rumale 0.22.0 → 0.22.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4e2f68b3182ada73537901e7bc74bddd100aff75264f9147c88d8240fb624e29
-  data.tar.gz: e2639a55fc84d1399b925f65b3a56b38f2ae3150dd15ab8556120af28d408cae
+  metadata.gz: '058078489d3ff66d67432e1418ae786292c263e05e75b6703fb5a7e65e88bd46'
+  data.tar.gz: bd7ed9b223e0cd0074ffdd3e521b01c195f82909013c93f4736ab338d5920c96
 SHA512:
-  metadata.gz: 91ffcbade578bbb9c6a5d87a54ebd89a2b5990eb70835e7a5549afe78541dbfeafe3af50833725bee751fa89c059484970e5add7ebf8adee3e25bc000fbe3778
-  data.tar.gz: 2ee2b1448a486581ef98561f65bc3446b2e161c89a3a12bd6cd78867350e26151bc0b350bd431902d21f6979493ab2d01a6ee81b55c1099f631aa84c84a704e6
+  metadata.gz: 79ce4715a503b1b5a618526832adad5912daac72af3e8f1892ff2df14b7695e546419d6f85e5ea735abd2ea06da649a763f96c82b95eee75341934fa65fce93e
+  data.tar.gz: 5948583ec6c5ca10b320e09c447f9cc1e244dd3bfbf95800338dba2eb7e1b46a342d44020fa24c26a7161786feb63c82b0677654e4aa087c311337a606880a22

data/.coveralls.yml

@@ -0,0 +1 @@
+service_name: github-ci

data/.github/workflows/build.yml

@@ -1,13 +1,14 @@
 name: build
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
-        ruby: [ '2.5', '2.6', '2.7' ]
+        ruby: [ '2.5', '2.6', '2.7', '3.0' ]
     steps:
       - uses: actions/checkout@v2
       - name: Install BLAS and LAPACK
@@ -17,7 +18,9 @@ jobs:
         with:
           ruby-version: ${{ matrix.ruby }}
       - name: Build and test with Rake
+        env:
+          LD_LIBRARY_PATH: '/usr/lib/x86_64-linux-gnu/'
         run: |
-          gem install bundler
+          gem install --no-document bundler
           bundle install --jobs 4 --retry 3
           bundle exec rake

data/.github/workflows/coverage.yml

@@ -0,0 +1,28 @@
+name: coverage
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  coverage:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+      - name: Install BLAS and LAPACK
+        run: sudo apt-get install -y libopenblas-dev liblapacke-dev
+      - name: Set up Ruby 2.7
+        uses: actions/setup-ruby@v1
+        with:
+          ruby-version: '2.7'
+      - name: Build and test with Rake
+        run: |
+          gem install bundler
+          bundle install
+          bundle exec rake
+      - name: Coveralls GitHub Action
+        uses: coverallsapp/github-action@v1.1.2
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}

data/.gitignore

@@ -16,6 +16,7 @@
 tags
 .DS_Store
 .ruby-version
+iterate.dat
 /spec/dump_dbl.t
 /spec/dump_int.t
 /spec/dump_mult_dbl.t

data/.rubocop.yml

@@ -1,5 +1,6 @@
 require:
   - rubocop-performance
+  - rubocop-rake
   - rubocop-rspec
 
 AllCops:

