boost-loss


Nameboost-loss JSON
Version 0.5.5 PyPI version JSON
download
home_pagehttps://github.com/34j/boost-loss
SummaryUtilities for easy use of custom losses in CatBoost, LightGBM, XGBoost
upload_time2024-01-26 06:50:04
maintainer
docs_urlNone
author34j
requires_python>=3.8,<4.0
licenseMIT
keywords
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls. 
            # Boost Loss

<p align="center">
  <a href="https://github.com/34j/boost-loss/actions/workflows/ci.yml?query=branch%3Amain">
    <img src="https://img.shields.io/github/actions/workflow/status/34j/boost-loss/ci.yml?branch=main&label=CI&logo=github&style=flat-square" alt="CI Status" >
  </a>
  <a href="https://boost-loss.readthedocs.io">
    <img src="https://img.shields.io/readthedocs/boost-loss.svg?logo=read-the-docs&logoColor=fff&style=flat-square" alt="Documentation Status">
  </a>
  <a href="https://codecov.io/gh/34j/boost-loss">
    <img src="https://img.shields.io/codecov/c/github/34j/boost-loss.svg?logo=codecov&logoColor=fff&style=flat-square" alt="Test coverage percentage">
  </a>
</p>
<p align="center">
  <a href="https://python-poetry.org/">
    <img src="https://img.shields.io/badge/packaging-poetry-299bd7?style=flat-square&logo=data:image/png;base64,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" alt="Poetry">
  </a>
  <a href="https://github.com/ambv/black">
    <img src="https://img.shields.io/badge/code%20style-black-000000.svg?style=flat-square" alt="black">
  </a>
  <a href="https://github.com/pre-commit/pre-commit">
    <img src="https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white&style=flat-square" alt="pre-commit">
  </a>
</p>
<p align="center">
  <a href="https://pypi.org/project/boost-loss/">
    <img src="https://img.shields.io/pypi/v/boost-loss.svg?logo=python&logoColor=fff&style=flat-square" alt="PyPI Version">
  </a>
  <img src="https://img.shields.io/pypi/pyversions/boost-loss.svg?style=flat-square&logo=python&amp;logoColor=fff" alt="Supported Python versions">
  <img src="https://img.shields.io/pypi/l/boost-loss.svg?style=flat-square" alt="License">
</p>

Utilities for easy use of custom losses in CatBoost, LightGBM, XGBoost. This sounds very simple, but in reality it took a lot of work.

## Installation

Install this via pip (or your favourite package manager):

```shell
pip install boost-loss
```

## Usage

### Basic Usage

```python
import numpy as np

from boost_loss import LossBase
from numpy.typing import NDArray


class L2Loss(LossBase):
    def loss(self, y_true: NDArray, y_pred: NDArray) -> NDArray:
        return (y_true - y_pred) ** 2 / 2

    def grad(self, y_true: NDArray, y_pred: NDArray) -> NDArray: # dL/dy_pred
        return - (y_true - y_pred)

    def hess(self, y_true: NDArray, y_pred: NDArray) -> NDArray: # d^2L/dy_pred^2
        return np.ones_like(y_true)
```

```python
import lightgbm as lgb

from boost_loss import apply_custom_loss
from sklearn.datasets import load_boston


X, y = load_boston(return_X_y=True)
apply_custom_loss(lgb.LGBMRegressor(), L2Loss()).fit(X, y)
```

Built-in losses are available. [^bokbokbok]

```python
from boost_loss.regression import LogCoshLoss
```

### [`torch.autograd`](https://pytorch.org/docs/stable/autograd.html) Loss [^autograd]

```python
import torch

from boost_loss.torch import TorchLossBase


class L2LossTorch(TorchLossBase):
    def loss_torch(self, y_true: torch.Tensor, y_pred: torch.Tensor) -> torch.Tensor:
        return (y_true - y_pred) ** 2 / 2
```

## Contributors ✨

Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):

<!-- prettier-ignore-start -->
<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->
<!-- prettier-ignore-start -->
<!-- markdownlint-disable -->
<table>
  <tbody>
    <tr>
      <td align="center" valign="top" width="14.28%"><a href="https://github.com/34j"><img src="https://avatars.githubusercontent.com/u/55338215?v=4?s=80" width="80px;" alt="34j"/><br /><sub><b>34j</b></sub></a><br /><a href="https://github.com/34j/boost-loss/commits?author=34j" title="Code">💻</a> <a href="#ideas-34j" title="Ideas, Planning, & Feedback">🤔</a> <a href="https://github.com/34j/boost-loss/commits?author=34j" title="Documentation">📖</a></td>
    </tr>
  </tbody>
</table>

<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->

<!-- ALL-CONTRIBUTORS-LIST:END -->
<!-- prettier-ignore-end -->

This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!

