rumale 0.12.9 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c55e2ab90432838616c16fdf35d4eac150cc02b8
-  data.tar.gz: c605feef7c8d3d7dce4e8330419ba88288d17f74
+  metadata.gz: cdd9f655f3a1f95edc68476dd614deac7718ef65
+  data.tar.gz: f979c070a55fc8fb2afce0c04b1fa26bf92aa2af
 SHA512:
-  metadata.gz: f3ec59d17a66d74d978860537271c0d7c8881924cce6589345d43079897879ac603b6c01c7b0884419457e4bf6a99187345d203e8638be6d96aabe1ce513560f
-  data.tar.gz: 86f0cbf4c92b72b9caff2e5a9ed39b47013e4c11bdacf6661148a01f3c69a72253bc8690fa5c28207888461b8bc1070f39b87bc23df11866b9018d61cd37b2fd
+  metadata.gz: 94a6aed271a2f0da786544aaef2dc81b62c357f7dbd552c5ebbdd6a67c39b3584b9b139a6ea8be269a030ca2c7ec0f5852ccc3990492d3f4aabf55ab46172d9a
+  data.tar.gz: b89de3059991cecfe92d492193287777cd8278715ee55e52868005a8df5489005f02ed862b8a782111e0cc8f76da67b1965b690e5a5876c7877025d7657f6be3

data/.travis.yml

@@ -1,13 +1,17 @@
 sudo: false
 os: linux
-dist: trusty
+dist: xenial
 language: ruby
 rvm:
-  - 2.3
-  - 2.4
-  - 2.5
-  - 2.6
-before_install:
-  - travis_retry gem update --system || travis_retry gem update --system 2.7.8
-  - travis_retry gem install bundler --no-document || travis_retry gem install bundler --no-document -v 1.17.3
+  - '2.4'
+  - '2.5'
+  - '2.6'
+
+addons:
+  apt:
+    packages:
+      - libopenblas-dev
+      - liblapacke-dev
 
+before_install:
+  - gem install bundler -v 2.0.2

data/CHANGELOG.md

@@ -1,3 +1,17 @@
+# 0.13.0
+- Introduce [Numo::Linalg](https://github.com/ruby-numo/numo-linalg) to use linear algebra algorithms on the optimization.
+- Add the solver parameter that specifies the optimization algorithm to Rumale::Decomposition::PCA.
+
+```ruby
+require 'rumale'
+
+# Loading Numo::Linalg enables features based on linear algebra algorithms.
+require 'numo/linalg/autoloader'
+
+decomposer = Rumale::Decomposition::PCA.new(n_components: 2, solver: 'evd')
+low_dimensional_samples = decomposer.fit_transform(samples)
+```
+
 # 0.12.9
 - Add class for K-Medoids clustering.
 - Fix extension codes of decision tree regressor for using Numo::NArray.

data/README.md

@@ -6,7 +6,7 @@
 [![Coverage Status](https://coveralls.io/repos/github/yoshoku/rumale/badge.svg?branch=master)](https://coveralls.io/github/yoshoku/rumale?branch=master)
 [![Gem Version](https://badge.fury.io/rb/rumale.svg)](https://badge.fury.io/rb/rumale)
 [![BSD 2-Clause License](https://img.shields.io/badge/License-BSD%202--Clause-orange.svg)](https://github.com/yoshoku/rumale/blob/master/LICENSE.txt)
-[![Documentation](http://img.shields.io/badge/docs-rdoc.info-blue.svg)](https://www.rubydoc.info/gems/rumale/0.12.9)
+[![Documentation](http://img.shields.io/badge/docs-rdoc.info-blue.svg)](https://www.rubydoc.info/gems/rumale/0.13.0)
 
 Rumale (**Ru**by **ma**chine **le**arning) is a machine learning library in Ruby.
 Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.

