statsample 1.4.0 → 1.4.1

data/lib/statsample/version.rb

@@ -1,3 +1,3 @@
 module Statsample
-  VERSION = '1.4.0'
+  VERSION = '1.4.1'
 end

data/lib/statsample.rb

@@ -1,4 +1,4 @@
-# = statsample.rb - 
+# = statsample.rb -
 # Statsample - Statistic package for Ruby
 # Copyright (C) 2008-2014  Claudio Bustos
 #
@@ -17,17 +17,16 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 #
 
-
-#$:.unshift(File.dirname(__FILE__))
 require 'matrix'
 require 'extendmatrix'
 require 'distribution'
 require 'dirty-memoize'
 require 'reportbuilder'
 
-
 class Numeric
-  def square ; self * self ; end
+  def square
+    self * self
+  end
 end
 
 class String
@@ -41,10 +40,10 @@ class String
 end
 
 class Module
-  def include_aliasing(m, suffix="ruby")
+  def include_aliasing(m, suffix = 'ruby')
     m.instance_methods.each do |f|
       if instance_methods.include? f
-        alias_method("#{f}_#{suffix}",f) 
+        alias_method("#{f}_#{suffix}", f)
         remove_method f
       end
     end
@@ -60,15 +59,26 @@ class Array
   #   a.recode_repeated
   #   => ["a","b","c_1","c_2","d_1","d_2","d_3","e"]
   def recode_repeated
-    if self.size!=self.uniq.size
+    if size != uniq.size
       # Find repeated
-      repeated=self.inject({}) {|a,v|
-      (a[v].nil? ? a[v]=1 : a[v]+=1); a }.find_all{|k,v| v>1}.collect{|k,v| k}
-      ns=repeated.inject({}) {|a,v| a[v]=0;a}
-      self.collect do |f|
+      repeated = inject({}) do |acc, v|
+        if acc[v].nil?
+          acc[v] = 1
+        else
+          acc[v] += 1
+        end
+        acc
+      end.select { |_k, v| v > 1 }.keys
+
+      ns = repeated.inject({}) do |acc, v|
+        acc[v] = 0
+        acc
+      end
+
+      collect do |f|
         if repeated.include? f
-          ns[f]+=1
-          sprintf("%s_%d",f,ns[f])
+          ns[f] += 1
+          sprintf('%s_%d', f, ns[f])
         else
           f
         end
@@ -79,61 +89,62 @@ class Array
   end
 end
 
