rumale 0.23.3 → 0.24.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e4a9185e28434614c19947fd5e038cdf731349b0e92bba5ba1c2c9b6ba4e67d2
-  data.tar.gz: ced4878155440aaae7ffd33cf419b3c1b0529d1ea8b5be1dd82400574302de8b
+  metadata.gz: 94217b519d1715e9845565f2dbc03bf9379794936192583bfdbfbc049dd163ce
+  data.tar.gz: 156b5c891c2c52a31208aae5726ccdf3902b93fc3dd332dc416297375c1e0605
 SHA512:
-  metadata.gz: 606a7559baf6d199ac5781d9f4945d27cfbb66f844d5467768a2610744a9cc93e2beb0673da67bc60caf36508791235d002f877ce309e74d89c9cd9c149d2fac
-  data.tar.gz: 5f8dbb3c247e785c8cfd698afad6d1f69da2a045ddc94ecf862a6ec119d3f129b410136249e9ffded46266969d1ab867a8338ab8d762e4620544666c78e56809
+  metadata.gz: fde44d93f43001b6155d6722dc09b2683b2c7e145d11d9f99e49509f374bba4c9d825c2dc1f46b5b3f7ae8df8795a8eb0f6548c822241313d17c72b05d5608fc
+  data.tar.gz: ad6108febf2d62454af1af592c5396ca2bf292b48e8004a583e47b63f63503608436344d3213216e879298de84aef63c74f101e2792d92ae85387c1ce96d0102

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2017-2022 Atsushi Tatsuma
+Copyright (c) 2022 Atsushi Tatsuma
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without
@@ -11,6 +11,10 @@ modification, are permitted provided that the following conditions are met:
   this list of conditions and the following disclaimer in the documentation
   and/or other materials provided with the distribution.
 
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE

data/README.md

@@ -1,25 +1,10 @@
 # Rumale
 
-**This project is suspended for the author's health reasons. It will be resumed when the author recovers.**
-
-![Rumale](https://dl.dropboxusercontent.com/s/joxruk2720ur66o/rumale_header_400.png)
-
-[![Build Status](https://github.com/yoshoku/rumale/actions/workflows/build.yml/badge.svg)](https://github.com/yoshoku/rumale/actions/workflows/build.yml)
 [![Gem Version](https://badge.fury.io/rb/rumale.svg)](https://badge.fury.io/rb/rumale)
-[![BSD 2-Clause License](https://img.shields.io/badge/License-BSD%202--Clause-orange.svg)](https://github.com/yoshoku/rumale/blob/main/LICENSE.txt)
+[![BSD 3-Clause License](https://img.shields.io/badge/License-BSD%203--Clause-orange.svg)](https://github.com/yoshoku/rumale/blob/main/LICENSE.txt)
 [![Documentation](https://img.shields.io/badge/api-reference-blue.svg)](https://yoshoku.github.io/rumale/doc/)
 
 Rumale (**Ru**by **ma**chine **le**arning) is a machine learning library in Ruby.
-Rumale provides machine learning algorithms with interfaces similar to Scikit-Learn in Python.
-Rumale supports Support Vector Machine,
-Logistic Regression, Ridge, Lasso,
-Multi-layer Perceptron,
-Naive Bayes, Decision Tree, Gradient Tree Boosting, Random Forest,
-K-Means, Gaussian Mixture Model, DBSCAN, Spectral Clustering,
-Mutidimensional Scaling, t-SNE,
-Fisher Discriminant Analysis, Neighbourhood Component Analysis,
-Principal Component Analysis, Non-negative Matrix Factorization,
-and many other algorithms.
 
 ## Installation
 
@@ -31,7 +16,7 @@ gem 'rumale'
 
 And then execute:
 
-    $ bundle
+    $ bundle install
 
 Or install it yourself as:
 
@@ -41,276 +26,6 @@ Or install it yourself as:
 
 - [Rumale API Documentation](https://yoshoku.github.io/rumale/doc/)
 
