rumale 0.20.1 → 0.22.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0f361026cd2922a2d36846a817eee855bf0c000156ed6c756bca29d2e42d67a2
-  data.tar.gz: 016fa40aa2546824cacbc32353263cbfc9427f0ceabb7e703f99854914bb9a2e
+  metadata.gz: 475798da3815141b5337bc7803eca26978bbc98c36a2be4d681bc63f778f5840
+  data.tar.gz: 71841127edccbeea2b30c4bd8a744735933c1fcf8c7d6afa507cd2d361c8b5c8
 SHA512:
-  metadata.gz: 7a53a958db7ec8b56236018505370b9908ae81a9afc9d7c8ff0b16d83971539c1ad729b5ab350eb49ae9b90ada43a8912ed2404a37eef97a4d34dad90b1d3e9f
-  data.tar.gz: 2f2b3d48625c7120464179bc7759c01ba7de85cb0d54720665eaf1e4822f24c1870474ebc24a47cff123e44a8626b0e0fac6a7e81216c057286071770ea5ba79
+  metadata.gz: 8c90eaffa3847e3cc4f31c58e3d74f66a86e2cf0bd1c6e5aa386f9519de3984ac1c605187119e0ec01585c82cf8c06e4f4aa2f19c7b40883b784e834e2e801d8
+  data.tar.gz: 336b1afcc35e52e1c13ced74f527d54c994ff66509cf9b8b2f81dce62692078964a453df790a5bcaf8ea2bd156277d719a33958de2f57aa64d97beeafdc48d01

data/.github/workflows/build.yml

@@ -0,0 +1,23 @@
+name: build
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby: [ '2.5', '2.6', '2.7' ]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Install BLAS and LAPACK
+        run: sudo apt-get install -y libopenblas-dev liblapacke-dev
+      - name: Set up Ruby ${{ matrix.ruby }}
+        uses: actions/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+      - name: Build and test with Rake
+        run: |
+          gem install bundler
+          bundle install --jobs 4 --retry 3
+          bundle exec rake

data/.rubocop.yml

@@ -20,6 +20,9 @@ Layout/LineLength:
   Max: 145
   IgnoredPatterns: ['(\A|\s)#']
 
+Lint/ConstantDefinitionInBlock:
+  Enabled: false
+
 Lint/MissingSuper:
   Enabled: false
 
@@ -70,6 +73,9 @@ Style/StringConcatenation:
 RSpec/MultipleExpectations:
   Enabled: false
 
+RSpec/MultipleMemoizedHelpers:
+  Max: 25
+
 RSpec/NestedGroups:
   Max: 4
 
@@ -81,3 +87,6 @@ RSpec/InstanceVariable:
 
 RSpec/LeakyConstantDeclaration:
   Enabled: false
+
+Performance/Sum:
+  Enabled: false

data/CHANGELOG.md

@@ -1,3 +1,27 @@
+# 0.22.1
+- Add transfomer class for MLKR, that implements Metric Learning for Kernel Regression.
+- Refactor NeighbourhoodComponentAnalysis.
+- Update API documentation.
+
+# 0.22.0
+## Breaking change
+- Add lbfgsb.rb gem to runtime dependencies. Rumale uses lbfgsb gem for optimization.
+This eliminates the need to require the mopti gem when using [NeighbourhoodComponentAnalysis](https://yoshoku.github.io/rumale/doc/Rumale/MetricLearning/NeighbourhoodComponentAnalysis.html).
+- Add lbfgs solver to [LogisticRegression](https://yoshoku.github.io/rumale/doc/Rumale/LinearModel/LogisticRegression.html) and make it the default solver.
+
+# 0.21.0
+## Breaking change
+- Change the default value of max_iter argument on LinearModel estimators to 1000.
+
+# 0.20.3
+- Fix to use automatic solver of PCA in NeighbourhoodComponentAnalysis.
+- Refactor some codes with Rubocop.
+- Update README.
+
+# 0.20.2
+- Add cross-validator class for time-series data.
+  - [TimeSeriesSplit](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/TimeSeriesSplit.html)
+
 # 0.20.1
 - Add cross-validator classes that split data according group labels.
   - [GroupKFold](https://yoshoku.github.io/rumale/doc/Rumale/ModelSelection/GroupKFold.html)

data/Gemfile

@@ -3,11 +3,13 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in rumale.gemspec
 gemspec
 
-gem 'coveralls', '~> 0.8'
 gem 'mmh3', '>= 1.0'
-gem 'mopti', '>= 0.1.0'
 gem 'numo-linalg', '>= 0.1.4'
 gem 'parallel', '>= 1.17.0'
 gem 'rake', '~> 12.0'
 gem 'rake-compiler', '~> 1.0'
 gem 'rspec', '~> 3.0'
+gem 'rubocop', '~> 0.91'
+gem 'rubocop-performance', '~> 1.8'
+gem 'rubocop-rspec', '~> 1.43'
+gem 'simplecov', '~> 0.19'

data/README.md

@@ -2,8 +2,7 @@
 
 ![Rumale](https://dl.dropboxusercontent.com/s/joxruk2720ur66o/rumale_header_400.png)
 
