redux-scraper/sorbet/rbi/gems/rumale-model_selection@1.0.0.rbi

# typed: true

# DO NOT EDIT MANUALLY
# This is an autogenerated file for types exported from the `rumale-model_selection` gem.
# Please instead update this file by running `bin/tapioca gem rumale-model_selection`.


# source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#5
module Rumale; end

# This module consists of the classes for model validation techniques.
#
# source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#6
module Rumale::ModelSelection
  private

  # Split randomly data set into test and train data.
  #
  # @example
  #   require 'rumale/model_selection/function'
  #
  #   x_train, x_test, y_train, y_test = Rumale::ModelSelection.train_test_split(x, y, test_size: 0.2, stratify: true, random_seed: 1)
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The dataset to be used to generate data indices.
  # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used to generate data indices for stratified random permutation.
  #   If stratify = false, this parameter is ignored.
  # @param test_size [Float] The ratio of number of samples for test data.
  # @param train_size [Float] The ratio of number of samples for train data.
  #   If nil is given, it sets to 1 - test_size.
  # @param stratify [Boolean] The flag indicating whether to perform stratify split.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [Array<Numo::NArray>] The set of training and testing data.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/function.rb#29
  def train_test_split(x, y = T.unsafe(nil), test_size: T.unsafe(nil), train_size: T.unsafe(nil), stratify: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  class << self
    # Split randomly data set into test and train data.
    #
    # @example
    #   require 'rumale/model_selection/function'
    #
    #   x_train, x_test, y_train, y_test = Rumale::ModelSelection.train_test_split(x, y, test_size: 0.2, stratify: true, random_seed: 1)
    # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The dataset to be used to generate data indices.
    # @param y [Numo::Int32] (shape: [n_samples]) The labels to be used to generate data indices for stratified random permutation.
    #   If stratify = false, this parameter is ignored.
    # @param test_size [Float] The ratio of number of samples for test data.
    # @param train_size [Float] The ratio of number of samples for train data.
    #   If nil is given, it sets to 1 - test_size.
    # @param stratify [Boolean] The flag indicating whether to perform stratify split.
    # @param random_seed [Integer] The seed value using to initialize the random generator.
    # @return [Array<Numo::NArray>] The set of training and testing data.
    #
    # source://rumale-model_selection//lib/rumale/model_selection/function.rb#29
    def train_test_split(x, y = T.unsafe(nil), test_size: T.unsafe(nil), train_size: T.unsafe(nil), stratify: T.unsafe(nil), random_seed: T.unsafe(nil)); end
  end
end

# CrossValidation is a class that evaluates a given classifier with cross-validation method.
#
# @example
#   require 'rumale/linear_model'
#   require 'rumale/model_selection/stratified_k_fold'
#   require 'rumale/model_selection/cross_validation'
#
#   svc = Rumale::LinearModel::SVC.new
#   kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5)
#   cv = Rumale::ModelSelection::CrossValidation.new(estimator: svc, splitter: kf)
#   report = cv.perform(samples, labels)
#   mean_test_score = report[:test_score].inject(:+) / kf.n_splits
#
# source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#21
class Rumale::ModelSelection::CrossValidation
  # Create a new evaluator with cross-validation method.
  #
  # @param estimator [Classifier] The classifier of which performance is evaluated.
  # @param splitter [Splitter] The splitter that divides dataset to training and testing dataset.
  # @param evaluator [Evaluator] The evaluator that calculates score of estimator results.
  # @param return_train_score [Boolean] The flag indicating whether to calculate the score of training dataset.
  # @return [CrossValidation] a new instance of CrossValidation
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#44
  def initialize(estimator: T.unsafe(nil), splitter: T.unsafe(nil), evaluator: T.unsafe(nil), return_train_score: T.unsafe(nil)); end

  # Return the classifier of which performance is evaluated.
  #
  # @return [Classifier]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#24
  def estimator; end

  # Return the evaluator that calculates score.
  #
  # @return [Evaluator]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#32
  def evaluator; end

  # Perform the evalution of given classifier with cross-validation method.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features])
  #   The dataset to be used to evaluate the estimator.
  # @param y [Numo::Int32 / Numo::DFloat] (shape: [n_samples] / [n_samples, n_outputs])
  #   The labels to be used to evaluate the classifier / The target values to be used to evaluate the regressor.
  # @return [Hash] The report summarizing the results of cross-validation.
  #   * :fit_time (Array<Float>) The calculation times of fitting the estimator for each split.
  #   * :test_score (Array<Float>) The scores of testing dataset for each split.
  #   * :train_score (Array<Float>) The scores of training dataset for each split. This option is nil if
  #   the return_train_score is false.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#62
  def perform(x, y); end

  # Return the flag indicating whether to caculate the score of training dataset.
  #
  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#36
  def return_train_score; end

  # Return the splitter that divides dataset.
  #
  # @return [Splitter]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#28
  def splitter; end

  private

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#98
  def kernel_machine?; end

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/cross_validation.rb#102
  def log_loss?; end
end

# GridSearchCV is a class that performs hyperparameter optimization with grid search method.
#
# @example
#   require 'rumale/ensemble'
#   require 'rumale/model_selection/stratified_k_fold'
#   require 'rumale/model_selection/grid_search_cv'
#
#   rfc = Rumale::Ensemble::RandomForestClassifier.new(random_seed: 1)
#   pg = { n_estimators: [5, 10], max_depth: [3, 5], max_leaf_nodes: [15, 31] }
#   kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5)
#   gs = Rumale::ModelSelection::GridSearchCV.new(estimator: rfc, param_grid: pg, splitter: kf)
#   gs.fit(samples, labels)
#   p gs.cv_results
#   p gs.best_params
# @example
#   rbf = Rumale::KernelApproximation::RBF.new(random_seed: 1)
#   svc = Rumale::LinearModel::SVC.new
#   pipe = Rumale::Pipeline::Pipeline.new(steps: { rbf: rbf, svc: svc })
#   pg = { rbf__gamma: [32.0, 1.0], rbf__n_components: [4, 128], svc__reg_param: [16.0, 0.1] }
#   kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5)
#   gs = Rumale::ModelSelection::GridSearchCV.new(estimator: pipe, param_grid: pg, splitter: kf)
#   gs.fit(samples, labels)
#   p gs.cv_results
#   p gs.best_params
#
# source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#34
class Rumale::ModelSelection::GridSearchCV < ::Rumale::Base::Estimator
  # Create a new grid search method.
  #
  # @param estimator [Classifier/Regresor] The estimator to be searched for optimal parameters with grid search method.
  # @param param_grid [Array<Hash>] The parameter sets is represented with array of hash that
  #   consists of parameter names as keys and array of parameter values as values.
  # @param splitter [Splitter] The splitter that divides dataset to training and testing dataset on cross validation.
  # @param evaluator [Evaluator] The evaluator that calculates score of estimator results on cross validation.
  #   If nil is given, the score method of estimator is used to evaluation.
  # @param greater_is_better [Boolean] The flag that indicates whether the estimator is better as
  #   evaluation score is larger.
  # @return [GridSearchCV] a new instance of GridSearchCV
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#65
  def initialize(estimator: T.unsafe(nil), param_grid: T.unsafe(nil), splitter: T.unsafe(nil), evaluator: T.unsafe(nil), greater_is_better: T.unsafe(nil)); end

  # Return the estimator learned with the best parameter.
  #
  # @return [Estimator]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#53
  def best_estimator; end

  # Return the index of the best parameter.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#49
  def best_index; end

  # Return the best parameter set.
  #
  # @return [Hash]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#45
  def best_params; end

  # Return the score of the estimator learned with the best parameter.
  #
  # @return [Float]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#41
  def best_score; end

  # Return the result of cross validation for each parameter.
  #
  # @return [Hash]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#37
  def cv_results; end

  # Call the decision_function method of learned estimator with the best parameter.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to compute the scores.
  # @return [Numo::DFloat] (shape: [n_samples]) Confidence score per sample.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#102
  def decision_function(x); end

