rumale-kernel_machine 0.24.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 6c53bda994de48371ca60e6fb8e957a0f77e96943de0f73d989deeaa9edbcf89
+  data.tar.gz: 6a08ecbfd73f1e9b64a29ffd11114766bebc5b9b8cf8def6325e89528af50b82
+SHA512:
+  metadata.gz: 7a1b192c7e8c31f769d2fef8ccf8be830bf0e129e0249269e807cd9e69f7bed06c8968612515b4d7817de59be4755e713dbf1a0e206b9dc4f6cd55308cf0111e
+  data.tar.gz: cd368663f5f48eca166ac8b3832df2c26e24ac09e64164886bf3815ba308f0cb64fd908768765d126d62d5103ec1edc99adf8a54f1900ee6581bbe5e17a65cb3

data/LICENSE.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2022 Atsushi Tatsuma
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/README.md

@@ -0,0 +1,34 @@
+# Rumale::KernelMachine
+
+[![Gem Version](https://badge.fury.io/rb/rumale-kernel_machine.svg)](https://badge.fury.io/rb/rumale-kernel_machine)
+[![BSD 3-Clause License](https://img.shields.io/badge/License-BSD%203--Clause-orange.svg)](https://github.com/yoshoku/rumale/blob/main/rumale-kernel_machine/LICENSE.txt)
+[![Documentation](https://img.shields.io/badge/api-reference-blue.svg)](https://yoshoku.github.io/rumale/doc/Rumale/KernelMachine.html)
+
+Rumale is a machine learning library in Ruby.
+Rumale::KernelMachine provides kernel method-based algorithms,
+such as Kernel Support Vector Machine, Kernel Principal Componenet Analysis, and Kernel Ridge Regression,
+with Rumale interface.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'rumale-kernel_machine'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install rumale-kernel_machine
+
+## Documentation
+
+- [Rumale API Documentation - KernelMachine](https://yoshoku.github.io/rumale/doc/Rumale/KernelMachine.html)
+
+## License
+
+The gem is available as open source under the terms of the [BSD-3-Clause License](https://opensource.org/licenses/BSD-3-Clause).

