rumale 0.22.2 → 0.23.1

data/ext/rumale/tree.h

@@ -3,7 +3,9 @@
 
 #include <math.h>
 #include <string.h>
+
 #include <ruby.h>
+
 #include <numo/narray.h>
 #include <numo/template.h>
 

data/lib/rumale.rb

@@ -2,7 +2,7 @@
 
 require 'numo/narray'
 
-require 'rumale/rumale'
+require 'rumale/rumaleext'
 
 require 'rumale/version'
 require 'rumale/validation'
@@ -30,10 +30,12 @@ require 'rumale/linear_model/linear_regression'
 require 'rumale/linear_model/ridge'
 require 'rumale/linear_model/lasso'
 require 'rumale/linear_model/elastic_net'
+require 'rumale/linear_model/nnls'
 require 'rumale/kernel_machine/kernel_svc'
 require 'rumale/kernel_machine/kernel_pca'
 require 'rumale/kernel_machine/kernel_fda'
 require 'rumale/kernel_machine/kernel_ridge'
+require 'rumale/kernel_machine/kernel_ridge_classifier'
 require 'rumale/multiclass/one_vs_rest_classifier'
 require 'rumale/nearest_neighbors/vp_tree'
 require 'rumale/nearest_neighbors/k_neighbors_classifier'
@@ -61,6 +63,8 @@ require 'rumale/ensemble/extra_trees_classifier'
 require 'rumale/ensemble/extra_trees_regressor'
 require 'rumale/ensemble/stacking_classifier'
 require 'rumale/ensemble/stacking_regressor'
+require 'rumale/ensemble/voting_classifier'
+require 'rumale/ensemble/voting_regressor'
 require 'rumale/clustering/k_means'
 require 'rumale/clustering/mini_batch_k_means'
 require 'rumale/clustering/k_medoids'
@@ -100,6 +104,7 @@ require 'rumale/preprocessing/one_hot_encoder'
 require 'rumale/preprocessing/ordinal_encoder'
 require 'rumale/preprocessing/binarizer'
 require 'rumale/preprocessing/polynomial_features'
+require 'rumale/preprocessing/kernel_calculator'
 require 'rumale/model_selection/k_fold'
 require 'rumale/model_selection/group_k_fold'
 require 'rumale/model_selection/stratified_k_fold'

data/lib/rumale/base/base_estimator.rb

@@ -11,13 +11,15 @@ module Rumale
 
       private
 
-      def enable_linalg?
+      def enable_linalg?(warning: true)
         if defined?(Numo::Linalg).nil?
-          warn('If you want to use features that depend on Numo::Linalg, you should install and load Numo::Linalg in advance.')
+          warn('If you want to use features that depend on Numo::Linalg, you should install and load Numo::Linalg in advance.') if warning
           return false
         end
         if Numo::Linalg::VERSION < '0.1.4'
-          warn('The loaded Numo::Linalg does not implement the methods required by Rumale. Please load Numo::Linalg version 0.1.4 or later.')
+          if warning
+            warn('The loaded Numo::Linalg does not implement the methods required by Rumale. Please load Numo::Linalg version 0.1.4 or later.')
+          end
           return false
         end
         true

data/lib/rumale/dataset.rb

@@ -12,22 +12,26 @@ module Rumale
       # Load a dataset with the libsvm file format into Numo::NArray.
       #
       # @param filename [String] A path to a dataset file.
+      # @param n_features [Integer/Nil] The number of features of data to load.
+      #   If nil is given, it will be detected automatically from given file.
       # @param zero_based [Boolean] Whether the column index starts from 0 (true) or 1 (false).
       # @param dtype [Numo::NArray] Data type of Numo::NArray for features to be loaded.
       #
       # @return [Array<Numo::NArray>]
       #   Returns array containing the (n_samples x n_features) matrix for feature vectors
       #   and (n_samples) vector for labels or target values.
-      def load_libsvm_file(filename, zero_based: false, dtype: Numo::DFloat)
+      def load_libsvm_file(filename, n_features: nil, zero_based: false, dtype: Numo::DFloat)
         ftvecs = []
         labels = []
-        n_features = 0
+        n_features_detected = 0
         CSV.foreach(filename, col_sep: "\s", headers: false) do |line|
           label, ftvec, max_idx = parse_libsvm_line(line, zero_based)
           labels.push(label)
           ftvecs.push(ftvec)
-          n_features = max_idx if n_features < max_idx
+          n_features_detected = max_idx if n_features_detected < max_idx
         end
+        n_features ||= n_features_detected
+        n_features = [n_features, n_features_detected].max
         [convert_to_matrix(ftvecs, n_features, dtype), Numo::NArray.asarray(labels)]
       end
 

