{
    "info": {
        "author": "Gregory Giecold",
        "author_email": "ggiecold@jimmy.harvard.edu",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 4 - Beta",
            "Environment :: Console",
            "Intended Audience :: Developers",
            "Intended Audience :: End Users/Desktop",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Natural Language :: English",
            "Operating System :: MacOS :: MacOS X",
            "Operating System :: POSIX",
            "Programming Language :: Python :: 2.7",
            "Topic :: Scientific/Engineering",
            "Topic :: Scientific/Engineering :: Mathematics",
            "Topic :: Scientific/Engineering :: Visualization"
        ],
        "description": "DBSCAN\\_multiplex\r\n=================\r\n\r\nOverview\r\n--------\r\n\r\nA fast and memory-efficient implementation of DBSCAN (Density-Based\r\nSpatial Clustering of Applications with Noise).\r\n\r\nIt is especially suited for multiple rounds of down-sampling and\r\nclustering from a joint dataset: after an initial overhead O(N log(N)),\r\neach subsequent run of clustering will have O(N) time complexity.\r\n\r\nAs illustrated by a doctest embedded in the present module's docstring,\r\non a dataset of 15,000 samples and 47 features, on a Asus Zenbook laptop\r\nwith 8 GiB of RAM and an Intel Core M processor,\r\nDBSCAN\\_multiplex processes 50 rounds of sub-sampling and clustering \r\nin about 4 minutes, whereas Scikit-learn's implementation of DBSCAN \r\nperforms the same task in more than 28 minutes.\r\n\r\nSuch a test can be performed quite conveniently on your machine: simply\r\nentering ``python DBSCAN_multiplex``\\ in your terminal will prompt a\r\ndoctest to start comparing the performance of the two afore-mentioned\r\nimplementations of DBSCAN.\r\n\r\nThis 7-fold gain in performance proved critical to the statistical\r\nlearning application that prompted the design of this algorithm.\r\n\r\nInstallation and Requirements\r\n-----------------------------\r\n\r\nDBSCAN\\_multiplex requires a machine running any member of the Unix-like \r\nfamily of operaating systems, Python 2.7 along with the following packages\r\nand a few modules from the Standard Python Library:\r\n\r\n-  NumPy >= 1.9\r\n\r\n-  PyTables\r\n\r\n-  scikit-learn\r\n\r\nYou can install DBSCAN_multiplex from the official Python Package Index (PyPI) as follows:\r\n\r\n-  open a terminal window;\r\n-  type in ``pip install DBSCAN_multiplex``.\r\n\r\nThe command listed above should automatically install or upgrade any missing or outdated dependency among those listed at the beginning of this section.\r\n\r\nUsage and Example\r\n-----------------\r\n\r\nSee the docstrings associated to each function of the DBSCAN\\_multiplex\r\nmodule for more information; in a Python interpreter console, they can\r\nbe viewed by calling the built-in help system, e.g.,\r\n``help(DBSCAN_multiplex.load)``.\r\n\r\nThe following few lines show how DBSCAN\\_multiplex can be used for\r\nclustering 50 randomly selected subsamples out of a common Gaussian\r\ndistributed dataset. This situation arises in consensus clustering where\r\none might want to obtain and then combine multiple vectors of cluster\r\nlabels.\r\n\r\n::\r\n\r\n    >>> import numpy as np\r\n    >>> import DBSCAN_multiplex as DB\r\n\r\n    >>> data = np.random.randn(15000, 7)\r\n    >>> N_iterations = 50\r\n    >>> N_sub = 9 * data.shape[0] / 10\r\n    >>> subsamples_matrix = np.zeros((N_iterations, N_sub), dtype = int)\r\n    >>> for i in xrange(N_iterations): \r\n            subsamples_matrix[i] = np.random.choice(data.shape[0], N_sub, replace = False)\r\n    >>> eps, labels_matrix = DB.DBSCAN(data, minPts = 3, subsamples_matrix = subsamples_matrix, verbose = True)\r\n    \r\nReferences\r\n----------\r\n\r\n-  Ester, M., Kriegel, H.-P., Sander, J. and Xu, X. (1996) \"A density-based\r\n   algorithm for discovering clusters in large spatial databases with noise\".\r\n   Proceedings of the Second International Conference on Knowledge Discovery\r\n   and Data Mining (KDD-96). AAAI Press. pp. 226-231.\r\n\r\n-  Kriegel, H.-P., Kroeger, P., Sander, J. and Zimek, A. (2011) \"Density-based\r\n   Clustering\". WIREs Data Mining and Knowledge Discovery 1 (3): 231-240.",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "https://github.com/GGiecold/DBSCAN_multiplex",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/GGiecold/DBSCAN_multiplex",