data/lib/rumale/kernel_machine/kernel_fda.rb

@@ -0,0 +1,121 @@
+# frozen_string_literal: true
+
+require 'rumale/base/estimator'
+require 'rumale/base/transformer'
+require 'rumale/validation'
+
+module Rumale
+  module KernelMachine
+    # KernelFDA is a class that implements Kernel Fisher Discriminant Analysis.
+    #
+    # @example
+    #   require 'numo/linalg/autoloader'
+    #   require 'rumale/pairwise_metric'
+    #   require 'rumale/kernel_machine/kernel_fda'
+    #
+    #   kernel_mat_train = Rumale::PairwiseMetric::rbf_kernel(x_train)
+    #   kfda = Rumale::KernelMachine::KernelFDA.new
+    #   mapped_traininig_samples = kfda.fit_transform(kernel_mat_train, y)
+    #
+    #   kernel_mat_test = Rumale::PairwiseMetric::rbf_kernel(x_test, x_train)
+    #   mapped_test_samples = kfda.transform(kernel_mat_test)
+    #
+    # *Reference*
+    # - Baudat, G., and Anouar, F., "Generalized Discriminant Analysis using a Kernel Approach," Neural Computation, vol. 12, pp. 2385--2404, 2000.
+    class KernelFDA < ::Rumale::Base::Estimator
+      include ::Rumale::Base::Transformer
+
+      # Returns the eigenvectors for embedding.
+      # @return [Numo::DFloat] (shape: [n_training_sampes, n_components])
+      attr_reader :alphas
+
+      # Create a new transformer with Kernel FDA.
+      #
+      # @param n_components [Integer] The number of components.
+      # @param reg_param [Float] The regularization parameter.
+      def initialize(n_components: nil, reg_param: 1e-8)
+        super()
+        @params = {
+          n_components: n_components,
+          reg_param: reg_param
+        }
+      end
+
+      # Fit the model with given training data.
+      # To execute this method, Numo::Linalg must be loaded.
+      #
+      # @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
+      #   The kernel matrix of the training data to be used for fitting the model.
+      # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
+      # @return [KernelFDA] The learned transformer itself.
+      def fit(x, y)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        y = ::Rumale::Validation.check_convert_label_array(y)
+        ::Rumale::Validation.check_sample_size(x, y)
+        raise ArgumentError, 'Expect the kernel matrix of training data to be square.' unless x.shape[0] == x.shape[1]
+        raise 'KernelFDA#fit requires Numo::Linalg but that is not loaded.' unless enable_linalg?(warning: false)
+
+        # initialize some variables.
+        n_samples = x.shape[0]
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        n_classes = @classes.size
+        n_components = if @params[:n_components].nil?
+                         [n_samples, n_classes - 1].min
+                       else
+                         [n_samples, @params[:n_components]].min
+                       end
+
+        # centering
+        @row_mean = x.mean(0)
+        @all_mean = @row_mean.sum.fdiv(n_samples)
+        centered_kernel_mat = x - x.mean(1).expand_dims(1) - @row_mean + @all_mean
+
+        # calculate between and within scatter matrix.
+        class_mat = Numo::DFloat.zeros(n_samples, n_samples)
+        @classes.each do |label|
+          idx_vec = y.eq(label)
+          class_mat += Numo::DFloat.cast(idx_vec).outer(idx_vec) / idx_vec.count
+        end
+        between_mat = centered_kernel_mat.dot(class_mat).dot(centered_kernel_mat.transpose)
+        within_mat = centered_kernel_mat.dot(centered_kernel_mat.transpose) + @params[:reg_param] * Numo::DFloat.eye(n_samples)
+
+        # calculate projection matrix.
+        _, eig_vecs = Numo::Linalg.eigh(
+          between_mat, within_mat,
+          vals_range: (n_samples - n_components)...n_samples
+        )
+        @alphas = eig_vecs.reverse(1).dup
+        self
+      end
+
+      # Fit the model with training data, and then transform them with the learned model.
+      # To execute this method, Numo::Linalg must be loaded.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_samples])
+      #   The kernel matrix of the training data to be used for fitting the model and transformed.
+      # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
+      # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data
+      def fit_transform(x, y)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        y = ::Rumale::Validation.check_convert_label_array(y)
+        ::Rumale::Validation.check_sample_size(x, y)
+
+        fit(x, y).transform(x)
+      end
+
+      # Transform the given data with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #   The kernel matrix between testing samples and training samples to be transformed.
+      # @return [Numo::DFloat] (shape: [n_testing_samples, n_components]) The transformed data.
+      def transform(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        col_mean = x.sum(axis: 1) / @row_mean.shape[0]
+        centered_kernel_mat = x - col_mean.expand_dims(1) - @row_mean + @all_mean
+        transformed = centered_kernel_mat.dot(@alphas)
+        @params[:n_components] == 1 ? transformed[true, 0].dup : transformed
+      end
+    end
+  end
+end