data/CHANGELOG.md

@@ -1,3 +1,38 @@
+# 0.22.5
+- Add transformer class for calculating kernel matrix.
+  - [KernelCalculator](https://yoshoku.github.io/rumale/doc/Rumale/Preprocessing/KernelCalculator.html)
+- Add classifier class based on Ridge regression.
+  - [KernelRidgeClassifier](https://yoshoku.github.io/rumale/doc/Rumale/KernelMachine/KernelRidgeClassifier.html)
+- Add supported kernel functions to [Nystroem](https://yoshoku.github.io/rumale/doc/Rumale/KernelApproximation/Nystroem.html).
+- Add parameter for specifying the number of features to [load_libsvm_file](https://yoshoku.github.io/rumale/doc/Rumale/Dataset.html#load_libsvm_file-class_method).
+
+# 0.22.4
+- Add classifier and regressor classes for voting ensemble method.
+  - [VotingClassifier](https://yoshoku.github.io/rumale/doc/Rumale/Ensemble/VotingClassifier.html)
+  - [VotingRegressor](https://yoshoku.github.io/rumale/doc/Rumale/Ensemble/VotingRegressor.html)
+- Refactor some codes.
+- Fix some typos on API documentation.
+
+# 0.22.3
+- Add regressor class for non-negative least square method.
+  - [NNLS](https://yoshoku.github.io/rumale/doc/Rumale/LinearModel/NNLS.html)
+- Add lbfgs solver to [Ridge](https://yoshoku.github.io/rumale/doc/Rumale/LinearModel/Ridge.html) and [LinearRegression](https://yoshoku.github.io/rumale/doc/Rumale/LinearModel/LinearRegression.html).
+  - In version 0.23.0, these classes will be changed to attempt to optimize with 'svd' or 'lbfgs' solver if 'auto' is given to
+  the solver parameter. If you use 'sgd' solver, you need specify it explicitly.
+- Add GC guard to native extension codes.
+- Update API documentation.
+
+# 0.22.2
+- Add classifier and regressor classes for stacking method.
+  - [StackingClassifier](https://yoshoku.github.io/rumale/doc/Rumale/Ensemble/StackingClassifier.html)
+  - [StackingRegressor](https://yoshoku.github.io/rumale/doc/Rumale/Ensemble/StackingRegressor.html)
+- Refactor some codes with Rubocop.
+
+# 0.22.1
+- Add transfomer class for [MLKR](https://yoshoku.github.io/rumale/doc/Rumale/MetricLearning/MLKR.html), that implements Metric Learning for Kernel Regression.
+- Refactor NeighbourhoodComponentAnalysis.
+- Update API documentation.
+
 # 0.22.0
 ## Breaking change
 - Add lbfgsb.rb gem to runtime dependencies. Rumale uses lbfgsb gem for optimization.

data/Gemfile

@@ -6,10 +6,12 @@ gemspec
 gem 'mmh3', '>= 1.0'
 gem 'numo-linalg', '>= 0.1.4'
 gem 'parallel', '>= 1.17.0'
-gem 'rake', '~> 12.0'
+gem 'rake', '~> 13.0'
 gem 'rake-compiler', '~> 1.0'
 gem 'rspec', '~> 3.0'
-gem 'rubocop', '~> 0.91'
+gem 'rubocop', '~> 1.0'
 gem 'rubocop-performance', '~> 1.8'
-gem 'rubocop-rspec', '~> 1.43'
-gem 'simplecov', '~> 0.19'
+gem 'rubocop-rake', '~> 0.5'
+gem 'rubocop-rspec', '~> 2.0'
+gem 'simplecov', '~> 0.21'
+gem 'simplecov-lcov', '~> 0.8'

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2017-2020 Atsushi Tatsuma
+Copyright (c) 2017-2021 Atsushi Tatsuma
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -3,8 +3,9 @@
 ![Rumale](https://dl.dropboxusercontent.com/s/joxruk2720ur66o/rumale_header_400.png)
 
 [![Build Status](https://github.com/yoshoku/rumale/workflows/build/badge.svg)](https://github.com/yoshoku/rumale/actions?query=workflow%3Abuild)
+[![Coverage Status](https://coveralls.io/repos/github/yoshoku/rumale/badge.svg?branch=main)](https://coveralls.io/github/yoshoku/rumale?branch=main)
 [![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/master/LICENSE.txt)
+[![BSD 2-Clause License](https://img.shields.io/badge/License-BSD%202--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.
@@ -113,10 +114,10 @@ require 'rumale'
 samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
 
 # Define the estimator to be evaluated.
-lr = Rumale::LinearModel::LogisticRegression.new(learning_rate: 0.00001, reg_param: 0.0001, random_seed: 1)
+lr = Rumale::LinearModel::LogisticRegression.new
 
 # Define the evaluation measure, splitting strategy, and cross validation.
-ev = Rumale::EvaluationMeasure::LogLoss.new
+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)
 
@@ -124,15 +125,15 @@ cv = Rumale::ModelSelection::CrossValidation.new(estimator: lr, splitter: kf, ev
 report = cv.perform(samples, labels)
 
 # Output result.
-mean_logloss = report[:test_score].inject(:+) / kf.n_splits
-puts("5-CV mean log-loss: %.3f" % mean_logloss)
+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 log-loss: 0.355
+5-CV mean accuracy: 95.4%
 ```
 
 ### Example 3. Pipeline
@@ -143,10 +144,10 @@ require 'rumale'
 # Load dataset.
 samples, labels = Rumale::Dataset.load_libsvm_file('pendigits')
 
-# Construct pipeline with kernel approximation and SVC.
-rbf = Rumale::KernelApproximation::RBF.new(gamma: 0.0001, n_components: 800, random_seed: 1)
-svc = Rumale::LinearModel::SVC.new(reg_param: 0.0001, random_seed: 1)
-pipeline = Rumale::Pipeline::Pipeline.new(steps: { trns: rbf, clsf: svc })
+# 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)
@@ -156,7 +157,7 @@ cv = Rumale::ModelSelection::CrossValidation.new(estimator: pipeline, splitter:
 report = cv.perform(samples, labels)
 
 # Output result.
-mean_accuracy = report[:test_score].inject(:+) / kf.n_splits
+mean_accuracy = report[:test_score].sum / kf.n_splits
 puts("5-CV mean accuracy: %.1f %%" % (mean_accuracy * 100.0))
 ```
 
@@ -176,7 +177,7 @@ For example, using the [OpenBLAS](https://github.com/xianyi/OpenBLAS) speeds up
 
 Install OpenBLAS library.
 
-Mac:
+macOS:
 
 ```bash
 $ brew install openblas
@@ -185,12 +186,13 @@ $ brew install openblas
 Ubuntu:
 
 ```bash
-$ sudo apt-get install gcc gfortran
-$ wget https://github.com/xianyi/OpenBLAS/archive/v0.3.5.tar.gz
-$ tar xzf v0.3.5.tar.gz
-$ cd OpenBLAS-0.3.5
-$ make USE_OPENMP=1
-$ sudo make PREFIX=/usr/local install
+$ sudo apt-get install libopenblas-dev liblapacke-dev
+```
+
+Windows (MSYS2):
+
+```bash
+$ pacman -S mingw-w64-x86_64-ruby mingw-w64-x86_64-openblas mingw-w64-x86_64-lapack
 ```
 
 Install Numo::Linalg gem.
@@ -206,6 +208,37 @@ 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
+```
+
+Install Numo::OpenBLAS gem.
+
+```bash
+$ gem install numo-openblas
+```
+
+Load Numo::OpenBLAS gem instead of Numo::Linalg.
+
+```ruby
+require 'numo/openblas'
+require 'rumale'
+```
+
 ### Parallel
 Several estimators in Rumale support parallel processing.
 Parallel processing in Rumale is realized by [Parallel](https://github.com/grosser/parallel) gem,
@@ -227,6 +260,10 @@ When -1 is given to n_jobs parameter, all processors are used.
 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)
@@ -244,4 +281,4 @@ The gem is available as open source under the terms of the [BSD 2-clause License
 ## 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/master/CODE_OF_CONDUCT.md).
+chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/Rumale/blob/main/CODE_OF_CONDUCT.md).

data/ext/rumale/tree.c

@@ -5,9 +5,8 @@ RUBY_EXTERN VALUE mRumale;
 double*
 alloc_dbl_array(const long n_dimensions)
 {
-  long i;
   double* arr = ALLOC_N(double, n_dimensions);
-  for (i = 0; i < n_dimensions; i++) { arr[i] = 0.0; }
+  memset(arr, 0, n_dimensions * sizeof(double));
   return arr;
 }
 
@@ -257,10 +256,13 @@ find_split_params_cls(VALUE self, VALUE criterion, VALUE impurity, VALUE order,
   split_opts_cls opts = { StringValuePtr(criterion), NUM2LONG(n_classes), NUM2DBL(impurity) };
   VALUE params = na_ndloop3(&ndf, &opts, 3, order, features, labels);
   VALUE results = rb_ary_new2(4);
-  rb_ary_store(results, 0, DBL2NUM(((double*)na_get_pointer_for_read(params))[0]));
-  rb_ary_store(results, 1, DBL2NUM(((double*)na_get_pointer_for_read(params))[1]));
-  rb_ary_store(results, 2, DBL2NUM(((double*)na_get_pointer_for_read(params))[2]));
-  rb_ary_store(results, 3, DBL2NUM(((double*)na_get_pointer_for_read(params))[3]));
+  double* params_ptr = (double*)na_get_pointer_for_read(params);
+  rb_ary_store(results, 0, DBL2NUM(params_ptr[0]));
+  rb_ary_store(results, 1, DBL2NUM(params_ptr[1]));
+  rb_ary_store(results, 2, DBL2NUM(params_ptr[2]));
+  rb_ary_store(results, 3, DBL2NUM(params_ptr[3]));
+  RB_GC_GUARD(params);
+  RB_GC_GUARD(criterion);
   return results;
 }
 
@@ -375,10 +377,13 @@ find_split_params_reg(VALUE self, VALUE criterion, VALUE impurity, VALUE order,
   split_opts_reg opts = { StringValuePtr(criterion), NUM2DBL(impurity) };
   VALUE params = na_ndloop3(&ndf, &opts, 3, order, features, targets);
   VALUE results = rb_ary_new2(4);
-  rb_ary_store(results, 0, DBL2NUM(((double*)na_get_pointer_for_read(params))[0]));
-  rb_ary_store(results, 1, DBL2NUM(((double*)na_get_pointer_for_read(params))[1]));
-  rb_ary_store(results, 2, DBL2NUM(((double*)na_get_pointer_for_read(params))[2]));
-  rb_ary_store(results, 3, DBL2NUM(((double*)na_get_pointer_for_read(params))[3]));
+  double* params_ptr = (double*)na_get_pointer_for_read(params);
+  rb_ary_store(results, 0, DBL2NUM(params_ptr[0]));
+  rb_ary_store(results, 1, DBL2NUM(params_ptr[1]));
+  rb_ary_store(results, 2, DBL2NUM(params_ptr[2]));
+  rb_ary_store(results, 3, DBL2NUM(params_ptr[3]));
+  RB_GC_GUARD(params);
+  RB_GC_GUARD(criterion);
   return results;
 }
 
@@ -464,8 +469,10 @@ find_split_params_grad_reg
   double opts[3] = { NUM2DBL(sum_gradient), NUM2DBL(sum_hessian), NUM2DBL(reg_lambda) };
   VALUE params = na_ndloop3(&ndf, opts, 4, order, features, gradients, hessians);
   VALUE results = rb_ary_new2(2);
-  rb_ary_store(results, 0, DBL2NUM(((double*)na_get_pointer_for_read(params))[0]));
-  rb_ary_store(results, 1, DBL2NUM(((double*)na_get_pointer_for_read(params))[1]));
+  double* params_ptr = (double*)na_get_pointer_for_read(params);
+  rb_ary_store(results, 0, DBL2NUM(params_ptr[0]));
+  rb_ary_store(results, 1, DBL2NUM(params_ptr[1]));
+  RB_GC_GUARD(params);
   return results;
 }
 
@@ -497,6 +504,9 @@ node_impurity_cls(VALUE self, VALUE criterion, VALUE y_nary, VALUE n_elements_,
 
   xfree(histogram);
 
+  RB_GC_GUARD(y_nary);
+  RB_GC_GUARD(criterion);
+
   return ret;
 }
 
@@ -531,6 +541,8 @@ node_impurity_reg(VALUE self, VALUE criterion, VALUE y)
 
   xfree(sum_vec);
 
+  RB_GC_GUARD(criterion);
+
   return ret;
 }
 

data/lib/rumale.rb

@@ -30,10 +30,12 @@ require 'rumale/linear_model/linear_regression'
 require 'rumale/linear_model/ridge'
 require 'rumale/linear_model/lasso'
 require 'rumale/linear_model/elastic_net'
+require 'rumale/linear_model/nnls'
 require 'rumale/kernel_machine/kernel_svc'
 require 'rumale/kernel_machine/kernel_pca'
 require 'rumale/kernel_machine/kernel_fda'
 require 'rumale/kernel_machine/kernel_ridge'
+require 'rumale/kernel_machine/kernel_ridge_classifier'
 require 'rumale/multiclass/one_vs_rest_classifier'
 require 'rumale/nearest_neighbors/vp_tree'
 require 'rumale/nearest_neighbors/k_neighbors_classifier'
@@ -59,6 +61,10 @@ require 'rumale/ensemble/random_forest_classifier'
 require 'rumale/ensemble/random_forest_regressor'
 require 'rumale/ensemble/extra_trees_classifier'
 require 'rumale/ensemble/extra_trees_regressor'
+require 'rumale/ensemble/stacking_classifier'
+require 'rumale/ensemble/stacking_regressor'
+require 'rumale/ensemble/voting_classifier'
+require 'rumale/ensemble/voting_regressor'
 require 'rumale/clustering/k_means'
 require 'rumale/clustering/mini_batch_k_means'
 require 'rumale/clustering/k_medoids'
@@ -77,6 +83,7 @@ require 'rumale/manifold/tsne'
 require 'rumale/manifold/mds'
 require 'rumale/metric_learning/fisher_discriminant_analysis'
 require 'rumale/metric_learning/neighbourhood_component_analysis'
+require 'rumale/metric_learning/mlkr'
 require 'rumale/neural_network/adam'
 require 'rumale/neural_network/base_mlp'
 require 'rumale/neural_network/mlp_regressor'
@@ -97,6 +104,7 @@ require 'rumale/preprocessing/one_hot_encoder'
 require 'rumale/preprocessing/ordinal_encoder'
 require 'rumale/preprocessing/binarizer'
 require 'rumale/preprocessing/polynomial_features'
+require 'rumale/preprocessing/kernel_calculator'
 require 'rumale/model_selection/k_fold'
 require 'rumale/model_selection/group_k_fold'
 require 'rumale/model_selection/stratified_k_fold'

data/lib/rumale/base/base_estimator.rb

@@ -11,13 +11,15 @@ module Rumale
 
       private
 
-      def enable_linalg?
+      def enable_linalg?(warning: true)
         if defined?(Numo::Linalg).nil?
-          warn('If you want to use features that depend on Numo::Linalg, you should install and load Numo::Linalg in advance.')
+          warn('If you want to use features that depend on Numo::Linalg, you should install and load Numo::Linalg in advance.') if warning
           return false
         end
         if Numo::Linalg::VERSION < '0.1.4'
-          warn('The loaded Numo::Linalg does not implement the methods required by Rumale. Please load Numo::Linalg version 0.1.4 or later.')
+          if warning
+            warn('The loaded Numo::Linalg does not implement the methods required by Rumale. Please load Numo::Linalg version 0.1.4 or later.')
+          end
           return false
         end
         true

data/lib/rumale/dataset.rb

@@ -12,22 +12,26 @@ module Rumale
       # Load a dataset with the libsvm file format into Numo::NArray.
       #
       # @param filename [String] A path to a dataset file.
+      # @param n_features [Integer/Nil] The number of features of data to load.
+      #   If nil is given, it will be detected automatically from given file.
       # @param zero_based [Boolean] Whether the column index starts from 0 (true) or 1 (false).
       # @param dtype [Numo::NArray] Data type of Numo::NArray for features to be loaded.
       #
       # @return [Array<Numo::NArray>]
       #   Returns array containing the (n_samples x n_features) matrix for feature vectors
       #   and (n_samples) vector for labels or target values.
-      def load_libsvm_file(filename, zero_based: false, dtype: Numo::DFloat)
+      def load_libsvm_file(filename, n_features: nil, zero_based: false, dtype: Numo::DFloat)
         ftvecs = []
         labels = []
-        n_features = 0
+        n_features_detected = 0
         CSV.foreach(filename, col_sep: "\s", headers: false) do |line|
           label, ftvec, max_idx = parse_libsvm_line(line, zero_based)
           labels.push(label)
           ftvecs.push(ftvec)
-          n_features = max_idx if n_features < max_idx
+          n_features_detected = max_idx if n_features_detected < max_idx
         end
+        n_features ||= n_features_detected
+        n_features = [n_features, n_features_detected].max
         [convert_to_matrix(ftvecs, n_features, dtype), Numo::NArray.asarray(labels)]
       end