{
    "info": {
        "author": "CyberZHG",
        "author_email": "CyberZHG@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3.6"
        ],
        "description": "# Word/Character Embeddings in Keras\n\n[![Travis](https://travis-ci.org/CyberZHG/keras-word-char-embd.svg)](https://travis-ci.org/CyberZHG/keras-word-char-embd)\n[![Coverage](https://coveralls.io/repos/github/CyberZHG/keras-word-char-embd/badge.svg?branch=master)](https://coveralls.io/github/CyberZHG/keras-word-char-embd)\n\n## Introduction\n\n![image](https://user-images.githubusercontent.com/853842/43352939-c84b9724-925e-11e8-9488-29ef159a69ed.png)\n\nOut-of-vocabulary words are drawbacks of word embeddings. Sometimes both word and character features are used. The characters in a word are first mapped to character embeddings, then a bidirectional recurrent neural layer is used to encode the character embeddings to a single vector. The final feature of a word is the concatenation of the word embedding and the encoded character feature.\n\nThe repository contains some functions and a wrapper class that could be used to generate the first few layers that encodes the features of words and characters.\n\n## Install\n\n```bash\npip install keras-word-char-embd\n```\n\n### Demo\n\nThere is a sentiment analysis demo in the `demo` directory. Run the following commands, then your model should have about 70% accuracy:\n\n```bash\ncd demo\n./get_data.sh\npython sentiment_analysis.py\n```\n\n### Functions\n\nThis section only introduces the basic usages of the functions. For more detailed information please refer to the demo and the doc comments describing the functions in the source code.\n\n#### `get_dicts_generator`\n\nThe function returns a closure used to generate word and character dictionaries. The closure should be invoked for all the training sentences in order to record the frequencies of each word or character. After that, setting the parameter `return_dict=True` the dictionaries would be returned.\n\n```python\nfrom keras_wc_embd import get_dicts_generator\n\nsentences = [\n    ['All', 'work', 'and', 'no', 'play'],\n    ['makes', 'Jack', 'a', 'dull', 'boy', '.'],\n]\ndict_generator = get_dicts_generator(\n    word_min_freq=2,\n    char_min_freq=2,\n    word_ignore_case=False,\n    char_ignore_case=False,\n)\nfor sentence in sentences:\n    dict_generator(sentence)\n\nword_dict, char_dict, max_word_len = dict_generator(return_dict=True)\n```\n\nYou can generate dictionaries on your own, but make sure index `0` and index for `<UNK>` are preserved.\n\n#### `get_embedding_layer`\n\nGenerate the first few layers that encodes words in a sentence:\n\n```python\nimport keras\nfrom keras_wc_embd import get_embedding_layer\n\ninputs, embd_layer = get_embedding_layer(\n    word_dict_len=len(word_dict),\n    char_dict_len=len(char_dict),\n    max_word_len=max_word_len,\n    word_embd_dim=300,\n    char_embd_dim=50,\n    char_hidden_dim=150,\n    char_hidden_layer_type='lstm',\n)\nmodel = keras.models.Model(inputs=inputs, outputs=embd_layer)\nmodel.summary()\n```\n\nThe output shape of `embd_layer` should be `(None, None, 600)`, which represents the batch size, the length of sentence and the length of encoded word feature.\n\n`char_hidden_layer_type` could be `'lstm'`, `'gru'`, `'cnn'`, a Keras layer or a list of Keras layers. Remember to add `MaskedConv1D` and `MaskedFlatten` to custom objects if you are using `'cnn'`:\n\n```python\nimport keras\nfrom keras_wc_embd import MaskedConv1D, MaskedFlatten\n\nkeras.models.load_model(filepath, custom_objects={\n    'MaskedConv1D': MaskedConv1D,\n    'MaskedFlatten': MaskedFlatten,\n})\n```\n\n#### `get_batch_input`\n\nThe function is used to generate the batch inputs for the model.\n\n```python\nfrom keras_wc_embd import get_batch_input\n\nword_embd_input, char_embd_input = get_batch_input(\n    sentences,\n    max_word_len=max_word_len,\n    word_dict=word_dict,\n    char_dict=char_dict,\n)\n```\n\n#### `get_embedding_weights_from_file`\n\nA helper function that loads pre-trained embeddings for initializing the weights of the embedding layer. The format of the file should be similar to GloVe.