-[![Build Status](https://travis-ci.org/yoshoku/rumale.svg?branch=master)](https://travis-ci.org/yoshoku/rumale)
-[![Coverage Status](https://coveralls.io/repos/github/yoshoku/rumale/badge.svg?branch=master)](https://coveralls.io/github/yoshoku/rumale?branch=master)
+[![Build Status](https://github.com/yoshoku/rumale/workflows/build/badge.svg)](https://github.com/yoshoku/rumale/actions?query=workflow%3Abuild)
 [![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](https://img.shields.io/badge/api-reference-blue.svg)](https://yoshoku.github.io/rumale/doc/)
@@ -114,10 +113,10 @@ require 'rumale'
 samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
 
 # Define the estimator to be evaluated.
-lr = Rumale::LinearModel::LogisticRegression.new(learning_rate: 0.00001, reg_param: 0.0001, random_seed: 1)
+lr = Rumale::LinearModel::LogisticRegression.new
 
 # Define the evaluation measure, splitting strategy, and cross validation.
-ev = Rumale::EvaluationMeasure::LogLoss.new
+ev = Rumale::EvaluationMeasure::Accuracy.new
 kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5, shuffle: true, random_seed: 1)
 cv = Rumale::ModelSelection::CrossValidation.new(estimator: lr, splitter: kf, evaluator: ev)
 
@@ -125,15 +124,15 @@ cv = Rumale::ModelSelection::CrossValidation.new(estimator: lr, splitter: kf, ev
 report = cv.perform(samples, labels)
 
 # Output result.
-mean_logloss = report[:test_score].inject(:+) / kf.n_splits
-puts("5-CV mean log-loss: %.3f" % mean_logloss)
+mean_accuracy = report[:test_score].sum / kf.n_splits
+puts "5-CV mean accuracy: %.1f%%" % (100.0 * mean_accuracy)
 ```
 
 Execution of the above scripts result in the following.
 
 ```bash
 $ ruby cross_validation.rb
-5-CV mean log-loss: 0.355
+5-CV mean accuracy: 95.4%
 ```
 
 ### Example 3. Pipeline
@@ -144,10 +143,10 @@ require 'rumale'
 # Load dataset.
 samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
 
-# Construct pipeline with kernel approximation and SVC.
-rbf = Rumale::KernelApproximation::RBF.new(gamma: 0.0001, n_components: 800, random_seed: 1)
-svc = Rumale::LinearModel::SVC.new(reg_param: 0.0001, random_seed: 1)
-pipeline = Rumale::Pipeline::Pipeline.new(steps: { trns: rbf, clsf: svc })
+# Construct pipeline with kernel approximation and LogisticRegression.
+rbf = Rumale::KernelApproximation::RBF.new(gamma: 1e-4, n_components: 800, random_seed: 1)
+lr = Rumale::LinearModel::LogisticRegression.new(reg_param: 1e-3)
+pipeline = Rumale::Pipeline::Pipeline.new(steps: { trns: rbf, clsf: lr })
 
 # Define the splitting strategy and cross validation.
 kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5, shuffle: true, random_seed: 1)
@@ -157,7 +156,7 @@ cv = Rumale::ModelSelection::CrossValidation.new(estimator: pipeline, splitter:
 report = cv.perform(samples, labels)
 
 # Output result.
-mean_accuracy = report[:test_score].inject(:+) / kf.n_splits
+mean_accuracy = report[:test_score].sum / kf.n_splits
 puts("5-CV mean accuracy: %.1f %%" % (mean_accuracy * 100.0))
 ```
 