data/lib/rumale/kernel_machine/kernel_pca.rb

@@ -0,0 +1,98 @@
+# frozen_string_literal: true
+
+require 'rumale/base/estimator'
+require 'rumale/base/transformer'
+require 'rumale/validation'
+
+module Rumale
+  module KernelMachine
+    # KernelPCA is a class that implements Kernel Principal Component Analysis.
+    #
+    # @example
+    #   require 'numo/linalg/autoloader'
+    #   require 'rumale/pairwise_metric'
+    #   require 'rumale/kernel_machine/kernel_pca'
+    #
+    #   kernel_mat_train = Rumale::PairwiseMetric::rbf_kernel(training_samples)
+    #   kpca = Rumale::KernelMachine::KernelPCA.new(n_components: 2)
+    #   mapped_traininig_samples = kpca.fit_transform(kernel_mat_train)
+    #
+    #   kernel_mat_test = Rumale::PairwiseMetric::rbf_kernel(test_samples, training_samples)
+    #   mapped_test_samples = kpca.transform(kernel_mat_test)
+    #
+    # *Reference*
+    # - Scholkopf, B., Smola, A., and Muller, K-R., "Nonlinear Component Analysis as a Kernel Eigenvalue Problem," Neural Computation, Vol. 10 (5), pp. 1299--1319, 1998.
+    class KernelPCA < ::Rumale::Base::Estimator
+      include ::Rumale::Base::Transformer
+
+      # Returns the eigenvalues of the centered kernel matrix.
+      # @return [Numo::DFloat] (shape: [n_components])
+      attr_reader :lambdas
+
+      # Returns the eigenvectors of the centered kernel matrix.
+      # @return [Numo::DFloat] (shape: [n_training_sampes, n_components])
+      attr_reader :alphas
+
+      # Create a new transformer with Kernel PCA.
+      #
+      # @param n_components [Integer] The number of components.
+      def initialize(n_components: 2)
+        super()
+        @params = {
+          n_components: n_components
+        }
+      end
+
+      # Fit the model with given training data.
+      # To execute this method, Numo::Linalg must be loaded.
+      #
+      # @overload fit(x) -> KernelPCA
+      #   @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
+      #     The kernel matrix of the training data to be used for fitting the model.
+      #   @return [KernelPCA] The learned transformer itself.
+      def fit(x, _y = nil)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        raise ArgumentError, 'Expect the kernel matrix of training data to be square.' unless x.shape[0] == x.shape[1]
+        raise 'KernelPCA#fit requires Numo::Linalg but that is not loaded.' unless enable_linalg?(warning: false)
+
+        n_samples = x.shape[0]
+        @row_mean = x.mean(0)
+        @all_mean = @row_mean.sum.fdiv(n_samples)
+        centered_kernel_mat = x - x.mean(1).expand_dims(1) - @row_mean + @all_mean
+        eig_vals, eig_vecs = Numo::Linalg.eigh(centered_kernel_mat,
+                                               vals_range: (n_samples - @params[:n_components])...n_samples)
+        @alphas = eig_vecs.reverse(1).dup
+        @lambdas = eig_vals.reverse.dup
+        @transform_mat = @alphas.dot((1.0 / Numo::NMath.sqrt(@lambdas)).diag)
+        self
+      end
+
+      # Fit the model with training data, and then transform them with the learned model.
+      # To execute this method, Numo::Linalg must be loaded.
+      #
+      # @overload fit_transform(x) -> Numo::DFloat
+      #   @param x [Numo::DFloat] (shape: [n_samples, n_samples])
+      #     The kernel matrix of the training data to be used for fitting the model and transformed.
+      #   @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data
+      def fit_transform(x, _y = nil)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        fit(x).transform(x)
+      end
+
+      # Transform the given data with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #   The kernel matrix between testing samples and training samples to be transformed.
+      # @return [Numo::DFloat] (shape: [n_testing_samples, n_components]) The transformed data.
+      def transform(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        col_mean = x.sum(axis: 1) / @row_mean.shape[0]
+        centered_kernel_mat = x - col_mean.expand_dims(1) - @row_mean + @all_mean
+        transformed = centered_kernel_mat.dot(@transform_mat)
+        @params[:n_components] == 1 ? transformed[true, 0].dup : transformed
+      end
+    end
+  end
+end

data/lib/rumale/kernel_machine/kernel_ridge.rb

@@ -0,0 +1,81 @@
+# frozen_string_literal: true
+
+require 'rumale/base/estimator'
+require 'rumale/base/regressor'
+require 'rumale/validation'
+
+module Rumale
+  module KernelMachine
+    # KernelRidge is a class that implements kernel ridge regression.
+    #
+    # @example
+    #   require 'numo/linalg/autoloader'
+    #   require 'rumale/pairwise_metric'
+    #   require 'rumale/kernel_machine/kernel_ridge'
+    #
+    #   kernel_mat_train = Rumale::PairwiseMetric::rbf_kernel(training_samples)
+    #   kridge = Rumale::KernelMachine::KernelRidge.new(reg_param: 1.0)
+    #   kridge.fit(kernel_mat_train, traininig_values)
+    #
+    #   kernel_mat_test = Rumale::PairwiseMetric::rbf_kernel(test_samples, training_samples)
+    #   results = kridge.predict(kernel_mat_test)
+    class KernelRidge < ::Rumale::Base::Estimator
+      include ::Rumale::Base::Regressor
+
+      # Return the weight vector.
+      # @return [Numo::DFloat] (shape: [n_training_sample, n_outputs])
+      attr_reader :weight_vec
+
+      # Create a new regressor with kernel ridge regression.
+      #
+      # @param reg_param [Float/Numo::DFloat] The regularization parameter.
+      def initialize(reg_param: 1.0)
+        super()
+        @params = {
+          reg_param: reg_param
+        }
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
+      #   The kernel matrix of the training data to be used for fitting the model.
+      # @param y [Numo::DFloat] (shape: [n_samples, n_outputs]) The taget values to be used for fitting the model.
+      # @return [KernelRidge] The learned regressor itself.
+      def fit(x, y)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        y = ::Rumale::Validation.check_convert_target_value_array(y)
+        ::Rumale::Validation.check_sample_size(x, y)
+        raise ArgumentError, 'Expect the kernel matrix of training data to be square.' unless x.shape[0] == x.shape[1]
+        raise 'KernelRidge#fit requires Numo::Linalg but that is not loaded.' unless enable_linalg?(warning: false)
+
+        n_samples = x.shape[0]
+
+        if @params[:reg_param].is_a?(Float)
+          reg_kernel_mat = x + Numo::DFloat.eye(n_samples) * @params[:reg_param]
+          @weight_vec = Numo::Linalg.solve(reg_kernel_mat, y, driver: 'sym')
+        else
+          n_outputs = y.shape[1]
+          @weight_vec = Numo::DFloat.zeros(n_samples, n_outputs)
+          n_outputs.times do |n|
+            reg_kernel_mat = x + Numo::DFloat.eye(n_samples) * @params[:reg_param][n]
+            @weight_vec[true, n] = Numo::Linalg.solve(reg_kernel_mat, y[true, n], driver: 'sym')
+          end
+        end
+
+        self
+      end
+
+      # Predict values for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to predict values.
+      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted values per sample.
+      def predict(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        x.dot(@weight_vec)
+      end
+    end
+  end
+end