data/lib/rumale/decomposition/fast_ica.rb

@@ -81,7 +81,7 @@ module Rumale
         wx = @params[:whiten] ? (x - @mean).dot(whiten_mat.transpose) : x
         unmixing, @n_iter = ica(wx, @params[:fun], @params[:max_iter], @params[:tol], @rng.dup)
         @components = @params[:whiten] ? unmixing.dot(whiten_mat) : unmixing
-        @mixing = Numo::Linalg.pinv(@components)
+        @mixing = Numo::Linalg.pinv(@components).dup
         if @params[:n_components] == 1
           @components = @components.flatten.dup
           @mixing = @mixing.flatten.dup

data/lib/rumale/ensemble/gradient_boosting_classifier.rb

@@ -161,7 +161,7 @@ module Rumale
 
         proba = 1.0 / (Numo::NMath.exp(-decision_function(x)) + 1.0)
 
-        return (proba.transpose / proba.sum(axis: 1)).transpose if @classes.size > 2
+        return (proba.transpose / proba.sum(axis: 1)).transpose.dup if @classes.size > 2
 
         n_samples, = x.shape
         probs = Numo::DFloat.zeros(n_samples, 2)
@@ -182,7 +182,7 @@ module Rumale
                    else
                      @estimators.map { |tree| tree.apply(x) }
                    end
-        Numo::Int32[*leaf_ids].transpose
+        Numo::Int32[*leaf_ids].transpose.dup
       end
 
       private

data/lib/rumale/ensemble/gradient_boosting_regressor.rb

@@ -144,7 +144,7 @@ module Rumale
                    else
                      @estimators.map { |tree| tree.apply(x) }
                    end
-        Numo::Int32[*leaf_ids].transpose
+        Numo::Int32[*leaf_ids].transpose.dup
       end
 
       private

data/lib/rumale/ensemble/random_forest_classifier.rb

@@ -159,7 +159,7 @@ module Rumale
       # @return [Numo::Int32] (shape: [n_samples, n_estimators]) Leaf index for sample.
       def apply(x)
         x = check_convert_sample_array(x)
-        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose
+        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose.dup
       end
 
       private

data/lib/rumale/ensemble/random_forest_regressor.rb

@@ -136,7 +136,7 @@ module Rumale
       # @return [Numo::Int32] (shape: [n_samples, n_estimators]) Leaf index for sample.
       def apply(x)
         x = check_convert_sample_array(x)
-        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose
+        Numo::Int32[*Array.new(@params[:n_estimators]) { |n| @estimators[n].apply(x) }].transpose.dup
       end
 
       private

data/lib/rumale/ensemble/stacking_classifier.rb

@@ -2,6 +2,7 @@
 
 require 'rumale/base/base_estimator'
 require 'rumale/base/classifier'
+require 'rumale/preprocessing/label_encoder'
 
 module Rumale
   module Ensemble
@@ -10,18 +11,18 @@ module Rumale
     # @example
     #   estimators = {
     #     lgr: Rumale::LinearModel::LogisticRegression.new(reg_param: 1e-2, random_seed: 1),
-    #     mlp: Rumele::NeuralNetwork::MLPClassifier.new(hidden_units: [256], random_seed: 1),
+    #     mlp: Rumale::NeuralNetwork::MLPClassifier.new(hidden_units: [256], random_seed: 1),
     #     rnd: Rumale::Ensemble::RandomForestClassifier.new(random_seed: 1)
     #   }
     #   meta_estimator = Rumale::LinearModel::LogisticRegression.new(random_seed: 1)
     #   classifier = Rumale::Ensemble::StackedClassifier.new(
     #     estimators: estimators, meta_estimator: meta_estimator, random_seed: 1
     #   )
-    #   classifier.fit(training_samples, traininig_labels)
+    #   classifier.fit(training_samples, training_labels)
     #   results = classifier.predict(testing_samples)
     #
     # *Reference*
-    # - Zhou, Z-H., "Ensemble Mehotds - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
+    # - Zhou, Z-H., "Ensemble Methods - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
     class StackingClassifier
       include Base::BaseEstimator
       include Base::Classifier
@@ -149,7 +150,7 @@ module Rumale
 