\n\n```python\nfrom keras_wc_embd import get_embedding_layer, get_embedding_weights_from_file\n\nword_embd_weights = get_embedding_weights_from_file(word_dict, 'glove.6B.100d.txt', ignore_case=True)\ninputs, embd_layer = get_embedding_layer(\n    word_dict_len=len(word_dict),\n    char_dict_len=len(char_dict),\n    max_word_len=max_word_len,\n    word_embd_dim=300,\n    char_embd_dim=50,\n    char_hidden_dim=150,\n    word_embd_weights=word_embd_weights,\n    char_hidden_layer_type='lstm',\n)\n```\n\n### Wrapper Class `WordCharEmbd`\n\nThere is a wrapper class that makes things easier.\n\n```python\nfrom keras_wc_embd import WordCharEmbd\n\nsentences = [\n    ['All', 'work', 'and', 'no', 'play'],\n    ['makes', 'Jack', 'a', 'dull', 'boy', '.'],\n]\nwc_embd = WordCharEmbd(\n    word_min_freq=0,\n    char_min_freq=0,\n    word_ignore_case=False,\n    char_ignore_case=False,\n)\nfor sentence in sentences:\n    wc_embd.update_dicts(sentence)\n\ninputs, embd_layer = wc_embd.get_embedding_layer()\nlstm_layer = keras.layers.LSTM(units=5, name='LSTM')(embd_layer)\nsoftmax_layer = keras.layers.Dense(units=2, activation='softmax', name='Softmax')(lstm_layer)\nmodel = keras.models.Model(inputs=inputs, outputs=softmax_layer)\nmodel.compile(\n    optimizer='adam',\n    loss=keras.losses.sparse_categorical_crossentropy,\n    metrics=[keras.metrics.sparse_categorical_accuracy],\n)\nmodel.summary()\n\n\ndef batch_generator():\n    while True:\n        yield wc_embd.get_batch_input(sentences), np.asarray([0, 1])\n\nmodel.fit_generator(\n    generator=batch_generator(),\n    steps_per_epoch=200,\n    epochs=1,\n)\n```\n\n## Citation\n\nSeveral papers have done the same thing. Just choose the one you have seen.",
        "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/CyberZHG/keras-word-char-embd",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-word-char-embd",
        "package_url": "https://pypi.org/project/keras-word-char-embd/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-word-char-embd/",
        "project_urls": {
            "Homepage": "https://github.com/CyberZHG/keras-word-char-embd"
        },
        "release_url": "https://pypi.org/project/keras-word-char-embd/0.20.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Concatenate word and character embeddings in Keras",
        "version": "0.20.0"
    },
    "last_serial": 5011626,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "82865fe3635dfe2a3626ed5d86832df8",
                    "sha256": "72033721fe06321bdf004d3db4f3c79bbbafb95e337faf12b9a10e69432468f2"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.1-py3.6.egg",
                "has_sig": false,
                "md5_digest": "82865fe3635dfe2a3626ed5d86832df8",
                "packagetype": "bdist_egg",
                "python_version": "3.6",
                "requires_python": null,
                "size": 5838,
                "upload_time": "2018-07-28T04:35:00",
                "url": "https://files.pythonhosted.org/packages/48/ef/3a46bbcbe43266c9925504dc67c9bc29712e311fe703087522f77249508c/keras_word_char_embd-0.0.1-py3.6.egg"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "e0420443b6878a2d9b5c7a1542cc745e",
                    "sha256": "6cc861a0b60b598e4ab728fd9125ce03adc2961e9ecc60099fe37cf748da34a3"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "e0420443b6878a2d9b5c7a1542cc745e",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 4238,
                "upload_time": "2018-07-28T04:34:59",
                "url": "https://files.pythonhosted.org/packages/7e/66/d3489a55395a2d9701690438bc8e619af2ddcb37bfa4b4ba7f5b6d91306a/keras_word_char_embd-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "c29c7b7edec3d0c1fb701b9f8e6bd38e",
                    "sha256": "caf5b65367f0626fd12a355358b2fffbdaadabbd3f56300251a03365c6c22cd7"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "c29c7b7edec3d0c1fb701b9f8e6bd38e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2594,
                "upload_time": "2018-07-28T04:35:01",
                "url": "https://files.pythonhosted.org/packages/80/0b/0c9fd7842938989482e5c158f4ef1dc2feaf83472df80828ae51577670e7/keras_word_char_embd-0.0.1.tar.gz"
