{
    "info": {
        "author": "Lovit",
        "author_email": "soy.lovit@gmail.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "# soyclustering: Python clustering algorithm library for document clustering\n\n\ubb38\uc11c \uad70\uc9d1\ud654\ub97c \uc704\ud574\uc11c\ub294 Euclidean distance \uac00 \uc544\ub2cc Cosine distance \ub97c \uc774\uc6a9\ud558\ub294 Spherical k-means \ub97c \uc774\uc6a9\ud574\uc57c \ud569\ub2c8\ub2e4. \uadf8\ub7ec\ub098 scikit-learn \uc758 sklearn.cluster.KMeans \ub294 Spherical k-means \ub97c \uc81c\uacf5\ud558\uc9c0 \uc54a\uc2b5\ub2c8\ub2e4. \ub610\ud55c \ubb38\uc11c \uad70\uc9d1\ud654 \uacb0\uacfc\ub97c \ud574\uc11d\ud558\uae30 \uc704\ud558\uc5ec \uac01 \ud074\ub7ec\uc2a4\ud130\uc758 \ub808\uc774\ube14\uc744 \ub2ec\uc544\uc57c \ud569\ub2c8\ub2e4. \n\nsoyclustering \uc740 \ubb38\uc11c \uad70\uc9d1\ud654\ub97c \uc704\ud55c spherical k-means \uc54c\uace0\ub9ac\uc998\uacfc centroid \uae30\ubc18 cluster labeling algorithm \uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4.\n\nSpherical k-means \ub294 bag-of-words model \uacfc \uac19\uc740 sparse vector \uc640 Doc2Vec \uacfc \uac19\uc740 distribted repsentation \ubaa8\ub450\uc5d0\uc11c \uc798 \uc791\ub3d9\ud569\ub2c8\ub2e4. \ud558\uc9c0\ub9cc, cluster labeling \uc740 sparse vector \ub85c \ud45c\ud604\ub41c centroid vectors \ub97c \uae30\uc900\uc73c\ub85c \uc791\ub3d9\ud569\ub2c8\ub2e4.\n\n\ub610\ud55c k-means \uacc4\uc5f4 \uad70\uc9d1\ud654 \uc54c\uace0\ub9ac\uc998\uc744 \uc774\uc6a9\ud560 \ub54c \uc0ac\uc6a9\uc790\ub294 \uc801\uc808\ud55c k \ub97c \uacb0\uc815\ud574\uc57c \ud569\ub2c8\ub2e4. Silhouette score \uc640 \uac19\uc740 \ubc29\ubc95\uc774 \uc788\uc9c0\ub9cc, \uc774\ub294 \uc800\ucc28\uc6d0 \ubca1\ud130 \uacf5\uac04\uc758 \uad70\uc9d1\ud654\uc5d0 \uc801\ud569\ud558\uba70, bag-of-words model \uc774\ub098 distributed representation \uacfc \uac19\uc740 \uace0\ucc28\uc6d0 \uacf5\uac04\uc5d0\uc11c\ub294 \uc801\ud569\ud55c \ubc29\ubc95\uc774 \uc544\ub2d9\ub2c8\ub2e4. Uniform effect \uc640 \uac19\uc740 \ud604\uc0c1\uc744 \ud53c\ud560 \uc218 \uc788\ub294 \ud604\uc2e4\uc801\uc778 \ubc29\ubc95\uc740 \uc608\uc0c1\ud558\ub294 \uac83\ubcf4\ub2e4 \ub354 \ub9ce\uc740 \uad70\uc9d1\uc758 \uc218\ub97c k \ub85c \uc124\uc815\ud55c \ub4a4, \ube44\uc2b7\ud55c \uad70\uc9d1\uc744 \ud558\ub098\uc758 \uad70\uc9d1\uc73c\ub85c \ud6c4\ucc98\ub9ac \uacfc\uc815\uc5d0\uc11c \ubb36\ub294 \uac83\uc785\ub2c8\ub2e4.