glm 0.0.0

data/data/iris.data

@@ -0,0 +1,151 @@
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+4.6,3.1,1.5,0.2,Iris-setosa
+5.0,3.6,1.4,0.2,Iris-setosa
+5.4,3.9,1.7,0.4,Iris-setosa
+4.6,3.4,1.4,0.3,Iris-setosa
+5.0,3.4,1.5,0.2,Iris-setosa
+4.4,2.9,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+4.8,3.4,1.6,0.2,Iris-setosa
+4.8,3.0,1.4,0.1,Iris-setosa
+4.3,3.0,1.1,0.1,Iris-setosa
+5.8,4.0,1.2,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+5.4,3.9,1.3,0.4,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+5.7,3.8,1.7,0.3,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+5.4,3.4,1.7,0.2,Iris-setosa
+5.1,3.7,1.5,0.4,Iris-setosa
+4.6,3.6,1.0,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+4.8,3.4,1.9,0.2,Iris-setosa
+5.0,3.0,1.6,0.2,Iris-setosa
+5.0,3.4,1.6,0.4,Iris-setosa
+5.2,3.5,1.5,0.2,Iris-setosa
+5.2,3.4,1.4,0.2,Iris-setosa
+4.7,3.2,1.6,0.2,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
+5.4,3.4,1.5,0.4,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.5,4.2,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.0,3.2,1.2,0.2,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+4.4,3.0,1.3,0.2,Iris-setosa
+5.1,3.4,1.5,0.2,Iris-setosa
+5.0,3.5,1.3,0.3,Iris-setosa
+4.5,2.3,1.3,0.3,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+5.0,3.5,1.6,0.6,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+4.8,3.0,1.4,0.3,Iris-setosa
+5.1,3.8,1.6,0.2,Iris-setosa
+4.6,3.2,1.4,0.2,Iris-setosa
+5.3,3.7,1.5,0.2,Iris-setosa
+5.0,3.3,1.4,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+5.5,2.3,4.0,1.3,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.3,3.3,4.7,1.6,Iris-versicolor
+4.9,2.4,3.3,1.0,Iris-versicolor
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+5.0,2.0,3.5,1.0,Iris-versicolor
+5.9,3.0,4.2,1.5,Iris-versicolor
+6.0,2.2,4.0,1.0,Iris-versicolor
+6.1,2.9,4.7,1.4,Iris-versicolor
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.7,3.1,4.4,1.4,Iris-versicolor
+5.6,3.0,4.5,1.5,Iris-versicolor
+5.8,2.7,4.1,1.0,Iris-versicolor
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.9,3.2,4.8,1.8,Iris-versicolor
+6.1,2.8,4.0,1.3,Iris-versicolor
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.1,2.8,4.7,1.2,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+6.6,3.0,4.4,1.4,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+6.7,3.0,5.0,1.7,Iris-versicolor
+6.0,2.9,4.5,1.5,Iris-versicolor
+5.7,2.6,3.5,1.0,Iris-versicolor
+5.5,2.4,3.8,1.1,Iris-versicolor
+5.5,2.4,3.7,1.0,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.0,2.7,5.1,1.6,Iris-versicolor
+5.4,3.0,4.5,1.5,Iris-versicolor
+6.0,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+6.3,2.3,4.4,1.3,Iris-versicolor
+5.6,3.0,4.1,1.3,Iris-versicolor
+5.5,2.5,4.0,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+6.1,3.0,4.6,1.4,Iris-versicolor
+5.8,2.6,4.0,1.2,Iris-versicolor
+5.0,2.3,3.3,1.0,Iris-versicolor
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.7,3.0,4.2,1.2,Iris-versicolor
+5.7,2.9,4.2,1.3,Iris-versicolor
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.1,2.5,3.0,1.1,Iris-versicolor
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+6.5,3.0,5.8,2.2,Iris-virginica
+7.6,3.0,6.6,2.1,Iris-virginica
+4.9,2.5,4.5,1.7,Iris-virginica
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+7.2,3.6,6.1,2.5,Iris-virginica
+6.5,3.2,5.1,2.0,Iris-virginica
+6.4,2.7,5.3,1.9,Iris-virginica
+6.8,3.0,5.5,2.1,Iris-virginica
+5.7,2.5,5.0,2.0,Iris-virginica
+5.8,2.8,5.1,2.4,Iris-virginica
+6.4,3.2,5.3,2.3,Iris-virginica
+6.5,3.0,5.5,1.8,Iris-virginica
+7.7,3.8,6.7,2.2,Iris-virginica
+7.7,2.6,6.9,2.3,Iris-virginica
+6.0,2.2,5.0,1.5,Iris-virginica
+6.9,3.2,5.7,2.3,Iris-virginica
+5.6,2.8,4.9,2.0,Iris-virginica
+7.7,2.8,6.7,2.0,Iris-virginica
+6.3,2.7,4.9,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+7.2,3.2,6.0,1.8,Iris-virginica
+6.2,2.8,4.8,1.8,Iris-virginica
+6.1,3.0,4.9,1.8,Iris-virginica
+6.4,2.8,5.6,2.1,Iris-virginica
+7.2,3.0,5.8,1.6,Iris-virginica
+7.4,2.8,6.1,1.9,Iris-virginica
+7.9,3.8,6.4,2.0,Iris-virginica
+6.4,2.8,5.6,2.2,Iris-virginica
+6.3,2.8,5.1,1.5,Iris-virginica
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3.0,6.1,2.3,Iris-virginica
+6.3,3.4,5.6,2.4,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.0,3.0,4.8,1.8,Iris-virginica
+6.9,3.1,5.4,2.1,Iris-virginica
+6.7,3.1,5.6,2.4,Iris-virginica
+6.9,3.1,5.1,2.3,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+6.7,3.3,5.7,2.5,Iris-virginica
+6.7,3.0,5.2,2.3,Iris-virginica
+6.3,2.5,5.0,1.9,Iris-virginica
+6.5,3.0,5.2,2.0,Iris-virginica
+6.2,3.4,5.4,2.3,Iris-virginica
+5.9,3.0,5.1,1.8,Iris-virginica
+