  # Fit the model with given training data and all sets of parameters.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the model.
  # @param y [Numo::NArray] (shape: [n_samples, n_outputs]) The target values or labels to be used for fitting the model.
  # @return [GridSearchCV] The learned estimator with grid search.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#81
  def fit(x, y); end

  # Call the predict method of learned estimator with the best parameter.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to obtain prediction result.
  # @return [Numo::NArray] Predicted results.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#110
  def predict(x); end

  # Call the predict_log_proba method of learned estimator with the best parameter.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the log-probailities.
  # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted log-probability of each class per sample.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#118
  def predict_log_proba(x); end

  # Call the predict_proba method of learned estimator with the best parameter.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to predict the probailities.
  # @return [Numo::DFloat] (shape: [n_samples, n_classes]) Predicted probability of each class per sample.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#126
  def predict_proba(x); end

  # Call the score method of learned estimator with the best parameter.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) Testing data.
  # @param y [Numo::NArray] (shape: [n_samples, n_outputs]) True target values or labels for testing data.
  # @return [Float] The score of estimator.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#135
  def score(x, y); end

  private

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#166
  def configurated_estimator(prms); end

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#202
  def find_best_params; end

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#179
  def init_attrs; end

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#152
  def param_combinations; end

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#159
  def perform_cross_validation(x, y, prms); end

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#208
  def pipeline?; end

  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#189
  def store_cv_result(prms, report); end

  # @raise [TypeError]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/grid_search_cv.rb#141
  def valid_param_grid(grid); end
end

# GroupKFold is a class that generates the set of data indices for K-fold cross-validation.
# The data points belonging to the same group do not be split into different folds.
# The number of groups should be greater than or equal to the number of splits.
#
# @example
#   require 'rumale/model_selection/group_k_fold'
#
#   cv = Rumale::ModelSelection::GroupKFold.new(n_splits: 3)
#   x = Numo::DFloat.new(8, 2).rand
#   groups = Numo::Int32[1, 1, 1, 2, 2, 3, 3, 3]
#   cv.split(x, nil, groups).each do |train_ids, test_ids|
#   puts '---'
#   pp train_ids
#   pp test_ids
#   end
#
#   # ---
#   # [0, 1, 2, 3, 4]
#   # [5, 6, 7]
#   # ---
#   # [3, 4, 5, 6, 7]
#   # [0, 1, 2]
#   # ---
#   # [0, 1, 2, 5, 6, 7]
#   # [3, 4]
#
# source://rumale-model_selection//lib/rumale/model_selection/group_k_fold.rb#34
class Rumale::ModelSelection::GroupKFold
  include ::Rumale::Base::Splitter

  # Create a new data splitter for grouped K-fold cross validation.
  #
  # @param n_splits [Integer] The number of folds.
  # @return [GroupKFold] a new instance of GroupKFold
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_k_fold.rb#44
  def initialize(n_splits: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_k_fold.rb#39
  def n_splits; end

  # Generate data indices for grouped K-fold cross validation.
  #
  # @overload split
  # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_k_fold.rb#58
  def split(x, _y, groups); end
end

# GroupShuffleSplit is a class that generates the set of data indices
# for random permutation cross-validation by randomly selecting group labels.
#
# @example
#   require 'rumale/model_selection/group_shuffle_split'
#
#   cv = Rumale::ModelSelection::GroupShuffleSplit.new(n_splits: 2, test_size: 0.2, random_seed: 1)
#   x = Numo::DFloat.new(8, 2).rand
#   groups = Numo::Int32[1, 1, 1, 2, 2, 3, 3, 3]
#   cv.split(x, nil, groups).each do |train_ids, test_ids|
#   puts '---'
#   pp train_ids
#   pp test_ids
#   end
#
#   # ---
#   # [0, 1, 2, 5, 6, 7]
#   # [3, 4]
#   # ---
#   # [3, 4, 5, 6, 7]
#   # [0, 1, 2]
#
# source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#29
class Rumale::ModelSelection::GroupShuffleSplit
  include ::Rumale::Base::Splitter