@@ -228,6 +227,10 @@ When -1 is given to n_jobs parameter, all processors are used.
 estimator = Rumale::Ensemble::RandomForestClassifier.new(n_jobs: -1, random_seed: 1)
 ```
 
+## Novelties
+
+* [Rumale SHOP](https://suzuri.jp/yoshoku)
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/rumale.

data/lib/rumale.rb

@@ -77,6 +77,7 @@ require 'rumale/manifold/tsne'
 require 'rumale/manifold/mds'
 require 'rumale/metric_learning/fisher_discriminant_analysis'
 require 'rumale/metric_learning/neighbourhood_component_analysis'
+require 'rumale/metric_learning/mlkr'
 require 'rumale/neural_network/adam'
 require 'rumale/neural_network/base_mlp'
 require 'rumale/neural_network/mlp_regressor'
@@ -103,6 +104,7 @@ require 'rumale/model_selection/stratified_k_fold'
 require 'rumale/model_selection/shuffle_split'
 require 'rumale/model_selection/group_shuffle_split'
 require 'rumale/model_selection/stratified_shuffle_split'
+require 'rumale/model_selection/time_series_split'
 require 'rumale/model_selection/cross_validation'
 require 'rumale/model_selection/grid_search_cv'
 require 'rumale/model_selection/function'

data/lib/rumale/clustering/snn.rb

@@ -51,7 +51,7 @@ module Rumale
       # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be used for cluster analysis.
       #   If the metric is 'precomputed', x must be a square distance matrix (shape: [n_samples, n_samples]).
       # @return [Numo::Int32] (shape: [n_samples]) Predicted cluster label per sample.
-      def fit_predict(x)
+      def fit_predict(x) # rubocop:disable Lint/UselessMethodDefinition
         super
       end
 

data/lib/rumale/evaluation_measure/roc_auc.rb

@@ -75,9 +75,12 @@ module Rumale
         false_pos, true_pos, thresholds = binary_roc_curve(y_true, y_score, pos_label)
 
         if true_pos.size.zero? || false_pos[0] != 0 || true_pos[0] != 0
+          # NOTE: Numo::NArray#insert is not a destructive method.
+          # rubocop:disable Style/RedundantSelfAssignment
           true_pos = true_pos.insert(0, 0)
           false_pos = false_pos.insert(0, 0)
           thresholds = thresholds.insert(0, thresholds[0] + 1)
+          # rubocop:enable Style/RedundantSelfAssignment
         end
 
         tpr = true_pos / true_pos[-1].to_f

data/lib/rumale/kernel_machine/kernel_svc.rb

@@ -11,9 +11,10 @@ module Rumale
     # with stochastic gradient descent (SGD) optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
-    # Rumale::SVM provides kernel support vector classifier based on LIBSVM.
-    # If you prefer execution speed, you should use Rumale::SVM::SVC.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides kernel support vector classifier based on LIBSVM.
+    #   If you prefer execution speed, you should use Rumale::SVM::SVC.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   training_kernel_matrix = Rumale::PairwiseMetric::rbf_kernel(training_samples)

data/lib/rumale/linear_model/base_sgd.rb

@@ -171,7 +171,7 @@ module Rumale
         @params[:fit_bias] = true
         @params[:reg_param] = 0.0
         @params[:l1_ratio] = 0.0
-        @params[:max_iter] = 200
+        @params[:max_iter] = 1000
         @params[:batch_size] = 50
         @params[:tol] = 0.0001
         @params[:verbose] = false

data/lib/rumale/linear_model/elastic_net.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::ElasticNet.new(reg_param: 0.1, l1_ratio: 0.5, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::ElasticNet.new(reg_param: 0.1, l1_ratio: 0.5, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -59,7 +59,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, l1_ratio: 0.5, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, l1_ratio: l1_ratio, bias_scale: bias_scale,

data/lib/rumale/linear_model/lasso.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::Lasso.new(reg_param: 0.1, max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::Lasso.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -55,7 +55,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, bias_scale: bias_scale,

data/lib/rumale/linear_model/linear_regression.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::LinearRegression.new(max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::LinearRegression.new(max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -68,7 +68,7 @@ module Rumale
       #   If solver = 'svd', this parameter is ignored.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
-                     fit_bias: true, bias_scale: 1.0, max_iter: 200, batch_size: 50, tol: 1e-4,
+                     fit_bias: true, bias_scale: 1.0, max_iter: 1000, batch_size: 50, tol: 1e-4,
                      solver: 'auto',
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,

data/lib/rumale/linear_model/logistic_regression.rb

@@ -1,21 +1,24 @@
 # frozen_string_literal: true
 
-require 'rumale/linear_model/base_sgd'
+require 'lbfgsb'
 require 'rumale/base/classifier'
+require 'rumale/linear_model/base_sgd'
+require 'rumale/preprocessing/label_binarizer'
 
 module Rumale
   module LinearModel
-    # LogisticRegression is a class that implements Logistic Regression
-    # with stochastic gradient descent optimization.