-def create_test(*args,&proc) 
-  description=args.shift
-  fields=args
+def create_test(*args, &_proc)
+  description = args.shift
+  fields = args
   [description, fields, Proc.new]
 end
+
 #--
 # Test extensions
 begin
   require 'gettext'
 rescue LoadError
   def bindtextdomain(d) #:nodoc:
-  d
+    d
   end
-  
+
   # Bored module
   module GetText  #:nodoc:
-    def _(t)  
-        t
+    def _(t)
+      t
     end
   end
 end
+
 # Library for statistical analysis on Ruby
 #
 # * Classes for manipulation and storage of data:
 # * Module Statsample::Bivariate provides covariance and pearson, spearman, point biserial, tau a, tau b, gamma, tetrachoric (see Bivariate::Tetrachoric) and polychoric (see Bivariate::Polychoric) correlations. Include methods to create correlation and covariance matrices
 # * Multiple types of regression on Statsample::Regression
 # * Factorial Analysis algorithms on Statsample::Factor module.
-# * Dominance Analysis. Based on Budescu and Azen papers.link[http://psycnet.apa.org/journals/met/8/2/129/]. 
+# * Dominance Analysis. Based on Budescu and Azen papers.link[http://psycnet.apa.org/journals/met/8/2/129/].
 # * Module Statsample::Codification, to help to codify open questions
 # * Converters to import and export data from databases, csv and excel files.
 # * Module Statsample::Crosstab provides function to create crosstab for categorical data
 # * Reliability analysis provides functions to analyze scales.
 # * Module Statsample::SRS (Simple Random Sampling) provides a lot of functions to estimate standard error for several type of samples
-# * Interfaces to gdchart, gnuplot and SVG::Graph 
+# * Interfaces to gdchart, gnuplot and SVG::Graph
 #
 module Statsample
-  
   def self.create_has_library(library)
     define_singleton_method("has_#{library}?") do
-      cv="@@#{library}"
-      if !class_variable_defined? cv
-        begin 
+      cv = "@@#{library}"
+      unless class_variable_defined? cv
+        begin
           require library.to_s
-          class_variable_set(cv,true)
+          class_variable_set(cv, true)
         rescue LoadError
-          class_variable_set(cv,false)
+          class_variable_set(cv, false)
         end
       end
       class_variable_get(cv)
     end
   end
-  
+
   create_has_library :gsl
-  
-  SPLIT_TOKEN = ","
+
+  SPLIT_TOKEN = ','
   autoload(:Analysis, 'statsample/analysis')
   autoload(:Database, 'statsample/converters')
   autoload(:Anova, 'statsample/anova')
@@ -154,133 +165,122 @@ module Statsample
   autoload(:Multivariate, 'statsample/multivariate')
   autoload(:Multiset, 'statsample/multiset')
   autoload(:StratifiedSample, 'statsample/multiset')
-  autoload(:MLE, 'statsample/mle')    
+  autoload(:MLE, 'statsample/mle')
   autoload(:Regression, 'statsample/regression')
   autoload(:Test, 'statsample/test')
   autoload(:Factor, 'statsample/factor')
   autoload(:Graph, 'statsample/graph')
-  
-  
+
   class << self
     # Load a object saved on a file.
     def load(filename)
       if File.exist? filename
-        o=false
-        File.open(filename,"r") {|fp| o=Marshal.load(fp) }
+        o = false
+        File.open(filename, 'r') { |fp| o = Marshal.load(fp) }
         o
       else
         false
       end
     end
-    
-    
-    
+
     # Create a matrix using vectors as columns.
     # Use:
     #
     #   matrix=Statsample.vector_cols_matrix(v1,v2)
     def vector_cols_matrix(*vs)
       # test
-      size=vs[0].size
-      vs.each{|v|
-        raise ArgumentError,"Arguments should be Vector" unless v.instance_of? Statsample::Vector
-        raise ArgumentError,"Vectors size should be the same" if v.size!=size
-      }
-      Matrix.rows((0...size).to_a.collect() {|i|
-        vs.collect{|v| v[i]}
-      })
+      size = vs[0].size
+
+      vs.each do |v|
+        fail ArgumentError, 'Arguments should be Vector' unless v.instance_of? Statsample::Vector
+        fail ArgumentError, 'Vectors size should be the same' if v.size != size
+      end
+
+      Matrix.rows((0...size).to_a.collect { |i| vs.collect { |v| v[i] } })
     end
+
     # Returns a duplicate of the input vectors, without missing data
     # for any of the vectors.
-    # 
+    #
     #  a=[1,2,3,6,7,nil,3,5].to_scale
     #  b=[nil,nil,5,6,4,5,10,2].to_scale
     #  c=[2,4,6,7,4,5,6,7].to_scale
     #  a2,b2,c2=Statsample.only_valid(a,b,c)
-    #  => [#<Statsample::Scale:0xb748c8c8 @data=[3, 6, 7, 3, 5]>, 
-    #        #<Statsample::Scale:0xb748c814 @data=[5, 6, 4, 10, 2]>, 
+    #  => [#<Statsample::Scale:0xb748c8c8 @data=[3, 6, 7, 3, 5]>,
+    #        #<Statsample::Scale:0xb748c814 @data=[5, 6, 4, 10, 2]>,
     #        #<Statsample::Scale:0xb748c760 @data=[6, 7, 4, 6, 7]>]
     #
     def only_valid(*vs)
-      i=1
-      h=vs.inject({}) {|a,v| a["v#{i}"]=v;i+=1;a}
-      ds=Statsample::Dataset.new(h).dup_only_valid
+      i = 1
+      h = vs.inject({}) { |acc, v| acc["v#{i}"] = v; i += 1; acc }
+      ds = Statsample::Dataset.new(h).dup_only_valid
       ds.vectors.values
     end
-    
-    # Cheap version of #only_valid. 
+
+    # Cheap version of #only_valid.
     # If any vectors have missing_values, return only valid.
     # If not, return the vectors itself
     def only_valid_clone(*vs)
-      if vs.any? {|v| v.flawed?}
+      if vs.any?(&:flawed?)
         only_valid(*vs)
       else
         vs
       end
     end
-  end  
-  
-  
-  
-  
+  end
+
   module Util
     # Reference: http://www.itl.nist.gov/div898/handbook/eda/section3/normprpl.htm
-    def normal_order_statistic_medians(i,n)
-      if i==1
-        u= 1.0 - normal_order_statistic_medians(n,n)
-      elsif i==n
-        u=0.5**(1 / n.to_f)
+    def normal_order_statistic_medians(i, n)
+      if i == 1
+        u = 1.0 - normal_order_statistic_medians(n, n)
+      elsif i == n
+        u = 0.5**(1 / n.to_f)
       else
-        u= (i - 0.3175) / (n + 0.365)
+        u = (i - 0.3175) / (n + 0.365)
       end
       u
     end
-    
-    def self.nice(s,e) # :nodoc:
-      reverse = e<s
+
+    def self.nice(s, e) # :nodoc:
+      reverse = e < s
       min = reverse ? e : s
       max = reverse ? s : e
-      span=max-min
-      return [s, e] if (!span or (span.respond_to? :infinite? and span.infinite?))
-      
-      step=10**((Math::log(span).quo(Math::log(10))).round - 1).to_f  
-      out=[(min.quo(step)).floor * step, (max.quo(step)).ceil * step]
+      span = max - min
+      return [s, e] if span == 0 || (span.respond_to?(:infinite?) && span.infinite?)
+
+      step = 10**((Math.log(span).quo(Math.log(10))).round - 1).to_f
+      out = [(min.quo(step)).floor * step, (max.quo(step)).ceil * step]
       out.reverse! if reverse
       out
     end
-    
-    
   end
-  
-  
-  
+
   module Writable
     def save(filename)
-      fp=File.open(filename,"w")
-      Marshal.dump(self,fp)
+      fp = File.open(filename, 'w')
+      Marshal.dump(self, fp)
       fp.close
-    end        
+    end
   end
   # Provides method summary to generate summaries and include GetText
   module Summarizable
     include GetText
-    bindtextdomain("statsample")
-    def summary(method=:to_text)
-      ReportBuilder.new(:no_title=>true).add(self).send(method)
+    bindtextdomain('statsample')
+    def summary(method = :to_text)
+      ReportBuilder.new(no_title: true).add(self).send(method)
     end
   end
   module STATSAMPLE__ #:nodoc:
   end
 end
 
