{
    "info": {
        "author": "AutoDeploy AI",
        "author_email": "autodeploy.ai@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 4 - Beta",
            "Environment :: Console",
            "Environment :: Web Environment",
            "Intended Audience :: Developers",
            "Intended Audience :: System Administrators",
            "License :: OSI Approved :: Apache Software License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# PyPMML\n\n_PyPMML_ is a Python PMML scoring library, it really is the Python API for [PMML4S](https://github.com/autodeployai/pmml4s).\n\n## Prerequisites\n - Java >= 1.8\n - Python 2.7 or >= 3.5\n\n## Dependencies\n  - Py4J\n  - Pandas (optional)\n  \n## Installation\n\n```bash\npip install pypmml\n```\n\nOr install the latest version from github:\n\n```bash\npip install --upgrade git+https://github.com/autodeployai/pypmml.git\n```\n\n## Usage\n1. Load model from various sources, e.g. filename, string, or array of bytes.\n\n    ```python\n    from pypmml import Model\n    \n    # The model is from http://dmg.org/pmml/pmml_examples/KNIME_PMML_4.1_Examples/single_iris_dectree.xml\n    model = Model.fromFile('single_iris_dectree.xml')\n    ```\n\n2. Call `predict(data)` to predict new values that can be in different types, e.g. dict, json, Series or DataFrame of Pandas.\n\n    ```python\n    # data in dict\n    result = model.predict({'sepal_length': 5.1, 'sepal_width': 3.5, 'petal_length': 1.4, 'petal_width': 0.2})\n     >>> print(result)\n    {'probability': 1.0, 'node_id': '1', 'probability_Iris-virginica': 0.0, 'probability_Iris-setosa': 1.0, 'probability_Iris-versicolor': 0.0, 'predicted_class': 'Iris-setosa'}\n    \n    # data in 'records' json\n    result = model.predict('[{\"sepal_length\": 5.1, \"sepal_width\": 3.5, \"petal_length\": 1.4, \"petal_width\": 0.2}]')\n     >>> print(result)\n    [{\"probability\":1.0,\"probability_Iris-versicolor\":0.0,\"probability_Iris-setosa\":1.0,\"probability_Iris-virginica\":0.0,\"predicted_class\":\"Iris-setosa\",\"node_id\":\"1\"}]\n \n    # data in 'split' json\n    result = model.predict('{\"columns\": [\"sepal_length\", \"sepal_width\", \"petal_length\", \"petal_width\"], \"data\": [[5.1, 3.5, 1.4, 0.2]]}')\n     >>> print(result)\n    {\"columns\":[\"predicted_class\",\"probability\",\"probability_Iris-setosa\",\"probability_Iris-versicolor\",\"probability_Iris-virginica\",\"node_id\"],\"data\":[[\"Iris-setosa\",1.0,1.0,0.0,0.0,\"1\"]]}\n    ```\n\n    How to work with Pandas\n    \n    ```python\n    import pandas as pd\n    \n    # data in Series\n    result = model.predict(pd.Series({'sepal_length': 5.1, 'sepal_width': 3.5, 'petal_length': 1.4, 'petal_width': 0.2}))\n    >>> print(result)\n    node_id                                   1\n    predicted_class                 Iris-setosa\n    probability                               1\n    probability_Iris-setosa                   1\n    probability_Iris-versicolor               0\n    probability_Iris-virginica                0\n    Name: 0, dtype: object\n    \n    # The data is from here: http://dmg.org/pmml/pmml_examples/Iris.csv\n    data = pd.read_csv('Iris.csv')\n    \n    # data in DataFrame\n    result = model.predict(data)\n     >>> print(result)\n        node_id   predicted_class  probability  probability_Iris-setosa  probability_Iris-versicolor  probability_Iris-virginica\n    0         1       Iris-setosa     1.000000                      1.0                     0.000000                    0.000000\n    1         1       Iris-setosa     1.000000                      1.0                     0.000000                    0.000000\n    ..      ...               ...          ...                      ...                          ...                         ...\n    148      10    Iris-virginica     0.978261                      0.0                     0.021739                    0.978261\n    149      10    Iris-virginica     0.978261                      0.0                     0.021739                    0.978261\n    \n    [150 rows x 6 columns]\n    ```\n\n## Use PMML in Scala or Java\nSee the [PMML4S](https://github.com/autodeployai/pmml4s) project. _PMML4S_ a PMML scoring library for Scala. It provides both Scala and Java Evaluator API for PMML.\n\n## Use PMML in Spark\nSee the [PMML4S-Spark](https://github.com/autodeployai/pmml4s-spark) project. _PMML4S-Spark_ is a PMML scoring library for Spark as SparkML Transformer.\n\n## Use PMML in PySpark\nSee the [PyPMML-Spark](https://github.com/autodeployai/pypmml-spark) project. _PyPMML-Spark_ is a Python PMML scoring library for PySpark as SparkML Transformer, it really is the Python API for PMML4s-Spark.\n\n## Deploy PMML as REST API\nSee the [DaaS](https://www.autodeploy.ai/) system that deploys AI & ML models in production at scale on Kubernetes.\n\n## Support\nIf you have any questions about the _PyPMML_ library, please open issues on this repository.\n\nFeedback and contributions to the project, no matter what kind, are always very welcome. \n\n## License\n_PyPMML_ is licensed under [APL 2.0](http://www.apache.org/licenses/LICENSE-2.0).",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "https://github.com/autodeployai/pypmml/archive/v0.9.3.tar.gz",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/autodeployai/pypmml",