data/lib/rumale/kernel_machine/kernel_ridge_classifier.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+require 'rumale/base/estimator'
+require 'rumale/base/classifier'
+require 'rumale/utils'
+require 'rumale/validation'
+
+module Rumale
+  module KernelMachine
+    # KernelRidgeClassifier is a class that implements classifier based-on kernel ridge regression.
+    # It learns a classifier by converting labels to target values { -1, 1 } and performing kernel ridge regression.
+    #
+    # @example
+    #   require 'numo/linalg/autoloader'
+    #   require 'rumale/pairwise_metric'
+    #   require 'rumale/kernel_machine/kernel_ridge_classifier'
+    #
+    #   kernel_mat_train = Rumale::PairwiseMetric::rbf_kernel(training_samples)
+    #   kridge = Rumale::KernelMachine::KernelRidgeClassifier.new(reg_param: 0.5)
+    #   kridge.fit(kernel_mat_train, traininig_values)
+    #
+    #   kernel_mat_test = Rumale::PairwiseMetric::rbf_kernel(test_samples, training_samples)
+    #   results = kridge.predict(kernel_mat_test)
+    class KernelRidgeClassifier < ::Rumale::Base::Estimator
+      include ::Rumale::Base::Classifier
+
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Return the weight vector.
+      # @return [Numo::DFloat] (shape: [n_training_sample, n_classes])
+      attr_reader :weight_vec
+
+      # Create a new regressor with kernel ridge classifier.
+      #
+      # @param reg_param [Float/Numo::DFloat] The regularization parameter.
+      def initialize(reg_param: 1.0)
+        super()
+        @params = {
+          reg_param: reg_param
+        }
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
+      #   The kernel matrix of the training data to be used for fitting the model.
+      # @param y [Numo::Int32] (shape: [n_training_samples]) The labels to be used for fitting the model.
+      # @return [KernelRidgeClassifier] The learned classifier itself.
+      def fit(x, y)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        y = ::Rumale::Validation.check_convert_label_array(y)
+        ::Rumale::Validation.check_sample_size(x, y)
+        raise ArgumentError, 'Expect the kernel matrix of training data to be square.' unless x.shape[0] == x.shape[1]
+        raise 'KernelRidgeClassifier#fit requires Numo::Linalg but that is not loaded.' unless enable_linalg?(warning: false)
+
+        y_encoded = Numo::DFloat.cast(::Rumale::Utils.binarize_labels(y)) * 2 - 1
+        @classes = Numo::NArray[*y.to_a.uniq.sort]
+
+        n_samples = x.shape[0]
+        reg_kernel_mat = x + Numo::DFloat.eye(n_samples) * @params[:reg_param]
+        @weight_vec = Numo::Linalg.solve(reg_kernel_mat, y_encoded, driver: 'sym')
+
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to predict values.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) The confidence score per sample.
+      def decision_function(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        x.dot(@weight_vec)
+      end
+
+      # Predict class labels for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to predict the labels.
+      # @return [Numo::Int32] (shape: [n_testing_samples]) Predicted class label per sample.
+      def predict(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        scores = decision_function(x)
+        n_samples, n_classes = scores.shape
+        label_ids = scores.max_index(axis: 1) - Numo::Int32.new(n_samples).seq * n_classes
+        @classes[label_ids].dup
+      end
+    end
+  end
+end

