# hep_ml
**hep_ml** provides specific machine learning tools for purposes of high energy physics.
[![Run tests](https://github.com/arogozhnikov/hep_ml/actions/workflows/run_tests.yml/badge.svg)](https://github.com/arogozhnikov/hep_ml/actions/workflows/run_tests.yml)
[![travis status](https://travis-ci.org/arogozhnikov/hep_ml.svg?branch=master)](https://travis-ci.org/arogozhnikov/hep_ml)
[![PyPI version](https://badge.fury.io/py/hep-ml.svg)](https://badge.fury.io/py/hep-ml)
[![Documentation](https://img.shields.io/badge/documentation-link-blue.svg)](https://arogozhnikov.github.io/hep_ml/)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1247379.svg)](https://doi.org/10.5281/zenodo.1247379)
![hep_ml, python library for high energy physics](https://github.com/arogozhnikov/hep_ml/blob/data/data_to_download/hep_ml_image.png)
### Main features
* uniform classifiers - the classifiers with low correlation of predictions and mass (or some other variable, or even set of variables)
* __uBoost__ optimized implementation inside
* __UGradientBoosting__ (with different losses, specially __FlatnessLoss__ is of high interest)
* measures of uniformity (see **hep_ml.metrics**)
* advanced losses for classification, regression and ranking for __UGradientBoosting__ (see **hep_ml.losses**).
* **hep_ml.nnet** - theano-based flexible neural networks
* **hep_ml.reweight** - reweighting multidimensional distributions <br />
(_multi_ here means 2, 3, 5 and more dimensions - see GBReweighter!)
* **hep_ml.splot** - minimalistic sPlot-ting
* **hep_ml.speedup** - building models for fast classification (Bonsai BDT)
* **sklearn**-compatibility of estimators.
### Installation
Basic installation:
```bash
pip install hep_ml
```
If you're new to python and never used `pip`, first install scikit-learn [with these instructions](http://scikit-learn.org/stable/install.html).
To use **latest development version**, clone it and install with `pip`:
```bash
git clone https://github.com/arogozhnikov/hep_ml.git
cd hep_ml
pip install .
```
Local testing:
```bash
nosetests tests/
```
### Links
* [documentation](https://arogozhnikov.github.io/hep_ml/)
* [notebooks, code examples](https://github.com/arogozhnikov/hep_ml/tree/master/notebooks)
- you may need to install `ROOT` and `root_numpy` to run those
* [repository](https://github.com/arogozhnikov/hep_ml)
* [issue tracker](https://github.com/arogozhnikov/hep_ml/issues)
### Related projects
Libraries you'll require to make your life easier and HEPpier.
* [IPython Notebook](http://ipython.org/notebook.html) — web-shell for python
* [scikit-learn](http://scikit-learn.org/) — general-purpose library for machine learning in python
* [numpy](http://www.numpy.org/) — 'MATLAB in python', vector operation in python.
Use it you need to perform any number crunching.
* [theano](http://deeplearning.net/software/theano/) — optimized vector analytical math engine in python
* [ROOT](https://root.cern.ch/) — main data format in high energy physics
* [root_numpy](http://rootpy.github.io/root_numpy/) — python library to deal with ROOT files (without pain)
### License
Apache 2.0, `hep_ml` is an open-source library.
### Platforms
Linux, Mac OS X and Windows are supported.