-    # For multiclass classification problem, it uses one-vs-the-rest strategy.
+    # LogisticRegression is a class that implements Logistic Regression.
+    # In multiclass classification problem, it uses one-vs-the-rest strategy for the sgd solver
+    # and multinomial logistic regression for the lbfgs solver.
     #
-    # Rumale::SVM provides Logistic Regression based on LIBLINEAR.
-    # If you prefer execution speed, you should use Rumale::SVM::LogisticRegression.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides Logistic Regression based on LIBLINEAR.
+    #   If you prefer execution speed, you should use Rumale::SVM::LogisticRegression.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::LogisticRegression.new(reg_param: 1.0, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::LogisticRegression.new(reg_param: 1.0, random_seed: 1)
     #   estimator.fit(training_samples, traininig_labels)
     #   results = estimator.predict(testing_samples)
     #
@@ -42,19 +45,24 @@ module Rumale
       # @return [Random]
       attr_reader :rng
 
-      # Create a new classifier with Logisitc Regression by the SGD optimization.
+      # Create a new classifier with Logisitc Regression.
       #
       # @param learning_rate [Float] The initial value of learning rate.
       #   The learning rate decreases as the iteration proceeds according to the equation: learning_rate / (1 + decay * t).
+      #   If solver = 'lbfgs', this parameter is ignored.
       # @param decay [Float] The smoothing parameter for decreasing learning rate as the iteration proceeds.
       #   If nil is given, the decay sets to 'reg_param * learning_rate'.
+      #   If solver = 'lbfgs', this parameter is ignored.
       # @param momentum [Float] The momentum factor.
+      #   If solver = 'lbfgs', this parameter is ignored.
       # @param penalty [String] The regularization type to be used ('l1', 'l2', and 'elasticnet').
+      #   If solver = 'lbfgs', only 'l2' can be selected for this parameter.
       # @param l1_ratio [Float] The elastic-net type regularization mixing parameter.
       #   If penalty set to 'l2' or 'l1', this parameter is ignored.
       #   If l1_ratio = 1, the regularization is similar to Lasso.
       #   If l1_ratio = 0, the regularization is similar to Ridge.
       #   If 0 < l1_ratio < 1, the regularization is a combination of L1 and L2.
+      #   If solver = 'lbfgs', this parameter is ignored.
       # @param reg_param [Float] The regularization parameter.
       # @param fit_bias [Boolean] The flag indicating whether to fit the bias term.
       # @param bias_scale [Float] The scale of the bias term.
@@ -62,28 +70,38 @@ module Rumale
       # @param max_iter [Integer] The maximum number of epochs that indicates
       #   how many times the whole data is given to the training process.
       # @param batch_size [Integer] The size of the mini batches.
+      #   If solver = 'lbfgs', this parameter is ignored.
       # @param tol [Float] The tolerance of loss for terminating optimization.
+      #   If solver = 'lbfgs', this value is given as tol / Lbfgsb::DBL_EPSILON to the factr argument of Lbfgsb.minimize method.
+      # @param solver [String] The algorithm for optimization. ('lbfgs' or 'sgd').
+      #   'lbfgs' uses the L-BFGS with lbfgs.rb gem.
+      #   'sgd' uses the stochastic gradient descent optimization.
       # @param n_jobs [Integer] The number of jobs for running the fit and predict methods in parallel.
       #   If nil is given, the methods do not execute in parallel.
       #   If zero or less is given, it becomes equal to the number of processors.
-      #   This parameter is ignored if the Parallel gem is not loaded.
+      #   This parameter is ignored if the Parallel gem is not loaded or the solver is 'lbfgs'.
       # @param verbose [Boolean] The flag indicating whether to output loss during iteration.
+      #   If solver = 'lbfgs' and 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(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
+                     solver: 'lbfgs',
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, l1_ratio: l1_ratio, bias_scale: bias_scale,
                              max_iter: max_iter, batch_size: batch_size, tol: tol)
         check_params_boolean(fit_bias: fit_bias, verbose: verbose)
-        check_params_string(penalty: penalty)
+        check_params_string(solver: solver, penalty: penalty)
         check_params_numeric_or_nil(decay: decay, n_jobs: n_jobs, random_seed: random_seed)
         check_params_positive(learning_rate: learning_rate, reg_param: reg_param,
                               bias_scale: bias_scale, max_iter: max_iter, batch_size: batch_size)
+        raise ArgumentError, "The 'lbfgs' solver supports only 'l2' penalties." if solver == 'lbfgs' && penalty != 'l2'
+
         super()
         @params.merge!(method(:initialize).parameters.map { |_t, arg| [arg, binding.local_variable_get(arg)] }.to_h)
+        @params[:solver] = solver == 'sgd' ? 'sgd' : 'lbfgs'
         @params[:decay] ||= @params[:reg_param] * @params[:learning_rate]
         @params[:random_seed] ||= srand
