ruby-regress 0.0.1 → 0.1.1

data/README.mdown

@@ -4,10 +4,29 @@
 `ruby-regress` is a tool for computing correlations and regression equations
 from two-variable input. It is designed to function as a drop-in replacement
 for Gary Perlman's `regress`, at least for those who use only the basic
-functionality that `regress` provides...
+functionality that `regress` provides.
 
+## Why!?
+
+The problem with Gary Perlman's excellent |STAT programs is twofold: 
+
+   + The only way of obtaining a copy is by emailing Perlman and asking for it.
+   + The distribution of modified copies is [expressely forbidden](http://oldwww.acm.org/perlman/stat/history.html#conditions).
+
+If you need bulletproof robustness you're probably better off dealing with Perlman's terms of access and using |STAT; if you want ease of installation, try `ruby-regress`.
 ## Installation
 
+#### From rubygems
+
+If you're using Gemcutter.org as a your gem host (hint: you almost certainly are) you can 
+install ruby-regress using rubygems:
+
+    gem install ruby-regress
+    
+which installs the `regress` executable.
+
+#### From source
+
 Download the most recent source from Github:
 
     git clone git://github.com/doches/ruby-regress.git
@@ -35,4 +54,4 @@ we can get the correlation coefficient between these two variables by:
     cat data.txt | regress
 
 which will dump a load of statistical information about the datasets to
-the terminal.
+the terminal.

data/Rakefile

@@ -44,7 +44,7 @@ task :test => :check_dependencies
 
 task :default => :test
 
-require 'rake/rdoctask'
+require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
   version = File.exist?('VERSION') ? File.read('VERSION') : ""
 

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.1.1

data/bin/regress

@@ -19,28 +19,44 @@ require 'ruby-regress'
 
 input = []
 STDIN.each_line do |line|
-  cols = line.strip.gsub(/#.+$/,'').split(/\s/).map { |x| x.to_f }
-	input.push cols if cols.size == 2
+	cols = line.strip.gsub(/#.+$/,'').split(/\s/).map { |x| x.to_f }
+	input.push cols if cols.size > 0
 end
-a,b = *[0,1].map { |i| input.collect { |x| x[i] } }
+if input[0].size == 1 # Single column, stats only
+	a = input.flatten
+	puts "Analysis for #{a.size} cases of 1 variable:"
+	puts "Variable          A"
+	puts "Min#{sprintf("%18.4f",Regress.min(a))}"
+	puts "Max#{sprintf("%18.4f",Regress.max(a))}"
+	puts "Sum#{sprintf("%18.4f",Regress.sum(a))}"
+	puts "Mean#{sprintf("%17.4f",Regress.mean(a))}"
+	puts "SD#{sprintf("%19.4f",Regress.standard_deviation(a))}"
+elsif input[0].size == 2 # Two column, stats + regression
+	a,b = *[0,1].map { |i| input.collect { |x| x[i] } }
 
-regress = Regress.new(a,b)
-puts "Analysis for #{a.size} cases of 2 variables:"
-puts "Variable          REG          A "
-puts "Min#{sprintf("%18.4f",Regress.min(a))}#{sprintf("%11.4f ",Regress.min(b))}"
-puts "Max#{sprintf("%18.4f",Regress.max(a))}#{sprintf("%11.4f ",Regress.max(b))}"
-puts "Sum#{sprintf("%18.4f",Regress.sum(a))}#{sprintf("%11.4f ",Regress.sum(b))}"
-puts "Mean#{sprintf("%17.4f",Regress.mean(a))}#{sprintf("%11.4f ",Regress.mean(b))}"
-puts "SD#{sprintf("%19.4f",Regress.standard_deviation(a))}#{sprintf("%11.4f ",Regress.standard_deviation(b))}"
-puts ""
-puts "Correlation Matrix:"
-puts "REG            1.0000 "
-puts "A              #{sprintf("%1.4f",regress.r)}     1.0000 "
-puts "Variable          REG          A"
-puts ""
-#puts "Regression Equation for REG:"
-#puts "REG  =#{sprintf("%3.3f",Regress.slope)} A  +#{sprintf("%4.4f",Regress.intercept)}"
-#puts ""
-puts "Significance test for prediction of REG"
-puts "    Mult-R  R-Squared "
-puts " #{sprintf("%9.4f",regress.r)}  #{sprintf("%9.4f",regress.r**2)} "
+	regress = Regress.new(a,b)
+	puts "Analysis for #{a.size} cases of 2 variables:"
+	puts "Variable          REG          A "
+	puts "Min#{sprintf("%18.4f",Regress.min(a))}#{sprintf("%11.4f ",Regress.min(b))}"
+	puts "Max#{sprintf("%18.4f",Regress.max(a))}#{sprintf("%11.4f ",Regress.max(b))}"
+	puts "Sum#{sprintf("%18.4f",Regress.sum(a))}#{sprintf("%11.4f ",Regress.sum(b))}"
+	puts "Mean#{sprintf("%17.4f",Regress.mean(a))}#{sprintf("%11.4f ",Regress.mean(b))}"
+	puts "SD#{sprintf("%19.4f",Regress.standard_deviation(a))}#{sprintf("%11.4f ",Regress.standard_deviation(b))}"
+	puts ""
+	puts "Correlation Matrix:"
+	puts "REG            1.0000 "
+	puts "A              #{sprintf("%1.4f",regress.r)}     1.0000 "
+	puts "Variable          REG          A"
+	puts ""
+	#puts "Regression Equation for REG:"
+	#puts "REG  =#{sprintf("%3.3f",Regress.slope)} A  +#{sprintf("%4.4f",Regress.intercept)}"
+	#puts ""
+	puts "Significance test for prediction of REG"
+	puts "    Mult-R  R-Squared "
+	puts " #{sprintf("%9.4f",regress.r)}  #{sprintf("%9.4f",regress.r**2)} "
+else
+	STDERR.puts "> 2 column input not supported."
+	STDERR.puts ""
+	STDERR.puts "Sorry."
+	exit(1)
+end

data/lib/ruby-regress.rb

@@ -2,15 +2,20 @@ class Regress
   attr_reader :r, :slope, :intercept
   
   # Create a Regress object from two vectors +a+ and +b+. Note that +a+ and +b+ must be of the same length.
-  def initialize(a,b)
-    raise "Regress#initialize expects two vectors of equal length (given vectors of lengths #{a.size}, #{b.size})." if a.size != b.size
-    
-    sa,sb = *[a,b].map { |d| Regress.sum(d) }
-    sa2,sb2 = *[a,b].map { |d| Regress.sum(Regress.square(d)) }
-    sab = Regress.multiply(a,b)
-    n = a.size
-    
-    @r = (n * sab - sa * sb) / (( (n * sa2 - sa**2) * (n * sb2 - sb**2) ) ** 0.5)
+  def initialize(a,b=nil)
+    if b.nil?
+      # Don't do regression if we're only given one item
+    else
+      raise "Regress#initialize expects two vectors of equal length (given vectors of lengths #{a.size}, #{b.size})." if a.size != b.size
+      
+      sa,sb = *[a,b].map { |d| Regress.sum(d) }
+      sa2,sb2 = *[a,b].map { |d| Regress.sum(Regress.square(d)) }
+      sab = Regress.multiply(a,b)
+      n = a.size
+      
+      @r = (n * sab - sa * sb) / (( (n * sa2 - sa**2) * (n * sb2 - sb**2) ) ** 0.5)
+      @r = 0.0 if @r.nan?
+    end
   end
   
   def Regress.sum(vector)

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: ruby-regress
 version: !ruby/object:Gem::Version 
-  hash: 29
-  prerelease: false
+  hash: 25
+  prerelease: 
   segments: 
   - 0
-  - 0
   - 1
-  version: 0.0.1
+  - 1
+  version: 0.1.1
 platform: ruby
 authors: 
 - Trevor Fountain
@@ -15,8 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-08-25 00:00:00 +01:00
-default_executable: regress
+date: 2012-04-17 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: wrong
@@ -44,8 +43,6 @@ extra_rdoc_files:
 - LICENSE
 - README.mdown
 files: 
-- .document
-- .gitignore
 - LICENSE
 - README.mdown
 - Rakefile
@@ -54,13 +51,12 @@ files:
 - lib/ruby-regress.rb
 - test/helper.rb
 - test/test_ruby-regress.rb
-has_rdoc: true
 homepage: http://github.com/doches/ruby-regress
 licenses: []
 
 post_install_message: 
-rdoc_options: 
-- --charset=UTF-8
+rdoc_options: []
+
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
@@ -84,10 +80,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: CLI tool for computing correlation (Pearson's r)
-test_files: 
-- test/helper.rb
-- test/test_ruby-regress.rb
+test_files: []
+

data/.document

@@ -1,5 +0,0 @@
-README.rdoc
-lib/**/*.rb
-bin/*
-features/**/*.feature
-LICENSE

data/.gitignore

@@ -1,21 +0,0 @@
-## MAC OS
-.DS_Store
-
-## TEXTMATE
-*.tmproj
-tmtags
-
-## EMACS
-*~
-\#*
-.\#*
-
-## VIM
-*.swp
-
-## PROJECT::GENERAL
-coverage
-rdoc
-pkg
-
-## PROJECT::SPECIFIC