data/examples/prepare.rb

@@ -0,0 +1,14 @@
+  #It just loads iris data as a 2-d array, rows being samples, columns 0...n-1 being flaot-valued features and column n-1 being target {0,1}
+  def load_iris
+    ifile = File.open(
+                     File.join("data","iris.data"))
+    iris = ((ifile.readlines.map {|l|
+               fields = l.chomp.split(pattern=",")
+               fields
+             }).select {|fields|
+              fields[4] != "Iris-virginica" && fields != []}).map {|fields|
+      fields[4] = (fields[4] == "Iris-setosa") ? 1 : 0
+      fields.map{|f| f.to_f}}
+    ifile.close
+    return iris
+  end

data/examples/test_glm_linear.rb

@@ -0,0 +1,28 @@
+require 'glm'
+require 'pp'
+require 'ruby-debug' ; Debugger.start(:post_mortem => true)
+Debugger.settings[:autoeval] = true
+require 'prepare'
+
+T = 2000
+
+iris = load_iris
+y_arr = iris.map {|r| r[0]}
+x = iris.map {|r| r[1...-1]}
+x = x.map{|r| r << 1}
+x,y = GLM::Util.formatArrays(x, y_arr)
+
+linear = GLM::Linear.new(x, y)
+
+(1..T).each do |i|
+  linear.sto_update
+  est_y =  linear.est(x)
+  err = (y.zip(est_y).map{|e| (e[0]-e[1])**2}).reduce(:+)/y.row_size
+  puts err
+end
+
+#end
+
+#puts ((y_est - y).map {|e| e ** 2}).reduce(:+)/y.row_size
+#    puts "Theta: #{y_est.to_a.to_s}"
+