data/lib/rumale/kernel_machine/kernel_svc.rb

@@ -0,0 +1,187 @@
+# frozen_string_literal: true
+
+require 'rumale/base/estimator'
+require 'rumale/base/classifier'
+require 'rumale/probabilistic_output'
+require 'rumale/validation'
+
+module Rumale
+  module KernelMachine
+    # KernelSVC is a class that implements (Nonlinear) Kernel Support Vector Classifier
+    # with stochastic gradient descent (SGD) optimization.
+    # For multiclass classification problem, it uses one-vs-the-rest strategy.
+    #
+    # @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
+    #   require 'rumale/pairwise_metric'
+    #   require 'rumale/kernel_machine/kernel_svc'
+    #
+    #   training_kernel_matrix = Rumale::PairwiseMetric::rbf_kernel(training_samples)
+    #   estimator =
+    #     Rumale::KernelMachine::KernelSVC.new(reg_param: 1.0, max_iter: 1000, random_seed: 1)
+    #   estimator.fit(training_kernel_matrix, traininig_labels)
+    #   testing_kernel_matrix = Rumale::PairwiseMetric::rbf_kernel(testing_samples, training_samples)
+    #   results = estimator.predict(testing_kernel_matrix)
+    #
+    # *Reference*
+    # - Shalev-Shwartz, S., Singer, Y., Srebro, N., and Cotter, A., "Pegasos: Primal Estimated sub-GrAdient SOlver for SVM," Mathematical Programming, vol. 127 (1), pp. 3--30, 2011.
+    class KernelSVC < ::Rumale::Base::Estimator
+      include ::Rumale::Base::Classifier
+
+      # Return the weight vector for Kernel SVC.
+      # @return [Numo::DFloat] (shape: [n_classes, n_trainig_sample])
+      attr_reader :weight_vec
+
+      # Return the class labels.
+      # @return [Numo::Int32] (shape: [n_classes])
+      attr_reader :classes
+
+      # Return the random generator for performing random sampling.
+      # @return [Random]
+      attr_reader :rng
+
+      # Create a new classifier with Kernel Support Vector Machine by the SGD optimization.
+      #
+      # @param reg_param [Float] The regularization parameter.
+      # @param max_iter [Integer] The maximum number of iterations.
+      # @param probability [Boolean] The flag indicating whether to perform probability estimation.
+      # @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.
+      # @param random_seed [Integer] The seed value using to initialize the random generator.
+      def initialize(reg_param: 1.0, max_iter: 1000, probability: false, n_jobs: nil, random_seed: nil)
+        super()
+        @params = {
+          reg_param: reg_param,
+          max_iter: max_iter,
+          probability: probability,
+          n_jobs: n_jobs,
+          random_seed: (random_seed || srand)
+        }
+        @rng = Random.new(@params[:random_seed])
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_training_samples, n_training_samples])
+      #   The kernel matrix of the training data to be used for fitting the model.
+      # @param y [Numo::Int32] (shape: [n_training_samples]) The labels to be used for fitting the model.
+      # @return [KernelSVC] The learned classifier itself.
+      def fit(x, y)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+        y = ::Rumale::Validation.check_convert_label_array(y)
+        ::Rumale::Validation.check_sample_size(x, y)
+
+        @classes = Numo::Int32[*y.to_a.uniq.sort]
+        n_classes = @classes.size
+        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)
+          models = if enable_parallel?
+                     parallel_map(n_classes) do |n|
+                       bin_y = Numo::Int32.cast(y.eq(@classes[n])) * 2 - 1
+                       partial_fit(x, bin_y)
+                     end
+                   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, @prob_param = partial_fit(x, bin_y)
+        end
+
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_testing_samples, n_classes]) Confidence score per sample.
+      def decision_function(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        x.dot(@weight_vec.transpose)
+      end
+
+      # Predict class labels for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to predict the labels.
+      # @return [Numo::Int32] (shape: [n_testing_samples]) Predicted class label per sample.
+      def predict(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        return Numo::Int32.cast(decision_function(x).ge(0.0)) * 2 - 1 if @classes.size <= 2
+
+        n_samples, = x.shape
+        decision_values = decision_function(x)
+        predicted = if enable_parallel?
+                      parallel_map(n_samples) { |n| @classes[decision_values[n, true].max_index] }
+                    else
+                      Array.new(n_samples) { |n| @classes[decision_values[n, true].max_index] }
+                    end
+        Numo::Int32.asarray(predicted)
+      end
+
+      # Predict probability for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_testing_samples, n_training_samples])
+      #     The kernel matrix between testing samples and training samples to predict the labels.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
+      def predict_proba(x)
+        x = ::Rumale::Validation.check_convert_sample_array(x)
+
+        if @classes.size > 2
+          probs = 1.0 / (Numo::NMath.exp(@prob_param[true, 0] * decision_function(x) + @prob_param[true, 1]) + 1.0)
+          return (probs.transpose / probs.sum(axis: 1)).transpose.dup
+        end
+
+        n_samples, = x.shape
+        probs = Numo::DFloat.zeros(n_samples, 2)
+        probs[true, 1] = 1.0 / (Numo::NMath.exp(@prob_param[0] * decision_function(x) + @prob_param[1]) + 1.0)
+        probs[true, 0] = 1.0 - probs[true, 1]
+        probs
+      end
+
+      private
+
+      def partial_fit(x, bin_y)
+        # Initialize some variables.
+        n_training_samples = x.shape[0]
+        rand_ids = []
+        weight_vec = Numo::DFloat.zeros(n_training_samples)
+        sub_rng = @rng.dup
+        # Start optimization.
+        @params[:max_iter].times do |t|
+          # random sampling
+          rand_ids = Array(0...n_training_samples).shuffle(random: sub_rng) if rand_ids.empty?
+          target_id = rand_ids.shift
+          # update the weight vector
+          func = (weight_vec * bin_y).dot(x[target_id, true].transpose).to_f
+          func *= bin_y[target_id] / (@params[:reg_param] * (t + 1))
+          weight_vec[target_id] += 1.0 if func < 1.0
+        end
+        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
+end