-## Usage
-
-### Example 1. Pendigits dataset classification
-
-Rumale provides function loading libsvm format dataset file.
-We start by downloading the pendigits dataset from LIBSVM Data web site.
-
-```bash
-$ wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/pendigits
-$ wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/pendigits.t
-```
-
-Training of the classifier with Linear SVM and RBF kernel feature map is the following code.
-
-```ruby
-require 'rumale'
-
-# Load the training dataset.
-samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
-
-# Map training data to RBF kernel feature space.
-transformer = Rumale::KernelApproximation::RBF.new(gamma: 0.0001, n_components: 1024, random_seed: 1)
-transformed = transformer.fit_transform(samples)
-
-# Train linear SVM classifier.
-classifier = Rumale::LinearModel::SVC.new(reg_param: 0.0001, random_seed: 1)
-classifier.fit(transformed, labels)
-
-# Save the model.
-File.open('transformer.dat', 'wb') { |f| f.write(Marshal.dump(transformer)) }
-File.open('classifier.dat', 'wb') { |f| f.write(Marshal.dump(classifier)) }
-```
-
-Classifying testing data with the trained classifier is the following code.
-
-```ruby
-require 'rumale'
-
-# Load the testing dataset.
-samples, labels = Rumale::Dataset.load_libsvm_file('pendigits.t')
-
-# Load the model.
-transformer = Marshal.load(File.binread('transformer.dat'))
-classifier = Marshal.load(File.binread('classifier.dat'))
-
-# Map testing data to RBF kernel feature space.
-transformed = transformer.transform(samples)
-
-# Classify the testing data and evaluate prediction results.
-puts("Accuracy: %.1f%%" % (100.0 * classifier.score(transformed, labels)))
-
-# Other evaluating approach
-# results = classifier.predict(transformed)
-# evaluator = Rumale::EvaluationMeasure::Accuracy.new
-# puts("Accuracy: %.1f%%" % (100.0 * evaluator.score(results, labels)))
-```
-
-Execution of the above scripts result in the following.
-
-```bash
-$ ruby train.rb
-$ ruby test.rb
-Accuracy: 98.7%
-```
-
-### Example 2. Cross-validation
-
-```ruby
-require 'rumale'
-
-# Load dataset.
-samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
-
-# Define the estimator to be evaluated.
-lr = Rumale::LinearModel::LogisticRegression.new
-
-# Define the evaluation measure, splitting strategy, and cross validation.
-ev = Rumale::EvaluationMeasure::Accuracy.new
-kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5, shuffle: true, random_seed: 1)
-cv = Rumale::ModelSelection::CrossValidation.new(estimator: lr, splitter: kf, evaluator: ev)
-
-# Perform 5-cross validation.
-report = cv.perform(samples, labels)
-
-# Output result.
-mean_accuracy = report[:test_score].sum / kf.n_splits
-puts "5-CV mean accuracy: %.1f%%" % (100.0 * mean_accuracy)
-```
-
-Execution of the above scripts result in the following.
-
-```bash
-$ ruby cross_validation.rb
-5-CV mean accuracy: 95.4%
-```
-
-### Example 3. Pipeline
-
-```ruby
-require 'rumale'
-
-# Load dataset.
-samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
-
-# Construct pipeline with kernel approximation and LogisticRegression.
-rbf = Rumale::KernelApproximation::RBF.new(gamma: 1e-4, n_components: 800, random_seed: 1)
-lr = Rumale::LinearModel::LogisticRegression.new(reg_param: 1e-3)
-pipeline = Rumale::Pipeline::Pipeline.new(steps: { trns: rbf, clsf: lr })
-
-# Define the splitting strategy and cross validation.
-kf = Rumale::ModelSelection::StratifiedKFold.new(n_splits: 5, shuffle: true, random_seed: 1)
-cv = Rumale::ModelSelection::CrossValidation.new(estimator: pipeline, splitter: kf)