\n\nsoyclustering \uc740 \uc774\ub97c \uc704\ud574 centroid vectors \uc758 pairwise distance matrix \ub97c \uc2dc\uac01\ud654 \ud568\uc73c\ub85c\uc368, \ud604\uc7ac \uad70\uc9d1\ud654\uc758 \uacb0\uacfc\uc5d0 \uc911\ubcf5 \uad70\uc9d1\uc740 \uc5c6\ub294\uc9c0 \uc0b4\ud3b4\ubcf4\uba70, \ube44\uc2b7\ud55c \uad70\uc9d1\ub4e4\uc744 \ud558\ub098\uc758 \uad70\uc9d1\uc73c\ub85c \ubb36\ub294 \ud6c4\ucc98\ub9ac \uacfc\uc815\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4.\n\n\uadf8\ub9ac\uace0 k-means \uc758 initializer \ub85c \uc774\uc6a9\ub418\ub294 k-means++ \uc740 \uc5ed\uc2dc \uc800\ucc28\uc6d0 \ubca1\ud130 \uacf5\uac04\uc5d0\uc11c \uc791\ub3d9\ud558\ub294 \uc54c\uace0\ub9ac\uc998\uc785\ub2c8\ub2e4. \uace0\ucc28\uc6d0 \uacf5\uac04\uc5d0\uc11c\ub294 \ub9e4\uc6b0 \ub290\ub9b0 initialization \uc131\ub2a5\uc744 \ubcf4\uc774\uae30 \ub54c\ubb38\uc5d0 soyclustering \uc740 \uc774\ub97c \uac1c\uc120\ud558\ub294 fast initializer \ub97c \uc81c\uacf5\ud569\ub2c8\ub2e4.\n\n## Usage\n\n\ud1a0\ud06c\ub098\uc774\uc9d5\uc774 \ub418\uc5b4 \uc788\ub294 matrix market \ud615\uc2dd\uc758 \ud30c\uc77c\uc744 \uc77d\uc2b5\ub2c8\ub2e4. Doc2Vec \uacfc \uac19\uc740 distributed representation \uc5d0 \ub300\ud574\uc11c\ub3c4 spherical k-means \ub294 \uc791\ub3d9\ud558\uc9c0\ub9cc, cluster labeling algorithm \uc740 bag-of-words model \uc5d0\uc11c\ub9cc \uc791\ub3d9\ud569\ub2c8\ub2e4.\n\n```python\nfrom scipy.io import mmread\nx = mmread(mm_file).tocsr()\n```\n\n\uad6c\ud604\ub41c spherical k-means \ub294 \uc544\ub798\ucc98\ub7fc \uc774\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. init='similar_cut' \uc740 \uace0\ucc28\uc6d0 \ubca1\ud130\uc5d0\uc11c \ud6a8\uc728\uc801\uc73c\ub85c \uc791\ub3d9\ud558\ub294 initializer \uc785\ub2c8\ub2e4. \ub610\ud55c centroid \uc758 sparsity \ub97c \uc720\uc9c0\ud558\uae30 \uc704\ud574 minimum_df \ubc29\ubc95\uc744 \uc774\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uadf8 \uc678\uc758 interface \ub294 scikit-learn \uc758 k-means \uc640 \ub3d9\uc77c\ud569\ub2c8\ub2e4. fit_predict \ub97c \ud1b5\ud558\uc5ec \uad70\uc9d1\ud654 \uacb0\uacfc\uc758 labels \ub97c \uc5bb\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n\n```python\nfrom soyclustering import SphericalKMeans\nspherical_kmeans = SphericalKMeans(\n    n_clusters=1000,\n    max_iter=10,\n    verbose=1,\n    init='similar_cut',\n    sparsity='minimum_df', \n    minimum_df_factor=0.05\n)\n\nlabels = spherical_kmeans.fit_predict(x)\n```\n\nVerbose mode \uc77c \ub54c\uc5d0\ub294 initialization \uacfc \ub9e4 iteration \uc5d0\uc11c\uc758 \uacc4\uc0b0 \uc2dc\uac04\uacfc centroid vectors \uc758 sparsity \uac00 \ucd9c\ub825\ub429\ub2c8\ub2e4.