  # Create a new data splitter for random permutation cross validation with given group labels.
  #
  # @param n_splits [Integer] The number of folds.
  # @param test_size [Float] The ratio of number of groups for test data.
  # @param train_size [Float/Nil] The ratio of number of groups for train data.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [GroupShuffleSplit] a new instance of GroupShuffleSplit
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#46
  def initialize(n_splits: T.unsafe(nil), test_size: T.unsafe(nil), train_size: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#34
  def n_splits; end

  # Return the random generator for shuffling the dataset.
  #
  # @return [Random]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#38
  def rng; end

  # Generate train and test data indices by randomly selecting group labels.
  #
  # @overload split
  # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#65
  def split(_x, _y, groups); end

  private

  # source://rumale-model_selection//lib/rumale/model_selection/group_shuffle_split.rb#101
  def in1d(a, b); end
end

# KFold is a class that generates the set of data indices for K-fold cross-validation.
#
# @example
#   require 'rumale/model_selection/k_fold'
#
#   kf = Rumale::ModelSelection::KFold.new(n_splits: 3, shuffle: true, random_seed: 1)
#   kf.split(samples, labels).each do |train_ids, test_ids|
#   train_samples = samples[train_ids, true]
#   test_samples = samples[test_ids, true]
#   ...
#   end
#
# source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#20
class Rumale::ModelSelection::KFold
  include ::Rumale::Base::Splitter

  # Create a new data splitter for K-fold cross validation.
  #
  # @param n_splits [Integer] The number of folds.
  # @param shuffle [Boolean] The flag indicating whether to shuffle the dataset.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [KFold] a new instance of KFold
  #
  # source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#40
  def initialize(n_splits: T.unsafe(nil), shuffle: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#25
  def n_splits; end

  # Return the random generator for shuffling the dataset.
  #
  # @return [Random]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#33
  def rng; end

  # Return the flag indicating whether to shuffle the dataset.
  #
  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#29
  def shuffle; end

  # Generate data indices for K-fold cross validation.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features])
  #   The dataset to be used to generate data indices for K-fold cross validation.
  # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/k_fold.rb#53
  def split(x, _y = T.unsafe(nil)); end
end

# ShuffleSplit is a class that generates the set of data indices for random permutation cross-validation.
#
# @example
#   require 'rumale/model_selection/shuffle_split'
#
#   ss = Rumale::ModelSelection::ShuffleSplit.new(n_splits: 3, test_size: 0.2, random_seed: 1)
#   ss.split(samples, labels).each do |train_ids, test_ids|
#   train_samples = samples[train_ids, true]
#   test_samples = samples[test_ids, true]
#   ...
#   end
#
# source://rumale-model_selection//lib/rumale/model_selection/shuffle_split.rb#19
class Rumale::ModelSelection::ShuffleSplit
  include ::Rumale::Base::Splitter

  # Create a new data splitter for random permutation cross validation.
  #
  # @param n_splits [Integer] The number of folds.
  # @param test_size [Float] The ratio of number of samples for test data.
  # @param train_size [Float] The ratio of number of samples for train data.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [ShuffleSplit] a new instance of ShuffleSplit
  #
  # source://rumale-model_selection//lib/rumale/model_selection/shuffle_split.rb#36
  def initialize(n_splits: T.unsafe(nil), test_size: T.unsafe(nil), train_size: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/shuffle_split.rb#24
  def n_splits; end

  # Return the random generator for shuffling the dataset.
  #
  # @return [Random]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/shuffle_split.rb#28
  def rng; end

  # Generate data indices for random permutation cross validation.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features])
  #   The dataset to be used to generate data indices for random permutation cross validation.
  # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/shuffle_split.rb#50
  def split(x, _y = T.unsafe(nil)); end
end

# StratifiedKFold is a class that generates the set of data indices for K-fold cross-validation.
# The proportion of the number of samples in each class will be almost equal for each fold.
#
# @example
#   require 'rumale/model_selection/stratified_k_fold'
#
#   kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 3, shuffle: true, random_seed: 1)
#   kf.split(samples, labels).each do |train_ids, test_ids|
#   train_samples = samples[train_ids, true]
#   test_samples = samples[test_ids, true]
#   ...
#   end
#
# source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#20
class Rumale::ModelSelection::StratifiedKFold
  include ::Rumale::Base::Splitter

  # Create a new data splitter for stratified K-fold cross validation.
  #
  # @param n_splits [Integer] The number of folds.
  # @param shuffle [Boolean] The flag indicating whether to shuffle the dataset.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [StratifiedKFold] a new instance of StratifiedKFold
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#40
  def initialize(n_splits: T.unsafe(nil), shuffle: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#25
  def n_splits; end

  # Return the random generator for shuffling the dataset.
  #
  # @return [Random]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#33
  def rng; end

  # Return the flag indicating whether to shuffle the dataset.
  #
  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#29
  def shuffle; end

  # Generate data indices for stratified K-fold cross validation.
  #
  # @overload split
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#57
  def split(_x, y); end

  private

  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#76
  def fold_sets(y, label, sub_rng); end

  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#87
  def train_test_sets(fold_sets_each_class, fold_id); end

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_k_fold.rb#72
  def valid_n_splits?(y); end
end

# StratifiedShuffleSplit is a class that generates the set of data indices for random permutation cross-validation.
# The proportion of the number of samples in each class will be almost equal for each fold.
#
# @example
#   require 'rumale/model_selection/stratified_shuffle_split'
#
#   ss = Rumale::ModelSelection::StratifiedShuffleSplit.new(n_splits: 3, test_size: 0.2, random_seed: 1)
#   ss.split(samples, labels).each do |train_ids, test_ids|
#   train_samples = samples[train_ids, true]
#   test_samples = samples[test_ids, true]
#   ...
#   end
#
# source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#20
class Rumale::ModelSelection::StratifiedShuffleSplit
  include ::Rumale::Base::Splitter

  # Create a new data splitter for random permutation cross validation.
  #
  # @param n_splits [Integer] The number of folds.
  # @param test_size [Float] The ratio of number of samples for test data.
  # @param train_size [Float] The ratio of number of samples for train data.
  # @param random_seed [Integer] The seed value using to initialize the random generator.
  # @return [StratifiedShuffleSplit] a new instance of StratifiedShuffleSplit
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#37
  def initialize(n_splits: T.unsafe(nil), test_size: T.unsafe(nil), train_size: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Return the number of folds.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#25
  def n_splits; end

  # Return the random generator for shuffling the dataset.
  #
  # @return [Random]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#29
  def rng; end

  # Generate data indices for stratified random permutation cross validation.
  #
  # @overload split
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#55
  def split(_x, y); end

  private

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#104
  def enough_data_size_each_class?(y, data_size, data_type); end

  # @return [Boolean]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/stratified_shuffle_split.rb#100
  def valid_n_splits?(y); end
end

# 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
#   require 'rumale/model_selection/time_series_split'
#
#   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]
#
# source://rumale-model_selection//lib/rumale/model_selection/time_series_split.rb#37
class Rumale::ModelSelection::TimeSeriesSplit
  include ::Rumale::Base::Splitter

  # 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.
  # @return [TimeSeriesSplit] a new instance of TimeSeriesSplit
  #
  # source://rumale-model_selection//lib/rumale/model_selection/time_series_split.rb#52
  def initialize(n_splits: T.unsafe(nil), max_train_size: T.unsafe(nil)); end

  # Return the maximum number of training samples in a split.
  #
  # @return [Integer/Nil]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/time_series_split.rb#46
  def max_train_size; end

  # Return the number of splits.
  #
  # @return [Integer]
  #
  # source://rumale-model_selection//lib/rumale/model_selection/time_series_split.rb#42
  def n_splits; end

  # Generate data indices for time series cross-validation.
  #
  # @overload split
  # @return [Array] The set of data indices for constructing the training and testing dataset in each fold.
  #
  # source://rumale-model_selection//lib/rumale/model_selection/time_series_split.rb#66
  def split(x, _y); end
end

# source://rumale-model_selection//lib/rumale/model_selection/version.rb#6
Rumale::ModelSelection::VERSION = T.let(T.unsafe(nil), String)