-
-# Perform 5-cross validation.
-report = cv.perform(samples, labels)
-
-# Output result.
-mean_accuracy = report[:test_score].sum / kf.n_splits
-puts("5-CV mean accuracy: %.1f %%" % (mean_accuracy * 100.0))
-```
-
-Execution of the above scripts result in the following.
-
-```bash
-$ ruby pipeline.rb
-5-CV mean accuracy: 99.6 %
-```
-
-## Speed up
-
-### Numo::Linalg
-Rumale uses [Numo::NArray](https://github.com/ruby-numo/numo-narray) for typed arrays.
-Loading the [Numo::Linalg](https://github.com/ruby-numo/numo-linalg) allows to perform matrix product of Numo::NArray using BLAS libraries.
-For example, using the [OpenBLAS](https://github.com/xianyi/OpenBLAS) speeds up many estimators in Rumale.
-
-Install OpenBLAS library.
-
-macOS:
-
-```bash
-$ brew install openblas
-```
-
-Ubuntu:
-
-```bash
-$ sudo apt-get install libopenblas-dev liblapacke-dev
-```
-
-Fedora:
-
-```bash
-$ sudo dnf install openblas-devel lapack-devel
-```
-
-Windows (MSYS2):
-
-```bash
-$ pacman -S mingw-w64-x86_64-ruby mingw-w64-x86_64-openblas mingw-w64-x86_64-lapack
-```
-
-Install Numo::Linalg gem.
-
-```bash
-$ gem install numo-linalg
-```
-
-In ruby script, you only need to require the autoloader module of Numo::Linalg.
-
-```ruby
-require 'numo/linalg/autoloader'
-require 'rumale'
-```
-
-### Numo::OpenBLAS
-[Numo::OpenBLAS](https://github.com/yoshoku/numo-openblas) downloads and builds OpenBLAS during installation
-and uses that as a background library for Numo::Linalg.
-
-Install compilers for building OpenBLAS.
-
-macOS:
-
-```bash
-$ brew install gcc gfortran make
-```
-
-Ubuntu:
-
-```bash
-$ sudo apt-get install gcc gfortran make
-```
-
-Fedora:
-
-```bash
-$ sudo dnf install gcc gcc-gfortran make
-```
-
-Install Numo::OpenBLAS gem.
-
-```bash
-$ gem install numo-openblas
-```
-
-Load Numo::OpenBLAS gem instead of Numo::Linalg.
-
-```ruby
-require 'numo/openblas'
-require 'rumale'
-```
-
-### Numo::BLIS
-[Numo::BLIS](https://github.com/yoshoku/numo-blis) downloads and builds BLIS during installation
-and uses that as a background library for Numo::Linalg.
-BLIS is one of the high-performance BLAS as with OpenBLAS,
-and using that can be expected to speed up of processing in Rumale.
-
-Install Numo::BLIS gem.
-
-```bash
-$ gem install numo-blis
-```
-
-Load Numo::BLIS gem instead of Numo::Linalg.
-
-```ruby
-require 'numo/blis'
-require 'rumale'
-```
-
-### Parallel
-Several estimators in Rumale support parallel processing.
-Parallel processing in Rumale is realized by [Parallel](https://github.com/grosser/parallel) gem,
-so install and load it.
-
-```bash
-$ gem install parallel
-```
-
-```ruby
-require 'parallel'
-require 'rumale'
-```
-
-Estimators that support parallel processing have n_jobs parameter.
-When -1 is given to n_jobs parameter, all processors are used.
-
-```ruby
-estimator = Rumale::Ensemble::RandomForestClassifier.new(n_jobs: -1, random_seed: 1)
-```
-
-## Related Projects
-- [Rumale::SVM](https://github.com/yoshoku/rumale-svm) provides support vector machine algorithms in LIBSVM and LIBLINEAR with Rumale interface.
-- [Rumale::Torch](https://github.com/yoshoku/rumale-torch) provides the learning and inference by the neural network defined in torch.rb with Rumale interface.
-
-## Novelties
-
-* [Rumale SHOP](https://suzuri.jp/yoshoku)
-
-## Contributing
-
-Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/rumale.
-This project is intended to be a safe, welcoming space for collaboration,
-and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
-
 ## License
 