         @rng = Random.new(@params[:random_seed])
@@ -105,30 +123,10 @@ module Rumale
         check_sample_label_size(x, y)
 
         @classes = Numo::Int32[*y.to_a.uniq.sort]
-
-        if multiclass_problem?
-          n_classes = @classes.size
-          n_features = x.shape[1]
-          @weight_vec = Numo::DFloat.zeros(n_classes, n_features)
-          @bias_term = Numo::DFloat.zeros(n_classes)
-          if enable_parallel?
-            # :nocov:
-            models = parallel_map(n_classes) do |n|
-              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-              partial_fit(x, bin_y)
-            end
-            # :nocov:
-            n_classes.times { |n| @weight_vec[n, true], @bias_term[n] = models[n] }
-          else
-            n_classes.times do |n|
-              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
-              @weight_vec[n, true], @bias_term[n] = partial_fit(x, bin_y)
-            end
-          end
+        if @params[:solver] == 'sgd'
+          fit_sgd(x, y)
         else
-          negative_label = @classes[0]
-          bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
-          @weight_vec, @bias_term = partial_fit(x, bin_y)
+          fit_lbfgs(x, y)
         end
 
         self
@@ -182,6 +180,96 @@ module Rumale
       def multiclass_problem?
         @classes.size > 2
       end
+
+      def fit_lbfgs(base_x, base_y)
+        if multiclass_problem?
+          fnc = proc do |w, x, y, a|
+            n_features = x.shape[1]
+            n_classes = y.shape[1]
+            z = x.dot(w.reshape(n_classes, n_features).transpose)
+            # logsumexp and softmax
+            z_max = z.max(-1).expand_dims(-1).dup
+            z_max[~z_max.isfinite] = 0.0
+            lgsexp = Numo::NMath.log(Numo::NMath.exp(z - z_max).sum(-1)).expand_dims(-1) + z_max
+            t = z - lgsexp
+            sftmax = Numo::NMath.exp(t)
+            # loss and gradient
+            loss = -(y * t).sum + 0.5 * a * w.dot(w)
+            grad = (sftmax - y).transpose.dot(x).flatten.dup + a * w
+            [loss, grad]
+          end
+
+          base_x = expand_feature(base_x) if fit_bias?
+          encoder = Rumale::Preprocessing::LabelBinarizer.new
+          onehot_y = encoder.fit_transform(base_y)
+          n_classes = @classes.size
+          n_features = base_x.shape[1]
+          w_init = Numo::DFloat.zeros(n_classes * n_features)
+
+          verbose = @params[:verbose] ? 1 : -1
+          res = Lbfgsb.minimize(
+            fnc: fnc, jcb: true, x_init: w_init, args: [base_x, onehot_y, @params[:reg_param]],
+            maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
+          )
+
+          if fit_bias?
+            weight = res[:x].reshape(n_classes, n_features)
+            @weight_vec = weight[true, 0...-1].dup
+            @bias_term = weight[true, -1].dup
+          else
+            @weight_vec = res[:x].reshape(n_classes, n_features)
+            @bias_term = Numo::DFloat.zeros(n_classes)
+          end
+        else
+          fnc = proc do |w, x, y, a|
+            z = 1 + Numo::NMath.exp(-y * x.dot(w))
+            loss = Numo::NMath.log(z).sum + 0.5 * a * w.dot(w)
+            grad = (y / z - y).dot(x) + a * w
+            [loss, grad]
+          end
+
+          base_x = expand_feature(base_x) if fit_bias?
+          negative_label = @classes[0]
+          bin_y = Numo::Int32.cast(base_y.ne(negative_label)) * 2 - 1
+          n_features = base_x.shape[1]
+          w_init = Numo::DFloat.zeros(n_features)
+
+          verbose = @params[:verbose] ? 1 : -1
+          res = Lbfgsb.minimize(
+            fnc: fnc, jcb: true, x_init: w_init, args: [base_x, bin_y, @params[:reg_param]],
+            maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
+          )
+
+          @weight_vec, @bias_term = split_weight(res[:x])
+        end
+      end
+
+      def fit_sgd(x, y)
+        if multiclass_problem?
+          n_classes = @classes.size
+          n_features = x.shape[1]
+          @weight_vec = Numo::DFloat.zeros(n_classes, n_features)
+          @bias_term = Numo::DFloat.zeros(n_classes)
+          if enable_parallel?
+            # :nocov:
+            models = parallel_map(n_classes) do |n|
+              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
+              partial_fit(x, bin_y)
+            end
+            # :nocov:
+            n_classes.times { |n| @weight_vec[n, true], @bias_term[n] = models[n] }
+          else
+            n_classes.times do |n|
+              bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
+              @weight_vec[n, true], @bias_term[n] = partial_fit(x, bin_y)
+            end
+          end
+        else
+          negative_label = @classes[0]
+          bin_y = Numo::Int32.cast(y.ne(negative_label)) * 2 - 1
+          @weight_vec, @bias_term = partial_fit(x, bin_y)
+        end
+      end
     end
   end
 end

data/lib/rumale/linear_model/ridge.rb

@@ -10,7 +10,7 @@ module Rumale
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::Ridge.new(reg_param: 0.1, max_iter: 500, batch_size: 20, random_seed: 1)
+    #     Rumale::LinearModel::Ridge.new(reg_param: 0.1, max_iter: 1000, batch_size: 20, random_seed: 1)
