rumale 0.18.5 → 0.19.2

data/lib/rumale/model_selection/grid_search_cv.rb

@@ -156,6 +156,7 @@ module Rumale
 
       def valid_param_grid(grid)
         raise TypeError, 'Expect class of param_grid to be Hash or Array' unless grid.is_a?(Hash) || grid.is_a?(Array)
+
         grid = [grid] if grid.is_a?(Hash)
         grid.each do |h|
           raise TypeError, 'Expect class of elements in param_grid to be Hash' unless h.is_a?(Hash)

data/lib/rumale/naive_bayes/bernoulli_nb.rb

@@ -12,7 +12,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    # - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
     class BernoulliNB < BaseNaiveBayes
       # Return the class labels.
       # @return [Numo::Int32] (size: n_classes)

data/lib/rumale/naive_bayes/multinomial_nb.rb

@@ -12,7 +12,7 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - C D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press., 2008.
+    # - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
     class MultinomialNB < BaseNaiveBayes
       # Return the class labels.
       # @return [Numo::Int32] (size: n_classes)

data/lib/rumale/nearest_neighbors/k_neighbors_classifier.rb

@@ -67,6 +67,7 @@ module Rumale
         y = check_convert_label_array(y)
         check_sample_label_size(x, y)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         @prototypes = if @params[:metric] == 'euclidean'
                         if @params[:algorithm] == 'vptree'
                           VPTree.new(x)

data/lib/rumale/nearest_neighbors/k_neighbors_regressor.rb

@@ -61,6 +61,7 @@ module Rumale
         y = check_convert_tvalue_array(y)
         check_sample_tvalue_size(x, y)
         raise ArgumentError, 'Expect the input distance matrix to be square.' if @params[:metric] == 'precomputed' && x.shape[0] != x.shape[1]
+
         @prototypes = if @params[:metric] == 'euclidean'
                         if @params[:algorithm] == 'vptree'
                           VPTree.new(x)
@@ -82,6 +83,7 @@ module Rumale
         if @params[:metric] == 'precomputed' && x.shape[1] != @values.shape[0]
           raise ArgumentError, 'Expect the size input matrix to be n_testing_samples-by-n_training_samples.'
         end
+
         # Initialize some variables.
         n_samples = x.shape[0]
         n_prototypes, n_outputs = @values.shape

data/lib/rumale/nearest_neighbors/vp_tree.rb

@@ -11,7 +11,7 @@ module Rumale
     # This class is used internally for k-nearest neighbor estimators.
     #
     # *Reference*
-    # P N. Yianilos, "Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces," Proc. SODA'93, pp. 311--321, 1993.
+    # - Yianilos, P N., "Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces," Proc. SODA'93, pp. 311--321, 1993.
     class VPTree
       include Validation
       include Base::BaseEstimator

data/lib/rumale/neural_network/adam.rb

@@ -11,7 +11,7 @@ module Rumale
       # Adam is a class that implements Adam optimizer.
       #
       # *Reference*
-      # - D P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," Proc. ICLR'15, 2015.
+      # - Kingma, D P., and Ba, J., "Adam: A Method for Stochastic Optimization," Proc. ICLR'15, 2015.
       class Adam
         include Base::BaseEstimator
 
@@ -32,7 +32,7 @@ module Rumale
         end
 
         # @!visibility private
-        # Calculate the updated weight with Nadam adaptive learning rate.
+        # Calculate the updated weight with Adam adaptive learning rate.
         #
         # @param weight [Numo::DFloat] (shape: [n_features]) The weight to be updated.
         # @param gradient [Numo::DFloat] (shape: [n_features]) The gradient for updating the weight.

data/lib/rumale/neural_network/base_mlp.rb

@@ -233,6 +233,7 @@ module Rumale
             # calc loss function
             loss, dout = loss_func.call(out, sub_y)
             break if loss < @params[:tol]
+
             # backward
             backward.call(dout)
           end

