rumale 0.20.3 → 0.22.3

data/lib/rumale/metric_learning/neighbourhood_component_analysis.rb

@@ -2,13 +2,15 @@
 
 require 'rumale/base/base_estimator'
 require 'rumale/base/transformer'
+require 'rumale/utils'
+require 'rumale/pairwise_metric'
+require 'lbfgsb'
 
 module Rumale
   module MetricLearning
     # NeighbourhoodComponentAnalysis is a class that implements Neighbourhood Component Analysis.
     #
     # @example
-    #   require 'mopti'
     #   require 'rumale'
     #
     #   transformer = Rumale::MetricLearning::NeighbourhoodComponentAnalysis.new
@@ -39,7 +41,9 @@ module Rumale
       # @param init [String] The initialization method for components ('random' or 'pca').
       # @param max_iter [Integer] The maximum number of iterations.
       # @param tol [Float] The tolerance of termination criterion.
+      #   This value is given as tol / Lbfgsb::DBL_EPSILON to the factr argument of Lbfgsb.minimize method.
       # @param verbose [Boolean] The flag indicating whether to output loss during iteration.
+      #   If true is given, 'iterate.dat' file is generated by lbfgsb.rb.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(n_components: nil, init: 'random', max_iter: 100, tol: 1e-6, verbose: false, random_seed: nil)
         check_params_numeric_or_nil(n_components: n_components, random_seed: random_seed)
@@ -65,8 +69,6 @@ module Rumale
       # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
       # @return [NeighbourhoodComponentAnalysis] The learned classifier itself.
       def fit(x, y)
-        raise 'NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded.' unless enable_mopti?
-
         x = check_convert_sample_array(x)
         y = check_convert_label_array(y)
         check_sample_label_size(x, y)
@@ -102,14 +104,6 @@ module Rumale
 
       private
 
-      def enable_mopti?
-        if defined?(Mopti).nil?
-          warn('NeighbourhoodComponentAnalysis#fit requires Mopti but that is not loaded. You should intall and load mopti gem in advance.')
-          return false
-        end
-        true
-      end
-
       def init_components(x, n_features, n_components)
         if @params[:init] == 'pca'
           pca = Rumale::Decomposition::PCA.new(n_components: n_components)
@@ -127,28 +121,18 @@ module Rumale
         res[:x] = comp_init
         res[:n_iter] = 0
         # perform optimization.
-        optimizer = Mopti::ScaledConjugateGradient.new(
-          fnc: method(:nca_loss), jcb: method(:nca_dloss),
-          x_init: comp_init, args: [x, y],
-          max_iter: @params[:max_iter], ftol: @params[:tol]
+        verbose = @params[:verbose] ? 1 : -1
+        res = Lbfgsb.minimize(
+          fnc: method(:nca_fnc), jcb: true, x_init: comp_init, args: [x, y],
+          maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
         )
-        fold = 0.0
-        dold = 0.0
-        optimizer.each do |prm|
-          res = prm
-          puts "[NeighbourhoodComponentAnalysis] The value of objective function after #{res[:n_iter]} epochs: #{x.shape[0] - res[:fnc]}" if @params[:verbose]
-          break if (fold - res[:fnc]).abs <= @params[:tol] && (dold - res[:jcb]).abs <= @params[:tol]
-
-          fold = res[:fnc]
-          dold = res[:jcb]
-        end
         # return the results.
         n_iter = res[:n_iter]
         comps = n_components == 1 ? res[:x].dup : res[:x].reshape(n_components, n_features)
         [comps, n_iter]
       end
 