       # Predict probability for samples.
       #
-      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the probailities.
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the probabilities.
       # @return [Numo::DFloat] (shape: [n_samples, n_classes]) The predicted probability of each class per sample.
       def predict_proba(x)
         x = check_convert_sample_array(x)

data/lib/rumale/ensemble/stacking_regressor.rb

@@ -10,18 +10,18 @@ module Rumale
     # @example
     #   estimators = {
     #     las: Rumale::LinearModel::Lasso.new(reg_param: 1e-2, random_seed: 1),
-    #     mlp: Rumele::NeuralNetwork::MLPRegressor.new(hidden_units: [256], random_seed: 1),
+    #     mlp: Rumale::NeuralNetwork::MLPRegressor.new(hidden_units: [256], random_seed: 1),
     #     rnd: Rumale::Ensemble::RandomForestRegressor.new(random_seed: 1)
     #   }
     #   meta_estimator = Rumale::LinearModel::Ridge.new(random_seed: 1)
     #   regressor = Rumale::Ensemble::StackedRegressor.new(
     #     estimators: estimators, meta_estimator: meta_estimator, random_seed: 1
     #   )
-    #   regressor.fit(training_samples, traininig_values)
+    #   regressor.fit(training_samples, training_values)
     #   results = regressor.predict(testing_samples)
     #
     # *Reference*
-    # - Zhou, Z-H., "Ensemble Mehotds - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
+    # - Zhou, Z-H., "Ensemble Methods - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
     class StackingRegressor
       include Base::BaseEstimator
       include Base::Regressor

data/lib/rumale/ensemble/voting_classifier.rb

@@ -0,0 +1,126 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/classifier'
+require 'rumale/preprocessing/label_encoder'
+
+module Rumale
+  module Ensemble
+    # VotingClassifier is a class that implements classifier with voting ensemble method.
+    #
+    # @example
+    #   estimators = {
+    #     lgr: Rumale::LinearModel::LogisticRegression.new(reg_param: 1e-2, random_seed: 1),
+    #     mlp: Rumale::NeuralNetwork::MLPClassifier.new(hidden_units: [256], random_seed: 1),
+    #     rnd: Rumale::Ensemble::RandomForestClassifier.new(random_seed: 1)
+    #   }
+    #   weights = { lgr: 0.2, mlp: 0.3, rnd: 0.5 }
+    #
+    #   classifier = Rumale::Ensemble::VotingClassifier.new(estimators: estimators, weights: weights, voting: 'soft')
+    #   classifier.fit(x_train, y_train)
+    #   results = classifier.predict(x_test)
+    #
+    # *Reference*
+    # - Zhou, Z-H., "Ensemble Methods - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
+    class VotingClassifier
+      include Base::BaseEstimator
+      include Base::Classifier
+
+      # Return the sub-classifiers that voted.
+      # @return [Hash<Symbol,Classifier>]
+      attr_reader :estimators
+
+      # Return the class labels.
+      # @return [Numo::Int32] (size: n_classes)
+      attr_reader :classes
+
+      # Create a new ensembled classifier with voting rule.
+      #
+      # @param estimators [Hash<Symbol,Classifier>] The sub-classifiers to vote.
+      # @param weights [Hash<Symbol,Float>] The weight value for each classifier.
+      # @param voting [String] The voting rule for the predicted results of each classifier.
+      #   If 'hard' is given, the ensembled classifier predicts the class label by majority vote.
+      #   If 'soft' is given, the ensembled classifier uses the weighted average of predicted probabilities for the prediction.
+      def initialize(estimators:, weights: nil, voting: 'hard')
+        check_params_type(Hash, estimators: estimators)
+        check_params_type_or_nil(Hash, weights: weights)
+        check_params_string(voting: voting)
+        @estimators = estimators
+        @classes = nil
+        @params = {}
+        @params[:weights] = weights || estimators.each_key.with_object({}) { |name, w| w[name] = 1.0 }
+        @params[:voting] = voting
+      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::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
+      # @return [VotingClassifier] The learned classifier itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_label_array(y)
+        check_sample_label_size(x, y)
+
+        @encoder = Rumale::Preprocessing::LabelEncoder.new
+        y_encoded = @encoder.fit_transform(y)
+        @classes = Numo::NArray[*@encoder.classes]
+        @estimators.each_key { |name| @estimators[name].fit(x, y_encoded) }
+
+        self
+      end
+
+      # Calculate confidence scores for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) The confidence score per sample.
+      def decision_function(x)
+        x = check_convert_sample_array(x)
+        return predict_proba(x) if soft_voting?
+
+        n_samples = x.shape[0]
+        n_classes = @classes.size
+        z = Numo::DFloat.zeros(n_samples, n_classes)
+        @estimators.each do |name, estimator|
+          estimator.predict(x).to_a.each_with_index { |c, i| z[i, c] += @params[:weights][name] }
+        end
+        z
+      end
+
+      # Predict class labels for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the labels.
+      # @return [Numo::Int32] (shape: [n_samples]) The predicted class label per sample.
+      def predict(x)
+        x = check_convert_sample_array(x)
+        n_samples = x.shape[0]
+        n_classes = @classes.size
+        z = decision_function(x)
+        predicted = z.max_index(axis: 1) - Numo::Int32.new(n_samples).seq * n_classes
+        Numo::Int32.cast(@encoder.inverse_transform(predicted))
+      end
+
+      # Predict probability for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the probabilities.
+      # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
+      def predict_proba(x)
+        x = check_convert_sample_array(x)
+        n_samples = x.shape[0]
+        n_classes = @classes.size
+        z = Numo::DFloat.zeros(n_samples, n_classes)
+        sum_weight = @params[:weights].each_value.inject(&:+)
+        @estimators.each do |name, estimator|
+          z += @params[:weights][name] * estimator.predict_proba(x)
+        end
+        z /= sum_weight
+      end
+
+      private
+
+      def soft_voting?
+        @params[:voting] == 'soft'
+      end
+    end
+  end
+end