data/ext/rumale/rumale.c

@@ -459,14 +459,13 @@ iter_find_split_params_grad_reg(na_loop_t const* lp)
  * Find for split point with maximum information gain.
  *
  * @overload find_split_params(order, features, gradients, hessians, sum_gradient, sum_hessian, reg_lambda) -> Array<Float>
- *
- * @param order [Numo::Int32] (shape: [n_elements]) The element indices sorted according to feature values.
- * @param features [Numo::DFloat] (shape: [n_elements]) The feature values.
- * @param gradients [Numo::DFloat] (shape: [n_elements]) The gradient values.
- * @param hessians [Numo::DFloat] (shape: [n_elements]) The hessian values.
- * @param sum_gradient [Float] The sum of gradient values.
- * @param sum_hessian [Float] The sum of hessian values.
- * @param reg_lambda [Float] The L2 regularization term on weight.
+ *   @param order [Numo::Int32] (shape: [n_elements]) The element indices sorted according to feature values.
+ *   @param features [Numo::DFloat] (shape: [n_elements]) The feature values.
+ *   @param gradients [Numo::DFloat] (shape: [n_elements]) The gradient values.
+ *   @param hessians [Numo::DFloat] (shape: [n_elements]) The hessian values.
+ *   @param sum_gradient [Float] The sum of gradient values.
+ *   @param sum_hessian [Float] The sum of hessian values.
+ *   @param reg_lambda [Float] The L2 regularization term on weight.
  * @return [Array<Float>] The array consists of optimal parameters including threshold and gain.
  */
 static VALUE

data/lib/rumale/base/base_estimator.rb

@@ -11,8 +11,24 @@ module Rumale
 
       private
 
+      def enable_linalg?
+        if defined?(Numo::Linalg).nil?
+          warn('If you want to use features that depend on Numo::Linalg, you should install and load Numo::Linalg in advance.')
+          return false
+        end
+        if Numo::Linalg::VERSION < '0.1.4'
+          warn('The loaded Numo::Linalg does not implement the methods required by Rumale. Please load Numo::Linalg version 0.1.4 or later.')
+          return false
+        end
+        true
+      end
+
       def enable_parallel?
-        return false if @params[:n_jobs].nil? || defined?(Parallel).nil?
+        return false if @params[:n_jobs].nil?
+        if defined?(Parallel).nil?
+          warn('If you want to use parallel option, you should install and load Parallel in advance.')
+          return false
+        end
         true
       end
 

data/lib/rumale/decomposition/pca.rb

@@ -12,6 +12,11 @@ module Rumale
     #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2)
     #   representaion = decomposer.fit_transform(samples)
     #
+    #   # If Numo::Linalg is installed, you can specify 'evd' for the solver option.
+    #   require 'numo/linalg/autoloader'
+    #   decomposer = Rumale::Decomposition::PCA.new(n_components: 2, solver: 'evd')
+    #   representaion = decomposer.fit_transform(samples)
+    #
     # *Reference*
     # - A. Sharma and K K. Paliwal, "Fast principal component analysis using fixed-point algorithm," Pattern Recognition Letters, 28, pp. 1151--1155, 2007.
     class PCA
@@ -23,7 +28,7 @@ module Rumale
       attr_reader :components
 
       # Returns the mean vector.
-      # @return [Numo::DFloat] (shape: [n_features]
+      # @return [Numo::DFloat] (shape: [n_features])
       attr_reader :mean
 