            }
        ],
        "0.0.10": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "47a135cfed1e7cbfd2cb4d1511e5de41",
                    "sha256": "18ac3fb7e1f82e72e7d1b62f7a548d2cfcf5998c94e461da602d8a1c67b23b50"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.10.tar.gz",
                "has_sig": false,
                "md5_digest": "47a135cfed1e7cbfd2cb4d1511e5de41",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5330,
                "upload_time": "2018-08-15T07:47:03",
                "url": "https://files.pythonhosted.org/packages/c3/d6/350fd2b21b6cadc143177305bc05b64655cb01626c3b0dfde5ce6c6ce104/keras-word-char-embd-0.0.10.tar.gz"
            }
        ],
        "0.0.11": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "580fa9f55f1465276f85db5a4f9d7a0c",
                    "sha256": "c2cb2494b57b0f33a1da902192e267f1ba5654cf6aa7923f9df22d8d8bbc7532"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.11.tar.gz",
                "has_sig": false,
                "md5_digest": "580fa9f55f1465276f85db5a4f9d7a0c",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5286,
                "upload_time": "2018-08-17T09:34:47",
                "url": "https://files.pythonhosted.org/packages/07/cd/3cef531631ed3785990c3f8472496cadca1e0389e75505575d63ce145ed5/keras-word-char-embd-0.0.11.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "27be977a07d20bbaa3a8b94ba6b0abd7",
                    "sha256": "e541aa392de0db2deafc14d274c77c50f47448d050911e321f9ac5b33d80eff3"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "27be977a07d20bbaa3a8b94ba6b0abd7",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 4892,
                "upload_time": "2018-07-28T07:41:19",
                "url": "https://files.pythonhosted.org/packages/3c/01/75e48d362b06ad94c45446f2f320f4b51d387fc754d852741599a4777bb6/keras_word_char_embd-0.0.2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "32ca8795b6f6525dbeeb40e4b7fe8515",
                    "sha256": "e64e67a05d4cd955c21e72767b4a925ef6cd4933b6e533a0110f80d8efb70172"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "32ca8795b6f6525dbeeb40e4b7fe8515",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 3158,
                "upload_time": "2018-07-28T07:41:22",
                "url": "https://files.pythonhosted.org/packages/05/2d/a60a4010d128a5d3f0d6ab24b6aaa7c0c34cf5e40555b4ed68bc166ab15a/keras_word_char_embd-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "523c1f1966bb063ef856ff82e8807184",
                    "sha256": "706380502a826736b751ef5769aba7873eef97db34cc957e5c32351c30ef00bc"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "523c1f1966bb063ef856ff82e8807184",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 7213,
                "upload_time": "2018-07-28T11:05:50",
                "url": "https://files.pythonhosted.org/packages/88/13/356fa342fe1a1b5ddffcfe94f0c97586c23a6df021deafc67b3bd74f4388/keras_word_char_embd-0.0.3-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "21d614325fe638d174813021c4c266d9",
                    "sha256": "c159a0cc13b1cdc2f41ebe503044d0adef99a11258134d950a66f1418cb43a6f"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "21d614325fe638d174813021c4c266d9",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4501,
                "upload_time": "2018-07-28T11:05:53",
                "url": "https://files.pythonhosted.org/packages/43/d3/1074541c57f91b50cdbe85fcf276ee9f7929a40978173b20de7a00fa0c02/keras_word_char_embd-0.0.3.tar.gz"
            }
        ],
        "0.0.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "beb23649e421cb82ba86ecbcae3d04f5",
                    "sha256": "f263f7f48d4c1791ca52f242e3ebbddc2845af714a7a455706b2fa258bda773f"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.4-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "beb23649e421cb82ba86ecbcae3d04f5",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 4925,
                "upload_time": "2018-07-31T01:18:03",
                "url": "https://files.pythonhosted.org/packages/c2/33/3254a92555bc0f6e17a11ef644e5a1a8d99c46bf6eca1e04f2498a5bdc83/keras_word_char_embd-0.0.4-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a849d49e699728108e6b90f002c0082b",