data/lib/rumale/ensemble/voting_regressor.rb

@@ -0,0 +1,82 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/regressor'
+
+module Rumale
+  module Ensemble
+    # VotingRegressor is a class that implements regressor with voting ensemble method.
+    #
+    # @example
+    #   estimators = {
+    #     rdg: Rumale::LinearModel::Ridge.new(reg_param: 1e-2, random_seed: 1),
+    #     mlp: Rumale::NeuralNetwork::MLPRegressor.new(hidden_units: [256], random_seed: 1),
+    #     rnd: Rumale::Ensemble::RandomForestRegressor.new(random_seed: 1)
+    #   }
+    #   weights = { rdg: 0.2, mlp: 0.3, rnd: 0.5 }
+    #
+    #   regressor = Rumale::Ensemble::VotingRegressor.new(estimators: estimators, weights: weights, voting: 'soft')
+    #   regressor.fit(x_train, y_train)
+    #   results = regressor.predict(x_test)
+    #
+    # *Reference*
+    # - Zhou, Z-H., "Ensemble Methods - Foundations and Algorithms," CRC Press Taylor and Francis Group, Chapman and Hall/CRC, 2012.
+    class VotingRegressor
+      include Base::BaseEstimator
+      include Base::Regressor
+
+      # Return the sub-regressors that voted.
+      # @return [Hash<Symbol,Regressor>]
+      attr_reader :estimators
+
+      # Create a new ensembled regressor with voting rule.
+      #
+      # @param estimators [Hash<Symbol,Regressor>] The sub-regressors to vote.
+      # @param weights [Hash<Symbol,Float>] The weight value for each regressor.
+      def initialize(estimators:, weights: nil)
+        check_params_type(Hash, estimators: estimators)
+        check_params_type_or_nil(Hash, weights: weights)
+        @estimators = estimators
+        @n_outputs = nil
+        @params = {}
+        @params[:weights] = weights || estimators.each_key.with_object({}) { |name, w| w[name] = 1.0 }
+      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::Int32] (shape: [n_samples]) The labels to be used for fitting the model.
+      # @return [VotingRegressor] The learned regressor itself.
+      def fit(x, y)
+        x = check_convert_sample_array(x)
+        y = check_convert_tvalue_array(y)
+        check_sample_tvalue_size(x, y)
+
+        @n_outputs = y.ndim > 1 ? y.shape[1] : 1
+        @estimators.each_key { |name| @estimators[name].fit(x, y) }
+
+        self
+      end
+
+      # Predict values for samples.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the values.
+      # @return [Numo::DFloat] (shape: [n_samples, n_outputs]) Predicted value per sample.
+      def predict(x)
+        x = check_convert_sample_array(x)
+        z = single_target? ? Numo::DFloat.zeros(x.shape[0]) : Numo::DFloat.zeros(x.shape[0], @n_outputs)
+        sum_weight = @params[:weights].each_value.inject(&:+)
+        @estimators.each do |name, estimator|
+          z += @params[:weights][name] * estimator.predict(x)
+        end
+        z / sum_weight
+      end
+
+      private
+
+      def single_target?
+        @n_outputs == 1
+      end
+    end
+  end
+end