data/lib/rumale/optimizer/ada_grad.rb

@@ -7,8 +7,10 @@ module Rumale
   module Optimizer
     # AdaGrad is a class that implements AdaGrad optimizer.
     #
+    # @deprecated AdaGrad will be deleted in version 0.20.0.
+    #
     # *Reference*
-    # - J. Duchi, E Hazan, and Y. Singer, "Adaptive Subgradient Methods for Online Learning and Stochastic Optimization," J. Machine Learning Research, vol. 12, pp. 2121--2159, 2011.
+    # - Duchi, J., Hazan, E., and Singer, Y., "Adaptive Subgradient Methods for Online Learning and Stochastic Optimization," J. Machine Learning Research, vol. 12, pp. 2121--2159, 2011.
     class AdaGrad
       include Base::BaseEstimator
       include Validation
@@ -17,6 +19,7 @@ module Rumale
       #
       # @param learning_rate [Float] The initial value of learning rate.
       def initialize(learning_rate: 0.01)
+        warn 'warning: AdaGrad is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate)
         check_params_positive(learning_rate: learning_rate)
         @params = {}

data/lib/rumale/optimizer/adam.rb

@@ -7,8 +7,10 @@ module Rumale
   module Optimizer
     # Adam is a class that implements Adam optimizer.
     #
+    # @deprecated Adam will be deleted in version 0.20.0.
+    #
     # *Reference*
-    # - D P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," Proc. ICLR'15, 2015.
+    # - Kingma, D P., and Ba, J., "Adam: A Method for Stochastic Optimization," Proc. ICLR'15, 2015.
     class Adam
       include Base::BaseEstimator
       include Validation
@@ -19,6 +21,7 @@ module Rumale
       # @param decay1 [Float] The smoothing parameter for the first moment.
       # @param decay2 [Float] The smoothing parameter for the second moment.
       def initialize(learning_rate: 0.001, decay1: 0.9, decay2: 0.999)
+        warn 'warning: Adam is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate, decay1: decay1, decay2: decay2)
         check_params_positive(learning_rate: learning_rate, decay1: decay1, decay2: decay2)
         @params = {}

data/lib/rumale/optimizer/nadam.rb

@@ -5,11 +5,15 @@ require 'rumale/base/base_estimator'
 
 module Rumale
   # This module consists of the classes that implement optimizers adaptively tuning hyperparameters.
+  #
+  # @deprecated Optimizer module will be deleted in version 0.20.0.
   module Optimizer
     # Nadam is a class that implements Nadam optimizer.
     #
+    # @deprecated Nadam will be deleted in version 0.20.0.
+    #
     # *Reference*
-    # - T. Dozat, "Incorporating Nesterov Momentum into Adam," Tech. Repo. Stanford University, 2015.
+    # - Dozat, T., "Incorporating Nesterov Momentum into Adam," Tech. Repo. Stanford University, 2015.
     class Nadam
       include Base::BaseEstimator
       include Validation
@@ -20,6 +24,7 @@ module Rumale
       # @param decay1 [Float] The smoothing parameter for the first moment.
       # @param decay2 [Float] The smoothing parameter for the second moment.
       def initialize(learning_rate: 0.01, decay1: 0.9, decay2: 0.999)
+        warn 'warning: Nadam is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate, decay1: decay1, decay2: decay2)
         check_params_positive(learning_rate: learning_rate, decay1: decay1, decay2: decay2)
         @params = {}

data/lib/rumale/optimizer/rmsprop.rb

@@ -7,9 +7,11 @@ module Rumale
   module Optimizer
     # RMSProp is a class that implements RMSProp optimizer.
     #
+    # @deprecated RMSProp will be deleted in version 0.20.0.
+    #
     # *Reference*
-    # - I. Sutskever, J. Martens, G. Dahl, and G. Hinton, "On the importance of initialization and momentum in deep learning," Proc. ICML' 13, pp. 1139--1147, 2013.
-    # - G. Hinton, N. Srivastava, and K. Swersky, "Lecture 6e rmsprop," Neural Networks for Machine Learning, 2012.
+    # - Sutskever, I., Martens, J., Dahl, G., and Hinton, G., "On the importance of initialization and momentum in deep learning," Proc. ICML' 13, pp. 1139--1147, 2013.
+    # - Hinton, G., Srivastava, N., and Swersky, K., "Lecture 6e rmsprop," Neural Networks for Machine Learning, 2012.
     class RMSProp
       include Base::BaseEstimator
       include Validation
@@ -20,6 +22,7 @@ module Rumale
       # @param momentum [Float] The initial value of momentum.
       # @param decay [Float] The smooting parameter.
       def initialize(learning_rate: 0.01, momentum: 0.9, decay: 0.9)
+        warn 'warning: RMSProp is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate, momentum: momentum, decay: decay)
         check_params_positive(learning_rate: learning_rate, momentum: momentum, decay: decay)
         @params = {}

data/lib/rumale/optimizer/sgd.rb

@@ -6,6 +6,8 @@ require 'rumale/base/base_estimator'
 module Rumale
   module Optimizer
     # SGD is a class that implements SGD optimizer.
+    #
+    # @deprecated SGD will be deleted in version 0.20.0.
     class SGD
       include Base::BaseEstimator
       include Validation
@@ -16,6 +18,7 @@ module Rumale
       # @param momentum [Float] The initial value of momentum.
       # @param decay [Float] The smooting parameter.
       def initialize(learning_rate: 0.01, momentum: 0.0, decay: 0.0)
+        warn 'warning: SGD is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate, momentum: momentum, decay: decay)
         check_params_positive(learning_rate: learning_rate, momentum: momentum, decay: decay)
         @params = {}

data/lib/rumale/optimizer/yellow_fin.rb

@@ -7,8 +7,10 @@ module Rumale
   module Optimizer
     # YellowFin is a class that implements YellowFin optimizer.
     #
+    # @deprecated YellowFin will be deleted in version 0.20.0.
+    #
     # *Reference*
-    # - J. Zhang and I. Mitliagkas, "YellowFin and the Art of Momentum Tuning," CoRR abs/1706.03471, 2017.
+    # - Zhang, J., and Mitliagkas, I., "YellowFin and the Art of Momentum Tuning," CoRR abs/1706.03471, 2017.
     class YellowFin
       include Base::BaseEstimator
       include Validation
@@ -20,6 +22,7 @@ module Rumale
       # @param decay [Float] The smooting parameter.
       # @param window_width [Integer] The sliding window width for searching curvature range.
       def initialize(learning_rate: 0.01, momentum: 0.9, decay: 0.999, window_width: 20)
+        warn 'warning: YellowFin is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(learning_rate: learning_rate, momentum: momentum, decay: decay, window_width: window_width)
         check_params_positive(learning_rate: learning_rate, momentum: momentum, decay: decay, window_width: window_width)
         @params = {}

data/lib/rumale/pipeline/pipeline.rb

@@ -119,6 +119,7 @@ module Rumale
         @steps.keys.reverse_each do |name|
           transformer = @steps[name]
           next if transformer.nil?
+
           itrans_z = transformer.inverse_transform(itrans_z)
         end
         itrans_z
@@ -140,6 +141,7 @@ module Rumale
         steps.keys[0...-1].each do |name|
           transformer = steps[name]
           next if transformer.nil? || %i[fit transform].all? { |m| transformer.class.method_defined?(m) }
+
           raise TypeError,
                 'Class of intermediate step in pipeline should be implemented fit and transform methods: ' \
                 "#{name} => #{transformer.class}"
@@ -158,6 +160,7 @@ module Rumale
         @steps.keys[0...-1].each do |name|
           transformer = @steps[name]
           next if transformer.nil?
+
           transformer.fit(trans_x, y) if fit
           trans_x = transformer.transform(trans_x)
         end

data/lib/rumale/polynomial_model/base_factorization_machine.rb

@@ -5,9 +5,13 @@ require 'rumale/optimizer/nadam'
 
 module Rumale
   # This module consists of the classes that implement polynomial models.
+  #
+  # @deprecated PolynomialModel module will be deleted in version 0.20.0.
   module PolynomialModel
     # BaseFactorizationMachine is an abstract class for implementation of Factorization Machine-based estimators.
     # This class is used internally.
+    #
+    # @deprecated BaseFactorizationMachine will be deleted in version 0.20.0.
     class BaseFactorizationMachine
       include Base::BaseEstimator
 
@@ -75,6 +79,7 @@ module Rumale
             # Calculate gradients for loss function.
             loss_grad = loss_gradient(sub_x, ex_sub_x, sub_y, factor_mat, weight_vec)
             next if loss_grad.ne(0.0).count.zero?
+
             # Update each parameter.
             weight_vec = weight_optimizer.call(weight_vec, weight_gradient(loss_grad, ex_sub_x, weight_vec))
             @params[:n_factors].times do |n|

