rumale 0.12.0 → 0.12.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f662b1bf4abdb9aba9c978362094d80f59fcb390
-  data.tar.gz: eb5087ce4b4f2dfdc8e789c340139dd7d36693e0
+  metadata.gz: e069b026a9236e69924051af75689ba292632b50
+  data.tar.gz: b98e3260e947f66936a7149a8b09eb24bb5219fe
 SHA512:
-  metadata.gz: 8418aa3932962b135c3a9725262e84b741825ed2491e98dba508e04ea4104d7abe0a9938d6248d9405bc7d9793d1f128a7e37c89804a79367626a47d3fa6a773
-  data.tar.gz: 40fff97c335d5720eaf1c90b45ed39531c61827777797a3a4bbc5c8b5f4b8df9b3814290686c959f9f7a9726966187a064b521850139124c9be2c64189d1d29f
+  metadata.gz: 2ff9dac0d7d633064fc3f4b5127a639a4617357c219fc20ad38c79048981c555fdddebc3f8d16047798bdfc658292e98cbc04d1f26733bcebf4a6412ca84f3ab
+  data.tar.gz: 9ad31638ea47d527a0af109a8cda2dcb44d0296ce31a88509833e4f8a116f49601dbf6353606fca080ed378425f5ce759c440791e8eccd90743ed65b14b1ef86

data/.gitignore

@@ -13,6 +13,7 @@
 
 *.swp
 *.bundle
+tags
 .DS_Store
 .ruby-version
 /spec/dump_dbl.t

data/.rubocop.yml

@@ -1,7 +1,5 @@
 require: rubocop-performance
 
-inherit_from: .rubocop_todo.yml
-
 AllCops:
   TargetRubyVersion: 2.3
   DisplayCopNames: true
@@ -31,7 +29,14 @@ Metrics/MethodLength:
 Metrics/AbcSize:
   Max: 60
 
+Metrics/CyclomaticComplexity:
+  Max: 16
+
+Metrics/PerceivedComplexity:
+  Max: 16
+
 Metrics/BlockLength:
+  Max: 40
   Exclude:
     - 'spec/**/*'
 

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+# 0.12.1
+- Refactor kernel support vector classifier.
+- Refactor random sampling on tree estimators.
+
 # 0.12.0
 ## Breaking changes
 - For reproductivity, Rumale changes to not repeatedly use the same random number generator in the same estimator.

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/0.12.0)
+[![Documentation](http://img.shields.io/badge/docs-rdoc.info-blue.svg)](https://www.rubydoc.info/gems/rumale/0.12.1)
 
 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.
@@ -209,7 +209,7 @@ Install OpenBLAS library.
 Mac:
 
 ```bash
-$ brew install openblas --with-openmp
+$ brew install openblas
 ```
 
 Ubuntu:

data/ext/rumale/extconf.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'mkmf'
 
 create_makefile('rumale/rumale')

data/lib/rumale/ensemble/extra_trees_regressor.rb

@@ -129,7 +129,7 @@ module Rumale
         Tree::ExtraTreeRegressor.new(
           criterion: @params[:criterion], max_depth: @params[:max_depth],
           max_leaf_nodes: @params[:max_leaf_nodes], min_samples_leaf: @params[:min_samples_leaf],
-          max_features: @params[:max_features], random_seed:rnd_seed
+          max_features: @params[:max_features], random_seed: rnd_seed
         )
       end
     end

data/lib/rumale/kernel_machine/kernel_svc.rb

@@ -79,45 +79,29 @@ module Rumale
 
         @classes = Numo::Int32[*y.to_a.uniq.sort]
         n_classes = @classes.size
-        _n_samples, n_features = x.shape
+        n_features = x.shape[1]
 
         if n_classes > 2
           @weight_vec = Numo::DFloat.zeros(n_classes, n_features)
           @prob_param = Numo::DFloat.zeros(n_classes, 2)
-          if enable_parallel?
-            # :nocov:
-            models = parallel_map(n_classes) do |n|
-              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-              w = binary_fit(x, bin_y)
-              p = if @params[:probability]
-                    Rumale::ProbabilisticOutput.fit_sigmoid(x.dot(w), bin_y)
-                  else
-                    Numo::DFloat[1, 0]
-                  end
-              [w, p]
-            end
-            # :nocov:
-            n_classes.times { |n| @weight_vec[n, true], @prob_param[n, true] = models[n] }
-          else
-            n_classes.times do |n|
-              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-              @weight_vec[n, true] = binary_fit(x, bin_y)
-              @prob_param[n, true] = if @params[:probability]
-                                       Rumale::ProbabilisticOutput.fit_sigmoid(x.dot(@weight_vec[n, true].transpose), bin_y)
-                                     else
-                                       Numo::DFloat[1, 0]
-                                     end
-            end
-          end
+          models = if enable_parallel?
+                     # :nocov:
+                     parallel_map(n_classes) do |n|
+                       bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
+                       partial_fit(x, bin_y)
+                     end
+                     # :nocov:
+                   else
+                     Array.new(n_classes) do |n|
+                       bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
+                       partial_fit(x, bin_y)
+                     end
+                   end
+          models.each_with_index { |model, n| @weight_vec[n, true], @prob_param[n, true] = model }
         else
           negative_label = y.to_a.uniq.min
           bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
-          @weight_vec = binary_fit(x, bin_y)
-          @prob_param = if @params[:probability]
-                          Rumale::ProbabilisticOutput.fit_sigmoid(x.dot(@weight_vec.transpose), bin_y)
-                        else
-                          Numo::DFloat[1, 0]
-                        end
+          @weight_vec, @prob_param = partial_fit(x, bin_y)
         end
 
