{
    "info": {
        "author": "Luca Cappelletti",
        "author_email": "cappelletti.luca94@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 3"
        ],
        "description": "extra_keras_metrics\n=========================================================================================\n|travis| |sonar_quality| |sonar_maintainability| |codacy| |code_climate_maintainability| |pip| |downloads|\n\nAdditional metrics integrated with the Keras NN library, taken directly from `Tensorflow <https://www.tensorflow.org/api_docs/python/tf/metrics/>`_\n\nHow do I install this package?\n----------------------------------------------\nAs usual, just download it using pip:\n\n.. code:: shell\n\n    pip install extra_keras_metrics\n\nTests Coverage\n----------------------------------------------\nSince some software handling coverages sometimes get slightly different results, here's three of them:\n\n|coveralls| |sonar_coverage| |code_climate_coverage|\n\nHow do I use this package?\n----------------------------------------------\nJust by importing it you will be able to access all the non-parametric metrics, such as `\"auprc\"` and `\"auroc\"`:\n\n.. code:: python\n\n    import extra_keras_metrics\n\n    model = my_keras_model()\n    model.compile(\n        optimizer=\"sgd\",\n        loss=\"binary_crossentropy\",\n        metrics=[\"auroc\", \"auprc\"]\n    )\n\nFor the parametric metrics, such as `\"average_precision_at_k\"`, you will need to import them, such as:\n\n.. code:: python\n\n    from extra_keras_metrics import average_precision_at_k\n\n    model = my_keras_model()\n    model.compile(\n        optimizer=\"sgd\",\n        loss=\"binary_crossentropy\",\n        metrics=[average_precision_at_k(1), average_precision_at_k(2)]\n    )\n\nThis way in the history of the model you will find both the metrics indexed as `\"average_precision_at_k_1\"` and `\"average_precision_at_k_2\"` respectively.\n\nWhich metrics do I get?\n----------------------------------------------\nYou will get all the following metrics taken directly from `Tensorflow <https://www.tensorflow.org/api_docs/python/tf/metrics/>`_. At the time of writing, the ones available are the following:\n\nThe **non-parametric** ones are (tested against their conterpart from sklearn):\n\n- `AUPRC <https://www.tensorflow.org/api_docs/python/tf/metrics/auc>`_  (tested against `sklearn's average_precision_score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html#sklearn.metrics.average_precision_score>`_).\n- `AUROC <https://www.tensorflow.org/api_docs/python/tf/metrics/auc>`_  (tested against `sklearn's roc_auc_score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html>`_).\n- `false_negatives <https://www.tensorflow.org/api_docs/python/tf/metrics/false_negatives>`_  (tested against false negatives from `sklearn's confusion_matrix <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html#sklearn.metrics.confusion_matrix>`_).\n- `false_positives <https://tensorflow.org/api_docs/python/tf/metrics/false_positives>`_  (tested against false positives from `sklearn's confusion_matrix <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html#sklearn.metrics.confusion_matrix>`_).\n- `mean_absolute_error <https://www.tensorflow.org/api_docs/python/tf/metrics/mean_absolute_error>`_ (tested against `sklearn's mean_absolute_error <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_absolute_error.html#sklearn.metrics.mean_absolute_error>`_)\n- `mean_squared_error <https://www.tensorflow.org/api_docs/python/tf/metrics/mean_squared_error>`_ (tested against `sklearn's mean_squared_error <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_squared_error.html#sklearn.metrics.mean_squared_error>`_)\n- `precision <https://www.tensorflow.org/api_docs/python/tf/metrics/precision>`_ (tested against `sklearn's precision_score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_score.html#sklearn.metrics.precision_score>`_)\n- `recall <https://www.tensorflow.org/api_docs/python/tf/metrics/recall>`_ (tested against `sklearn's recall_score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.recall_score.html#sklearn.metrics.recall_score>`_)\n- `root_mean_squared_error <https://www.tensorflow.org/api_docs/python/tf/metrics/root_mean_squared_error>`_ (tested against squared root of `sklean's mean_squared_error <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_squared_error.html#sklearn.metrics.mean_squared_error>`_)\n- `true_negatives <https://www.tensorflow.org/api_docs/python/tf/metrics/true_negatives>`_ (tested against true negatives from `sklearn's confusion_matrix <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html#sklearn.metrics.confusion_matrix>`_)\n- `true_positives <https://www.tensorflow.org/api_docs/python/tf/metrics/true_positives>`_ (tested against true positives from `sklearn's confusion_matrix <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html#sklearn.metrics.confusion_matrix>`_)\n\nThe **parametric** ones are (only execution is tested, no baseline in sklearn was available):\n\n- `average_precision_at_k <https://www.tensorflow.org/api_docs/python/tf/metrics/average_precision_at_k>`_\n- `precision_at_k <https://www.tensorflow.org/api_docs/python/tf/metrics/precision_at_k>`_\n- `recall_at_k <https://www.tensorflow.org/api_docs/python/tf/metrics/recall_at_k>`_\n- `mean_iou <https://www.tensorflow.org/api_docs/python/tf/metrics/mean_iou>`_\n- `sensitivity_at_specificity <https://www.tensorflow.org/api_docs/python/tf/metrics/sensitivity_at_specificity>`_\n- `specificity_at_sensitivity <https://www.tensorflow.org/api_docs/python/tf/metrics/specificity_at_sensitivity>`_\n\nExtras\n----------------------------\nI've created also another couple packages you might enjoy: one, called `extra_keras_utils <https://github.com/LucaCappelletti94/extra_keras_utils>`_ that contains some commonly used code for Keras projects and `plot_keras_history <https://github.com/LucaCappelletti94/plot_keras_history>`_ which automatically plots a keras training history.\n\n\n.. |travis| image:: https://travis-ci.org/LucaCappelletti94/extra_keras_metrics.png\n   :target: https://travis-ci.org/LucaCappelletti94/extra_keras_metrics\n   :alt: Travis CI build\n\n.. |sonar_quality| image:: https://sonarcloud.io/api/project_badges/measure?project=LucaCappelletti94_extra_keras_metrics&metric=alert_status\n    :target: https://sonarcloud.io/dashboard/index/LucaCappelletti94_extra_keras_metrics\n    :alt: SonarCloud Quality\n\n.. |sonar_maintainability| image:: https://sonarcloud.io/api/project_badges/measure?project=LucaCappelletti94_extra_keras_metrics&metric=sqale_rating\n    :target: https://sonarcloud.io/dashboard/index/LucaCappelletti94_extra_keras_metrics\n    :alt: SonarCloud Maintainability\n\n.. |sonar_coverage| image:: https://sonarcloud.io/api/project_badges/measure?project=LucaCappelletti94_extra_keras_metrics&metric=coverage\n    :target: https://sonarcloud.io/dashboard/index/LucaCappelletti94_extra_keras_metrics\n    :alt: SonarCloud Coverage\n\n.. |coveralls| image:: https://coveralls.io/repos/github/LucaCappelletti94/extra_keras_metrics/badge.svg?branch=master\n    :target: https://coveralls.io/github/LucaCappelletti94/extra_keras_metrics?branch=master\n    :alt: Coveralls Coverage\n\n.. |pip| image:: https://badge.fury.io/py/extra-keras-metrics.svg\n    :target: https://badge.fury.io/py/extra_keras_metrics\n    :alt: Pypi project\n\n.. |downloads| image:: https://pepy.tech/badge/extra-keras-metrics\n    :target: https://pepy.tech/badge/extra-keras-metrics\n    :alt: Pypi total project downloads \n\n.. |codacy|  image:: https://api.codacy.com/project/badge/Grade/5c1fbcfbffc047e6bf810e9372198a5b\n    :target: https://www.codacy.com/app/LucaCappelletti94/extra_keras_metrics?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=LucaCappelletti94/extra_keras_metrics&amp;utm_campaign=Badge_Grade\n    :alt: Codacy Maintainability\n\n.. |code_climate_maintainability| image:: https://api.codeclimate.com/v1/badges/b1008a3d75104ce62162/maintainability\n    :target: https://codeclimate.com/github/LucaCappelletti94/extra_keras_metrics/maintainability\n    :alt: Maintainability\n\n.. |code_climate_coverage| image:: https://api.codeclimate.com/v1/badges/b1008a3d75104ce62162/test_coverage\n    :target: https://codeclimate.com/github/LucaCappelletti94/extra_keras_metrics/test_coverage\n    :alt: Code Climate Coverate",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/LucaCappelletti94/extra_keras_metrics",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "extra-keras-metrics",
        "package_url": "https://pypi.org/project/extra-keras-metrics/",
        "platform": "",
        "project_url": "https://pypi.org/project/extra-keras-metrics/",
        "project_urls": {
            "Homepage": "https://github.com/LucaCappelletti94/extra_keras_metrics"
        },
        "release_url": "https://pypi.org/project/extra-keras-metrics/1.3.1/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Additional metrics integrated with the keras NN library, taken directly from `Tensorflow <https://www.tensorflow.org/api_docs/python/tf/metrics/>`_",
        "version": "1.3.1"
    },
    "last_serial": 5809670,
    "releases": {
        "1.0.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "553a30283d08931dfc149524180aef40",
                    "sha256": "bb8460d1bf415845fa4684099578e3daf768ba53ab79f7d3784f083accbf9986"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.0.0.tar.gz",