data/lib/rumale/polynomial_model/factorization_machine_classifier.rb

@@ -10,6 +10,10 @@ module Rumale
     # with stochastic gradient descent (SGD) optimization.
     # For multiclass classification problem, it uses one-vs-the-rest strategy.
     #
+    # @deprecated
+    #   FactorizationMachineClassifier will be deleted in version 0.20.0.
+    #   The Ruamle author recommends using the xlearn gem instead.
+    #
     # @example
     #   estimator =
     #     Rumale::PolynomialModel::FactorizationMachineClassifier.new(
@@ -19,8 +23,8 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Rendle, "Factorization Machines with libFM," ACM TIST, vol. 3 (3), pp. 57:1--57:22, 2012.
-    # - S. Rendle, "Factorization Machines," Proc. ICDM'10, pp. 995--1000, 2010.
+    # - Rendle, S., "Factorization Machines with libFM," ACM TIST, vol. 3 (3), pp. 57:1--57:22, 2012.
+    # - Rendle, S., "Factorization Machines," Proc. ICDM'10, pp. 995--1000, 2010.
     class FactorizationMachineClassifier < BaseFactorizationMachine
       include Base::Classifier
 
@@ -65,6 +69,7 @@ module Rumale
       def initialize(n_factors: 2, loss: 'hinge', reg_param_linear: 1.0, reg_param_factor: 1.0,
                      max_iter: 200, batch_size: 50, tol: 1e-4,
                      optimizer: nil, n_jobs: nil, verbose: false, random_seed: nil)
+        warn 'warning: FactorizationMachineClassifier is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor,
                              n_factors: n_factors, max_iter: max_iter, batch_size: batch_size, tol: tol)
         check_params_string(loss: loss)

data/lib/rumale/polynomial_model/factorization_machine_regressor.rb

@@ -8,6 +8,10 @@ module Rumale
     # FactorizationMachineRegressor is a class that implements Factorization Machine
     # with stochastic gradient descent (SGD) optimization.
     #
+    # @deprecated
+    #   FactorizationMachineRegressor will be deleted in version 0.20.0.
+    #   The Ruamle author recommends using the xlearn gem instead.
+    #
     # @example
     #   estimator =
     #     Rumale::PolynomialModel::FactorizationMachineRegressor.new(
@@ -17,8 +21,8 @@ module Rumale
     #   results = estimator.predict(testing_samples)
     #
     # *Reference*
-    # - S. Rendle, "Factorization Machines with libFM," ACM TIST, vol. 3 (3), pp. 57:1--57:22, 2012.
-    # - S. Rendle, "Factorization Machines," Proc. ICDM'10, pp. 995--1000, 2010.
+    # - Rendle, S., "Factorization Machines with libFM," ACM TIST, vol. 3 (3), pp. 57:1--57:22, 2012.
+    # - Rendle, S., "Factorization Machines," Proc. ICDM'10, pp. 995--1000, 2010.
     class FactorizationMachineRegressor < BaseFactorizationMachine
       include Base::Regressor
 
@@ -58,6 +62,7 @@ module Rumale
       def initialize(n_factors: 2, reg_param_linear: 1.0, reg_param_factor: 1.0,
                      max_iter: 200, batch_size: 50, tol: 1e-4,
                      optimizer: nil, n_jobs: nil, verbose: false, random_seed: nil)
+        warn 'warning: FactorizationMachineClassifier is deprecated. This class will be deleted in version 0.20.0.'
         check_params_numeric(reg_param_linear: reg_param_linear, reg_param_factor: reg_param_factor,
                              n_factors: n_factors, max_iter: max_iter, batch_size: batch_size, tol: tol)
         check_params_boolean(verbose: verbose)