[^bokbokbok]: Inspired by [orchardbirds/bokbokbok](https://github.com/orchardbirds/bokbokbok)
[^autograd]: Inspired by [TomerRonen34/treeboost_autograd](https://github.com/TomerRonen34/treeboost_autograd)

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/34j/boost-loss",
    "name": "boost-loss",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.8,<4.0",
    "maintainer_email": "",
    "keywords": "",
    "author": "34j",
    "author_email": "34j.95a2p@simplelogin.com",
    "download_url": "https://files.pythonhosted.org/packages/ae/cf/849acb3e7bd97018d1c9764343e27debd89795e6f900cd89c30f978ab428/boost_loss-0.5.5.tar.gz",
    "platform": null,
    "description": "# Boost Loss\n\n<p align=\"center\">\n  <a href=\"https://github.com/34j/boost-loss/actions/workflows/ci.yml?query=branch%3Amain\">\n    <img src=\"https://img.shields.io/github/actions/workflow/status/34j/boost-loss/ci.yml?branch=main&label=CI&logo=github&style=flat-square\" alt=\"CI Status\" >\n  </a>\n  <a href=\"https://boost-loss.readthedocs.io\">\n    <img src=\"https://img.shields.io/readthedocs/boost-loss.svg?logo=read-the-docs&logoColor=fff&style=flat-square\" alt=\"Documentation Status\">\n  </a>\n  <a href=\"https://codecov.io/gh/34j/boost-loss\">\n    <img src=\"https://img.shields.io/codecov/c/github/34j/boost-loss.svg?logo=codecov&logoColor=fff&style=flat-square\" alt=\"Test coverage percentage\">\n  </a>\n</p>\n<p align=\"center\">\n  <a href=\"https://python-poetry.org/\">\n    <img src=\"https://img.shields.io/badge/packaging-poetry-299bd7?style=flat-square&logo=data:image/png;base64,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\" alt=\"Poetry\">\n  </a>\n  <a href=\"https://github.com/ambv/black\">\n    <img src=\"https://img.shields.io/badge/code%20style-black-000000.svg?style=flat-square\" alt=\"black\">\n  </a>\n  <a href=\"https://github.com/pre-commit/pre-commit\">\n    <img src=\"https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white&style=flat-square\" alt=\"pre-commit\">\n  </a>\n</p>\n<p align=\"center\">\n  <a href=\"https://pypi.org/project/boost-loss/\">\n    <img src=\"https://img.shields.io/pypi/v/boost-loss.svg?logo=python&logoColor=fff&style=flat-square\" alt=\"PyPI Version\">\n  </a>\n  <img src=\"https://img.shields.io/pypi/pyversions/boost-loss.svg?style=flat-square&logo=python&amp;logoColor=fff\" alt=\"Supported Python versions\">\n  <img src=\"https://img.shields.io/pypi/l/boost-loss.svg?style=flat-square\" alt=\"License\">\n</p>\n\nUtilities for easy use of custom losses in CatBoost, LightGBM, XGBoost. This sounds very simple, but in reality it took a lot of work.\n\n## Installation\n\nInstall this via pip (or your favourite package manager):\n\n```shell\npip install boost-loss\n```\n\n## Usage\n\n### Basic Usage\n\n```python\nimport numpy as np\n\nfrom boost_loss import LossBase\nfrom numpy.typing import NDArray\n\n\nclass L2Loss(LossBase):\n    def loss(self, y_true: NDArray, y_pred: NDArray) -> NDArray:\n        return (y_true - y_pred) ** 2 / 2\n\n    def grad(self, y_true: NDArray, y_pred: NDArray) -> NDArray: # dL/dy_pred\n        return - (y_true - y_pred)\n\n    def hess(self, y_true: NDArray, y_pred: NDArray) -> NDArray: # d^2L/dy_pred^2\n        return np.ones_like(y_true)\n```\n\n```python\nimport lightgbm as lgb\n\nfrom boost_loss import apply_custom_loss\nfrom sklearn.datasets import load_boston\n\n\nX, y = load_boston(return_X_y=True)\napply_custom_loss(lgb.LGBMRegressor(), L2Loss()).fit(X, y)\n```\n\nBuilt-in losses are available. [^bokbokbok]\n\n```python\nfrom boost_loss.regression import LogCoshLoss\n```\n\n### [`torch.autograd`](https://pytorch.org/docs/stable/autograd.html) Loss [^autograd]\n\n```python\nimport torch\n\nfrom boost_loss.torch import TorchLossBase\n\n\nclass L2LossTorch(TorchLossBase):\n    def loss_torch(self, y_true: torch.Tensor, y_pred: torch.Tensor) -> torch.Tensor:\n        return (y_true - y_pred) ** 2 / 2\n```\n\n## Contributors \u2728\n\nThanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):\n\n<!