Analysis
 # Requires Alglib gem and uses a listwise aproach.
+# Faster than GslEngine on massive prediction use, because process is c-based.
+# Prefer GslEngine if you need good memory use.
 # If you need pairwise, use RubyEngine
 # Example:
 #

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

@@ -4,6 +4,8 @@ module Regression
 module Multiple
 # Class for Multiple Regression Analysis
 # Requires rbgsl and uses a listwise aproach.
+# Slower on prediction of values than Alglib, because predict is ruby based.
+# Better memory management on multiple (+1000) series of regression. 
 # If you need pairwise, use RubyEngine
 # Example:
 #
@@ -42,9 +44,11 @@ class GslEngine < BaseEngine
         }
         @dep_columns=columns.dup
         @lr_s=nil
-        @c, @cov, @chisq, @status = GSL::MultiFit.linear(max_deps, @dy.gsl)
-        @constant=@c[constant_col]
-        @coeffs=@c.to_a.slice(0...constant_col)
+        c, @cov, @chisq, @status = GSL::MultiFit.linear(max_deps, @dy.gsl)
+        @constant=c[constant_col]
+        @coeffs_a=c.to_a.slice(0...constant_col)
+        @coeffs=assign_names(@coeffs_a)
+        c=nil
     end
     
     def _dump(i)
@@ -56,7 +60,7 @@ class GslEngine < BaseEngine
     end
     
     def coeffs
-        assign_names(@coeffs)
+        @coeffs
     end
     # Coefficients using a constant
     # Based on http://www.xycoon.com/ols1.htm

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

@@ -2,7 +2,8 @@ module Statsample
 module Regression
 module Multiple
 # Pure Ruby Class for Multiple Regression Analysis.
-# Slower than AlglibEngine, but is pure ruby and uses a pairwise aproach for missing values. 
+# Slower than AlglibEngine, but is pure ruby and can use a pairwise aproach for missing values. 
+# Coeffient calculation uses correlation matrix between the vectors
 # If you need listwise aproach for missing values, use AlglibEngine, because is faster.
 # 
 # Example:

data/lib/statsample/regression/multiple.rb

@@ -15,14 +15,14 @@ module Regression
         
         
 module Multiple
-    # Creates an object for listwise regression. According to resources
-    # select the best engine
+    # Creates an object for listwise regression. 
+    # Alglib is faster, so is prefered over GSL
     #   lr=Statsample::Regression::Multiple.listwise(ds,'y')
     def self.listwise(ds,y_var)
-        if HAS_GSL
-            GslEngine.new(ds,y_var)
-        elsif HAS_ALGIB
+        if HAS_ALGIB
             AlglibEngine.new(ds,y_var)
+        elsif HAS_GSL
+            GslEngine.new(ds,y_var)
         else
             ds2=ds.dup_only_valid
             RubyEngine.new(ds2,y_var)
@@ -132,14 +132,7 @@ module Multiple
             ds.each{|k,v|
                 ds[k]=v.to_vector(:scale)
             }
-    if HAS_ALGIB
-        lr_class=AlglibEngine
-        ds=ds.to_dataset
-    else
-        lr_class=RubyEngine
-        ds=ds.to_dataset.dup_only_valid
-    end
-    lr=lr_class.new(ds,var)
+            lr=Multiple.listwise(ds.to_dataset,var)
             1-lr.r2
         end
         # Tolerances for each coefficient

data/lib/statsample/vector.rb

@@ -393,6 +393,14 @@ class Vector < DelegateClass(Array)
                 return "INTEGER"
             end
         end
+        # Return true if all data is Numeric or nil
+        def can_be_scale?
+            if @data.find {|v| !v.nil? and !v.is_a? Numeric}
+                false
+            else
+                true
+            end
+        end
         def summary(out="")
             @delegate.summary(@labels,out)
         end

data/lib/statsample.rb

@@ -29,19 +29,43 @@ class Numeric
   def square ; self * self ; end
 end
 
+class String
+    def is_number?
+        if self =~ /^-?\d+[,.]?\d*(e-?\d+)?$/
+            true
+        else
+            false
+        end
+    end
+end
 