     #   estimator.fit(training_samples, traininig_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -70,7 +70,7 @@ module Rumale
       # @param random_seed [Integer] The seed value using to initialize the random generator.
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      reg_param: 1.0, fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      solver: 'auto',
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,

data/lib/rumale/linear_model/svc.rb

@@ -11,13 +11,14 @@ module Rumale
     # with stochastic gradient descent optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
-    # Rumale::SVM provides linear support vector classifier based on LIBLINEAR.
-    # If you prefer execution speed, you should use Rumale::SVM::LinearSVC.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides linear support vector classifier based on LIBLINEAR.
+    #   If you prefer execution speed, you should use Rumale::SVM::LinearSVC.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::SVC.new(reg_param: 1.0, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::SVC.new(reg_param: 1.0, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_labels)
     #   results = estimator.predict(testing_samples)
     #
@@ -74,7 +75,7 @@ module Rumale
       def initialize(learning_rate: 0.01, decay: nil, momentum: 0.9,
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      probability: false,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,

data/lib/rumale/linear_model/svr.rb

@@ -8,13 +8,14 @@ module Rumale
     # SVR is a class that implements Support Vector Regressor
     # with stochastic gradient descent optimization.
     #
-    # Rumale::SVM provides linear and kernel support vector regressor based on LIBLINEAR and LIBSVM.
-    # If you prefer execution speed, you should use Rumale::SVM::LinearSVR.
-    # https://github.com/yoshoku/rumale-svm
+    # @note
+    #   Rumale::SVM provides linear and kernel support vector regressor based on LIBLINEAR and LIBSVM.
+    #   If you prefer execution speed, you should use Rumale::SVM::LinearSVR.
+    #   https://github.com/yoshoku/rumale-svm
     #
     # @example
     #   estimator =
-    #     Rumale::LinearModel::SVR.new(reg_param: 1.0, epsilon: 0.1, max_iter: 200, batch_size: 50, random_seed: 1)
+    #     Rumale::LinearModel::SVR.new(reg_param: 1.0, epsilon: 0.1, max_iter: 1000, batch_size: 50, random_seed: 1)
     #   estimator.fit(training_samples, traininig_target_values)
     #   results = estimator.predict(testing_samples)
     #
@@ -68,7 +69,7 @@ module Rumale
                      penalty: 'l2', reg_param: 1.0, l1_ratio: 0.5,
                      fit_bias: true, bias_scale: 1.0,
                      epsilon: 0.1,
-                     max_iter: 200, batch_size: 50, tol: 1e-4,
+                     max_iter: 1000, batch_size: 50, tol: 1e-4,
                      n_jobs: nil, verbose: false, random_seed: nil)
         check_params_numeric(learning_rate: learning_rate, momentum: momentum,
                              reg_param: reg_param, bias_scale: bias_scale, epsilon: epsilon,

data/lib/rumale/metric_learning/mlkr.rb

@@ -0,0 +1,161 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/transformer'
+require 'rumale/decomposition/pca'
+require 'rumale/pairwise_metric'
+require 'rumale/utils'
+require 'lbfgsb'
+
+module Rumale
+  module MetricLearning
+    # MLKR is a class that implements Metric Learning for Kernel Regression.
+    #
+    # @example
+    #   transformer = Rumale::MetricLearning::MLKR.new
+    #   transformer.fit(training_samples, traininig_target_values)
+    #   low_samples = transformer.transform(testing_samples)
+    #
+    # *Reference*
+    # - Weinberger, K. Q. and Tesauro, G., "Metric Learning for Kernel Regression," Proc. AISTATS'07, pp. 612--629, 2007.
+    class MLKR
+      include Base::BaseEstimator
+      include Base::Transformer
+
+      # Returns the metric components.
+      # @return [Numo::DFloat] (shape: [n_components, n_features])
+      attr_reader :components
+
+      # Return the number of iterations run for optimization
+      # @return [Integer]
+      attr_reader :n_iter
+
+      # Return the random generator.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new transformer with MLKR.
+      #
+      # @param n_components [Integer] The number of components.
+      # @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)
+        check_params_numeric(max_iter: max_iter, tol: tol)
+        check_params_string(init: init)
+        check_params_boolean(verbose: verbose)
+        @params = {}
+        @params[:n_components] = n_components
+        @params[:init] = init
+        @params[:max_iter] = max_iter
+        @params[:tol] = tol
+        @params[:verbose] = verbose
+        @params[:random_seed] = random_seed
+        @params[:random_seed] ||= srand
+        @components = nil
+        @n_iter = nil
+        @rng = Random.new(@params[:random_seed])
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples]) The target values to be used for fitting the model.
+      # @return [MLKR] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+        n_features = x.shape[1]