-- prettier-ignore-start -->\n<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->\n<!-- prettier-ignore-start -->\n<!-- markdownlint-disable -->\n<table>\n  <tbody>\n    <tr>\n      <td align=\"center\" valign=\"top\" width=\"14.28%\"><a href=\"https://github.com/34j\"><img src=\"https://avatars.githubusercontent.com/u/55338215?v=4?s=80\" width=\"80px;\" alt=\"34j\"/><br /><sub><b>34j</b></sub></a><br /><a href=\"https://github.com/34j/boost-loss/commits?author=34j\" title=\"Code\">\ud83d\udcbb</a> <a href=\"#ideas-34j\" title=\"Ideas, Planning, & Feedback\">\ud83e\udd14</a> <a href=\"https://github.com/34j/boost-loss/commits?author=34j\" title=\"Documentation\">\ud83d\udcd6</a></td>\n    </tr>\n  </tbody>\n</table>\n\n<!-- markdownlint-restore -->\n<!-- prettier-ignore-end -->\n\n<!-- ALL-CONTRIBUTORS-LIST:END -->\n<!-- prettier-ignore-end -->\n\nThis project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!\n\n[^bokbokbok]: Inspired by [orchardbirds/bokbokbok](https://github.com/orchardbirds/bokbokbok)\n[^autograd]: Inspired by [TomerRonen34/treeboost_autograd](https://github.com/TomerRonen34/treeboost_autograd)\n\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "Utilities for easy use of custom losses in CatBoost, LightGBM, XGBoost",
    "version": "0.5.5",
    "project_urls": {
        "Bug Tracker": "https://github.com/34j/boost-loss/issues",
        "Changelog": "https://github.com/34j/boost-loss/blob/main/CHANGELOG.md",
        "Documentation": "https://boost-loss.readthedocs.io",
        "Homepage": "https://github.com/34j/boost-loss",
        "Repository": "https://github.com/34j/boost-loss"
    },
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "8248ec77613130aa71b09ca48bbafc0486771542e1c8de666b0b44d713e647e0",
                "md5": "60fe0ffbb82414b9dbcad7dadabfcfb7",
                "sha256": "1967f08dc2f3c3cffdefdf996a1e9c1ddc69c37f41ea818b7cf6a50f35d3bb35"
            },
            "downloads": -1,
            "filename": "boost_loss-0.5.5-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "60fe0ffbb82414b9dbcad7dadabfcfb7",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8,<4.0",
            "size": 20914,
            "upload_time": "2024-01-26T06:50:02",
            "upload_time_iso_8601": "2024-01-26T06:50:02.451344Z",
            "url": "https://files.pythonhosted.org/packages/82/48/ec77613130aa71b09ca48bbafc0486771542e1c8de666b0b44d713e647e0/boost_loss-0.5.5-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "aecf849acb3e7bd97018d1c9764343e27debd89795e6f900cd89c30f978ab428",
                "md5": "284639f1df99d46df2abe2057f2174e1",
                "sha256": "b301e6a8b711a9ef40c02fce478426fcbf7eeba9073b9a6c2dc5d859230baf05"
            },
            "downloads": -1,
            "filename": "boost_loss-0.5.5.tar.gz",
            "has_sig": false,
            "md5_digest": "284639f1df99d46df2abe2057f2174e1",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8,<4.0",
            "size": 19791,
            "upload_time": "2024-01-26T06:50:04",
            "upload_time_iso_8601": "2024-01-26T06:50:04.507636Z",
            "url": "https://files.pythonhosted.org/packages/ae/cf/849acb3e7bd97018d1c9764343e27debd89795e6f900cd89c30f978ab428/boost_loss-0.5.5.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-01-26 06:50:04",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "34j",
    "github_project": "boost-loss",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "boost-loss"
}
34j
Elapsed time: 0.59969s