        "keywords": "",
        "license": "Apache License 2.0",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pypmml",
        "package_url": "https://pypi.org/project/pypmml/",
        "platform": "",
        "project_url": "https://pypi.org/project/pypmml/",
        "project_urls": {
            "Download": "https://github.com/autodeployai/pypmml/archive/v0.9.3.tar.gz",
            "Homepage": "https://github.com/autodeployai/pypmml"
        },
        "release_url": "https://pypi.org/project/pypmml/0.9.3/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Python PMML scoring library",
        "version": "0.9.3"
    },
    "last_serial": 5798050,
    "releases": {
        "0.9.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "088404bfedf8bda1c3a6257f5cbde916",
                    "sha256": "f77c20843684b8586ad0f912b70f1c4c69035bbc2ecd270e430c07b4789b1a95"
                },
                "downloads": -1,
                "filename": "pypmml-0.9.0.tar.gz",
                "has_sig": false,
                "md5_digest": "088404bfedf8bda1c3a6257f5cbde916",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 14716599,
                "upload_time": "2019-06-03T13:58:49",
                "url": "https://files.pythonhosted.org/packages/2f/fe/22e754e0528c968296926e0f0a61123e09be4400f889846a492a9fde0295/pypmml-0.9.0.tar.gz"
            }
        ],
        "0.9.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f6441486146794647ac5b658cdd6f5e1",
                    "sha256": "17c5d4ed02448c4b335a194a9cfdd4d928d9b5ac38eeb41d0c8e80b8d8741028"
                },
                "downloads": -1,
                "filename": "pypmml-0.9.1.tar.gz",
                "has_sig": false,
                "md5_digest": "f6441486146794647ac5b658cdd6f5e1",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 14717155,
                "upload_time": "2019-06-19T01:55:34",
                "url": "https://files.pythonhosted.org/packages/b4/d7/127ecebcf7fdd6f1dd1e8d1c621aed35573fc6f8f8c49a827b4ed22a650c/pypmml-0.9.1.tar.gz"
            }
        ],
        "0.9.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "9a76260292c4a4111ac7a46a9760da13",
                    "sha256": "8eef9e15a09446af422b9bc121ea6934999970de888e144be9fe587c30db9ced"
                },
                "downloads": -1,
                "filename": "pypmml-0.9.2.tar.gz",
                "has_sig": false,
                "md5_digest": "9a76260292c4a4111ac7a46a9760da13",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 14942757,
                "upload_time": "2019-07-13T15:38:27",
                "url": "https://files.pythonhosted.org/packages/1b/cd/8133c0c54fc9fb5be6d98aa6c04a2f38d4b9382d4d95cf7eb5d4117c0fa5/pypmml-0.9.2.tar.gz"
            }
        ],
        "0.9.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f45d41621b9a3adaafdd98415190eb6e",
                    "sha256": "64ea25ac37354009210796da78770a6d2040f98a2061de3bc85b71e88fb96de4"
                },
                "downloads": -1,
                "filename": "pypmml-0.9.3.tar.gz",
                "has_sig": false,
                "md5_digest": "f45d41621b9a3adaafdd98415190eb6e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 15057511,
                "upload_time": "2019-09-08T02:22:56",
                "url": "https://files.pythonhosted.org/packages/4a/19/f6b525fbd291c5d8378f6dcd9f95b459fab83e4edb9ca0076c34aaffc355/pypmml-0.9.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "f45d41621b9a3adaafdd98415190eb6e",
                "sha256": "64ea25ac37354009210796da78770a6d2040f98a2061de3bc85b71e88fb96de4"
            },
            "downloads": -1,
            "filename": "pypmml-0.9.3.tar.gz",
            "has_sig": false,
            "md5_digest": "f45d41621b9a3adaafdd98415190eb6e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 15057511,
            "upload_time": "2019-09-08T02:22:56",
            "url": "https://files.pythonhosted.org/packages/4a/19/f6b525fbd291c5d8378f6dcd9f95b459fab83e4edb9ca0076c34aaffc355/pypmml-0.9.3.tar.gz"
        }
    ]
}