data/lib/rumale/preprocessing/l1_normalizer.rb

@@ -0,0 +1,62 @@
+# frozen_string_literal: true
+
+require 'rumale/base/base_estimator'
+require 'rumale/base/transformer'
+
+module Rumale
+  module Preprocessing
+    # Normalize samples to unit L1-norm.
+    #
+    # @example
+    #   normalizer = Rumale::Preprocessing::L1Normalizer.new
+    #   new_samples = normalizer.fit_transform(samples)
+    class L1Normalizer
+      include Base::BaseEstimator
+      include Base::Transformer
+
+      # Return the vector consists of L1-norm for each sample.
+      # @return [Numo::DFloat] (shape: [n_samples])
+      attr_reader :norm_vec # :nodoc:
+
+      # Create a new normalizer for normaliing to L1-norm.
+      def initialize
+        @params = {}
+        @norm_vec = nil
+      end
+
+      # Calculate L1-norms of each sample.
+      #
+      # @overload fit(x) -> L1Normalizer
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
+      # @return [L1Normalizer]
+      def fit(x, _y = nil)
+        x = check_convert_sample_array(x)
+        @norm_vec = x.abs.sum(1)
+        @norm_vec[@norm_vec.eq(0)] = 1
+        self
+      end
+
+      # Calculate L1-norms of each sample, and then normalize samples to L1-norm.
+      #
+      # @overload fit_transform(x) -> Numo::DFloat
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
+      # @return [Numo::DFloat] The normalized samples.
+      def fit_transform(x, _y = nil)
+        x = check_convert_sample_array(x)
+        fit(x)
+        x / @norm_vec.expand_dims(1)
+      end
+
+      # Calculate L1-norms of each sample, and then normalize samples to L1-norm.
+      # This method calls the fit_transform method. This method exists for the Pipeline class.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
+      # @return [Numo::DFloat] The normalized samples.
+      def transform(x)
+        fit_transform(x)
+      end
+    end
+  end
+end

data/lib/rumale/preprocessing/l2_normalizer.rb

@@ -34,6 +34,7 @@ module Rumale
       def fit(x, _y = nil)
         x = check_convert_sample_array(x)
         @norm_vec = Numo::NMath.sqrt((x**2).sum(1))
+        @norm_vec[@norm_vec.eq(0)] = 1
         self
       end
 
@@ -46,7 +47,7 @@ module Rumale
       def fit_transform(x, _y = nil)
         x = check_convert_sample_array(x)
         fit(x)
-        x / @norm_vec.tile(x.shape[1], 1).transpose
+        x / @norm_vec.expand_dims(1)
       end
 
       # Calculate L2-norms of each sample, and then normalize samples to unit L2-norm.

data/lib/rumale/preprocessing/one_hot_encoder.rb

@@ -51,6 +51,7 @@ module Rumale
       def fit(x, _y = nil)
         x = Numo::Int32.cast(x) unless x.is_a?(Numo::Int32)
         raise ArgumentError, 'Expected the input samples only consists of non-negative integer values.' if x.lt(0).any?
+
         @n_values = x.max(0) + 1
         @feature_indices = Numo::Int32.hstack([[0], @n_values]).cumsum
         @active_features = encode(x, @feature_indices).sum(0).ne(0).where
@@ -67,6 +68,7 @@ module Rumale
         x = Numo::Int32.cast(x) unless x.is_a?(Numo::Int32)
         raise ArgumentError, 'Expected the input samples only consists of non-negative integer values.' if x.lt(0).any?
         raise ArgumentError, 'Expected the input samples only consists of non-negative integer values.' if x.lt(0).any?
+
         fit(x).transform(x)
       end
 
@@ -77,6 +79,7 @@ module Rumale
       def transform(x)
         x = Numo::Int32.cast(x) unless x.is_a?(Numo::Int32)
         raise ArgumentError, 'Expected the input samples only consists of non-negative integer values.' if x.lt(0).any?
+
         codes = encode(x, @feature_indices)
         codes[true, @active_features].dup
       end

data/lib/rumale/preprocessing/ordinal_encoder.rb

@@ -51,6 +51,7 @@ module Rumale
       def fit(x, _y = nil)
         raise TypeError, 'Expect class of sample matrix to be Numo::NArray' unless x.is_a?(Numo::NArray)
         raise ArgumentError, 'Expect sample matrix to be 2-D array' unless x.shape.size == 2
+
         n_features = x.shape[1]
         @categories = Array.new(n_features) { |n| x[true, n].to_a.uniq.sort }
         self
@@ -65,6 +66,7 @@ module Rumale
       def fit_transform(x, _y = nil)
         raise TypeError, 'Expect class of sample matrix to be Numo::NArray' unless x.is_a?(Numo::NArray)
         raise ArgumentError, 'Expect sample matrix to be 2-D array' unless x.shape.size == 2
+
         fit(x).transform(x)
       end
 

data/lib/rumale/preprocessing/polynomial_features.rb

@@ -41,6 +41,7 @@ module Rumale
       def initialize(degree: 2)
         check_params_numeric(degree: degree)
         raise ArgumentError, 'Expect the value of degree parameter greater than or eqaul to 1.' if degree < 1
+
         @params = {}
         @params[:degree] = degree
         @n_output_features = nil