                    "sha256": "2f758e368c35d5a8321a96d498e3c026d101067c0c8428f882439bf133de02d4"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.4.tar.gz",
                "has_sig": false,
                "md5_digest": "a849d49e699728108e6b90f002c0082b",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4504,
                "upload_time": "2018-07-31T01:18:04",
                "url": "https://files.pythonhosted.org/packages/93/02/aa1cd81bda26436d83c78666c05654e00c96a2a30250e3be3fc48e31db62/keras-word-char-embd-0.0.4.tar.gz"
            }
        ],
        "0.0.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "27701d91d64d551e1d23a56fe1b698da",
                    "sha256": "b1f119fb27ae2f4698b08438232c41d8a1b6c4359e1e4ffecd8cbd8ca60707fb"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.5-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "27701d91d64d551e1d23a56fe1b698da",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 8161,
                "upload_time": "2018-07-31T02:51:58",
                "url": "https://files.pythonhosted.org/packages/3a/3e/e8d4f1e8c560ad3d4a6dfdd11a2169fc7d1ea09337530a138850d5b7317c/keras_word_char_embd-0.0.5-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "34f59be596d806262a97fa599816cb48",
                    "sha256": "b801c877f4a6260f25502882f252a25cdeef993053f5d313896c5c7ac971da8d"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.5.tar.gz",
                "has_sig": false,
                "md5_digest": "34f59be596d806262a97fa599816cb48",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5256,
                "upload_time": "2018-07-31T02:52:00",
                "url": "https://files.pythonhosted.org/packages/87/c9/bddda5a7abbf31f00fba133c1b6cd8e408ad12fe72848038e0748afe240d/keras-word-char-embd-0.0.5.tar.gz"
            }
        ],
        "0.0.6": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b04b60d51eec6838ed8b5a7c9a685337",
                    "sha256": "4dd415b10a3c02956903f4eb0cf497c476800c370d5affbf576235da03b520a1"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.6-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b04b60d51eec6838ed8b5a7c9a685337",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 8183,
                "upload_time": "2018-07-31T03:13:26",
                "url": "https://files.pythonhosted.org/packages/ef/43/8ef41972609fd49461cd6e098e9a8f7fef5133de270df3dda3f629b39a43/keras_word_char_embd-0.0.6-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "b4ebbf96826bd8bcbb056e1f95c41ab8",
                    "sha256": "c376df77bbbeeb75d1887fb5e25a2776b51bd177c9d9aacc6ad86ddee5b91c70"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.6.tar.gz",
                "has_sig": false,
                "md5_digest": "b4ebbf96826bd8bcbb056e1f95c41ab8",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5266,
                "upload_time": "2018-07-31T03:13:30",
                "url": "https://files.pythonhosted.org/packages/3f/84/25425d4bb2f65cf2d8ab29868c4fb5bcb042c90134692b700911e37033a3/keras-word-char-embd-0.0.6.tar.gz"
            }
        ],
        "0.0.7": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "df9a87f671b6b3bc4343310e425ff98d",
                    "sha256": "e892b77c58e17b869443200c18d1029363199d87c84cb82bbf28ecb2f7b03034"
                },
                "downloads": -1,
                "filename": "keras_word_char_embd-0.0.7-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "df9a87f671b6b3bc4343310e425ff98d",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 8236,
                "upload_time": "2018-08-03T00:56:40",
                "url": "https://files.pythonhosted.org/packages/32/61/e5209748e652ee8ad2d8a239220c09b67c5b1e5824f0e63b0382c9dfa50e/keras_word_char_embd-0.0.7-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a11d18c5970a6f03366ca483933e07d2",
                    "sha256": "6cd6a5b29db720b154a9e833c1cc7100d1c1184e77d37771dc5cd7f11d41638c"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.7.tar.gz",
                "has_sig": false,