-
-
 #--
-begin 
+begin
   require 'statsamplert'
 rescue LoadError
   module Statsample
-    OPTIMIZED=false
+    OPTIMIZED = false
   end
 end
 

data/references.txt

@@ -8,11 +8,13 @@ References
 * Dziuban, C., & Shirkey E. (1974). When is a correlation matrix appropriate for factor analysis? Some decision rules. Psychological Bulletin, 81(6), 358-361.
 * Hayton, J., Allen, D. & Scarpello, V.(2004). Factor Retention Decisions in Exploratory Factor Analysis: a Tutorial on Parallel Analysis. <i>Organizational Research Methods, 7</i> (2), 191-205.
 * Härdle, W. & Simar, L. (2003). Applied Multivariate Statistical Analysis. Springer
+* Leach, L. & Henson, R. (2007). The Use and Impact of Adjusted R2 Effects in Published Regression Research. Multiple Linear Regression Viewpoints, 33(1), 1-11.
 * Lin, J. (2007). VARIMAX_K58 [Source code]. [http://www.johnny-lin.com/idl_code/varimax_k58.pro]
 * Liu, O., & Rijmen, F. (2008). A modified procedure for parallel analysis of ordered categorical data. Behavior Research Methods, 40(2), 556-562.
 * McGraw, K. & Wong, S.P. (1996). Forming Inferences About Some Intraclass Correlation Coefficients. Psychological methods, 1(1), 30-46.
 * O'Connor, B. (2000). SPSS and SAS programs for determining the number of components using parallel analysis and Velicer's MAP test. Behavior Research Methods, Instruments, & Computers, 32(3), 396-402.
 * SPSS Manual
+* Sawyer, S. (2005). Resampling Data: Using a Statistical Jacknife.
 * Shrout,P. & Fleiss, J. (1979). Intraclass Correlation: Uses in assessing rater reliability. Psychological Bulletin, 86(2), 420-428
 * Smith, L. (2002). A tutorial on Principal Component Analysis. Available on http://courses.eas.ualberta.ca/eas570/pca_tutorial.pdf 
 * http://en.wikipedia.org/wiki/Welch-Satterthwaite_equation
@@ -20,4 +22,3 @@ References
 * http://stattrek.com/Lesson6/SRS.aspx
 * http://talkstats.com/showthread.php?t=5056
 * http://www.gnu.org/software/gsl/manual/html_node/The-histogram-struct.html
-* http://www.taygeta.com/random/gaussian.html

