{
    "info": {
        "author": "Rein van 't Veer",
        "author_email": "rein@geodan.nl",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3"
        ],
        "description": "# deep-geometry\nA python library for preprocessing geospatial vector geometries for use in deep learning\n\n## Rationale\nDeep learning can use geospatial vector polygons directly (rather than a feature-extracted pre-processd version), but it requires vectorization and normalisation first, like any data source.\n\n## Installation\n`pip install deep-geometry`\n\n## Usage\n### Geometry vectorization\nMake a numerical vector from a geometry: \n```\n>>> from deep_geometry import vectorizer as gv\n\n>>> geoms = [\n...     'POINT(0 0)',\n...     'POINT(1 1)',\n...     'POINT(2 2)',\n...     'POINT(3 3)',\n...     'POINT(4 4)',\n...     'POINT(5 5)',\n...     'POLYGON((0 0, 1 0, 1 1, 0 1, 0 0))',\n... ]\n\n>>> gv.vectorize_wkt(geoms[0])\narray([[ 0.,  0.,  0.,  0.,  0.,  0.,  1.]])\n\n>>> gv.vectorize_wkt(geoms[6])\narray([[ 0.,  0.,  0., 1., 1.,  0.,  0.],\n       [ 1.,  0.,  0., 1., 1.,  0.,  0.],\n       [ 1.,  1.,  0., 1., 1.,  0.,  0.],\n       [ 0.,  1.,  0., 1., 1.,  0.,  0.],\n       [ 0.,  0.,  0., 1., 0.,  0.,  1.]])\n```\n\nCollect the max length from a set of geometries:\n```\n>>> max_len = gv.get_max_points(geoms)\n>>> print('Maximum geometry node size in set:', max_len)\nMaximum geometry node size in set: 7\n```\n\n### Numerical data normalization\nGeometries regularly are in some kind of earth projection that is far from the origin of the coordinate system. In order for machine learning models to learn, data needs to be normalized. A usual way to go about this is to mean-center the instances and to divide by the dataset standard deviation.\n\nThe library provides a convenience class for normalization, modeled after the scalers from [scikit-learn](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html) with a .fit() and a .transform() method:\n\n```\n>>> from deep_geometry import GeomScaler\n>>> import numpy\n>>> gs = GeomScaler()  # simply initialize\n>>> geom6 = gv.vectorize_wkt(geoms[6])\n>>> dataset = numpy.repeat([geom6], 4, axis=0)\n>>> gs.fit(dataset)\n>>> gs.scale_factor\n0.5\n>>> normalized_data = gs.transform(dataset)\n>>> normalized_data[0]  # see: zero-mean and scaled to standard deviation\narray([[-1., -1.,  0.,  1.,  1.,  0.,  0.],\n       [ 1., -1.,  0.,  1.,  1.,  0.,  0.],\n       [ 1.,  1.,  0.,  1.,  1.,  0.,  0.],\n       [-1.,  1.,  0.,  1.,  1.,  0.,  0.],\n       [-1., -1.,  0.,  1.,  0.,  0.,  1.]])\n\n``` \n\n\n",
        "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/SPINlab/deep-geometry",
        "keywords": "",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "deep-geometry",
        "package_url": "https://pypi.org/project/deep-geometry/",
        "platform": "",
        "project_url": "https://pypi.org/project/deep-geometry/",
        "project_urls": {
            "Homepage": "https://github.com/SPINlab/deep-geometry"
        },
        "release_url": "https://pypi.org/project/deep-geometry/2.0.0/",
        "requires_dist": [
            "numpy",
            "shapely"
        ],
        "requires_python": ">=3.6",
        "summary": "A python library for preprocessing geospatial vector geometries for use in deep learning",
        "version": "2.0.0"
    },
    "last_serial": 5938511,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "53685e7ef232d79dd799f8b865fa3559",
                    "sha256": "124c89e37160da8b454a2538e6f16144e8e6109fda80cf4ea133a426c6df4420"
                },
                "downloads": -1,
                "filename": "deep_geometry-0.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "53685e7ef232d79dd799f8b865fa3559",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3",
                "size": 10831,
                "upload_time": "2018-09-11T12:37:36",
                "url": "https://files.pythonhosted.org/packages/9f/7b/78a439a86685448092d4dd24f4f1cdd974977ffc7fce9036b4a11d0f9d86/deep_geometry-0.1.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "355ed1a6f1cb763eb9189a4f0e393449",
                    "sha256": "a3d12a9b69c5ba670fe5e5e0d71ff042f1c09dc16d4c7c555e03558c9a23c383"
                },
                "downloads": -1,
                "filename": "deep-geometry-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "355ed1a6f1cb763eb9189a4f0e393449",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 5830,
                "upload_time": "2018-09-11T12:37:37",
                "url": "https://files.pythonhosted.org/packages/cb/a4/5d30a621265acd8a2db90dfdd3d60edf8c2e281ecbe2fdf1ed34cd1ac36c/deep-geometry-0.1.0.tar.gz"
            }
        ],
        "0.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "e64cbaf56b6f2532a272a1d97e640777",
                    "sha256": "5e4b86de6ed4780e313caf47f9ee7f51c77f61e5f96dddbb236770675a144cb9"
                },
                "downloads": -1,