                "md5_digest": "a11d18c5970a6f03366ca483933e07d2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5324,
                "upload_time": "2018-08-03T00:56:42",
                "url": "https://files.pythonhosted.org/packages/78/0e/58093586aa57b74c8588fce5b29350d9b7ff72e6295bc1fdcdad1a0d55c3/keras-word-char-embd-0.0.7.tar.gz"
            }
        ],
        "0.0.8": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "70bbc1b80c635e1b3156a9c876da65b2",
                    "sha256": "c6bdd2a2f7184a0c06d18108082461d00efa554a14be5f11c7768bfd04309d1f"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.8.tar.gz",
                "has_sig": false,
                "md5_digest": "70bbc1b80c635e1b3156a9c876da65b2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5334,
                "upload_time": "2018-08-07T02:28:08",
                "url": "https://files.pythonhosted.org/packages/46/15/702c84c53c9bc64bf005a4d3da9025f326df059f3f081292f7b74ec19ab8/keras-word-char-embd-0.0.8.tar.gz"
            }
        ],
        "0.0.9": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "89a396754f37d658d5dedfd68ae4c486",
                    "sha256": "9165b6fb3a82c43e32dab4ccdbcb2f4c64314242f35f7a86a5e3033d19d7a769"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.0.9.tar.gz",
                "has_sig": false,
                "md5_digest": "89a396754f37d658d5dedfd68ae4c486",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5323,
                "upload_time": "2018-08-07T03:20:33",
                "url": "https://files.pythonhosted.org/packages/44/3c/9401d71b4219b624fef03361fa8203b993b4c2663663cc2370216898825f/keras-word-char-embd-0.0.9.tar.gz"
            }
        ],
        "0.12": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "01227d497eeba0687bac4f176072efbf",
                    "sha256": "8d182e93937ce0a0accc9b42a37c48ef076c0d724589c2043c3afa5a79818183"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.12.tar.gz",
                "has_sig": false,
                "md5_digest": "01227d497eeba0687bac4f176072efbf",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 6940,
                "upload_time": "2018-09-13T09:00:09",
                "url": "https://files.pythonhosted.org/packages/87/e4/a595edb707e9de3e6ed2e1f0f26d44001d3739f86daa48ec8bff90bdb10d/keras-word-char-embd-0.12.tar.gz"
            }
        ],
        "0.13": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "45aa0cfd4377612741bbc5b14dc20772",
                    "sha256": "f883522c1993cd6e3d3a80aaf76643ca5508026ad2510916c98aaff6173e5e8b"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.13.tar.gz",
                "has_sig": false,
                "md5_digest": "45aa0cfd4377612741bbc5b14dc20772",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 6940,
                "upload_time": "2018-09-13T09:23:03",
                "url": "https://files.pythonhosted.org/packages/ab/bf/3b273e18fe9c5a78cbadf44b7d8a25d4e6bbaafbdf01a11ef52502c27408/keras-word-char-embd-0.13.tar.gz"
            }
        ],
        "0.14": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "2efa0fa3c702813e59c632f26c3ba9da",
                    "sha256": "6b524ec70cb80973dcc0f0f158ab6b6dbedc258f8e3302d4a6402c2124fb8041"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.14.tar.gz",
                "has_sig": false,
                "md5_digest": "2efa0fa3c702813e59c632f26c3ba9da",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7259,
                "upload_time": "2018-09-26T02:45:34",
                "url": "https://files.pythonhosted.org/packages/4b/42/23d920aace48b568114aedf6da7d9e2945c5fe0e5246c21e762f40822181/keras-word-char-embd-0.14.tar.gz"
            }
        ],
        "0.15": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "60ab85377e4f77ff37c20b17cc070830",
                    "sha256": "2d70a47434c6afc9c14bd1c17302f4e4cec25ba40873f0a1375109fda1ff72c7"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.15.tar.gz",
                "has_sig": false,
                "md5_digest": "60ab85377e4f77ff37c20b17cc070830",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7257,
                "upload_time": "2018-09-26T03:07:48",