         self
@@ -197,7 +181,7 @@ module Rumale
 
       private
 
-      def binary_fit(x, bin_y)
+      def partial_fit(x, bin_y)
         # Initialize some variables.
         n_training_samples = x.shape[0]
         rand_ids = []
@@ -213,7 +197,13 @@ module Rumale
           func *= bin_y[target_id] / (@params[:reg_param] * (t + 1))
           weight_vec[target_id] += 1.0 if func < 1.0
         end
-        weight_vec * bin_y
+        w = weight_vec * bin_y
+        p = if @params[:probability]
+              Rumale::ProbabilisticOutput.fit_sigmoid(x.dot(w), bin_y)
+            else
+              Numo::DFloat[1, 0]
+            end
+        [w, p]
       end
     end
   end

data/lib/rumale/tree/base_decision_tree.rb

@@ -62,14 +62,16 @@ module Rumale
 
       def build_tree(x, y)
         y = y.expand_dims(1).dup if y.shape[1].nil?
+        @feature_ids = Array.new(x.shape[1]) { |v| v }
         @tree = grow_node(0, x, y, impurity(y))
+        @feature_ids = nil
         nil
       end
 
-      def grow_node(depth, x, y, whole_impurity)
+      def grow_node(depth, x, y, impurity)
         # intialize node.
         n_samples, n_features = x.shape
-        node = Node.new(depth: depth, impurity: whole_impurity, n_samples: n_samples)
+        node = Node.new(depth: depth, impurity: impurity, n_samples: n_samples)
 
         # terminate growing.
         unless @params[:max_leaf_nodes].nil?
@@ -87,7 +89,7 @@ module Rumale
 
         # calculate optimal parameters.
         feature_id, left_imp, right_imp, threshold, gain =
-          rand_ids(n_features).map { |n| [n, *best_split(x[true, n], y, whole_impurity)] }.max_by(&:last)
+          rand_ids.map { |n| [n, *best_split(x[true, n], y, impurity)] }.max_by(&:last)
 
         return put_leaf(node, y) if gain.nil? || gain.zero?
 
@@ -112,8 +114,8 @@ module Rumale
         raise NotImplementedError, "#{__method__} has to be implemented in #{self.class}."
       end
 
-      def rand_ids(n)
-        [*0...n].sample(@params[:max_features], random: @sub_rng)
+      def rand_ids
+        @feature_ids.sample(@params[:max_features], random: @sub_rng)
       end
 
       def best_split(_features, _y, _impurity)

data/lib/rumale/tree/gradient_tree_regressor.rb

@@ -153,7 +153,9 @@ module Rumale
       end
 
       def build_tree(x, y, g, h)
+        @feature_ids = Array.new(x.shape[1]) { |v| v }
         @tree = grow_node(0, x, y, g, h)
+				@feature_ids = nil
         nil
       end
 
@@ -179,8 +181,7 @@ module Rumale
         return put_leaf(node, sum_g, sum_h) if stop_growing?(y)
 
         # calculate optimal parameters.
-        feature_id, threshold, gain =
-          rand_ids(n_features).map { |n| [n, *best_split(x[true, n], g, h, sum_g, sum_h)] }.max_by(&:last)
+        feature_id, threshold, gain = rand_ids.map { |n| [n, *best_split(x[true, n], g, h, sum_g, sum_h)] }.max_by(&:last)
 
         return put_leaf(node, sum_g, sum_h) if gain.nil? || gain.zero?
 