data/examples/test_glm_logit.rb

@@ -0,0 +1,26 @@
+require 'glm'
+require 'pp'
+require 'ruby-debug' ; Debugger.start(:post_mortem => true)
+Debugger.settings[:autoeval] = true
+require 'prepare'
+
+T = 200
+
+iris = load_iris
+y_arr = iris.map {|r| r[-1].to_i}
+x = iris.map {|r| r[0...-2]}
+x = x.map{|r| r << 1}
+x,y = GLM::Util.formatArrays(x, y_arr)
+
+glm = GLM::Logit.new(x, y, 0.1)
+
+(1..T).each do |i|
+  glm.sto_update
+
+  est_y =  glm.est(x)
+  err = (y.zip(est_y).map{|e| (e[0]!=e[1])?1:0}).reduce(:+)#/y.row_size
+#  pp y.zip(est_y)
+  
+  puts err
+  pp glm.theta
+end

data/lib/glm.rb

@@ -0,0 +1,20 @@
+require 'matrix'
+include Math
+
+
+#The main class
+#Generalized Linear Models
+#
+
+class GLM
+  
+  # Vectorize a function intended for 
+  def self.vectorize()
+  end
+
+end
+
+
+require 'glm/logit'
+require 'glm/linear'
+require 'glm/util'

data/lib/glm/base.rb

@@ -0,0 +1,103 @@
+class GLM::Base
+
+  def initialize(x,y,alpha = 0.1)
+    @x = x
+    @y = y
+    @@alpha = alpha
+    @theta = Array.new(x.column_size,1)
+  end
+
+  #Log partition function <b>a(eta)</b>, intended to be overriden
+  def a
+    raise 'Log partition function a(eta) undefined'
+  end
+
+  #intended to be overriden
+  def b
+    raise 'b undefined'
+  end
+
+  def format(x)
+    if x.is_a? Array
+      if x[0].is_a?(Array)
+        x.map {|e|
+          output(e)}
+      else
+        output(x)
+      end
+    #Assuming x.is_a?(Matrix) == true
+    else
+      x.row_vectors.map {|e|
+        output(Matrix.row_vector(e))
+      }
+    end
+  end
+
+
+  # Estimator
+  # =Arguments:
+  #   x: a feature vector in Array
+  # =Returns:
+  #   Estimation
+  def est(x)
+    format(x)
+  end
+
+  #Output estimation from E(y|theta,x)
+  #Need overriding, except for plain linear regression
+  def output(x)
+    return h(x.t)
+  end
+
+  #Natural parameter eta
+  def eta(x)
+    tmp = (Matrix.column_vector(@theta).t * x)[0,0]
+    return tmp
+  end
+
+  
+  #Sufficient statistic <b>T</b>
+  def T
+    return @y
+  end
+
+  #Canonical reponse function, intended to be overriden
+  def self.g(eta)
+    raise 'Canonical reponse function g(eta) undefined'
+  end
+
+  #Gradient on one sample
+  def gradient(x,y,v)
+    tmp = h(v)
+    return (y - tmp) * x
+  end
+
+  # Hypothesis function, outputs E(y|theta, x), mean of y given x parameterized by theta
+  # =Parameters:
+  #   x: a feature vector
+  # =Returns:
+  #   E(y|theta, x)
+  def h(x)
+    tmp = eta(x)
+    return self.class.g(tmp)
+  end
+
+  #A step based on one sample in stochastic gradient descent
+  def single_update()
+    
+  end
+
+  #One complete loop of stochastic gradient descend
+  def sto_update()
+    (0...(@x.row_size)).each do |i|
+      (0...(@x.column_size)).each do |j|
+        @theta[j] += @@alpha * gradient(@x[i,j], @y[i,0], Matrix.column_vector(@x.row(i)))
+      end
+    end
+  end
+
+  def theta()
+    return @theta
+  end
+
+end

data/lib/glm/linear.rb

@@ -0,0 +1,27 @@
+require 'glm/base'
+
+class GLM::Linear < GLM::Base
+  
+
+  def hi
+    return "Hi, this is #{self.class}"
+  end
+
+
+  # Canonical response function
+  # It's identity function here, obviously
+  def self.g(eta)
+    return eta
+  end
+
+  def ne_est(x)
+    @theta = ne_fit
+    [@theta, x * Matrix.column_vector(@theta)]
+  end
+
+  #Normal equation fit
+  def ne_fit
+    (( @x.t * @x ).inverse * @x.t * @y).to_a.flatten
+  end
+
+end