-The gem is available as open source under the terms of the [BSD 2-clause License](https://opensource.org/licenses/BSD-2-Clause).
-
-## Code of Conduct
-
-Everyone interacting in the Rumale project’s codebases, issue trackers,
-chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/Rumale/blob/main/CODE_OF_CONDUCT.md).
+The gem is available as open source under the terms of the [BSD-3-Clause License](https://opensource.org/licenses/BSD-3-Clause).

data/lib/rumale/version.rb

@@ -3,5 +3,5 @@
 # Rumale is a machine learning library in Ruby.
 module Rumale
   # The version of Rumale you are using.
-  VERSION = '0.23.3'
+  VERSION = '0.24.0'
 end

data/lib/rumale.rb

@@ -2,135 +2,24 @@
 
 require 'numo/narray'
 
+require 'rumale/core'
+
+require 'rumale/clustering'
+require 'rumale/decomposition'
+require 'rumale/ensemble'
+require 'rumale/evaluation_measure'
+require 'rumale/feature_extraction'
+require 'rumale/kernel_approximation'
+require 'rumale/kernel_machine'
+require 'rumale/linear_model'
+require 'rumale/manifold'
+require 'rumale/metric_learning'
+require 'rumale/model_selection'
+require 'rumale/naive_bayes'
+require 'rumale/nearest_neighbors'
+require 'rumale/neural_network'
+require 'rumale/pipeline'
+require 'rumale/preprocessing'
+require 'rumale/tree'
+
 require_relative 'rumale/version'
-require_relative 'rumale/rumaleext'
-require_relative 'rumale/validation'
-require_relative 'rumale/values'
-require_relative 'rumale/utils'
-require_relative 'rumale/pairwise_metric'
-require_relative 'rumale/dataset'
-require_relative 'rumale/probabilistic_output'
-require_relative 'rumale/base/base_estimator'
-require_relative 'rumale/base/classifier'
-require_relative 'rumale/base/regressor'
-require_relative 'rumale/base/cluster_analyzer'
-require_relative 'rumale/base/transformer'
-require_relative 'rumale/base/splitter'
-require_relative 'rumale/base/evaluator'
-require_relative 'rumale/pipeline/pipeline'
-require_relative 'rumale/pipeline/feature_union'
-require_relative 'rumale/kernel_approximation/rbf'
-require_relative 'rumale/kernel_approximation/nystroem'
-require_relative 'rumale/linear_model/base_sgd'
-require_relative 'rumale/linear_model/svc'
-require_relative 'rumale/linear_model/svr'
-require_relative 'rumale/linear_model/logistic_regression'
-require_relative 'rumale/linear_model/linear_regression'
-require_relative 'rumale/linear_model/ridge'
-require_relative 'rumale/linear_model/lasso'
-require_relative 'rumale/linear_model/elastic_net'
-require_relative 'rumale/linear_model/nnls'
-require_relative 'rumale/kernel_machine/kernel_svc'
-require_relative 'rumale/kernel_machine/kernel_pca'
-require_relative 'rumale/kernel_machine/kernel_fda'
-require_relative 'rumale/kernel_machine/kernel_ridge'
-require_relative 'rumale/kernel_machine/kernel_ridge_classifier'
-require_relative 'rumale/multiclass/one_vs_rest_classifier'
-require_relative 'rumale/nearest_neighbors/vp_tree'
-require_relative 'rumale/nearest_neighbors/k_neighbors_classifier'
-require_relative 'rumale/nearest_neighbors/k_neighbors_regressor'
-require_relative 'rumale/naive_bayes/base_naive_bayes'
-require_relative 'rumale/naive_bayes/bernoulli_nb'
-require_relative 'rumale/naive_bayes/complement_nb'
-require_relative 'rumale/naive_bayes/gaussian_nb'
-require_relative 'rumale/naive_bayes/multinomial_nb'
-require_relative 'rumale/naive_bayes/negation_nb'
-require_relative 'rumale/tree/node'
-require_relative 'rumale/tree/base_decision_tree'
-require_relative 'rumale/tree/decision_tree_classifier'
-require_relative 'rumale/tree/decision_tree_regressor'
-require_relative 'rumale/tree/extra_tree_classifier'
-require_relative 'rumale/tree/extra_tree_regressor'
-require_relative 'rumale/tree/gradient_tree_regressor'
-require_relative 'rumale/ensemble/ada_boost_classifier'
-require_relative 'rumale/ensemble/ada_boost_regressor'
-require_relative 'rumale/ensemble/gradient_boosting_classifier'
-require_relative 'rumale/ensemble/gradient_boosting_regressor'
-require_relative 'rumale/ensemble/random_forest_classifier'
-require_relative 'rumale/ensemble/random_forest_regressor'
-require_relative 'rumale/ensemble/extra_trees_classifier'
-require_relative 'rumale/ensemble/extra_trees_regressor'