+        n_components = if @params[:n_components].nil?
+                         n_features
+                       else
+                         [n_features, @params[:n_components]].min
+                       end
+        @components, @n_iter = optimize_components(x, y, n_features, n_components)
+        @prototypes = x.dot(@components.transpose)
+        @values = y
+        self
+      end
+
+      # Fit the model with training data, and then transform them with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples]) The target values to be used for fitting the model.
+      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data
+      def fit_transform(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+        fit(x, y).transform(x)
+      end
+
+      # Transform the given data with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The data to be transformed with the learned model.
+      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
+      def transform(x)
+        x = check_convert_sample_array(x)
+        x.dot(@components.transpose)
+      end
+
+      private
+
+      def init_components(x, n_features, n_components)
+        if @params[:init] == 'pca'
+          pca = Rumale::Decomposition::PCA.new(n_components: n_components)
+          pca.fit(x).components.flatten.dup
+        else
+          Rumale::Utils.rand_normal([n_features, n_components], @rng.dup).flatten.dup
+        end
+      end
+
+      def optimize_components(x, y, n_features, n_components)
+        # initialize components.
+        comp_init = init_components(x, n_features, n_components)
+        # initialize optimization results.
+        res = {}
+        res[:x] = comp_init
+        res[:n_iter] = 0
+        # perform optimization.
+        verbose = @params[:verbose] ? 1 : -1
+        res = Lbfgsb.minimize(
+          fnc: method(:mlkr_fnc), jcb: true, x_init: comp_init, args: [x, y],
+          maxiter: @params[:max_iter], factr: @params[:tol] / Lbfgsb::DBL_EPSILON, verbose: verbose
+        )
+        # 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 mlkr_fnc(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)
+        # predict values.
+        kernel_mat = Numo::NMath.exp(-Rumale::PairwiseMetric.squared_error(z))
+        kernel_mat[kernel_mat.diag_indices] = 0.0
+        norm = kernel_mat.sum(1)
+        norm[norm.eq(0)] = 1
+        y_pred = kernel_mat.dot(y) / norm
+        # calculate loss.
+        y_diff = y_pred - y
+        loss = (y_diff**2).sum
+        # calculate gradient.
+        weight_mat = y_diff * y_diff.expand_dims(1) * kernel_mat
+        weight_mat = weight_mat.sum(0).diag - weight_mat
+        gradient = 8 * z.transpose.dot(weight_mat).dot(x)
+        [loss, gradient.flatten.dup]
+      end
+    end
+  end
+end

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)
@@ -102,17 +104,9 @@ 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, solver: 'evd')
+          pca = Rumale::Decomposition::PCA.new(n_components: n_components)
           pca.fit(x).components.flatten.dup
         else
           Rumale::Utils.rand_normal([n_features, n_components], @rng.dup).flatten.dup
@@ -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/model_selection/time_series_split.rb

@@ -0,0 +1,91 @@
+# frozen_string_literal: true
+
+require 'rumale/base/splitter'
+
+module Rumale
+  module ModelSelection
+    # TimeSeriesSplit is a class that generates the set of data indices for time series cross-validation.
+    # It is assumed that the dataset given are already ordered by time information.
+    #
+    # @example
+    #   cv = Rumale::ModelSelection::TimeSeriesSplit.new(n_splits: 5)
+    #   x = Numo::DFloat.new(6, 2).rand
+    #   cv.split(x, nil).each do |train_ids, test_ids|
+    #     puts '---'
+    #     pp train_ids
+    #     pp test_ids
+    #   end
+    #
+    #   # ---
+    #   # [0]
+    #   # [1]
+    #   # ---
+    #   # [0, 1]
+    #   # [2]
+    #   # ---
+    #   # [0, 1, 2]
+    #   # [3]
+    #   # ---
+    #   # [0, 1, 2, 3]
+    #   # [4]
+    #   # ---
+    #   # [0, 1, 2, 3, 4]
+    #   # [5]
+    #
+    class TimeSeriesSplit
+      include Base::Splitter
+
+      # Return the number of splits.
+      # @return [Integer]
+      attr_reader :n_splits
+
+      # Return the maximum number of training samples in a split.
+      # @return [Integer/Nil]
+      attr_reader :max_train_size
+
+      # Create a new data splitter for time series cross-validation.
+      #
+      # @param n_splits [Integer] The number of splits.
+      # @param max_train_size [Integer/Nil] The maximum number of training samples in a split.
+      def initialize(n_splits: 5, max_train_size: nil)
+        check_params_numeric(n_splits: n_splits)
+        check_params_numeric_or_nil(max_train_size: max_train_size)
+        @n_splits = n_splits
+        @max_train_size = max_train_size
+      end
+
+      # Generate data indices for time series cross-validation.
+      #
+      # @overload split(x, y) -> Array
+      #   @param x [Numo::DFloat] (shape: [n_samples, n_features])
+      #     The dataset to be used to generate data indices for time series cross-validation.