                "filename": "deep_geometry-0.2.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "e64cbaf56b6f2532a272a1d97e640777",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3",
                "size": 10853,
                "upload_time": "2018-11-06T13:53:20",
                "url": "https://files.pythonhosted.org/packages/bc/7c/e996ad142da8f077bd87d2df58db3f701cae7e1f522ed0745a08ace99b42/deep_geometry-0.2.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "12fd8847014b74b3374c1ae3d4424cff",
                    "sha256": "02f26753b432b80febedbe28f21f989bb3cfbb18a548ebdd3b8d199884a1e346"
                },
                "downloads": -1,
                "filename": "deep-geometry-0.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "12fd8847014b74b3374c1ae3d4424cff",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 5860,
                "upload_time": "2018-11-06T13:53:22",
                "url": "https://files.pythonhosted.org/packages/b8/be/263b38e77df1e993e57fbdfb8443629bbde10c3399cea661605b31436bcc/deep-geometry-0.2.0.tar.gz"
            }
        ],
        "1.0.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "9d59e4e24271033f800eaaae456c51ab",
                    "sha256": "64f55500fc4c67055f9b72d97c7b2345b83cc236506f663e07004d632c86411f"
                },
                "downloads": -1,
                "filename": "deep_geometry-1.0.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "9d59e4e24271033f800eaaae456c51ab",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3",
                "size": 11233,
                "upload_time": "2018-11-07T11:04:08",
                "url": "https://files.pythonhosted.org/packages/28/02/9523bd6eeaca9b58ed2202659680a6bc333ad199b6c69c2db0cd94d382a2/deep_geometry-1.0.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "3f5b7f83f1f50455f4eb8418c5337a1e",
                    "sha256": "0f81dffa37a75e9bca5f7bbb07dbca14463ccde8dffe6eb1dc75316ab5c5f962"
                },
                "downloads": -1,
                "filename": "deep-geometry-1.0.0.tar.gz",
                "has_sig": false,
                "md5_digest": "3f5b7f83f1f50455f4eb8418c5337a1e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 6187,
                "upload_time": "2018-11-07T11:04:10",
                "url": "https://files.pythonhosted.org/packages/d8/29/1cbcbc5563d5a74dc273442a9d53e8a110d02e7e1fe023f583105c4ea6ea/deep-geometry-1.0.0.tar.gz"
            }
        ],
        "2.0.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "24989b78479c0670097c18ea92f17910",
                    "sha256": "3d8552203fcc03850ef45127f8f04eed8d7d452a11d1f0293f8b43a7df9adbcf"
                },
                "downloads": -1,
                "filename": "deep_geometry-2.0.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "24989b78479c0670097c18ea92f17910",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6",
                "size": 10120,
                "upload_time": "2019-10-07T12:43:37",
                "url": "https://files.pythonhosted.org/packages/e2/13/c473bd468fe1aff821a1e7b9835e95efde53b3430f997a94e992be4181c3/deep_geometry-2.0.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a3c38e81c06929ba585acfb1b0cca5c2",
                    "sha256": "89f002cd985ff527519d02b715ee648d04329cf4c37046b3226d5ecf856b505a"
                },
                "downloads": -1,
                "filename": "deep-geometry-2.0.0.tar.gz",
                "has_sig": false,
                "md5_digest": "a3c38e81c06929ba585acfb1b0cca5c2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6",
                "size": 7832,
                "upload_time": "2019-10-07T12:43:38",
                "url": "https://files.pythonhosted.org/packages/1d/eb/a0f672e09354772bfb17ee45900efb64751b9d0f42632958123a119bf4d7/deep-geometry-2.0.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "24989b78479c0670097c18ea92f17910",
                "sha256": "3d8552203fcc03850ef45127f8f04eed8d7d452a11d1f0293f8b43a7df9adbcf"
            },
            "downloads": -1,
            "filename": "deep_geometry-2.0.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "24989b78479c0670097c18ea92f17910",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6",
            "size": 10120,
            "upload_time": "2019-10-07T12:43:37",
            "url": "https://files.pythonhosted.org/packages/e2/13/c473bd468fe1aff821a1e7b9835e95efde53b3430f997a94e992be4181c3/deep_geometry-2.0.0-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "a3c38e81c06929ba585acfb1b0cca5c2",
                "sha256": "89f002cd985ff527519d02b715ee648d04329cf4c37046b3226d5ecf856b505a"
            },
            "downloads": -1,
            "filename": "deep-geometry-2.0.0.tar.gz",
            "has_sig": false,
            "md5_digest": "a3c38e81c06929ba585acfb1b0cca5c2",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6",
            "size": 7832,
            "upload_time": "2019-10-07T12:43:38",
            "url": "https://files.pythonhosted.org/packages/1d/eb/a0f672e09354772bfb17ee45900efb64751b9d0f42632958123a119bf4d7/deep-geometry-2.0.0.tar.gz"
        }
    ]
}