{
    "info": {
        "author": "Giacomo Berardi",
        "author_email": "barnets@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Environment :: Console",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: GNU Lesser General Public License v3 or later (LGPLv3+)",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3.5",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Information Analysis",
            "Topic :: Text Processing :: Linguistic"
        ],
        "description": "ShallowLearn\n============\nA collection of supervised learning models based on shallow neural network approaches (e.g., word2vec and fastText)\nwith some additional exclusive features.\nWritten in Python and fully compatible with `scikit-learn <http://scikit-learn.org>`_.\n\n**Discussion group** for users and developers: https://groups.google.com/d/forum/shallowlearn\n\n.. image:: https://travis-ci.org/giacbrd/ShallowLearn.svg?branch=master\n    :target: https://travis-ci.org/giacbrd/ShallowLearn\n.. image:: https://badge.fury.io/py/shallowlearn.svg\n    :target: https://badge.fury.io/py/shallowlearn\n\nGetting Started\n---------------\nInstall the latest version:\n\n.. code:: shell\n\n    pip install cython\n    pip install shallowlearn\n\nImport models from ``shallowlearn.models``, they implement the standard methods for supervised learning in scikit-learn,\ne.g., ``fit(X, y)``, ``predict(X)``, ``predict_proba(X)``, etc.\n\nData is raw text, each sample in the iterable ``X`` is a list of tokens (words of a document), \nwhile each element in the iterable ``y`` (corresponding to an element in ``X``) can be a single label or a list in case\nof a multi-label training set. Obviously, ``y`` must be of the same size of ``X``.\n\nModels\n------\n\nGensimFastText\n~~~~~~~~~~~~~~\n**Choose this model if your goal is classification with fastText!** (it is going to be the most stable and rich feature-wise)\n\nA supervised learning model based on the fastText algorithm [1]_.\nThe code is mostly taken and rewritten from `Gensim <https://radimrehurek.com/gensim>`_,\nit takes advantage of its optimizations (e.g. Cython) and support.\n\nIt is possible to choose the Softmax loss function (default) or one of its two \"approximations\":\nHierarchical Softmax and Negative Sampling. \n\nThe parameter ``bucket`` configures the feature hashing space, i.e., the *hashing trick* described in [1]_.\nUsing the hashing trick together with ``partial_fit(X, y)`` yields a powerful *online* text classifier (see `Online learning`_).\n\nIt is possible to load pre-trained word vectors at initialization,\npassing a Gensim ``Word2Vec`` or a ShallowLearn ``LabeledWord2Vec`` instance (the latter is retrievable from a\n``GensimFastText`` model by the attribute ``classifier``).\nWith method ``fit_embeddings(X)`` it is possible to pre-train word vectors, using the current parameter values of the model.\n\nConstructor argument names are a mix between the ones of Gensim and the ones of fastText (see this `class docstring <https://github.com/giacbrd/ShallowLearn/blob/develop/shallowlearn/models.py#L74>`_).\n\n.. code:: python\n\n    >>> from shallowlearn.models import GensimFastText\n    >>> clf = GensimFastText(size=100, min_count=0, loss='hs', iter=3, seed=66)\n    >>> clf.fit([('i', 'am', 'tall'), ('you', 'are', 'fat')], ['yes', 'no'])\n    >>> clf.predict([('tall', 'am', 'i')])\n    ['yes']\n\nFastText\n~~~~~~~~\nThe supervised algorithm of fastText implemented in `fastText.py <https://github.com/salestock/fastText.py>`_ ,\nwhich exposes an interface on the original C++ code.\nThe current advantages of this class over ``GensimFastText`` are the *subwords* and the *n-gram features* implemented\nvia the *hashing trick*.\nThe constructor arguments are equivalent to the original `supervised model\n<https://github.com/salestock/fastText.py#supervised-model>`_, except for ``input_file``, ``output`` and\n``label_prefix``.