Rumale Versions Save

rumale-decomposition

• Add transformer class for Sparse Principal Component Analysis.
  • SparsePCA

rumale-manifold

• Add transformer class for Local Tangent Space Alignment.
  • LocalTangentSpaceAlignment

others

• No changes, or minor changes in configuration files.

rumale-core

• Fix nil checks for the y argument of euclidean_distance and squared_error methods: #45 and 4eb1727

rumale-manifold

• Add transformer classes for Hessian Eigenmaps.
  • HessianEigenmaps

others

• No changes, or minor changes using RuboCop.

rumale-tree

Breaking change

• Rewrite native exntension codes with C++.
• Reimplements stop_growing? private method in DecisionTreeRegressor with native extension.

rumae-neural_network

• Add classifier and regressor classes for Radial Basis Function (RBF) Network.
  • RBFClassifier
  • RBFRegressor
• Add classifier and regressor classes for Random Vector Functinal Link (RVFL) Network.
  • RVFLClassifier
  • RVFLRegressor

others

• No changes, minor changes in configuration files, or minor refactoring using RuboCop.

rumale-linear_model

• Add partial_fit method to SGDClassifier and SGDRegressor.
  • It performs 1-epoch of stochastic gradient descent. It only supports binary labels and single target variables.

rumale-tree

• Remove unnecessary array generation in native extension.

others

• No changes, or minor changes using RuboCop.

rumale-clustering

• Add cluster analysis class for mean-shift method.
  • MeanShift

rumale-manifold

• Add transformer classes for Loccally Linear Embedding and Laplacian Eigenmaps.
  • LocallyLinearEmbedding
  • LaplacianEigenmaps

rumale-metric_learning

• Add transformer class for Local Fisher Discriminant Analysis.
  • LocalFisherDiscriminantAnalysis

others

• No changes, or only slight changes to configuration files.

rumale-linear_model

Breaking change

• Add new SGDClassfier and SGDRegressor by extracting stochastic gradient descent solver from each linear model.
• Change the optimization method of ElasticNet and Lasso to use the coordinate descent algorithm.
• Change the optimization method of SVC and SVR to use the L-BFGS method.
• Change the loss function of SVC to the squared hinge loss.
• Change the loss function of SVR to the squared epsilon-insensitive loss.
• Change not to use random vector for initialization of weights.
  • From the above changes, keyword arguments such as learning_rate, decay, momentum, batch_size, and random_seed for LinearModel estimators have been removed.
• Fix the column and row vectors of weight matrix are reversed in LinearRegression, Ridge, and NNLS.

rumale-decomposition

• Fix missing require method to load Rumale::Utils in PCA class. It is needed to initialize the principal components when optimizing with fixed-point algorithm.

rumale-evaluation_measure

• Apply automatic correction for Style/ZeroLengthPredicate of RuboCop to ROCAUC class.

others

• No changes, or only modifications in test code or configuration.

Rumale project is rebooted:

• Divided into gems for each machine learning algorithm, with Rumale as the meta-gem.
• Changed the license of Rumale to the 3-Caluse BSD License.

• Refactored into modern style code and config with linter.

Rumale project will be rebooted on version 0.24.0. This version is probably the last release of the series starting with version 0.8.0.

• Fixed all estimators to return inference results in a contiguous narray, not a view.
• To avoid SystemStackError, fixed to use until statement instead of recursive call on apply methods of tree estimators.

• Changed automalically selected solver from sgd to lbfgs in LinearRegression and Ridge.

  require 'rumale'
  
  reg = Rumale::LinearModel::Ridge.new(solver: 'auto')
  pp reg.params[:solver]
  # > "lbfgs"
  
  require 'numo/linalg/autoloader'
  
  reg = Rumale::LinearModel::Ridge.new(solver: 'auto')
  pp reg.params[:solver]
  # > "svd"