 def create_test(*args,&proc) 
     description=args.shift
     fields=args
     [description, fields, Proc.new]
 end
-
+# Test extensions
 begin
-	require 'rbgsl'
-	HAS_GSL=true
-rescue LoadError
-	HAS_GSL=false
+    require 'gettext'
+    rescue LoadError
+    def bindtextdomain(d)
+        d
+    end
+
+        # Bored module
+        module GetText
+            def _(t)
+                t
+            end
+        end
 end
+    
+    begin
+        require 'rbgsl'
+        HAS_GSL=true
+    rescue LoadError
+        HAS_GSL=false
+    end
     begin 
         require 'alglib'
         HAS_ALGIB=true
@@ -66,7 +90,7 @@ end
 # * Dataset: An union of vectors.
 #
 module Statsample
-    VERSION = '0.3.2'
+    VERSION = '0.3.3'
     SPLIT_TOKEN = ","
 	autoload(:Database, 'statsample/converters')
     autoload(:Anova, 'statsample/anova')
@@ -82,6 +106,10 @@ module Statsample
 	autoload(:Reliability, 'statsample/reliability')
 	autoload(:Bivariate, 'statsample/bivariate')
 	autoload(:Multivariate, 'statsample/multivariate')
+	autoload(:Multiset, 'statsample/multiset')
+	autoload(:StratifiedSample, 'statsample/multiset')
+    
+    
 	autoload(:Regression, 'statsample/regression')
 	autoload(:Test, 'statsample/test')
     def self.load(filename)

data/po/es/statsample.po

@@ -0,0 +1,108 @@
+msgid ""
+msgstr ""
+"Project-Id-Version: statsample 0.3.3\n"
+"POT-Creation-Date: 2009-08-10 11:59-0400\n"
+"PO-Revision-Date: 2009-08-04 15:57-0300\n"
+"Last-Translator: Claudio Bustos <clbustos@gmail.com>\n"
+"Language-Team: Desarrollador\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"X-Poedit-Language: Spanish\n"
+"X-Poedit-SourceCharset: utf-8\n"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:32
+msgid "Bootstrap %d of %d"
+msgstr "Bootstrap: %d de %d"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:71
+msgid "Summary for Bootstrap Dominance Analysis of %s on %s\n"
+msgstr "Resultados del Análisis de Dominancia Bootstrap de %s en %s\n"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:72
+msgid "Sample size: %d\n"
+msgstr "Tamaño de muestra: %d\n"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "pairs"
+msgstr "pares"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "SE(Dij)"
+msgstr "EE(Dij)"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "Reproducibility"
+msgstr "Reproducibilidad"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:79
+msgid "Complete dominance"
+msgstr "Dominancia Completa"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:87
+msgid "Conditional dominance"
+msgstr "Dominancia Condicional"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:96
+msgid "General Dominance"
+msgstr "Dominancia General"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:104
+msgid "General averages"
+msgstr "Promedios generales"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "var"
+msgstr "var"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "mean"
+msgstr "promedio"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "se"
+msgstr "de"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "p.5"
+msgstr "p.5"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "p.95"
+msgstr "p.95"
+
+#: lib/statsample/crosstab.rb:93
+msgid "Rows: %s\n"
+msgstr ""
+
+#: lib/statsample/crosstab.rb:94
+msgid "Columns: %s\n"
+msgstr ""
+
+#: lib/statsample/crosstab.rb:96 lib/statsample/crosstab.rb:111
+msgid "Total"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:169
+msgid "Summary for Dominance Analysis of %s on %s\n"
+msgstr "Resultado del Análisis de Dominancia de %s en %s\n"
+
+#: lib/statsample/dominanceanalysis.rb:172
+msgid "Model 0"
+msgstr "Modelo 0"
+
+#: lib/statsample/dominanceanalysis.rb:186
+msgid "k=%d Average"
+msgstr "k=%d Promedio"
+
+#: lib/statsample/dominanceanalysis.rb:199
+msgid "Overall averages"
+msgstr "Promedios generales"
+
+#: lib/statsample/dominanceanalysis.rb:206
+msgid "Pairwise"
+msgstr "De a pares"
+
+#: lib/statsample/dominanceanalysis.rb:210
+msgid "Pairs"
+msgstr "Pares"