\n\n**WARNING**: The only way of loading datasets in fastText.py is through the filesystem (as of version 0.8.2),\nso data passed to ``fit(X, y)`` will be written in temporary files on disk.\n\n.. code:: python\n\n    >>> from shallowlearn.models import FastText\n    >>> clf = FastText(dim=100, min_count=0, loss='hs', epoch=3, bucket=5, word_ngrams=2)\n    >>> clf.fit([('i', 'am', 'tall'), ('you', 'are', 'fat')], ['yes', 'no'])\n    >>> clf.predict([('tall', 'am', 'i')])\n    ['yes']\n\nDeepInverseRegression\n~~~~~~~~~~~~~~~~~~~~~\n*TODO*: Based on https://radimrehurek.com/gensim/models/word2vec.html#gensim.models.word2vec.Word2Vec.score\n\nDeepAveragingNetworks\n~~~~~~~~~~~~~~~~~~~~~\n*TODO*: Based on https://github.com/miyyer/dan\n\nExclusive Features\n------------------\nNext cool features will be listed as Issues in Github, for now:\n\nPersistence\n~~~~~~~~~~~\nAny model can be serialized and de-serialized with the two methods ``save`` and ``load``.\nThey overload the `SaveLoad <https://radimrehurek.com/gensim/utils.html#gensim.utils.SaveLoad>`_ interface of Gensim,\nso it is possible to control the cost on disk usage of the models, instead of simply *pickling* the objects.\nThe original interface also allows to use compression on the serialization outputs.\n\n``save`` may create multiple files with names prefixed by the name given to the serialized model.\n\n.. code:: python\n\n    >>> from shallowlearn.models import GensimFastText\n    >>> clf = GensimFastText(size=100, min_count=0, loss='hs', iter=3, seed=66)\n    >>> clf.save('./model')\n    >>> loaded = GensimFastText.load('./model') # it also creates ./model.CLF\n\nBenchmarks\n----------\n\nText classification\n~~~~~~~~~~~~~~~~~~~\n\nThe script ``scripts/document_classification_20newsgroups.py`` refers to this\n`scikit-learn example <http://scikit-learn.org/stable/auto_examples/text/document_classification_20newsgroups.html>`_\nin which text classifiers are compared on a reference dataset;\nwe added our models to the comparison.\n**The current results, even if still preliminary, are comparable with other\napproaches, achieving the best performance in speed**.\n\nResults as of release `0.0.5 <https://github.com/giacbrd/ShallowLearn/releases/tag/0.0.5>`_,\nwith *chi2_select* option set to 80%.\nThe times take into account of *tf-idf* vectorization in the \u201cclassic\u201d classifiers, and the I/O operations for the\ntraining of fastText.py.\nThe evaluation measure is *macro F1*.\n\n.. image:: https://cdn.rawgit.com/giacbrd/ShallowLearn/master/images/benchmark.svg\n    :alt: Text classifiers comparison\n    :align: center\n    :width: 888 px\n\nOnline learning\n~~~~~~~~~~~~~~~\n\nThe script ``scripts/plot_out_of_core_classification.py`` computes a benchmark on some scikit-learn classifiers which are able to\nlearn incrementally,\na batch of examples at a time.\nThese classifiers can learn online by using the scikit-learn method ``partial_fit(X, y)``.\nThe `original example <http://scikit-learn.org/stable/auto_examples/applications/plot_out_of_core_classification.html>`_\ndescribes the approach through feature hashing, which we set with parameter ``bucket``.\n\n**The results are decent but there is room for improvement**.\nWe configure our classifier with ``iter=1, size=100, alpha=0.1, sample=0, min_count=0``, so to keep the model fast and\nsmall, and to not cut off words from the few samples we have.\n\n.. image:: https://cdn.rawgit.com/giacbrd/ShallowLearn/master/images/onlinelearning.svg\n    :alt: Online learning\n    :align: center\n    :width: 888 px\n\nReferences\n----------\n.. [1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, Bag of Tricks for Efficient Text Classification",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/giacbrd/ShallowLearn",
        "keywords": "",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "ShallowLearn",
        "package_url": "https://pypi.org/project/ShallowLearn/",