data/lib/rumale/kernel_machine/version.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+# Rumale is a machine learning library in Ruby.
+module Rumale
+  # This module consists of the classes that implement kernel method-based estimator.
+  module KernelMachine
+    # @!visibility private
+    VERSION = '0.24.0'
+  end
+end

data/lib/rumale/kernel_machine.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require 'numo/narray'
+
+require_relative 'kernel_machine/kernel_fda'
+require_relative 'kernel_machine/kernel_pca'
+require_relative 'kernel_machine/kernel_ridge'
+require_relative 'kernel_machine/kernel_ridge_classifier'
+require_relative 'kernel_machine/kernel_svc'
+require_relative 'kernel_machine/version'

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: rumale-kernel_machine
+version: !ruby/object:Gem::Version
+  version: 0.24.0
+platform: ruby
+authors:
+- yoshoku
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2022-12-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: numo-narray
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.1
+- !ruby/object:Gem::Dependency
+  name: rumale-core
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.24.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.24.0
+description: |
+  Rumale::KernelMachine provides kernel method-based algorithms,
+  such as Kernel Support Vector Machine, Kernel Principal Componenet Analysis, and Kernel Ridge Regression,
+  with Rumale interface.
+email:
+- yoshoku@outlook.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE.txt
+- README.md
+- lib/rumale/kernel_machine.rb
+- lib/rumale/kernel_machine/kernel_fda.rb
+- lib/rumale/kernel_machine/kernel_pca.rb
+- lib/rumale/kernel_machine/kernel_ridge.rb
+- lib/rumale/kernel_machine/kernel_ridge_classifier.rb
+- lib/rumale/kernel_machine/kernel_svc.rb
+- lib/rumale/kernel_machine/version.rb
+homepage: https://github.com/yoshoku/rumale
+licenses:
+- BSD-3-Clause
+metadata:
+  homepage_uri: https://github.com/yoshoku/rumale
+  source_code_uri: https://github.com/yoshoku/rumale/tree/main/rumale-kernel_machine
+  changelog_uri: https://github.com/yoshoku/rumale/blob/main/CHANGELOG.md
+  documentation_uri: https://yoshoku.github.io/rumale/doc/
+  rubygems_mfa_required: 'true'
+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: []
+rubygems_version: 3.3.26
+signing_key:
+specification_version: 4
+summary: Rumale::KernelMachine provides kernel method-based algorithms with Rumale
+  interface.
+test_files: []