**hep_ml** supports both python 2 and python 3.
Raw data
{
"_id": null,
"home_page": "https://github.com/arogozhnikov/hep_ml",
"name": "hep-ml",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "machine learning,supervised learning,uncorrelated methods of machine learning,high energy physics,particle physics",
"author": "Alex Rogozhnikov",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/b2/c6/e3158c5b4177122e81c147a64f21920cc9aa509a787d099fcf7840aa0d8d/hep_ml-0.7.2.tar.gz",
"platform": null,
"description": "# hep_ml\n\n**hep_ml** provides specific machine learning tools for purposes of high energy physics.\n\n[![Run tests](https://github.com/arogozhnikov/hep_ml/actions/workflows/run_tests.yml/badge.svg)](https://github.com/arogozhnikov/hep_ml/actions/workflows/run_tests.yml)\n[![travis status](https://travis-ci.org/arogozhnikov/hep_ml.svg?branch=master)](https://travis-ci.org/arogozhnikov/hep_ml)\n[![PyPI version](https://badge.fury.io/py/hep-ml.svg)](https://badge.fury.io/py/hep-ml)\n[![Documentation](https://img.shields.io/badge/documentation-link-blue.svg)](https://arogozhnikov.github.io/hep_ml/)\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1247379.svg)](https://doi.org/10.5281/zenodo.1247379)\n\n\n\n![hep_ml, python library for high energy physics](https://github.com/arogozhnikov/hep_ml/blob/data/data_to_download/hep_ml_image.png)\n\n\n### Main features\n\n* uniform classifiers - the classifiers with low correlation of predictions and mass (or some other variable, or even set of variables)\n * __uBoost__ optimized implementation inside\n * __UGradientBoosting__ (with different losses, specially __FlatnessLoss__ is of high interest)\n* measures of uniformity (see **hep_ml.metrics**)\n* advanced losses for classification, regression and ranking for __UGradientBoosting__ (see **hep_ml.losses**). \n* **hep_ml.nnet** - theano-based flexible neural networks \n* **hep_ml.reweight** - reweighting multidimensional distributions <br />\n (_multi_ here means 2, 3, 5 and more dimensions - see GBReweighter!)\n* **hep_ml.splot** - minimalistic sPlot-ting \n* **hep_ml.speedup** - building models for fast classification (Bonsai BDT)\n* **sklearn**-compatibility of estimators.\n\n### Installation\n\nBasic installation:\n\n```bash\npip install hep_ml\n```\n\nIf you're new to python and never used `pip`, first install scikit-learn [with these instructions](http://scikit-learn.org/stable/install.html).\n\nTo use **latest development version**, clone it and install with `pip`:\n```bash\ngit clone https://github.com/arogozhnikov/hep_ml.git\ncd hep_ml\npip install .\n```\n\nLocal testing: \n```bash\nnosetests tests/\n```\n\n### Links\n\n* [documentation](https://arogozhnikov.github.io/hep_ml/)\n* [notebooks, code examples](https://github.com/arogozhnikov/hep_ml/tree/master/notebooks)\n - you may need to install `ROOT` and `root_numpy` to run those \n* [repository](https://github.com/arogozhnikov/hep_ml)\n* [issue tracker](https://github.com/arogozhnikov/hep_ml/issues)\n\n### Related projects \nLibraries you'll require to make your life easier and HEPpier.\n\n* [IPython Notebook](http://ipython.org/notebook.html) — web-shell for python\n* [scikit-learn](http://scikit-learn.org/) — general-purpose library for machine learning in python\n* [numpy](http://www.numpy.org/) — 'MATLAB in python', vector operation in python. \n Use it you need to perform any number crunching. \n* [theano](http://deeplearning.net/software/theano/) — optimized vector analytical math engine in python\n* [ROOT](https://root.cern.ch/) — main data format in high energy physics \n* [root_numpy](http://rootpy.github.io/root_numpy/) — python library to deal with ROOT files (without pain)\n\n\n### License\nApache 2.0, `hep_ml` is an open-source library.\n\n### Platforms \nLinux, Mac OS X and Windows are supported.\n\n**hep_ml** supports both python 2 and python 3.\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "Machine Learning for High Energy Physics",
"version": "0.7.2",
"split_keywords": [
"machine learning",
"supervised learning",
"uncorrelated methods of machine learning",
"high energy physics",
"particle physics"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fd41bf5b0c4ed20a5af76d59a9f5300b6e377c8f89b62855ca1179a764480cfe",
"md5": "54a5b251fc2c0a7f1f5d48e2ba6fb6e7",
"sha256": "293a54ba6a4aeec3775a9045d973becafe93a0b7a2f70111f3ddcea7b4a29fa6"
},
"downloads": -1,
"filename": "hep_ml-0.7.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "54a5b251fc2c0a7f1f5d48e2ba6fb6e7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 55168,
"upload_time": "2023-03-10T18:39:29",
"upload_time_iso_8601": "2023-03-10T18:39:29.945867Z",
"url": "https://files.pythonhosted.org/packages/fd/41/bf5b0c4ed20a5af76d59a9f5300b6e377c8f89b62855ca1179a764480cfe/hep_ml-0.7.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b2c6e3158c5b4177122e81c147a64f21920cc9aa509a787d099fcf7840aa0d8d",
"md5": "e112eaa8ba9523bc46a2046fa0cf3a12",
"sha256": "1729a13ef4c7187b05cd3723091f804ecba435f886567bd963a719ae108689b8"
},
"downloads": -1,
"filename": "hep_ml-0.7.2.tar.gz",
"has_sig": false,
"md5_digest": "e112eaa8ba9523bc46a2046fa0cf3a12",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 60193,
"upload_time": "2023-03-10T18:39:31",
"upload_time_iso_8601": "2023-03-10T18:39:31.850599Z",
"url": "https://files.pythonhosted.org/packages/b2/c6/e3158c5b4177122e81c147a64f21920cc9aa509a787d099fcf7840aa0d8d/hep_ml-0.7.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-10 18:39:31",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "arogozhnikov",
"github_project": "hep_ml",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "hep-ml"
}