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

# typed: true

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


# Rumale is a machine learning library in Ruby.
#
# source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#8
module Rumale; end

# Module for kernel approximation algorithms.
#
# source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#9
module Rumale::KernelApproximation; end

# Nystroem is a class that implements feature mapping with Nystroem method.
#
# *Reference*
# - Yang, T., Li, Y., Mahdavi, M., Jin, R., and Zhou, Z-H., "Nystrom Method vs Random Fourier Features: A Theoretical and Empirical Comparison," Advances in NIPS'12, Vol. 1, pp. 476--484, 2012.
#
# @example
#   require 'numo/linalg/autoloader'
#   require 'rumale/kernel_approximation/nystroem'
#
#   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)
#
# source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#22
class Rumale::KernelApproximation::Nystroem < ::Rumale::Base::Estimator
  include ::Rumale::Base::Transformer

  # Create a new transformer for mapping to kernel feature space with Nystrom method.
  #
  # @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.
  # @return [Nystroem] a new instance of Nystroem
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#49
  def initialize(kernel: T.unsafe(nil), gamma: T.unsafe(nil), degree: T.unsafe(nil), coef: T.unsafe(nil), n_components: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Returns the indices sampled training data.
  #
  # @return [Numo::Int32] (shape: [n_components])
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#31
  def component_indices; end

  # Returns the randomly sampled training data for feature mapping.
  #
  # @return [Numo::DFloat] (shape: n_components, n_features])
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#27
  def components; end

  # Fit the model with given training data.
  #
  # @overload fit
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#67
  def fit(x, _y = T.unsafe(nil)); end

  # Fit the model with training data, and then transform them with the learned model.
  #
  # @overload fit_transform
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#95
  def fit_transform(x, _y = T.unsafe(nil)); end

  # Returns the normalizing factors.
  #
  # @return [Numo::DFloat] (shape: [n_components, n_components])
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#35
  def normalizer; end

  # Return the random generator for transformation.
  #
  # @return [Random]
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#39
  def rng; end

  # Transform the given data with the learned model.
  #
  # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The data to be transformed with the learned model.
  # @return [Numo::DFloat] (shape: [n_samples, n_components]) The transformed data.
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#105
  def transform(x); end

  private

  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/nystroem.rb#114
  def kernel_mat(x, y = T.unsafe(nil)); end
end

# Class for RBF kernel feature mapping.
#
# *Refernce*:
# - Rahimi, A., and Recht, B., "Random Features for Large-Scale Kernel Machines," Proc. NIPS'07, pp.1177--1184, 2007.
#
# @example
#   require 'rumale/kernel_approximation/rbf'
#
#   transformer = Rumale::KernelApproximation::RBF.new(gamma: 1.0, n_components: 128, random_seed: 1)
#   new_training_samples = transformer.fit_transform(training_samples)
#   new_testing_samples = transformer.transform(testing_samples)
#
# source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#21
class Rumale::KernelApproximation::RBF < ::Rumale::Base::Estimator
  include ::Rumale::Base::Transformer

  # Create a new transformer for mapping to RBF kernel feature space.
  #
  # @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 random_seed [Integer] The seed value using to initialize the random generator.
  # @return [RBF] a new instance of RBF
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#41
  def initialize(gamma: T.unsafe(nil), n_components: T.unsafe(nil), random_seed: T.unsafe(nil)); end

  # Fit the model with given training data.
  #
  # @overload fit
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#57
  def fit(x, _y = T.unsafe(nil)); end

  # Fit the model with training data, and then transform them with the learned model.
  #
  # @overload fit_transform
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#76
  def fit_transform(x, _y = T.unsafe(nil)); end

  # Return the random matrix for transformation.
  #
  # @return [Numo::DFloat] (shape: [n_features, n_components])
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#26
  def random_mat; end

  # Return the random vector for transformation.
  #
  # @return [Numo::DFloat] (shape: [n_components])
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#30
  def random_vec; end

  # Return the random generator for transformation.
  #
  # @return [Random]
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#34
  def rng; end

  # Transform the given data with the learned model.
  #
  # @overload transform
  #
  # source://rumale-kernel_approximation//lib/rumale/kernel_approximation/rbf.rb#87
  def transform(x); end
end

# source://rumale-kernel_approximation//lib/rumale/kernel_approximation/version.rb#8
Rumale::KernelApproximation::VERSION = T.let(T.unsafe(nil), String)