        "platform": "",
        "project_url": "https://pypi.org/project/ShallowLearn/",
        "project_urls": {
            "Homepage": "https://github.com/giacbrd/ShallowLearn"
        },
        "release_url": "https://pypi.org/project/ShallowLearn/0.0.5/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "A collection of supervised learning models based on shallow neural network approaches (e.g., word2vec and fastText) with some additional exclusive features",
        "version": "0.0.5"
    },
    "last_serial": 2546364,
    "releases": {
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a8235ac70cf55e66e19d642719571dc2",
                    "sha256": "52aac29c6d6d57858f66035f73ed065b0743b837b6f5d63d09508f06fd340fa0"
                },
                "downloads": -1,
                "filename": "ShallowLearn-0.0.2-5.tar.gz",
                "has_sig": false,
                "md5_digest": "a8235ac70cf55e66e19d642719571dc2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 69986,
                "upload_time": "2016-10-14T12:45:28",
                "url": "https://files.pythonhosted.org/packages/20/41/da65f30862b13a78837dc234b27c0a745e097399f3225d0cdcd866d066fb/ShallowLearn-0.0.2-5.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "ad2094a81fef4cbce96b4fe26909784e",
                    "sha256": "c60f778a47e6f66763bc00f57261d512dacf95a29d3035c51e1f1a0b8a97dbc6"
                },
                "downloads": -1,
                "filename": "ShallowLearn-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "ad2094a81fef4cbce96b4fe26909784e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 83320,
                "upload_time": "2016-10-27T23:45:58",
                "url": "https://files.pythonhosted.org/packages/0b/82/691a73b09fa1e4e44769c20b2b44773fa02dc4acfc2e6dfb1e1ac7b89923/ShallowLearn-0.0.3.tar.gz"
            }
        ],
        "0.0.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "8ccb858e43b4bcdd5f3c8fcf364b63ae",
                    "sha256": "ee1a583bda743bca2c0e82ff732626fe2068a457c634ae00e1c30e0145933e41"
                },
                "downloads": -1,
                "filename": "ShallowLearn-0.0.4.tar.gz",
                "has_sig": false,
                "md5_digest": "8ccb858e43b4bcdd5f3c8fcf364b63ae",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 85529,
                "upload_time": "2016-11-06T17:01:57",
                "url": "https://files.pythonhosted.org/packages/cd/1d/39d0c58e782885412674e024645c1b9f15469095a2f650d284ffd6ddd6a8/ShallowLearn-0.0.4.tar.gz"
            }
        ],
        "0.0.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4a9fbc8dbeb1f7183f9db949c1aad24e",
                    "sha256": "b1ee718b47741be0d6e06d991ba4d33a93710f94af39483cddb4f20a3dac67ef"
                },
                "downloads": -1,
                "filename": "ShallowLearn-0.0.5.tar.gz",
                "has_sig": false,
                "md5_digest": "4a9fbc8dbeb1f7183f9db949c1aad24e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 93363,
                "upload_time": "2016-12-30T17:01:48",
                "url": "https://files.pythonhosted.org/packages/4b/95/053eef29979e514db4652e00dfac384ff80f7515a67e21a91cfb33c9cc2a/ShallowLearn-0.0.5.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "4a9fbc8dbeb1f7183f9db949c1aad24e",
                "sha256": "b1ee718b47741be0d6e06d991ba4d33a93710f94af39483cddb4f20a3dac67ef"
            },
            "downloads": -1,
            "filename": "ShallowLearn-0.0.5.tar.gz",
            "has_sig": false,
            "md5_digest": "4a9fbc8dbeb1f7183f9db949c1aad24e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 93363,
            "upload_time": "2016-12-30T17:01:48",
            "url": "https://files.pythonhosted.org/packages/4b/95/053eef29979e514db4652e00dfac384ff80f7515a67e21a91cfb33c9cc2a/ShallowLearn-0.0.5.tar.gz"
        }
    ]
}