                "has_sig": false,
                "md5_digest": "553a30283d08931dfc149524180aef40",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7477,
                "upload_time": "2019-05-25T12:20:05",
                "url": "https://files.pythonhosted.org/packages/2e/39/72d4b356cd186a565dd3478e1f7ba65bdb6bac78196ef2050a75995f5317/extra_keras_metrics-1.0.0.tar.gz"
            }
        ],
        "1.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f0ed9d73393157566197955a1d250d53",
                    "sha256": "f5de2cc3b067de6e50e938ca0ae3dbb2942b4d1f96c4197149796ad5c8547094"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "f0ed9d73393157566197955a1d250d53",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7484,
                "upload_time": "2019-05-27T09:54:10",
                "url": "https://files.pythonhosted.org/packages/9d/c7/265bbd75500ed6489970c949b4ec677cfb798c09b50dd6c6223c4737e4eb/extra_keras_metrics-1.1.0.tar.gz"
            }
        ],
        "1.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "dc8f532fdd55824ecd53303c9850fffe",
                    "sha256": "d5d7c3b6b30117ecdf0ef66df8edd68c770b04a462571dc458de42711bcb08ae"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "dc8f532fdd55824ecd53303c9850fffe",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7991,
                "upload_time": "2019-06-02T17:39:15",
                "url": "https://files.pythonhosted.org/packages/38/2a/48a287868b112904184da38ae5813a3e03e988d2e56b612bb93e880e99bc/extra_keras_metrics-1.1.1.tar.gz"
            }
        ],
        "1.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "c3c3ec73dbc5f18c70831ba99a1cc8b5",
                    "sha256": "b03ae66f1dde21a0cbe1edf1c72114f95d815570e463a81b8b5014eeb0877eee"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "c3c3ec73dbc5f18c70831ba99a1cc8b5",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8303,
                "upload_time": "2019-07-02T08:22:33",
                "url": "https://files.pythonhosted.org/packages/be/b5/43ebcb243910c89cf77a76a9893eb45439915de914a22164e937111f9aa8/extra_keras_metrics-1.1.2.tar.gz"
            }
        ],
        "1.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "20e0ab914d50a53fdab5d729e7345df9",
                    "sha256": "c06e83e9f7b82a30627f68531aad9ed11faf819e4526014a9276bfee68abf19e"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "20e0ab914d50a53fdab5d729e7345df9",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8442,
                "upload_time": "2019-07-29T18:45:06",
                "url": "https://files.pythonhosted.org/packages/9a/fd/4b22ee36a243be045366019edddee847256c35836d7d9417abadbcc81f34/extra_keras_metrics-1.2.0.tar.gz"
            }
        ],
        "1.3.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6599639b7ca89d18a08d7bbf4e4c47fb",
                    "sha256": "89683b6bdf5bdb553b0a3717704741fb12752657dc7793e64d28bb6064e2ca1a"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.3.0.tar.gz",
                "has_sig": false,
                "md5_digest": "6599639b7ca89d18a08d7bbf4e4c47fb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7194,
                "upload_time": "2019-08-01T12:13:48",
                "url": "https://files.pythonhosted.org/packages/05/6f/898e17c86f80fb357268b747561b4a3ba6778b466304de55560aa7fe9b3c/extra_keras_metrics-1.3.0.tar.gz"
            }
        ],
        "1.3.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "cbdd354ab2ef3c7e01ca76e6beef6575",
                    "sha256": "1e8efb676a368ebb004e3dd1690304e22c6c58718f8b46eeb4ce0cb54be48ac3"
                },
                "downloads": -1,
                "filename": "extra_keras_metrics-1.3.1.tar.gz",
                "has_sig": false,
                "md5_digest": "cbdd354ab2ef3c7e01ca76e6beef6575",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7941,
                "upload_time": "2019-09-10T15:35:16",
                "url": "https://files.pythonhosted.org/packages/82/0f/b3b2ab62df1b85f753d9a8f0eb29f2e333d085d75a160751b1591be18053/extra_keras_metrics-1.3.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "cbdd354ab2ef3c7e01ca76e6beef6575",
                "sha256": "1e8efb676a368ebb004e3dd1690304e22c6c58718f8b46eeb4ce0cb54be48ac3"
            },
            "downloads": -1,
            "filename": "extra_keras_metrics-1.3.1.tar.gz",
            "has_sig": false,
            "md5_digest": "cbdd354ab2ef3c7e01ca76e6beef6575",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7941,
            "upload_time": "2019-09-10T15:35:16",
            "url": "https://files.pythonhosted.org/packages/82/0f/b3b2ab62df1b85f753d9a8f0eb29f2e333d085d75a160751b1591be18053/extra_keras_metrics-1.3.1.tar.gz"
        }
    ]
}