ruby_linear_regression 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: fd88f39c66fb2efe50b976fe3b1f04e06b179d18
+  data.tar.gz: 83842d112a3d92d239a08422e750f616923b2942
+SHA512:
+  metadata.gz: a57cf9ee217bebd8ef47d417068c2abef876592d909fcf3359c05d11b12ebc7a4891cb583cd96193637c0cdbe6fe14278c92649377d860c8e32c33217a1d7a6e
+  data.tar.gz: 8f8aa53d404036c3ee657f94ad9d15f99f2ba9bf3da6b9854e10144fea7f87432e7ea2cf3bc9d8fe87a52c84121f242e472afc7a582407d6acfd0e088cd6fd0a

data/lib/ruby_linear_regression.rb

@@ -0,0 +1,94 @@
+require 'matrix'
+
+class RubyLinearRegression
+
+  attr_reader :x,:y,:theta,:mu,:sigma
+
+  def initialize
+    @mu = 0
+    @sigma = 1
+  end
+
+  def load_training_data x_data, y_data
+
+        # normalize the x_data
+        x_data = normalize_data( x_data )
+
+        # add 1 column to our data
+        x_data = x_data.map { |r| [1].concat(r) }
+
+        # build our x Matrix & y Vector
+        @x = Matrix.rows( x_data )
+        @y = Matrix.rows( y_data.collect { |e| [e] } )
+
+        @theta = Matrix[[0],[0]]
+  end
+
+  def compute_cost
+    # Compute the mean squared cost / error function
+    # First use matrix multiplication and vector subtracton to find errors
+    errors = (@x * @theta) - @y
+
+    # Then square all errors
+    errors = errors.map { |e| e * e  }
+
+    # Find the mean of the square errors
+    mean_square_error = 0.5 * (errors.inject{ |sum, e| sum + e }.to_f / errors.row_size)
+
+    return mean_square_error
+  end
+
+  def train_normal_equation
+    # Calculate the optimal theta using the normal equation
+    # theta = ( X' * X )^1 * X' * y
+    @theta = (@x.transpose * @x).inverse * @x.transpose * @y
+
+    return @theta
+  end
+
+  def predict data
+
+    # normalize
+    data.each_index do |i|
+      data[i] = (data[i] - @mu[i]) / @sigma[i].to_f
+    end
+
+    # add 1 column to prediction data
+    data = [1].concat( data )
+
+    # perform prediction
+    prediction = (Matrix[data] * @theta)[0,0].to_f
+
+    return prediction
+
+  end
+
+  private
+    def normalize_data x_data
+
+      row_size = x_data.size
+      column_count = x_data[0].is_a?( Array) ? x_data[0].size : 1
+
+      x_norm = Array.new(row_size)
+      @mu = Array.new(column_count)
+      @sigma = Array.new(column_count)
+
+      0.upto(column_count - 1) do |column|
+        column_data = x_data.map{ |e| e[column] }
+        @mu[column] = column_data.inject{ |sum, e| sum + e } / row_size
+        @sigma[column] = (column_data.max - column_data.min)
+      end
+
+      0.upto(row_size-1) do |row|
+        row_data = x_data[row]
+        x_norm[row] = Array.new(column_count)
+        row_data.each_index do |i|
+          x_norm[row][i] = (row_data[i] - @mu[i]) / @sigma[i].to_f
+        end
+      end
+
+      return x_norm
+
+    end
+
+end

metadata

@@ -0,0 +1,47 @@
+--- !ruby/object:Gem::Specification
+name: ruby_linear_regression
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Soren Blond Daugaard
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-10-06 00:00:00.000000000 Z
+dependencies: []
+description: "An implementation of a linear regression machine learning algorithm
+  implemented in Ruby.\n                This algorithm uses Ruby's Matrix implementation
+  and the normal equation to train the data to the best fit.\n                The
+  algorithm works with multiple independent variables to predict a dependent variable. "
+email: sbd@ineptum.dk
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/ruby_linear_regression.rb
+homepage: https://github.com/daugaard/linear-regression
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.8
+signing_key: 
+specification_version: 4
+summary: Linear regression implemented in Ruby.
+test_files: []