-      def nca_loss(w, x, y)
+      def nca_fnc(w, x, y)
         # initialize some variables.
         n_samples, n_features = x.shape
         n_components = w.size / n_features
@@ -157,32 +141,19 @@ module Rumale
         z = x.dot(w.transpose)
         # calculate probability matrix.
         prob_mat = probability_matrix(z)
-        # calculate loss.
+        # calculate loss and gradient.
         # NOTE:
         # NCA attempts to maximize its objective function.
         # For the minization algorithm, the objective function value is subtracted from the maixmum value (n_samples).
         mask_mat = y.expand_dims(1).eq(y)
         masked_prob_mat = prob_mat * mask_mat
-        n_samples - masked_prob_mat.sum
-      end
-
-      def nca_dloss(w, x, y)
-        # initialize some variables.
-        n_features = x.shape[1]
-        n_components = w.size / n_features
-        # projection.
-        w = w.reshape(n_components, n_features)
-        z = x.dot(w.transpose)
-        # calculate probability matrix.
-        prob_mat = probability_matrix(z)
-        # calculate gradient.
-        mask_mat = y.expand_dims(1).eq(y)
-        masked_prob_mat = prob_mat * mask_mat
-        weighted_prob_mat = masked_prob_mat - prob_mat * masked_prob_mat.sum(1).expand_dims(1)
-        weighted_prob_mat += weighted_prob_mat.transpose
-        weighted_prob_mat[weighted_prob_mat.diag_indices] = -weighted_prob_mat.sum(0)
-        gradient = 2 * z.transpose.dot(weighted_prob_mat).dot(x)
-        -gradient.flatten.dup
+        loss = n_samples - masked_prob_mat.sum
+        sum_probs = masked_prob_mat.sum(1)
+        weight_mat = (sum_probs.expand_dims(1) * prob_mat - masked_prob_mat)
+        weight_mat += weight_mat.transpose
+        weight_mat = weight_mat.sum(0).diag - weight_mat
+        gradient = -2 * z.transpose.dot(weight_mat).dot(x)
+        [loss, gradient.flatten.dup]
       end
 
       def probability_matrix(z)

data/lib/rumale/pairwise_metric.rb

@@ -123,7 +123,7 @@ module Rumale
       # @param gamma [Float] The parameter of polynomial kernel, if nil it is 1 / n_features.
       # @param coef [Integer] The parameter of polynomial kernel.
       # @return [Numo::DFloat] (shape: [n_samples_x, n_samples_x] or [n_samples_x, n_samples_y] if y is given)
-      def polynomial_kernel(x, y = nil, degree = 3, gamma = nil, coef = 1)
+      def polynomial_kernel(x, y = nil, degree = 3, gamma = nil, coef = 1) # rubocop:disable Metrics/ParameterLists
         y = x if y.nil?
         gamma ||= 1.0 / x.shape[1]
         x = Rumale::Validation.check_convert_sample_array(x)

data/lib/rumale/validation.rb

@@ -27,6 +27,7 @@ module Rumale
       y
     end
 
+    # @deprecated Use check_convert_sample_array instead of this method.
     # @!visibility private
     def check_sample_array(x)
       raise TypeError, 'Expect class of sample matrix to be Numo::DFloat' unless x.is_a?(Numo::DFloat)
@@ -35,6 +36,7 @@ module Rumale
       nil
     end
 
+    # @deprecated Use check_convert_label_array instead of this method.
     # @!visibility private
     def check_label_array(y)
       raise TypeError, 'Expect class of label vector to be Numo::Int32' unless y.is_a?(Numo::Int32)
@@ -43,6 +45,7 @@ module Rumale
       nil
     end
 
+    # @deprecated Use check_convert_tvalue_array instead of this method.
     # @!visibility private
     def check_tvalue_array(y)
       raise TypeError, 'Expect class of target value vector to be Numo::DFloat' unless y.is_a?(Numo::DFloat)
@@ -64,52 +67,61 @@ module Rumale
       nil
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_type(type, params = {})
       params.each { |k, v| raise TypeError, "Expect class of #{k} to be #{type}" unless v.is_a?(type) }
       nil
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_type_or_nil(type, params = {})
       params.each { |k, v| raise TypeError, "Expect class of #{k} to be #{type} or nil" unless v.is_a?(type) || v.is_a?(NilClass) }
       nil
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_numeric(params = {})
       check_params_type(Numeric, params)
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_numeric_or_nil(params = {})
       check_params_type_or_nil(Numeric, params)
     end
 
+    # @deprecated Use check_params_numeric instead of this method.
     # @!visibility private
     def check_params_float(params = {})
       check_params_type(Float, params)
     end
 