data/po/statsample.pot

@@ -0,0 +1,113 @@
+# Statsample po template.
+# Copyright (C) 2009-2009 Claudio Bustos
+# This file is distributed under the same license as the Statsample package.
+# Claudio Bustos <clbustos_AT_gmail.com>
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: statsample 0.3.3\n"
+"POT-Creation-Date: 2009-08-10 11:59-0400\n"
+"PO-Revision-Date: 2009-08-04 15:36-0400\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Plural-Forms: nplurals=INTEGER; plural=EXPRESSION;\n"
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:32
+msgid "Bootstrap %d of %d"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:71
+msgid "Summary for Bootstrap Dominance Analysis of %s on %s\n"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:72
+msgid "Sample size: %d\n"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "pairs"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "SE(Dij)"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:77
+msgid "Reproducibility"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:79
+msgid "Complete dominance"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:87
+msgid "Conditional dominance"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:96
+msgid "General Dominance"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:104
+msgid "General averages"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "var"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "mean"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "se"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "p.5"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis/bootstrap.rb:106
+msgid "p.95"
+msgstr ""
+
+#: lib/statsample/crosstab.rb:93
+msgid "Rows: %s\n"
+msgstr ""
+
+#: lib/statsample/crosstab.rb:94
+msgid "Columns: %s\n"
+msgstr ""
+
+#: lib/statsample/crosstab.rb:96 lib/statsample/crosstab.rb:111
+msgid "Total"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:169
+msgid "Summary for Dominance Analysis of %s on %s\n"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:172
+msgid "Model 0"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:186
+msgid "k=%d Average"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:199
+msgid "Overall averages"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:206
+msgid "Pairwise"
+msgstr ""
+
+#: lib/statsample/dominanceanalysis.rb:210
+msgid "Pairs"
+msgstr ""

data/test/test_anova.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample.rb'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleAnovaTestCase < Test::Unit::TestCase

data/test/test_codification.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'tempfile'
 require 'test/unit'
 

data/test/test_crosstab.rb

@@ -1,5 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
-require 'statsample/crosstab'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleCrosstabTestCase < Test::Unit::TestCase

data/test/test_csv.csv

@@ -3,5 +3,5 @@
 2,"Claude",23,"London","b,c"
 3,"Peter",25,"London","a"
 4,"Franz",27,"Paris",
-5,"George",5,"Tome","a,b,c"
+5,"George","5,5","Tome","a,b,c"
 6,"Fernand",,,

data/test/test_csv.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 	require 'tmpdir'
 require 'test/unit'
 
@@ -8,8 +9,20 @@ class StatsampleCSVTestCase < Test::Unit::TestCase
 		super
 	end
     def test_read
-        assert_equal(6,@ds.cases)
+                assert_equal(6,@ds.cases)
         assert_equal(%w{id name age city a1},@ds.fields)
+        id=[1,2,3,4,5,6].to_vector(:scale)
+        name=["Alex","Claude","Peter","Franz","George","Fernand"].to_vector(:nominal)
+        age=[20,23,25,27,5.5,nil].to_vector(:scale)
+        city=["New York","London","London","Paris","Tome",nil].to_vector(:nominal)
+        a1=["a,b","b,c","a",nil,"a,b,c",nil].to_vector(:nominal)
+        ds_exp=Statsample::Dataset.new({'id'=>id,'name'=>name,'age'=>age,'city'=>city,'a1'=>a1}, %w{id name age city a1})
+        ds_exp.fields.each{|f|
+            assert_equal(ds_exp[f],@ds[f])
+        }
+        assert_equal(ds_exp,@ds)
+        
+
     end
     def test_nil
         assert_equal(nil,@ds['age'][5])

data/test/test_dataset.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleDatasetTestCase < Test::Unit::TestCase

data/test/test_ggobi.rb

@@ -1,5 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
-require 'statsample/multiset'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleGGobiTestCase < Test::Unit::TestCase

data/test/test_multiset.rb

@@ -1,5 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample.rb'
-require 'statsample/multiset'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleMultisetTestCase < Test::Unit::TestCase

data/test/test_regression.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 class StatsampleRegressionTestCase < Test::Unit::TestCase
 	def initialize(*args)

data/test/test_reliability.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleReliabilityTestCase < Test::Unit::TestCase

data/test/test_resample.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleResampleTestCase < Test::Unit::TestCase

data/test/test_srs.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleSrsTestCase < Test::Unit::TestCase