        "keywords": "machine-learning clustering",
        "license": "MIT License",
        "maintainer": "",
        "maintainer_email": "",
        "name": "DBSCAN_multiplex",
        "package_url": "https://pypi.org/project/DBSCAN_multiplex/",
        "platform": "Any",
        "project_url": "https://pypi.org/project/DBSCAN_multiplex/",
        "project_urls": {
            "Download": "https://github.com/GGiecold/DBSCAN_multiplex",
            "Homepage": "https://github.com/GGiecold/DBSCAN_multiplex"
        },
        "release_url": "https://pypi.org/project/DBSCAN_multiplex/1.5/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "Fast and memory-efficient DBSCAN clustering,possibly on various subsamples out of a common dataset",
        "version": "1.5"
    },
    "last_serial": 1906525,
    "releases": {
        "1.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "9ad633f00eb9e450e53e524c73fd7196",
                    "sha256": "8dc5ab82963592448e16d04a32d5b279122d464f8ab77a3790f044bfae6364d7"
                },
                "downloads": -1,
                "filename": "DBSCAN_multiplex-1.3.tar.gz",
                "has_sig": false,
                "md5_digest": "9ad633f00eb9e450e53e524c73fd7196",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 9847,
                "upload_time": "2015-11-17T18:23:12",
                "url": "https://files.pythonhosted.org/packages/2f/9f/1b7f1b03ba6efb2d0969503e41d6952eaec24699943636506901eb441d49/DBSCAN_multiplex-1.3.tar.gz"
            }
        ],
        "1.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "8242cc10df56cbf43506b6c715473c73",
                    "sha256": "90b79aa61f111d4a721571c1e96b106ff3f4f35cbf7e9acbf9a09ae756461292"
                },
                "downloads": -1,
                "filename": "DBSCAN_multiplex-1.4.tar.gz",
                "has_sig": false,
                "md5_digest": "8242cc10df56cbf43506b6c715473c73",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 10015,
                "upload_time": "2015-11-18T18:26:06",
                "url": "https://files.pythonhosted.org/packages/c5/a6/1f53d611a65a27b043e1f2c17eb9cb62ab2489e8f5057c68f2224f6ba09d/DBSCAN_multiplex-1.4.tar.gz"
            }
        ],
        "1.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "767e25b9d76719c0bfc785eea016e0bd",
                    "sha256": "3836d25b453af5bc4fcc6680aad27868081d8bca30a5200aa18a2991b0388346"
                },
                "downloads": -1,
                "filename": "DBSCAN_multiplex-1.5.tar.gz",
                "has_sig": false,
                "md5_digest": "767e25b9d76719c0bfc785eea016e0bd",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 9980,
                "upload_time": "2015-12-07T16:16:20",
                "url": "https://files.pythonhosted.org/packages/65/63/8b64de0b81326ad6bed0fce0df79016d8141961d44b3447c6d96cf275645/DBSCAN_multiplex-1.5.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "767e25b9d76719c0bfc785eea016e0bd",
                "sha256": "3836d25b453af5bc4fcc6680aad27868081d8bca30a5200aa18a2991b0388346"
            },
            "downloads": -1,
            "filename": "DBSCAN_multiplex-1.5.tar.gz",
            "has_sig": false,
            "md5_digest": "767e25b9d76719c0bfc785eea016e0bd",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 9980,
            "upload_time": "2015-12-07T16:16:20",
            "url": "https://files.pythonhosted.org/packages/65/63/8b64de0b81326ad6bed0fce0df79016d8141961d44b3447c6d96cf275645/DBSCAN_multiplex-1.5.tar.gz"
        }
    ]
}