data/lib/rumale/kernel_approximation/nystroem.rb

@@ -11,7 +11,7 @@ module Rumale
     # @example
     #   require 'numo/linalg/autoloader'
     #
-    #   transformer = Rumale::KernelApproximation::Nystroem.new(gamma: 1, n_components: 128, random_seed: 1)
+    #   transformer = Rumale::KernelApproximation::Nystroem.new(kernel: 'rbf', gamma: 1, n_components: 128, random_seed: 1)
     #   new_training_samples = transformer.fit_transform(training_samples)
     #   new_testing_samples = transformer.transform(testing_samples)
     #
@@ -39,12 +39,15 @@ module Rumale
 
       # Create a new transformer for mapping to kernel feature space with Nystrom method.
       #
-      # @param kernel [String] The type of kernel. This parameter is ignored in the current implementation.
-      # @param gamma [Float] The parameter of RBF kernel: exp(-gamma * x^2).
-      # @param n_components [Integer] The number of dimensions of the RBF kernel feature space.
+      # @param kernel [String] The type of kernel function ('rbf', 'linear', 'poly', and 'sigmoid)
+      # @param gamma [Float] The gamma parameter in rbf/poly/sigmoid kernel function.
+      # @param degree [Integer] The degree parameter in polynomial kernel function.
+      # @param coef [Float] The coefficient in poly/sigmoid kernel function.
+      # @param n_components [Integer] The number of dimensions of the kernel feature space.
       # @param random_seed [Integer] The seed value using to initialize the random generator.
-      def initialize(kernel: 'rbf', gamma: 1, n_components: 100, random_seed: nil)
-        check_params_numeric(gamma: gamma, n_components: n_components)
+      def initialize(kernel: 'rbf', gamma: 1, degree: 3, coef: 1, n_components: 100, random_seed: nil)
+        check_params_string(kernel: kernel)
+        check_params_numeric(gamma: gamma, coef: coef, degree: degree, n_components: n_components)
         check_params_numeric_or_nil(random_seed: random_seed)
         @params = method(:initialize).parameters.map { |_t, arg| [arg, binding.local_variable_get(arg)] }.to_h
         @params[:random_seed] ||= srand
@@ -56,7 +59,7 @@ module Rumale
 
       # Fit the model with given training data.
       #
-      # @overload fit(x) -> RBF
+      # @overload fit(x) -> Nystroem
       #   @param x [Numo::NArray] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
       # @return [Nystroem] The learned transformer itself.
       def fit(x, _y = nil)
@@ -70,10 +73,10 @@ module Rumale
 
         # random sampling.
         @component_indices = Numo::Int32.cast(Array(0...n_samples).shuffle(random: sub_rng)[0...n_components])
-        @components = x[@component_indices, true]
+        @components = x[@component_indices, true].dup
 
         # calculate normalizing factor.
-        kernel_mat = Rumale::PairwiseMetric.rbf_kernel(@components, nil, @params[:gamma])
+        kernel_mat = kernel_mat(@components)
         eig_vals, eig_vecs = Numo::Linalg.eigh(kernel_mat)
         la = eig_vals.class.maximum(eig_vals.reverse, 1e-12)
         u = eig_vecs.reverse(1)
@@ -98,9 +101,26 @@ module Rumale
       # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
       def transform(x)
         x = check_convert_sample_array(x)
-        z = Rumale::PairwiseMetric.rbf_kernel(x, @components, @params[:gamma])
+        z = kernel_mat(x, @components)
         z.dot(@normalizer)
       end
+
+      private
+
+      def kernel_mat(x, y = nil)
+        case @params[:kernel]
+        when 'rbf'
+          Rumale::PairwiseMetric.rbf_kernel(x, y, @params[:gamma])
+        when 'poly'
+          Rumale::PairwiseMetric.polynomial_kernel(x, y, @params[:degree], @params[:gamma], @params[:coef])
+        when 'sigmoid'
+          Rumale::PairwiseMetric.sigmoid_kernel(x, y, @params[:gamma], @params[:coef])
+        when 'linear'
+          Rumale::PairwiseMetric.linear_kernel(x, y)
+        else
+          raise ArgumentError, "Expect kernel parameter to be given 'rbf', 'linear', 'poly', or 'sigmoid'."
+        end
+      end
     end
   end
 end