                "url": "https://files.pythonhosted.org/packages/2b/5b/d3b38aac8b4f6884bde6eafa35be1ebe9c13aa3060bf4465ccbc061c8a95/keras-word-char-embd-0.15.tar.gz"
            }
        ],
        "0.16.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "962580c1df169435f17526ada3b7a5af",
                    "sha256": "36ea66e9da16cb9565e7d6f9b9e493f656971649785761c80db73bdad2b52f87"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.16.0.tar.gz",
                "has_sig": false,
                "md5_digest": "962580c1df169435f17526ada3b7a5af",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7282,
                "upload_time": "2018-12-26T07:31:14",
                "url": "https://files.pythonhosted.org/packages/82/83/fc2e0a1f869b7216b81c85351620205a9f51f1eb7adbeb3ea1ab414665ac/keras-word-char-embd-0.16.0.tar.gz"
            }
        ],
        "0.17.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7507df62ecbde201ec242b4a5e93ef51",
                    "sha256": "67eb15538fa90964d37876d6eaa443f3da54fe595ecc99714261eb5a718430e3"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.17.0.tar.gz",
                "has_sig": false,
                "md5_digest": "7507df62ecbde201ec242b4a5e93ef51",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7172,
                "upload_time": "2019-02-01T03:26:31",
                "url": "https://files.pythonhosted.org/packages/b2/23/f59ba904c9533df7d73d1c0281e4d53d8d69c88ad49fba87dc1f4d3b72ad/keras-word-char-embd-0.17.0.tar.gz"
            }
        ],
        "0.18.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "1baf2e0049524a5e12fc6dd424f8ba4f",
                    "sha256": "1e49d7257a6b586eafab11c6c0e79e47fc9f7a7f132c4fe8e94b97e347e5441f"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.18.0.tar.gz",
                "has_sig": false,
                "md5_digest": "1baf2e0049524a5e12fc6dd424f8ba4f",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7340,
                "upload_time": "2019-02-01T03:28:08",
                "url": "https://files.pythonhosted.org/packages/85/c3/e0ce7ad1bbffb60632bb0be0796eabce3b7f3390cbb1a304267ab4eec041/keras-word-char-embd-0.18.0.tar.gz"
            }
        ],
        "0.19.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "95aaeaf4d1f600a8a553bbe94e59dc69",
                    "sha256": "2bef1f06a1b153831872f76b3635726f7ed778f8e3914de72643bbf1a622a662"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.19.0.tar.gz",
                "has_sig": false,
                "md5_digest": "95aaeaf4d1f600a8a553bbe94e59dc69",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7331,
                "upload_time": "2019-03-11T06:38:48",
                "url": "https://files.pythonhosted.org/packages/6e/24/7417e44a587a485385781087f3964d737bcb087d0b732baa46a0b1addf69/keras-word-char-embd-0.19.0.tar.gz"
            }
        ],
        "0.20.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "647ea1f51256be7382721c68edc510a6",
                    "sha256": "0d8e5a9bcf6ee89447a9f4a50ca10398425503922ad38634a77b13a51fd4e834"
                },
                "downloads": -1,
                "filename": "keras-word-char-embd-0.20.0.tar.gz",
                "has_sig": false,
                "md5_digest": "647ea1f51256be7382721c68edc510a6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7672,
                "upload_time": "2019-04-01T06:31:49",
                "url": "https://files.pythonhosted.org/packages/cd/31/b32b253197a159bde1385b394f5858edb3cbc7cde1cc111e629869a7b72b/keras-word-char-embd-0.20.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "647ea1f51256be7382721c68edc510a6",
                "sha256": "0d8e5a9bcf6ee89447a9f4a50ca10398425503922ad38634a77b13a51fd4e834"
            },
            "downloads": -1,
            "filename": "keras-word-char-embd-0.20.0.tar.gz",
            "has_sig": false,
            "md5_digest": "647ea1f51256be7382721c68edc510a6",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7672,
            "upload_time": "2019-04-01T06:31:49",
            "url": "https://files.pythonhosted.org/packages/cd/31/b32b253197a159bde1385b394f5858edb3cbc7cde1cc111e629869a7b72b/keras-word-char-embd-0.20.0.tar.gz"
        }
    ]
}