+      #     It is expected that the data will be ordered by time information.
+      #   @param y [Numo::Int32] (shape: [n_samples])
+      #     This argument exists to unify the interface between the K-fold methods, it is not used in the method.
+      # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
+      def split(x, _y)
+        x = check_convert_sample_array(x)
+
+        n_samples = x.shape[0]
+        unless (@n_splits + 1).between?(2, n_samples)
+          raise ArgumentError,
+                'The number of folds (n_splits + 1) must be not less than 2 and not more than the number of samples.'
+        end
+
+        test_size = n_samples / (@n_splits + 1)
+        offset = test_size + n_samples % (@n_splits + 1)
+
+        Array.new(@n_splits) do |n|
+          start = offset * (n + 1)
+          train_ids = if !@max_train_size.nil? && @max_train_size < test_size
+                        Array((start - @max_train_size)...start)
+                      else
+                        Array(0...start)
+                      end
+          test_ids = Array(start...(start + test_size))
+          [train_ids, test_ids]
+        end
+      end
+    end
+  end
+end

data/lib/rumale/pipeline/pipeline.rb

@@ -140,7 +140,7 @@ module Rumale
       def validate_steps(steps)
         steps.keys[0...-1].each do |name|
           transformer = steps[name]
-          next if transformer.nil? || %i[fit transform].all? { |m| transformer.class.method_defined?(m) }
+          next if transformer.nil? || (transformer.class.method_defined?(:fit) && transformer.class.method_defined?(:transform))
 
           raise TypeError,
                 'Class of intermediate step in pipeline should be implemented fit and transform methods: ' \

data/lib/rumale/tree/base_decision_tree.rb

@@ -75,17 +75,10 @@ module Rumale
         node = Node.new(depth: depth, impurity: impurity, n_samples: n_samples)
 
         # terminate growing.
-        unless @params[:max_leaf_nodes].nil?
-          return nil if @n_leaves >= @params[:max_leaf_nodes]
-        end
-
+        return nil if !@params[:max_leaf_nodes].nil? && @n_leaves >= @params[:max_leaf_nodes]
         return nil if n_samples < @params[:min_samples_leaf]
         return put_leaf(node, y) if n_samples == @params[:min_samples_leaf]
-
-        unless @params[:max_depth].nil?
-          return put_leaf(node, y) if depth == @params[:max_depth]
-        end
-
+        return put_leaf(node, y) if !@params[:max_depth].nil? && depth == @params[:max_depth]
         return put_leaf(node, y) if stop_growing?(y)
 
         # calculate optimal parameters.

data/lib/rumale/tree/gradient_tree_regressor.rb

@@ -138,7 +138,7 @@ module Rumale
         nil
       end
 
-      def grow_node(depth, x, y, g, h)
+      def grow_node(depth, x, y, g, h) # rubocop:disable Metrics/AbcSize
         # intialize some variables.
         sum_g = g.sum
         sum_h = h.sum
@@ -146,17 +146,10 @@ module Rumale
         node = Node.new(depth: depth, n_samples: n_samples)
 
         # terminate growing.
-        unless @params[:max_leaf_nodes].nil?
-          return nil if @n_leaves >= @params[:max_leaf_nodes]
-        end
-
+        return nil if !@params[:max_leaf_nodes].nil? && @n_leaves >= @params[:max_leaf_nodes]
         return nil if n_samples < @params[:min_samples_leaf]
         return put_leaf(node, sum_g, sum_h) if n_samples == @params[:min_samples_leaf]
-
-        unless @params[:max_depth].nil?
-          return put_leaf(node, sum_g, sum_h) if depth == @params[:max_depth]
-        end
-
+        return put_leaf(node, sum_g, sum_h) if !@params[:max_depth].nil? && depth == @params[:max_depth]
         return put_leaf(node, sum_g, sum_h) if stop_growing?(y)
 
         # calculate optimal parameters.

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 = '0.20.1'
+  VERSION = '0.22.1'
 end

data/rumale.gemspec

@@ -45,4 +45,5 @@ Gem::Specification.new do |spec|
   }
 
   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: 0.20.1
+  version: 0.22.1
 platform: ruby
 authors:
 - yoshoku
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-08-23 00:00:00.000000000 Z
+date: 2020-12-05 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.
@@ -43,7 +57,7 @@ extensions:
 - ext/rumale/extconf.rb
 extra_rdoc_files: []
 files:
-- ".coveralls.yml"
+- ".github/workflows/build.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
@@ -131,6 +145,7 @@ files:
 - 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
@@ -141,6 +156,7 @@ files:
 - lib/rumale/model_selection/shuffle_split.rb
 - lib/rumale/model_selection/stratified_k_fold.rb
 - lib/rumale/model_selection/stratified_shuffle_split.rb
+- lib/rumale/model_selection/time_series_split.rb
 - lib/rumale/multiclass/one_vs_rest_classifier.rb
 - lib/rumale/naive_bayes/base_naive_bayes.rb
 - lib/rumale/naive_bayes/bernoulli_nb.rb
@@ -208,7 +224,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.1.4
 signing_key:
 specification_version: 4
 summary: Rumale is a machine learning library in Ruby. Rumale provides machine learning

data/.coveralls.yml

@@ -1 +0,0 @@
-service_name: travis-ci