@@ -221,8 +222,8 @@ module Rumale
         find_split_params(sorted_f, sorted_g, sorted_h, sum_g, sum_h, @params[:reg_lambda])
       end
 
-      def rand_ids(n)
-        [*0...n].sample(@params[:max_features], random: @sub_rng)
+      def rand_ids
+        @feature_ids.sample(@params[:max_features], random: @sub_rng)
       end
     end
   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 = '0.12.0'
+  VERSION = '0.12.1'
 end

data/rumale.gemspec

@@ -1,3 +1,4 @@
+
 lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'rumale/version'
@@ -8,18 +9,18 @@ Gem::Specification.new do |spec|
   spec.authors       = ['yoshoku']
   spec.email         = ['yoshoku@outlook.com']
 
-  spec.summary       = <<MSG
-Rumale is a machine learning library in Ruby.
-Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
-MSG
-  spec.description   = <<MSG
-Rumale is a machine learning library in Ruby.
-Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
-Rumale currently supports Linear / Kernel Support Vector Machine,
-Logistic Regression, Linear Regression, Ridge, Lasso, Factorization Machine,
-Naive Bayes, Decision Tree, AdaBoost, Gradient Tree Boosting, Random Forest, Extra-Trees, K-nearest neighbor algorithm,
-K-Means, DBSCAN, t-SNE, Principal Component Analysis, and Non-negative Matrix Factorization.
-MSG
+  spec.summary       = <<~MSG
+    Rumale is a machine learning library in Ruby.
+    Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
+  MSG
+  spec.description   = <<~MSG
+    Rumale is a machine learning library in Ruby.
+    Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
+    Rumale currently supports Linear / Kernel Support Vector Machine,
+    Logistic Regression, Linear Regression, Ridge, Lasso, Factorization Machine,
+    Naive Bayes, Decision Tree, AdaBoost, Gradient Tree Boosting, Random Forest, Extra-Trees, K-nearest neighbor algorithm,
+    K-Means, DBSCAN, t-SNE, Principal Component Analysis, and Non-negative Matrix Factorization.
+  MSG
   spec.homepage      = 'https://github.com/yoshoku/rumale'
   spec.license       = 'BSD-2-Clause'
 
@@ -37,8 +38,8 @@ MSG
 
   spec.add_development_dependency 'bundler', '>= 1.16'
   spec.add_development_dependency 'coveralls', '~> 0.8'
+  spec.add_development_dependency 'parallel'
   spec.add_development_dependency 'rake', '~> 12.0'
   spec.add_development_dependency 'rake-compiler'
-  spec.add_development_dependency 'parallel'
   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: 0.12.0
+  version: 0.12.1
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-06-01 00:00:00.000000000 Z
+date: 2019-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -53,35 +53,35 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.8'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: parallel
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '12.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '12.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: rake-compiler
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '12.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '12.0'
 - !ruby/object:Gem::Dependency
-  name: parallel
+  name: rake-compiler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -126,7 +126,6 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
-- ".rubocop_todo.yml"
 - ".travis.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md

data/.rubocop_todo.yml

@@ -1,58 +0,0 @@
-# This configuration was generated by
-# `rubocop --auto-gen-config`
-# on 2018-06-10 12:21:53 +0900 using RuboCop version 0.57.1.
-# The point is for the user to remove these configuration records
-# one by one as the offenses are removed from the code base.
-# Note that changes in the inspected code, or installation of new
-# versions of RuboCop, may require this file to be generated again.
-
-# Offense count: 2
-# Cop supports --auto-correct.
-Layout/ClosingHeredocIndentation:
-  Exclude:
-    - 'rumale.gemspec'
-
-# Offense count: 2
-# Cop supports --auto-correct.
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: auto_detection, squiggly, active_support, powerpack, unindent
-Layout/IndentHeredoc:
-  Exclude:
-    - 'rumale.gemspec'
-
-# Offense count: 1
-# Cop supports --auto-correct.
-Layout/LeadingBlankLines:
-  Exclude:
-    - 'rumale.gemspec'
-
-# Offense count: 1
-# Configuration parameters: CountComments, ExcludedMethods.
-Metrics/BlockLength:
-  Max: 29
-
-# Offense count: 3
-Metrics/CyclomaticComplexity:
-  Max: 12
-
-# Offense count: 3
-Metrics/PerceivedComplexity:
-  Max: 13
-
-# Offense count: 1
-# Cop supports --auto-correct.
-# Configuration parameters: EnforcedStyle, UseHashRocketsWithSymbolValues, PreferHashRocketsForNonAlnumEndingSymbols.
-# SupportedStyles: ruby19, hash_rockets, no_mixed_keys, ruby19_no_mixed_keys
-Style/HashSyntax:
-  Exclude:
-    - 'Rakefile'
-
-# Offense count: 6
-# Cop supports --auto-correct.
-# Configuration parameters: EnforcedStyle, ConsistentQuotesInMultiline.
-# SupportedStyles: single_quotes, double_quotes
-Style/StringLiterals:
-  Exclude:
-    - 'Gemfile'
-    - 'Rakefile'
-    - 'bin/console'