-require_relative 'rumale/ensemble/stacking_classifier'
-require_relative 'rumale/ensemble/stacking_regressor'
-require_relative 'rumale/ensemble/voting_classifier'
-require_relative 'rumale/ensemble/voting_regressor'
-require_relative 'rumale/clustering/k_means'
-require_relative 'rumale/clustering/mini_batch_k_means'
-require_relative 'rumale/clustering/k_medoids'
-require_relative 'rumale/clustering/gaussian_mixture'
-require_relative 'rumale/clustering/dbscan'
-require_relative 'rumale/clustering/hdbscan'
-require_relative 'rumale/clustering/snn'
-require_relative 'rumale/clustering/power_iteration'
-require_relative 'rumale/clustering/spectral_clustering'
-require_relative 'rumale/clustering/single_linkage'
-require_relative 'rumale/decomposition/pca'
-require_relative 'rumale/decomposition/nmf'
-require_relative 'rumale/decomposition/factor_analysis'
-require_relative 'rumale/decomposition/fast_ica'
-require_relative 'rumale/manifold/tsne'
-require_relative 'rumale/manifold/mds'
-require_relative 'rumale/metric_learning/fisher_discriminant_analysis'
-require_relative 'rumale/metric_learning/neighbourhood_component_analysis'
-require_relative 'rumale/metric_learning/mlkr'
-require_relative 'rumale/neural_network/adam'
-require_relative 'rumale/neural_network/base_mlp'
-require_relative 'rumale/neural_network/mlp_regressor'
-require_relative 'rumale/neural_network/mlp_classifier'
-require_relative 'rumale/feature_extraction/hash_vectorizer'
-require_relative 'rumale/feature_extraction/feature_hasher'
-require_relative 'rumale/feature_extraction/tfidf_transformer'
-require_relative 'rumale/preprocessing/l2_normalizer'
-require_relative 'rumale/preprocessing/l1_normalizer'
-require_relative 'rumale/preprocessing/max_normalizer'
-require_relative 'rumale/preprocessing/min_max_scaler'
-require_relative 'rumale/preprocessing/max_abs_scaler'
-require_relative 'rumale/preprocessing/standard_scaler'
-require_relative 'rumale/preprocessing/bin_discretizer'
-require_relative 'rumale/preprocessing/label_binarizer'
-require_relative 'rumale/preprocessing/label_encoder'
-require_relative 'rumale/preprocessing/one_hot_encoder'
-require_relative 'rumale/preprocessing/ordinal_encoder'
-require_relative 'rumale/preprocessing/binarizer'
-require_relative 'rumale/preprocessing/polynomial_features'
-require_relative 'rumale/preprocessing/kernel_calculator'
-require_relative 'rumale/model_selection/k_fold'
-require_relative 'rumale/model_selection/group_k_fold'
-require_relative 'rumale/model_selection/stratified_k_fold'
-require_relative 'rumale/model_selection/shuffle_split'
-require_relative 'rumale/model_selection/group_shuffle_split'
-require_relative 'rumale/model_selection/stratified_shuffle_split'
-require_relative 'rumale/model_selection/time_series_split'
-require_relative 'rumale/model_selection/cross_validation'
-require_relative 'rumale/model_selection/grid_search_cv'
-require_relative 'rumale/model_selection/function'
-require_relative 'rumale/evaluation_measure/accuracy'
-require_relative 'rumale/evaluation_measure/precision'
-require_relative 'rumale/evaluation_measure/recall'
-require_relative 'rumale/evaluation_measure/f_score'
-require_relative 'rumale/evaluation_measure/roc_auc'
-require_relative 'rumale/evaluation_measure/log_loss'
-require_relative 'rumale/evaluation_measure/r2_score'
-require_relative 'rumale/evaluation_measure/explained_variance_score'
-require_relative 'rumale/evaluation_measure/mean_squared_error'
-require_relative 'rumale/evaluation_measure/mean_squared_log_error'
-require_relative 'rumale/evaluation_measure/mean_absolute_error'
-require_relative 'rumale/evaluation_measure/median_absolute_error'
-require_relative 'rumale/evaluation_measure/adjusted_rand_score'
-require_relative 'rumale/evaluation_measure/purity'
-require_relative 'rumale/evaluation_measure/mutual_information'
-require_relative 'rumale/evaluation_measure/normalized_mutual_information'
-require_relative 'rumale/evaluation_measure/silhouette_score'
-require_relative 'rumale/evaluation_measure/davies_bouldin_score'
-require_relative 'rumale/evaluation_measure/calinski_harabasz_score'
-require_relative 'rumale/evaluation_measure/function'