data/statsample.gemspec

@@ -0,0 +1,89 @@
+$:.unshift File.expand_path("../lib/", __FILE__)
+
+require 'statsample/version'
+require 'date'
+
+DESCRIPTION = <<MSG
+A suite for basic and advanced statistics on Ruby. Tested on CRuby 1.9.3, 2.0.0
+and 2.1.1. See `.travis.yml` for more information.
+
+Include:
+
+- Descriptive statistics: frequencies, median, mean,
+standard error, skew, kurtosis (and many others).
+- Imports and exports datasets from and to Excel, CSV and plain text files.
+- Correlations: Pearson's r, Spearman's rank correlation (rho), point biserial,
+tau a, tau b and  gamma. Tetrachoric and Polychoric correlation provides by
+statsample-bivariate-extension gem.
+- Intra-class correlation
+- Anova: generic and vector-based One-way ANOVA and Two-way ANOVA, with contrasts for
+One-way ANOVA.
+- Tests: F, T, Levene, U-Mannwhitney.
+- Regression: Simple, Multiple (OLS), Probit and Logit
+- Factorial Analysis: Extraction (PCA and Principal Axis), Rotation (Varimax,
+Equimax, Quartimax) and Parallel Analysis and Velicer's MAP test, for
+estimation of number of factors.
+- Reliability analysis for simple scale and a DSL to easily analyze multiple
+scales using factor analysis and correlations, if you want it.
+- Dominance Analysis, with multivariate dependent and bootstrap (Azen & Budescu)
+- Sample calculation related formulas
+- Structural Equation Modeling (SEM), using R libraries +sem+ and +OpenMx+
+- Creates reports on text, html and rtf, using ReportBuilder gem
+- Graphics: Histogram, Boxplot and Scatterplot.
+MSG
+
+POSTINSTALL = <<MSG
+***************************************************
+
+Thanks for installing statsample.
+
+On *nix, you could install statsample-optimization
+to retrieve gems gsl, statistics2 and a C extension
+to speed some methods.
+
+$ [sudo] gem install statsample-optimization
+
+*****************************************************
+MSG
+
+Gem::Specification.new do |s|
+  s.name = "statsample"
+  s.version = Statsample::VERSION
+  s.date = Date.today.to_s
+  s.homepage = "https://github.com/sciruby/statsample"
+
+  s.authors = ["Claudio Bustos", "Carlos Agarie"]
+  s.email = ["clbustos@gmail.com", "carlos@onox.com.br"]
+
+  s.summary = "A suite for basic and advanced statistics on Ruby"
+  s.description = DESCRIPTION
+  s.post_install_message = POSTINSTALL
+
+  s.rdoc_options = ["--main", "README.md"]
+  s.extra_rdoc_files = ["History.txt", "LICENSE.txt", "README.md", "references.txt"]
+  s.require_paths = ["lib"]
+
+  s.files = `git ls-files`.split("\n")
+  s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }
+
+  s.add_runtime_dependency 'spreadsheet', '~> 0.6.5'
+  s.add_runtime_dependency 'reportbuilder', '~> 1.4'
+  s.add_runtime_dependency 'minimization'
+  s.add_runtime_dependency 'dirty-memoize'
+  s.add_runtime_dependency 'extendmatrix'
+  s.add_runtime_dependency 'rserve-client'
+  s.add_runtime_dependency 'rubyvis', '~> 0.5.0'
+  s.add_runtime_dependency 'distribution'
+  s.add_runtime_dependency 'rb-gsl'
+  s.add_runtime_dependency 'awesome_print'
+
+  s.add_development_dependency 'bundler'
+  s.add_development_dependency 'rake'
+  s.add_development_dependency 'rdoc'
+  s.add_development_dependency 'shoulda'
+  s.add_development_dependency 'shoulda-matchers', '~> 2.2'
+  s.add_development_dependency 'minitest'
+  s.add_development_dependency 'gettext'
+  s.add_development_dependency 'mocha'
+end

data/test/test_awesome_print_bug.rb

@@ -0,0 +1,16 @@
+require(File.expand_path(File.dirname(__FILE__)+'/helpers_tests.rb'))
+class StatsampleAwesomePrintBug < MiniTest::Test
+  context("Awesome Print integration") do
+    setup do
+      require "awesome_print"
+    end
+    should "should be flawless" do
+      a=[1,2,3].to_scale
+      
+      assert(a!=[1,2,3])
+      assert_nothing_raised do 
+        ap a
+      end
+    end
+  end
+end

data/test/test_crosstab.rb

@@ -52,4 +52,12 @@ class StatsampleCrosstabTestCase < MiniTest::Unit::TestCase
     ct=Statsample::Crosstab.new(v1,v2)
     assert_equal(Matrix[[2.5,2.5],[2.5,2.5]],ct.matrix_expected)
   end
+  def test_crosstab_with_scale
+    v1=%w{1 1 1 1 1 0 0 0 0 0}.to_scale
+    v2=%w{0 0 0 0 0 1 1 1 1 1}.to_scale
+    ct=Statsample::Crosstab.new(v1,v2)
+    assert_equal(Matrix[[0,5],[5,0]],ct.to_matrix)
+    assert_nothing_raised { ct.summary }  
+  end
+
 end

data/test/test_histogram.rb

@@ -100,6 +100,13 @@ class StatsampleHistogramTestCase < MiniTest::Unit::TestCase
       assert_equal(2,h.sum(1,4))
 
     end
+    should "not raise exception when all values equal" do
+      assert_nothing_raised do
+        a = [5,5,5,5,5,5].to_scale
+        h=Statsample::Graph::Histogram.new(a)
+        h.to_svg
+      end
+    end
     
   end
 end