pca 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 8dc374097222849bba01f272a8df8d019bdefad9
+  data.tar.gz: 70af4ff18c1cb5796b54308ea43f1b202fcca8ed
+SHA512:
+  metadata.gz: 6c2508f2c7a86e677330736ea733e8fedb525301ae3d1c1e6ad00e95dc7be07ba50aa4a4ef5e27cde958bb0091fd0310e8d8ae44ec2cc0987928c26da7c0bd3d
+  data.tar.gz: f708f797cdb4811680ed4a4390db9b918555fec1c8033c44356ebe64950697b6d09855cb93fec8fcb56dab3930e66a17171fcf8e0953f7518b5259f9a87bcbc2

data/lib/pca.rb

@@ -0,0 +1,83 @@
+require 'gsl'
+
+class PCA
+  attr_reader :components, :singular_values, :mean, :explained_variance, :explained_variance_ratio
+
+  def initialize opts = {}
+    @n_components = opts[:components]
+  end
+
+  def fit x
+    x = prepare_data x
+    _fit x
+    self
+  end
+
+  def transform x
+    x = prepare_data x, use_saved_mean: true
+    _transform x
+  end
+
+  def fit_transform x
+    x = prepare_data x
+    _fit x
+    _transform x
+  end
+
+  def inverse_transform x
+    x = ensure_matrix x
+    out = x * @components.transpose
+    out.size2.times {|col| out.col(col).add! @mean[col] }
+    out
+  end
+
+  private
+    def prepare_data x, opts = {}
+      x = ensure_matrix x
+      @mean = calculate_mean(x) unless opts[:use_saved_mean]
+      mean_normalize x
+      x
+    end
+
+    def _fit x
+      covariance_matrix = (x.transpose * x) / x.size1
+      u, v, s = covariance_matrix.SV_decomp
+      @components = slice_n u
+      @singular_values = slice_n s
+      @explained_variance = @singular_values**2 / x.size1
+      @explained_variance_ratio = @explained_variance / @explained_variance.sum
+    end
+
+    def _transform x
+      x * @components
+    end
+
+    def ensure_matrix x
+      case x
+      when GSL::Matrix
+        x
+      when Array
+        GSL::Matrix[*x]
+      else
+        x.to_gm
+      end
+    end
+
+    def calculate_mean x
+      x.size2.times.map {|col| x.col(col).mean }
+    end
+
+    def mean_normalize x
+      x.size2.times {|col| x.col(col).sub! @mean[col] }
+    end
+
+    def slice_n x
+      return x unless @n_components
+      case x
+      when GSL::Matrix
+        x.submatrix(nil, 0, @n_components)
+      when GSL::Vector
+        x[0, @n_components]
+      end
+    end
+end

metadata

@@ -0,0 +1,59 @@
+--- !ruby/object:Gem::Specification
+name: pca
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Geoff Buesing
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-03-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rb-gsl
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Principal Component Analysis
+email: gbuesing@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/pca.rb
+homepage: https://github.com/gbuesing/pca
+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: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Principal Component Analysis
+test_files: []
+has_rdoc: