honzasterba_xgb 0.9.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 3808423fd61bfa3477189d83dcdb0789ff146f9ad9f9a35ac08394da5d2badb6
+  data.tar.gz: fabbd9b1d5fc5e9110e8af9ac37dd1d9d7cb80ad463e0836af88b627aab5a510
+SHA512:
+  metadata.gz: 48d0a215e06cd3d6a4de12a347dda259313bca7498b6ba5a173299368968eef52236379826602dbbc04eb3eb7fa8d6cae52cc10185d68d660a2ed2151fd003d7
+  data.tar.gz: bcdc78c430d76b4f95b537012b6dc8c03763ae86b20a5e3d5c038bb7b12651d011eef99f8cdb4e825209621f649fd144cc9f826583fe5d2e7ff1d662e406c1c8

data/CHANGELOG.md

@@ -0,0 +1,116 @@
+## 0.9.1 (unreleased)
+
+- Updated XGBoost to 2.1.2
+
+## 0.9.0 (2024-10-17)
+
+- Updated XGBoost to 2.1.1
+- Added support for callbacks
+- Added `num_features` and `save_config` methods to `Booster`
+- Added `num_nonmissing` and `data_split_mode` methods to `DMatrix`
+- Dropped support for Ruby < 3.1
+
+## 0.8.0 (2023-09-13)
+
+- Updated XGBoost to 2.0.0
+- Dropped support for Ruby < 3
+
+## 0.7.3 (2023-07-24)
+
+- Fixed error with `dup` and `clone`
+
+## 0.7.2 (2023-05-12)
+
+- Updated XGBoost to 1.7.5
+- Added musl shared library for Linux
+- Improved error message for invalid matrix
+
+## 0.7.1 (2022-10-31)
+
+- Updated XGBoost to 1.7.0
+
+## 0.7.0 (2022-06-05)
+
+- Updated XGBoost to 1.6.1
+- Improved ARM detection
+- Dropped support for Ruby < 2.7
+
+## 0.6.0 (2021-10-23)
+
+- Updated XGBoost to 1.5.0
+
+## 0.5.3 (2021-05-12)
+
+- Updated XGBoost to 1.4.0
+- Added ARM shared library for Linux
+
+## 0.5.2 (2021-03-09)
+
+- Added ARM shared library for Mac
+
+## 0.5.1 (2021-02-08)
+
+- Fixed error with validation sets without early stopping
+
+## 0.5.0 (2020-12-12)
+
+- Updated XGBoost to 1.3.0
+
+## 0.4.1 (2020-08-26)
+
+- Updated XGBoost to 1.2.0
+
+## 0.4.0 (2020-05-17)
+
+- Updated XGBoost to 1.1.0
+- Changed default `learning_rate` and `max_depth` for Scikit-Learn API to match Python
+- Added support for Rover
+- Improved performance of Numo datasets
+- Improved error message when OpenMP not found on Mac
+
+## 0.3.1 (2020-04-16)
+
+- Added `feature_names` and `feature_types` to `DMatrix`
+- Added feature names to `dump`
+
+## 0.3.0 (2020-02-19)
+
+- Updated XGBoost to 1.0.0
+
+## 0.2.1 (2020-02-11)
+
+- Fixed `Could not find XGBoost` error on some Linux platforms
+- Fixed `SignalException` on Windows
+
+## 0.2.0 (2020-01-26)
+
+- Prefer `XGBoost` over `Xgb`
+- Changed to Apache 2.0 license to match XGBoost
+- Added shared libraries
+- Added support for booster attributes
+
+## 0.1.3 (2019-10-27)
+
+- Added support for missing values
+- Fixed Daru training and prediction
+- Fixed error with JRuby
+
+## 0.1.2 (2019-08-19)
+
+- Friendlier message when XGBoost not found
+- Free memory when objects are destroyed
+- Added `Ranker`
+- Added early stopping to Scikit-Learn API
+
+## 0.1.1 (2019-08-16)
+
+- Added Scikit-Learn API
+- Added early stopping
+- Added `cv` method
+- Added support for Daru and Numo::NArray
+- Added many other methods
+- Fixed shape of multiclass predictions when loaded from file
+
+## 0.1.0 (2019-08-15)
+
+- First release

data/LICENSE.txt

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

data/NOTICE.txt

@@ -0,0 +1,14 @@
+Copyright XGBoost contributors
+Copyright 2019-2024 Andrew Kane
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.md

@@ -0,0 +1,195 @@
+# XGBoost Ruby
+
+[XGBoost](https://github.com/dmlc/xgboost) - high performance gradient boosting - for Ruby
+
+[![Build Status](https://github.com/ankane/xgboost-ruby/actions/workflows/build.yml/badge.svg)](https://github.com/ankane/xgboost-ruby/actions)
+
+## Installation
+
+Add this line to your application’s Gemfile:
+
+```ruby
+gem "xgb"
+```
+
+On Mac, also install OpenMP:
+
+```sh
+brew install libomp
+```
+
+## Learning API
+
+Prep your data
+
+```ruby
+x = [[1, 2], [3, 4], [5, 6], [7, 8]]
+y = [1, 2, 3, 4]
+```
+
+Train a model
+
+```ruby
+params = {objective: "reg:squarederror"}
+dtrain = XGBoost::DMatrix.new(x, label: y)
+booster = XGBoost.train(params, dtrain)
+```
+
+Predict
+
+```ruby
+dtest = XGBoost::DMatrix.new(x)
+booster.predict(dtest)
+```
+
+Save the model to a file
+
+```ruby
+booster.save_model("my.model")
+```
+
+Load the model from a file
+
+```ruby
+booster = XGBoost::Booster.new(model_file: "my.model")
+```
+
+Get the importance of features
+
+```ruby
+booster.score
+```
+
+Early stopping
+
+```ruby
+XGBoost.train(params, dtrain, evals: [[dtrain, "train"], [dtest, "eval"]], early_stopping_rounds: 5)
+```
+
+CV
+
+```ruby
+XGBoost.cv(params, dtrain, nfold: 3, verbose_eval: true)
+```
+
+Set metadata about a model
+
+```ruby
+booster["key"] = "value"
+booster.attributes
+```
+
+## Scikit-Learn API
+
+Prep your data
+
+```ruby
+x = [[1, 2], [3, 4], [5, 6], [7, 8]]
+y = [1, 2, 3, 4]
+```
+
+Train a model
+
+```ruby
+model = XGBoost::Regressor.new
+model.fit(x, y)
+```
+
+> For classification, use `XGBoost::Classifier`
+
+Predict
+
+```ruby
+model.predict(x)
+```
+
+> For classification, use `predict_proba` for probabilities
+
+Save the model to a file
+
+```ruby
+model.save_model("my.model")
+```
+
+Load the model from a file
+
+```ruby
+model.load_model("my.model")
+```
+
+Get the importance of features
+
+```ruby
+model.feature_importances
+```
+
+Early stopping
+
+```ruby
+model.fit(x, y, eval_set: [[x_test, y_test]], early_stopping_rounds: 5)
+```
+
+## Data
+
+Data can be an array of arrays
+
+```ruby
+[[1, 2, 3], [4, 5, 6]]
+```
+
+Or a Numo array
+
+```ruby
+Numo::NArray.cast([[1, 2, 3], [4, 5, 6]])
+```
+
+Or a Rover data frame
+
+```ruby
+Rover.read_csv("houses.csv")
+```
+
+Or a Daru data frame
+
+```ruby
+Daru::DataFrame.from_csv("houses.csv")
+```
+
+## Helpful Resources
+
+- [Parameters](https://xgboost.readthedocs.io/en/latest/parameter.html)
+- [Parameter Tuning](https://xgboost.readthedocs.io/en/latest/tutorials/param_tuning.html)
+
+## Related Projects
+
+- [LightGBM](https://github.com/ankane/lightgbm) - LightGBM for Ruby
+- [Eps](https://github.com/ankane/eps) - Machine learning for Ruby
+
+## Credits
+
+This library follows the [Python API](https://xgboost.readthedocs.io/en/latest/python/python_api.html), with the `get_` and `set_` prefixes removed from methods to make it more Ruby-like.
+
+Thanks to the [xgboost](https://github.com/PairOnAir/xgboost-ruby) gem for showing how to use FFI.
+
+## History
+
+View the [changelog](https://github.com/ankane/xgboost-ruby/blob/master/CHANGELOG.md)
+
+## Contributing
+
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
+
+- [Report bugs](https://github.com/ankane/xgboost-ruby/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/xgboost-ruby/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/ankane/xgboost-ruby.git
+cd xgboost-ruby
+bundle install
+bundle exec rake vendor:all
+bundle exec rake test
+```

data/lib/xgb.rb

@@ -0,0 +1,4 @@
+require_relative "xgboost"
+
+# legacy
+Xgb = XGBoost