data/test/test_statistics.rb

@@ -1,10 +1,23 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 class StatsampleStatisicsTestCase < Test::Unit::TestCase
 
 	def initialize(*args)
 		super
 	end
+    def test_is_number
+        assert("10".is_number?)
+        assert("-10".is_number?)
+        assert("0.1".is_number?)
+        assert("-0.1".is_number?)
+        assert("10e3".is_number?)
+        assert("10e-3".is_number?)
+        assert(!"1212-1212-1".is_number?)
+        assert(!"a10".is_number?)
+        assert(!"".is_number?)
+
+    end
     def test_chi_square
         assert_raise TypeError do
             Statsample::Test.chi_square(1,1)

data/test/test_stratified.rb

@@ -1,5 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
-require 'statsample/multiset'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleStratifiedTestCase < Test::Unit::TestCase

data/test/test_svg_graph.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'tempfile'
 require 'test/unit'
 begin

data/test/test_vector.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 
 class StatsampleVectorTestCase < Test::Unit::TestCase

data/test/test_xls.rb

@@ -1,4 +1,5 @@
-require File.dirname(__FILE__)+'/../lib/statsample'
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
 require 'test/unit'
 require 'tmpdir'
 begin
@@ -15,6 +16,17 @@ class StatsampleExcelTestCase < Test::Unit::TestCase
     def test_read
         assert_equal(6,@ds.cases)
         assert_equal(%w{id name age city a1},@ds.fields)
+        id=[1,2,3,4,5,6].to_vector(:scale)
+        name=["Alex","Claude","Peter","Franz","George","Fernand"].to_vector(:nominal)
+        age=[20,23,25,nil,5.5,nil].to_vector(:scale)
+        city=["New York","London","London","Paris","Tome",nil].to_vector(:nominal)
+        a1=["a,b","b,c","a",nil,"a,b,c",nil].to_vector(:nominal)
+        ds_exp=Statsample::Dataset.new({'id'=>id,'name'=>name,'age'=>age,'city'=>city,'a1'=>a1}, %w{id name age city a1})
+        ds_exp.fields.each{|f|
+            assert_equal(ds_exp[f],@ds[f])
+        }
+        assert_equal(ds_exp,@ds)
+        
     end
     def test_nil
         assert_equal(nil,@ds['age'][5])

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: statsample
 version: !ruby/object:Gem::Version 
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors: 
 - Claudio Bustos
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-08-04 00:00:00 -04:00
+date: 2009-08-11 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -30,7 +30,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: "0"
+        version: 1.0.0
     version: 
 - !ruby/object:Gem::Dependency 
   name: hoe
@@ -40,9 +40,9 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 2.3.2
+        version: 2.3.3
     version: 
-description: This package allows to process files and databases for statistical purposes, with focus on validation, recodification and estimation of parameters for several types of samples (simple random, stratified and multistage sampling).
+description: A suite for your basic and advanced statistics needs. Descriptive statistics, multiple regression, dominance analysis, scale's reliability analysis, bivariate statistics and others procedures.
 email: 
 - clbustos@gmail.com
 executables: 
@@ -60,6 +60,7 @@ files:
 - Manifest.txt
 - README.txt
 - bin/statsample
+- data/locale/es/LC_MESSAGES/statsample.mo
 - demo/benchmark.rb
 - demo/chi-square.rb
 - demo/crosstab.rb
@@ -104,6 +105,8 @@ files:
 - lib/statsample/srs.rb
 - lib/statsample/test.rb
 - lib/statsample/vector.rb
+- po/es/statsample.po
+- po/statsample.pot
 - setup.rb
 - test/_test_chart.rb
 - test/test_anova.rb
@@ -125,7 +128,7 @@ files:
 - test/test_xls.rb
 - test/test_xls.xls
 has_rdoc: true
-homepage: http://rubyforge.org/projects/ruby-statsample/
+homepage: http://ruby-statsample.rubyforge.org/
 licenses: []
 
 post_install_message: 
@@ -152,7 +155,7 @@ rubyforge_project: ruby-statsample
 rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
-summary: This package allows to process files and databases for statistical purposes, with focus on validation, recodification and estimation of parameters for several types of samples (simple random, stratified and multistage sampling).
+summary: A suite for your basic and advanced statistics needs
 test_files: 
 - test/test_anova.rb
 - test/test_codification.rb