data/lib/glm/logit.rb

@@ -0,0 +1,62 @@
+require 'glm/base'
+
+class GLM::Logit < GLM::Base
+
+
+  def a
+    return -Math.log(1-phi)
+  end
+  
+  def b
+    return 1
+  end
+
+  # Canonical response function
+  def self.g(eta)
+    self.sigmoid(eta)
+  end
+  
+  def output(x)
+    return (h(x.t) > 0.5)?1:0
+  end
+  
+  def phi
+    return h(x)
+  end
+
+  # Logistic function on vectors, parameterized by theta
+  # Arguments:
+  #   theta: An array
+  
+  def self.sigmoid_vec(theta)
+    # Returns a closure which takes
+    # Arguments:
+    #   x: single row matrix
+    return lambda {|x|
+      sigmoid(
+            (Matrix.row_vector(x) * Matrix.row_vector(theta).t).tr)}
+  end
+
+  # Logistic function
+  # Arguments: 
+  #   x: scalar
+  def self.sigmoid(x)
+    return 1/(1 + exp(-x))
+  end
+    
+  # Derivative of Logistic function
+  # Arguments: 
+  #   x: scalar
+  def self.deriv_sigmoid( x )
+    return sigmoid( x ) * ( 1 - sigmoid( x ) )
+  end
+
+  def self.logit(z)
+    Math.log(z/(1-z))
+  end
+
+  def self.truth
+    "Sanity is for the weak!"
+  end
+
+end

data/lib/glm/util.rb

@@ -0,0 +1,9 @@
+require 'matrix'
+
+class GLM::Util
+  def self.formatArrays(x, y)
+    x = Matrix.rows(x)
+    y = Matrix.column_vector(y)
+    return [x, y]
+  end
+end

data/test/test_glm.rb

@@ -0,0 +1,41 @@
+require 'test/unit'
+require 'glm'
+require 'pp'
+require 'ruby-debug' ; Debugger.start(:post_mortem => true)
+
+class GLMTest < Test::Unit::TestCase
+  def test_glm_logit_truth
+    assert_equal "Sanity is for the weak!",
+    GLM::Logit.truth
+  end
+
+  #Helper method
+  def load_iris
+    ifile = File.open(
+                     File.join("data","iris.data"))
+    iris = ((ifile.readlines.map {|l|
+               fields = l.chomp.split(pattern=",")
+               fields
+             }).select {|fields|
+              fields[4] != "Iris-virginica" && fields != []}).map {|fields|
+      fields[4] = (fields[4] == "Iris-setosa") ? 1 : 0
+      fields.map{|f| f.to_f}}
+    assert_equal 100, iris.length
+    ifile.close
+    return iris
+  end
+
+  def test_linear
+    iris = load_iris
+    y = iris.map {|r| r[0]}
+    x = iris.map {|r| r[1...-1]}
+    x = x.map{|r| r << 1}
+    x,y = GLM::Util.formatArrays(x, y)
+    linear = GLM::Linear.new(x, y)
+    theta, y_est = linear.ne_est(x)
+    assert  ((y_est - y).map {|e| e ** 2}).reduce(:+)/y.row_size < 0.1
+  end
+
+  
+
+end

metadata

@@ -0,0 +1,54 @@
+--- !ruby/object:Gem::Specification
+name: glm
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+  prerelease: 
+platform: ruby
+authors:
+- Yu Shen
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-03-19 00:00:00.000000000Z
+dependencies: []
+description: Generalized Linear Method
+email: yushen83@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/glm.rb
+- lib/glm/base.rb
+- lib/glm/linear.rb
+- lib/glm/logit.rb
+- lib/glm/util.rb
+- examples/prepare.rb
+- examples/test_glm_logit.rb
+- examples/test_glm_linear.rb
+- test/test_glm.rb
+- data/iris.data
+homepage: https://github.com/yushen
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.19
+signing_key: 
+specification_version: 3
+summary: This is a W.I.P implementation of GLM
+test_files: []