+    # @deprecated Use check_params_numeric instead of this method.
     # @!visibility private
     def check_params_integer(params = {})
       check_params_type(Integer, params)
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_string(params = {})
       check_params_type(String, params)
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_boolean(params = {})
       params.each { |k, v| raise TypeError, "Expect class of #{k} to be Boolean" unless v.is_a?(FalseClass) || v.is_a?(TrueClass) }
       nil
     end
 
+    # TODO: Better to replace with RBS in the future.
     # @!visibility private
     def check_params_positive(params = {})
-      params.reject { |_, v| v.nil? }.each { |k, v| raise ArgumentError, "Expect #{k} to be positive value" if v.negative? }
+      params.compact.each { |k, v| raise ArgumentError, "Expect #{k} to be positive value" if v.negative? }
       nil
     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 = '0.20.3'
+  VERSION = '0.22.3'
 end

data/rumale.gemspec

@@ -38,11 +38,12 @@ Gem::Specification.new do |spec|
 
   spec.metadata      = {
     'homepage_uri' => 'https://github.com/yoshoku/rumale',
-    'changelog_uri' => 'https://github.com/yoshoku/rumale/blob/master/CHANGELOG.md',
+    'changelog_uri' => 'https://github.com/yoshoku/rumale/blob/main/CHANGELOG.md',
     'source_code_uri' => 'https://github.com/yoshoku/rumale',
     'documentation_uri' => 'https://yoshoku.github.io/rumale/doc/',
     'bug_tracker_uri' => 'https://github.com/yoshoku/rumale/issues'
   }
 
   spec.add_runtime_dependency 'numo-narray', '>= 0.9.1'
+  spec.add_runtime_dependency 'lbfgsb', '>=0.3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.20.3
+  version: 0.22.3
 platform: ruby
 authors:
 - yoshoku
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-09-21 00:00:00.000000000 Z
+date: 2021-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -24,6 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.9.1
+- !ruby/object:Gem::Dependency
+  name: lbfgsb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
 description: |
   Rumale is a machine learning library in Ruby.
   Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
@@ -44,6 +58,8 @@ extensions:
 extra_rdoc_files: []
 files:
 - ".coveralls.yml"
+- ".github/workflows/build.yml"
+- ".github/workflows/coverage.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
@@ -90,6 +106,8 @@ files:
 - lib/rumale/ensemble/gradient_boosting_regressor.rb
 - lib/rumale/ensemble/random_forest_classifier.rb
 - lib/rumale/ensemble/random_forest_regressor.rb
+- lib/rumale/ensemble/stacking_classifier.rb
+- lib/rumale/ensemble/stacking_regressor.rb
 - lib/rumale/evaluation_measure/accuracy.rb
 - lib/rumale/evaluation_measure/adjusted_rand_score.rb
 - lib/rumale/evaluation_measure/calinski_harabasz_score.rb
@@ -125,12 +143,14 @@ files:
 - lib/rumale/linear_model/lasso.rb
 - lib/rumale/linear_model/linear_regression.rb
 - lib/rumale/linear_model/logistic_regression.rb
+- lib/rumale/linear_model/nnls.rb
 - lib/rumale/linear_model/ridge.rb
 - lib/rumale/linear_model/svc.rb
 - lib/rumale/linear_model/svr.rb
 - lib/rumale/manifold/mds.rb
 - lib/rumale/manifold/tsne.rb
 - lib/rumale/metric_learning/fisher_discriminant_analysis.rb
+- lib/rumale/metric_learning/mlkr.rb
 - lib/rumale/metric_learning/neighbourhood_component_analysis.rb
 - lib/rumale/model_selection/cross_validation.rb
 - lib/rumale/model_selection/function.rb
@@ -190,7 +210,7 @@ licenses:
 - BSD-2-Clause
 metadata:
   homepage_uri: https://github.com/yoshoku/rumale
-  changelog_uri: https://github.com/yoshoku/rumale/blob/master/CHANGELOG.md
+  changelog_uri: https://github.com/yoshoku/rumale/blob/main/CHANGELOG.md
   source_code_uri: https://github.com/yoshoku/rumale
   documentation_uri: https://yoshoku.github.io/rumale/doc/
   bug_tracker_uri: https://github.com/yoshoku/rumale/issues
@@ -209,7 +229,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: Rumale is a machine learning library in Ruby. Rumale provides machine learning