{
    "info": {
        "author": "Juan Luis Su\u00e1rez D\u00edaz",
        "author_email": "jlsuarezdiaz@ugr.es",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 5 - Production/Stable",
            "Intended Audience :: Developers",
            "Intended Audience :: Information Technology",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
            "Natural Language :: English",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: Implementation :: CPython",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Information Analysis",
            "Topic :: Scientific/Engineering :: Mathematics"
        ],
        "description": "# pyDML\n\n[![](https://travis-ci.org/jlsuarezdiaz/pyDML.svg?branch=master)](https://travis-ci.org/jlsuarezdiaz/pyDML)\n[![](https://img.shields.io/badge/language-Python-green.svg)](https://www.python.org/)\n[![](https://img.shields.io/badge/license-GPL-orange.svg)](https://www.gnu.org/licenses/gpl.html)\n[![](https://badge.fury.io/py/pyDML.svg)](http://badge.fury.io/py/pyDML)\n\nDistance Metric Learning Algorithms for Python\n\n## What is Distance Metric Learning?\n\nMany machine learning algorithms need a similarity measure to carry out their tasks. Usually, standard distances, like euclidean distance, are used to measure this similarity. Distance Metric Learning algorithms try to learn an optimal distance from the data.\n\n## How to learn a distance?\n\nThere are two main ways to learn a distance in Distance Metric Learning:\n\n- Learning a metric matrix M, that is, a positive semidefinite matrix. In this case, the distance is measured as\n<a href=\"https://www.codecogs.com/eqnedit.php?latex=d(x,y)&space;=&space;\\sqrt{(x-y)^TM(x-y)}\" target=\"_blank\"><img src=\"https://latex.codecogs.com/gif.latex?d(x,y)&space;=&space;\\sqrt{(x-y)^TM(x-y)}\" title=\"d(x,y) = \\sqrt{(x-y)^TM(x-y)}\" /></a>\n\n- Learning a linear map L. This map is also represented by a matrix, not necessarily definite or squared. Here, the distance between two elements is the euclidean distance after applying the transformation.\n\nEvery linear map defines a single metric (M = L'L), and two linear maps that define the same metric only differ in an isometry. So both approaches are equivalent.\n\n## Some applications\n\n### Improve distance based classifiers\n\n![](./plots/ex_learning_nca.png)\n*Improving 1-NN classification.*\n\n### Dimensionality reduction\n\n![](./plots/ex_red_dim.png)\n*Learning a projection onto a plane for the digits dataset (dimension 64).*\n\n## Documentation\n\nSee the available algorithms, the additional functionalities and the full documentation [here](https://pydml.readthedocs.io/en/latest/).\n\n## Stats\n\nThe distance metric learning algorithms in pyDML are being evaluated in several datasets. The results of these experiments are available in the [pyDML-Stats](https://github.com/jlsuarezdiaz/pyDML-Stats) repository.\n\n## Installation\n\n- PyPI latest version: `pip install pyDML`\n\n- From GitHub: clone or download this repository and run the command `python setup.py install` on the root directory.\n\n\n\n## Authors\n\n- Juan Luis Su\u00e1rez D\u00edaz ([jlsuarezdiaz](https://github.com/jlsuarezdiaz))",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/jlsuarezdiaz/pyDML",
        "keywords": "Distance Metric Learning,Classification,Mahalanobis Distance,Dimensionality,Similarity",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pyDML",
        "package_url": "https://pypi.org/project/pyDML/",
        "platform": "",
        "project_url": "https://pypi.org/project/pyDML/",
        "project_urls": {
            "Bug Reports": "https://github.com/jlsuarezdiaz/pyDML/issues",
            "Documentation": "https://pydml.readthedocs.io/",
            "Homepage": "https://github.com/jlsuarezdiaz/pyDML",
            "Say Thanks!": "https://saythanks.io/to/jlsuarezdiaz",
            "Software Stats": "https://jlsuarezdiaz.github.io/software/pyDML/stats/",
            "Source": "https://github.com/jlsuarezdiaz/pyDML"
        },
        "release_url": "https://pypi.org/project/pyDML/0.1.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Distance Metric Learning algorithms for Python",
        "version": "0.1.0"
    },
    "last_serial": 4550781,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "945c760238f9f795fb7ef5dc29363f01",
                    "sha256": "1b9745605680faa59d60c196cb6634e87adf40781776891bec63635713c82355"
                },
                "downloads": -1,
                "filename": "pyDML-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "945c760238f9f795fb7ef5dc29363f01",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 51678,
                "upload_time": "2018-08-08T09:12:19",
                "url": "https://files.pythonhosted.org/packages/a0/7f/aec492d530d451ba7b6b26c06bf9f3f5617d2311236603d3f261e9bcdde5/pyDML-0.0.1.tar.gz"
            }
        ],
        "0.0.1b0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "3f07264659a149550cbb47f76084d7d8",
                    "sha256": "f1c77ac4903d58c369f4ddb69e9bbaea562de0d6642b309161161ed4946cc4d0"
                },
                "downloads": -1,
                "filename": "pyDML-0.0.1b0.tar.gz",
                "has_sig": false,
                "md5_digest": "3f07264659a149550cbb47f76084d7d8",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 987174,
                "upload_time": "2018-08-07T11:34:33",
                "url": "https://files.pythonhosted.org/packages/12/f0/60e3b22e2d72312dc1b0ef55bd19f1e3047730b298b2936d762e426faa50/pyDML-0.0.1b0.tar.gz"
            }
        ],
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "3da74f737899cef5fe6c399b0c091b98",
                    "sha256": "8ee8af712fa2f3bc5d37494e84888af530fc5af37f48285f74003c4d6fc9ae6e"
                },
                "downloads": -1,
                "filename": "pyDML-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "3da74f737899cef5fe6c399b0c091b98",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 54825,
                "upload_time": "2018-12-01T18:57:41",
                "url": "https://files.pythonhosted.org/packages/96/20/2903ed13f1f5504ce35d6eb1abf0f7dd282d09d350c76f5342de55f339a0/pyDML-0.1.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "3da74f737899cef5fe6c399b0c091b98",
                "sha256": "8ee8af712fa2f3bc5d37494e84888af530fc5af37f48285f74003c4d6fc9ae6e"
            },
            "downloads": -1,
            "filename": "pyDML-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "3da74f737899cef5fe6c399b0c091b98",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 54825,
            "upload_time": "2018-12-01T18:57:41",
            "url": "https://files.pythonhosted.org/packages/96/20/2903ed13f1f5504ce35d6eb1abf0f7dd282d09d350c76f5342de55f339a0/pyDML-0.1.0.tar.gz"
        }
    ]
}