       # Return the random generator.
@@ -33,15 +38,19 @@ module Rumale
       # Create a new transformer with PCA.
       #
       # @param n_components [Integer] The number of principal components.
-      # @param max_iter [Integer] The maximum number of iterations.
-      # @param tol [Float] The tolerance of termination criterion.
+      # @param solver [String] The algorithm for the optimization ('fpt' or 'evd').
+      #   'fpt' uses the fixed-point algorithm. 'evd' performs eigen value decomposition of the covariance matrix of samples.
+      # @param max_iter [Integer] The maximum number of iterations. If solver = 'evd', this parameter is ignored.
+      # @param tol [Float] The tolerance of termination criterion. If solver = 'evd', this parameter is ignored.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(n_components: 2, max_iter: 100, tol: 1.0e-4, random_seed: nil)
+      def initialize(n_components: 2, solver: 'fpt', max_iter: 100, tol: 1.0e-4, random_seed: nil)
         check_params_integer(n_components: n_components, max_iter: max_iter)
+        check_params_string(solver: solver)
         check_params_float(tol: tol)
         check_params_type_or_nil(Integer, random_seed: random_seed)
         check_params_positive(n_components: n_components, max_iter: max_iter, tol: tol)
         @params = {}
+        @params[:solver] = solver != 'evd' ? 'fpt' : 'evd'
         @params[:n_components] = n_components
         @params[:max_iter] = max_iter
         @params[:tol] = tol
@@ -69,14 +78,19 @@ module Rumale
         centered_x = x - @mean
         # optimization.
         covariance_mat = centered_x.transpose.dot(centered_x) / (n_samples - 1)
-        @params[:n_components].times do
-          comp_vec = Rumale::Utils.rand_uniform(n_features, sub_rng)
-          @params[:max_iter].times do
-            updated = orthogonalize(covariance_mat.dot(comp_vec))
-            break if (updated.dot(comp_vec) - 1).abs < @params[:tol]
-            comp_vec = updated
+        if @params[:solver] == 'evd' && enable_linalg?
+          _, evecs = Numo::Linalg.eigh(covariance_mat, vals_range: (n_features - @params[:n_components])...n_features)
+          @components = evecs.reverse(1).transpose.dup
+        else
+          @params[:n_components].times do
+            comp_vec = Rumale::Utils.rand_uniform(n_features, sub_rng)
+            @params[:max_iter].times do
+              updated = orthogonalize(covariance_mat.dot(comp_vec))
+              break if (updated.dot(comp_vec) - 1).abs < @params[:tol]
+              comp_vec = updated
+            end
+            @components = @components.nil? ? comp_vec : Numo::NArray.vstack([@components, comp_vec])
           end
-          @components = @components.nil? ? comp_vec : Numo::NArray.vstack([@components, comp_vec])
         end
         self
       end

data/lib/rumale/version.rb

@@ -3,5 +3,5 @@
 # Rumale is a machine learning library in Ruby.
 module Rumale
   # The version of Rumale you are using.
-  VERSION = '0.12.9'
+  VERSION = '0.13.0'
 end

data/rumale.gemspec

@@ -37,10 +37,11 @@ Gem::Specification.new do |spec|
 
   spec.add_runtime_dependency 'numo-narray', '>= 0.9.1'
 
-  spec.add_development_dependency 'bundler', '>= 1.16'
-  spec.add_development_dependency 'coveralls', '~> 0.8'
-  spec.add_development_dependency 'parallel'
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'coveralls', '>= 0.8.23'
+  spec.add_development_dependency 'numo-linalg', '>= 0.1.4'
+  spec.add_development_dependency 'parallel', '>= 1.17.0'
   spec.add_development_dependency 'rake', '~> 12.0'
-  spec.add_development_dependency 'rake-compiler'
+  spec.add_development_dependency 'rake-compiler', '~> 1.0'
   spec.add_development_dependency 'rspec', '~> 3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.12.9
+  version: 0.13.0
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-07-27 00:00:00.000000000 Z
+date: 2019-08-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -26,46 +26,60 @@ dependencies:
         version: 0.9.1
 - !ruby/object:Gem::Dependency
   name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: 0.8.23
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: 0.8.23
 - !ruby/object:Gem::Dependency
-  name: coveralls
+  name: numo-linalg
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.1.4
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.1.4
 - !ruby/object:Gem::Dependency
   name: parallel
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.17.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.17.0
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -84,16 +98,16 @@ dependencies:
   name: rake-compiler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement