rubystats 0.1.0

data/lib/normal_distribution.rb

@@ -0,0 +1,114 @@
+require 'probability_distribution'
+require 'modules/special_math'
+# This class provides an object for encapsulating normal distributions
+# Ported to Ruby from PHPMath class by Bryan Donovan
+# Author:: Jaco van Kooten 
+# Author:: Paul Meagher
+# Author:: Bryan Donovan (mailto:bryandonovan@myrealbox.com)
+
+class NormalDistribution < ProbabilityDistribution
+	include SpecialMath
+
+	# Constructs a normal distribution (defaults to zero mean and
+	# unity variance).
+	def initialize(mu=0.0, sigma=1.0)
+		@mean = mu
+		if sigma <= 0.0
+			return "error"
+		end
+		@stdev = sigma
+		@variance = sigma**2
+		@pdf_denominator = Sqrt2pi * Math.sqrt(@variance)
+		@cdf_denominator = Sqrt2   * Math.sqrt(@variance)
+	end
+
+	# Returns the mean of the distribution
+	def get_mean 
+		return @mean
+	end
+
+	# Returns the standard deviation of the distribution
+	def get_standard_deviation
+		return @stdev
+	end
+
+	# Returns the variance of the distribution
+	def get_variance
+		return @variance
+	end
+
+	private
+
+	# Obtain single PDF value
+	# Returns the probability that a stochastic variable x has the value X,
+	# i.e. P(x=X)
+	def get_pdf(x)
+		Math.exp( -((x-@mean)**2) / (2 * @variance)) / @pdf_denominator
+	end
+
+	# Obtain single CDF value
+	# Returns the probability that a stochastic variable x is less than X,
+	# i.e. P(x<X)
+	def get_cdf(x)
+		complementary_error( -(x - @mean) / @cdf_denominator) / 2
+	end
+
+	# Obtain single inverse CDF value.
+	#	returns the value X for which P(x&lt;X).
+	def get_icdf(p)
+		check_range(p)
+		if p == 0.0
+			return -Max_value
+		end
+		if p == 1.0
+			return Max_value
+		end
+		if p == 0.5
+			return @mean
+		end
+
+		mean_save = @mean
+		var_save = @variance
+		pdf_D_save = @pdf_denominator
+		cdf_D_save = @cdf_denominator
+		@mean = 0.0
+		@variance = 1.0
+		@pdf_denominator = Math.sqrt(Two_pi)
+		@cdf_denominator = Sqrt2
+		x = find_root(p, 0.0, -100.0, 100.0)
+		#scale back
+		@mean = mean_save
+		@variance = var_save
+		@pdf_denominator = pdf_D_save
+		@cdf_denominator = cdf_D_save
+		return x * Math.sqrt(@variance) + @mean
+	end
+
+	# Uses the polar form of the Box-Muller transformation which
+	#	is both faster and more robust numerically than basic Box-Muller
+	# transform. To speed up repeated RNG computations, two random values
+	# are computed after the while loop and the second one is saved and
+	# directly used if the method is called again.
+	# see http://www.taygeta.com/random/gaussian.html
+	# returns single normal deviate
+	def get_rng
+		if @use_last
+			y1 = @last
+			@use_last = false
+		else
+			until w < 1.0 do
+				r1 = Kernel.rand
+				r2 = Kernel.rand
+				x1 = 2.0 * r1 - 1.0
+				x2 = 2.0 * r2 - 1.0
+				w  = x1 * x1 * x2 * x2
+			end
+			w = Math.sqrt((-2.0 * Math.log(w)) / w)
+			y1 = x1 * w
+			@last = x2 * w
+			@use_last = true
+		end
+		return @mean + y1 * Math.sqrt(@variance)
+	end
+end
+				

data/lib/probability_distribution.rb

@@ -0,0 +1,132 @@
+require 'modules/numerical_constants'
+require 'modules/extra_math'
+require 'modules/special_math'
+
+class ProbabilityDistribution
+	include NumericalConstants
+	include SpecialMath
+	include ExtraMath
+
+	def initialize
+	end
+
+	def mean
+		get_mean
+	end
+
+	def get_mean
+	end
+
+
+	def pdf(x) 
+		if x.class == Array
+			pdf_vals = []
+			for i in (0..x.length)
+				pdf_vals[i] = get_pdf(x[i])
+			end
+			return pdf_vals
+		else
+			return get_pdf(x)
+		end
+	end
+
+	def get_pdf(x)
+	end
+
+	def cdf(x)
+		if x.class == Array
+			cdf_vals = []
+			for i in (0...x.size)
+				cdf_vals[i] = get_cdf(x[i])
+			end
+			return cdf_vals
+		else
+			return get_cdf(x)
+		end
+	end
+
+	def get_cdf(x)
+	end
+
+	def icdf(p)
+		if p.class == Array
+			inv_vals = []
+			for i in (0..p.length)
+				inv_vals[i] = get_icdf(p[i])
+			end
+			return inv_vals
+		else
+			return get_icdf(p)
+		end
+	end
+
+	def get_icdf(p)
+	end
+
+	def rng(n=1)
+		if n < 1
+			return "Number of random numbers to return must be 1 or greater"
+		end
+		if (n > 1)
+			rnd_vals = []
+			for i in (0..n)
+				rnd_vals[i] = get_rng()
+			end
+			return rnd_vals
+		else
+			return get_rng()
+		end
+	end
+
+	def get_rng() 
+	end
+
+	def check_range(x, lo=0.0, hi=1.0)
+		if (x < lo) || (x > hi)
+			return "error"
+		end
+	end
+
+	def get_factorial(n)
+		if n <= 1
+			return 1
+		else 
+			return n * get_factorial(n-1)
+		end
+	end
+
+	def find_root (prob, guess, x_lo, x_hi) 
+		accuracy = 1.0e-10
+		max_iteration = 150
+		x 		= guess
+		x_new = guess
+		error = 0.0
+		pdf 	= 0.0
+		dx 		= 1000.0
+		i 		= 0
+		while ( dx.abs > accuracy && (i += 1) < max_iteration )
+			#Apply Newton-Raphson step
+			error = cdf(x) - prob
+			if error < 0.0
+				x_lo = x
+			else
+				x_hi = x
+			end
+			pdf = pdf(x)
+			if pdf != 0.0
+				dx = error / pdf
+				x_new = x -dx
+			end
+			# If the NR fails to converge (which for example may be the 
+			# case if the initial guess is to rough) we apply a bisection
+			# step to determine a more narrow interval around the root.
+			if  x_new < x_lo || x_new > x_hi || pdf == 0.0
+				x_new = (x_lo + x_hi) / 2.0
+				dx = x_new - x
+			end
+			x = x_new
+		end
+		return x
+	end
+end
+

data/tests/tc_beta.rb

@@ -0,0 +1,78 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+require 'test/unit'
+require 'beta_distribution'
+
+class TestBeta < Test::Unit::TestCase
+	def test_simple
+		p = 12
+		q = 59
+		beta = BetaDistribution.new(p,q)
+		assert_equal("0.169014084507042", beta.mean.to_s)
+		assert_equal("0.0441664031038187", beta.standard_deviation.to_s)
+		assert_equal("6.26075815849967", beta.pdf(0.2).to_s)
+		assert_equal("0.999999997766913", beta.cdf(0.50).to_s)
+		assert_equal("0.102003194113565", beta.icdf(0.05).to_s)
+
+		x_vals = [0.1, 0.15, 0.2, 0.25, 0.3, 0.35]
+		p_vals = beta.pdf(x_vals)
+		c_vals = beta.cdf(x_vals)
+		expected_pvals = [ 2.83232625227534,
+			8.89978000366836,
+			6.26075815849967,
+			1.72572305993386,
+			0.234475706454223,
+			0.0173700433944934]
+		expected_cvals = [0.0440640755091473,
+			0.356009606171447,
+			0.768319101921981,
+			0.956058132801147,
+			0.995358286711105,
+			0.99971672771575]
+		assert_equal(expected_pvals.to_s, p_vals.to_s)
+		assert_equal(expected_cvals.to_s, c_vals.to_s)
+		x_vals.each do |x|
+			cdf = beta.cdf(x)
+			inv_cdf = beta.icdf(cdf)
+			assert_in_delta(x.to_s, inv_cdf.to_s, 0.00000001)
+		end
+
+	end
+
+	def test_control_limits
+		trials = 50
+		alpha = 0.05
+		p = 10
+		lcl = get_lower_limit(trials, alpha, p)
+		ucl = get_upper_limit(trials, alpha, p)
+		assert_equal("0.112721613414076",lcl.to_s)
+		assert_equal("0.315596061420013",ucl.to_s)
+
+		trials = 210 
+		alpha = 0.10
+		p = 47 
+		lcl = get_lower_limit(trials, alpha, p)
+		ucl = get_upper_limit(trials, alpha, p)
+		assert_equal("0.186679485269901",lcl.to_s)
+		assert_equal("0.264957601783544",ucl.to_s)
+	end
+
+	def get_lower_limit(trials,alpha,p)
+		if p==0
+			lcl=0
+		else
+			q=trials-p+1
+			bin= BetaDistribution.new(p,q)
+			lcl=bin.icdf(alpha)
+		end
+		return lcl
+	end
+
+	def get_upper_limit(trials,alpha,p)
+		q=trials-p
+		p=p+1
+		bin= BetaDistribution.new(p,q)
+		ucl=bin.icdf(1-alpha)
+		return ucl
+	end
+
+end

data/tests/tc_binomial.rb

@@ -0,0 +1,22 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+require 'test/unit'
+require 'binomial_distribution'
+
+class TestBinomial < Test::Unit::TestCase
+	def test_simple
+		t = 100 
+		f = 7 
+		p = 0.05
+
+		bin = BinomialDistribution.new(t,p)
+		cdf = bin.cdf(f)
+		pdf = bin.pdf(f)
+		mean = bin.mean
+		inv_cdf = bin.icdf(cdf)
+
+		assert_equal("0.10602553736479",pdf.to_s)
+		assert_equal("0.872039521379601",cdf.to_s)
+		assert_equal("5.0",mean.to_s)
+		assert_equal(f,inv_cdf)
+	end
+end

data/tests/tc_fisher.rb

@@ -0,0 +1,20 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+require 'test/unit'
+require 'fishers_exact_test'
+
+class TestFisher < Test::Unit::TestCase
+	def test_simple
+		tested1 = 20
+		tested2 = 30
+		f1 = 10
+		f2 = 10
+		t1 = tested1 - f1
+		t2 = tested2 - f2
+		fet = FishersExactTest.new
+		fisher = fet.calculate(t1,t2,f1,f2)
+
+		assert_equal("0.188301375769922",fisher[:left].to_s)
+		assert_equal("0.929481131661052",fisher[:right].to_s)
+		assert_equal("0.257549242810992",fisher[:twotail].to_s)
+	end
+end

data/tests/tc_norm.rb

@@ -0,0 +1,13 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+require 'test/unit'
+require 'normal_distribution'
+
+class TestNormal < Test::Unit::TestCase
+	def test_simple
+
+		norm = NormalDistribution.new(10,2)
+		cdf = norm.cdf(11)
+
+		assert_equal("0.691462461274013",cdf.to_s)
+	end
+end

data/tests/ts_stats.rb

@@ -0,0 +1,5 @@
+require 'test/unit'
+require 'tc_fisher'
+require 'tc_binomial'
+require 'tc_beta'
+require 'tc_norm'

metadata

@@ -0,0 +1,61 @@
+--- !ruby/object:Gem::Specification 
+rubygems_version: 0.8.11
+specification_version: 1
+name: rubystats
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+date: 2006-01-04 00:00:00 -08:00
+summary: "Classes for statistical calculations, e.g., binomial, beta, and normal
+  distributions with PDF, CDF and inverse CDF (all ported from PHPMath) as well as
+  Fisher's Exact Test"
+require_paths: 
+  - lib
+email: Bryandonovan@myrealbox.com
+homepage: http://www.bryandonovan.com
+rubyforge_project: 
+description: 
+autorequire: 
+default_executable: 
+bindir: bin
+has_rdoc: true
+required_ruby_version: !ruby/object:Gem::Version::Requirement 
+  requirements: 
+    - 
+      - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+  version: 
+platform: ruby
+signing_key: 
+cert_chain: 
+authors: 
+  - Bryan Donovan
+files: 
+  - lib/beta_distribution.rb
+  - lib/binomial_distribution.rb
+  - lib/fishers_exact_test.rb
+  - lib/normal_distribution.rb
+  - lib/probability_distribution.rb
+  - lib/modules
+  - lib/modules/special_math.rb
+  - lib/modules/extra_math.rb
+  - lib/modules/numerical_constants.rb
+  - tests/tc_beta.rb
+  - tests/tc_fisher.rb
+  - tests/tc_binomial.rb
+  - tests/ts_stats.rb
+  - tests/tc_norm.rb
+  - examples/fisher.rb
+  - examples/binomial.rb
+  - examples/norm.rb
+  - examples/beta.rb
+  - README
+test_files: 
+  - tests/ts_stats.rb
+rdoc_options: []
+extra_rdoc_files: 
+  - README
+executables: []
+extensions: []
+requirements: []
+dependencies: []