\n\n```\ninitialization_time=1.218108 sec, sparsity=0.00796\nn_iter=1, changed=29969, inertia=15323.440, iter_time=4.435 sec, sparsity=0.116\nn_iter=2, changed=5062, inertia=11127.620, iter_time=4.466 sec, sparsity=0.108\nn_iter=3, changed=2179, inertia=10675.314, iter_time=4.463 sec, sparsity=0.105\nn_iter=4, changed=1040, inertia=10491.637, iter_time=4.449 sec, sparsity=0.103\nn_iter=5, changed=487, inertia=10423.503, iter_time=4.437 sec, sparsity=0.103\nn_iter=6, changed=297, inertia=10392.490, iter_time=4.483 sec, sparsity=0.102\nn_iter=7, changed=178, inertia=10373.646, iter_time=4.442 sec, sparsity=0.102\nn_iter=8, changed=119, inertia=10362.625, iter_time=4.449 sec, sparsity=0.102\nn_iter=9, changed=78, inertia=10355.905, iter_time=4.438 sec, sparsity=0.102\nn_iter=10, changed=80, inertia=10350.703, iter_time=4.452 sec, sparsity=0.102\n```\n\n\uad70\uc9d1\ud654 \uacb0\uacfc\uc758 \ud574\uc11d\uc744 \uc704\ud558\uc5ec cluster labeling \uc744 \uc218\ud589\ud569\ub2c8\ub2e4. soyclustering \uc774 \uc81c\uacf5\ud558\ub294 proportion keywords \ud568\uc218\ub294 keyword extraction \ubc29\ubc95\uc5d0 \uae30\ubc18\ud558\uc5ec \uac01 \uad70\uc9d1\uc758 \ud0a4\uc6cc\ub4dc\ub97c \ucd94\ucd9c\ud569\ub2c8\ub2e4. input arguments \ub85c \uad70\uc9d1\ud654 \uacb0\uacfc \uc5bb\ub294 cluster centroid vectors \uc640 list of str \ud615\uc2dd\uc73c\ub85c \uc774\ub904\uc9c4 vocab list \uac00 \ud544\uc694\ud569\ub2c8\ub2e4. \ub610\ud55c \uac01 \uad70\uc9d1\uc758 \ud06c\uae30\ub97c \uce21\uc815\ud560 \uc218 \uc788\ub294 labels \ub97c \uc785\ub825\ud574\uc57c \ud569\ub2c8\ub2e4.\n\n```python\nfrom soyclustering import proportion_keywords\n\ncenters = spherical_kmeans.cluster_centers_\nidx2vocab = ['list', 'of', 'str', 'vocab']\nkeywords = proportion_keywords(centers, labels, index2word=idx2vocab)\n```\n\n1,226k \uac1c\uc758 \ubb38\uc11c\ub85c \uc774\ub904\uc9c4 IMDB reviews \uc5d0 \ub300\ud558\uc5ec k=1000 \uc73c\ub85c \uc124\uc815\ud558\uc5ec spherical k-means \ub97c \ud559\uc2b5\ud55c \ub4a4, \uc704\uc758 proportion keywords \ud568\uc218\ub97c \uc774\uc6a9\ud558\uc5ec \uad70\uc9d1 \ub808\uc774\ube14\uc744 \ucd94\ucd9c\ud558\uc600\uc2b5\ub2c8\ub2e4. \uc544\ub798\ub294 5 \uac1c \uad70\uc9d1\uc758 \uc608\uc2dc\uc785\ub2c8\ub2e4.\n\n<table>\n  <colgroup>\n    <col width=\"20%\" />\n    <col width=\"80%\" />\n  </colgroup>\n  <thead>\n    <tr class=\"query_and_topic\">\n      <th>\uad70\uc9d1\uc758 \uc758\ubbf8</th>\n      <th>\ud0a4\uc6cc\ub4dc (\ub808\uc774\ube14)</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <td markdown=\"span\"> \uc601\ud654 \u201c\ud0c0\uc774\ud0c0\ub2c9\u201d </td>\n      <td markdown=\"span\"> iceberg, zane, sinking, titanic, rose, winslet, camerons, 1997, leonardo, leo, ship, cameron, dicaprio, kate, tragedy, jack, di saster, james, romance, love, effects, special, story, people, best, ever, made </td>\n    </tr>\n    <tr>\n      <td markdown=\"span\"> Marvle comics \uc758 heros (Avengers) </td>\n      <td markdown=\"span\"> zemo, chadwick, boseman, bucky, panther, holland, cap, infinity, mcu, russo, civil, bvs, antman, winter, ultron, airport, ave ngers, marvel, captain, superheroes, soldier, stark, evans, america, iron, spiderman, downey, tony, superhero, heroes </td>\n    </tr>\n    <tr>\n      <td markdown=\"span\"> Cover-field, District 9 \ub4f1 \uc678\uacc4\uc778 \uad00\ub828 \uc601\ud654 </td>\n      <td markdown=\"span\"> skyline, jarrod, balfour, strause, invasion, independence, cloverfield, angeles, district, los, worlds, aliens, alien, la, budget, scifi, battle, cgi, day, effects, war, special, ending, bad, better, why, they, characters, their, people </td>\n    </tr>\n    <tr>\n      <td markdown=\"span\"> \uc0b4\uc778\uc790\uac00 \ucd9c\uc5f0\ud558\ub294 \uacf5\ud3ec \uc601\ud654 </td>\n      <td markdown=\"span\"> gayheart, loretta, candyman, legends, urban, witt, campus, tara, reid, legend, alicia, englund, leto, rebecca, jared, scream, murders, slasher, helen, killer, student, college, students, teen, summer, cut, horror, final, sequel, scary </td>\n    </tr>\n    <tr>\n      <td markdown=\"span\"> \uc601\ud654 \u201c\ub9e4\ud2b8\ub9ad\uc2a4\" </td>\n      <td markdown=\"span\"> neo, morpheus, neos, oracle, trinity, zion, architect, hacker, reloaded, revolutions, wachowski, fishburne, machines, agents, matrix, keanu, smith, reeves, agent, jesus, machine, computer, humans, fighting, fight, world, cool, real, special, effects </td>\n    </tr>\n  </tbody>\n</table>\n\n\uc608\uc0c1\ud558\ub294 \uac83\ubcf4\ub2e4 \ud070 k \ub97c \uc124\uc815\ud558\uba74 \uba87 \uac1c\uc758 \uad70\uc9d1\ub4e4\uc740 \ube44\uc2b7\ud55c centroid vectors \ub97c \uc9c0\ub2d9\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uad70\uc9d1\uc774 \uc874\uc7ac\ud558\ub294\uc9c0 \ud655\uc778\ud558\uae30 \uc704\ud574\uc11c\ub294 pairwise distance matrix \ub97c \uc0b4\ud3b4\ubd10\uc57c \ud569\ub2c8\ub2e4.\n\n```python\nfrom soyclustering import visualize_pairwise_distance\n\n# visualize pairwise distance matrix\nfig = visualize_pairwise_distance(centers, max_dist=.7, sort=True)\n```\n\n\uadf8\ub9ac\uace0 \ube44\uc2b7\ud55c \uad70\uc9d1\ub4e4\uc774 \uc788\ub2e4\uba74 \uc774\ub97c \ud558\ub098\uc758 \uad70\uc9d1\uc73c\ub85c \ubb36\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n\n```python\nfrom soyclustering import merge_close_clusters\n\ngroup_centers, groups = merge_close_clusters(centers, labels, max_dist=.5)\nfig = visualize_pairwise_distance(group_centers, max_dist=.7, sort=True)\n```\n\n\uadf8 \ub4a4 \ub2e4\uc2dc groups \ub41c centroid vectors \ub97c \uc0b4\ud3b4\ubcf4\uba74 \uc544\ub798\uc758 \uadf8\ub9bc\uacfc \uac19\uc2b5\ub2c8\ub2e4. diagonal elements \ub9cc \uc9c4\ud55c \uc0c9\uc774 \ub748\ub2e4\uba74 \uac01\uac01\uc758 \uad70\uc9d1\uc774 \uc11c\ub85c \uc0c1\uc774\ud558\ub2e4\ub294 \uc758\ubbf8\uc785\ub2c8\ub2e4.\n\n![](https://github.com/lovit/clustering4docs/blob/master/assets/merge_similar_clusters.png)\n\nmerge_close_clusters \ud568\uc218\ub294 centroids \uac00 \uc8fc\uc5b4\uc9c0\uba74 Cosine distance \uac00 \ucd5c\ub300 max_dist \ub97c \ub118\uc9c0 \uc54a\ub294 \uad70\uc9d1\ub4e4\uc744 \ud558\ub098\uc758 \uadf8\ub8f9\uc73c\ub85c \ubb36\uc2b5\ub2c8\ub2e4. group centroid vectors \ub294 \uc6d0 \uad70\uc9d1\uc758 \ud06c\uae30 (labels) \uc5d0 \ube44\ub840\ud55c weighted average of centroids \ub85c \uacc4\uc0b0\ub429\ub2c8\ub2e4.\n\ngroups \ub294 \uac01 \uad70\uc9d1\uc774 \uc5b4\ub5a4 \uadf8\ub8f9\uc73c\ub85c \ubb36\uc600\ub294\uc9c0 nested list \ub85c \ud45c\ud604\ub429\ub2c8\ub2e4.\n\n```python\nfor group in groups:\n    print(group)\n```\n\n```\n[0, 19, 57, 68, 88, 115, 202, 223, 229, 237]\n[1]\n[2]\n[3, 4, 5, 8, 12, 14, 16, 18, 20, 22, 26, 28, ...]\n[6, 25, 29, 32, 37, 43, 45, 48, 53, 56, 65, ...]\n[7, 17, 34, 41, 52, 59, 76, 79, 84, 87, 93, ...]\n[9, 15, 24, 47, 51, 97]\n[10, 100, 139]\n[11, 23, 251]\n...\n```\n\n## See more\n\npyLDAvis \ub97c \uc774\uc6a9\ud558\uba74 \uad70\uc9d1\ud654 \uacb0\uacfc\ub97c \uc2dc\uac01\uc801\uc73c\ub85c \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774\uc5d0 \uad00\ub828\ud55c \ucf54\ub4dc\ub294 \ub2e4\uc74c\uc758 github \uc5d0\uc11c \uc81c\uacf5\ud569\ub2c8\ub2e4. [kmeans_to_pyLDAvis](https://github.com/lovit/kmeans_to_pyLDAvis)\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/lovit/clustering4docs",
        "keywords": "document clustering,clustering labeling",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "soyclustering",
        "package_url": "https://pypi.org/project/soyclustering/",
        "platform": "",
        "project_url": "https://pypi.org/project/soyclustering/",
        "project_urls": {
            "Homepage": "https://github.com/lovit/clustering4docs"
        },
        "release_url": "https://pypi.org/project/soyclustering/0.1.0/",
        "requires_dist": [
            "numpy (>=1.1)"
        ],
        "requires_python": "",
        "summary": "Python library for document clustering",
        "version": "0.1.0"
    },
    "last_serial": 5704725,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b440c5d9132c68f74f4e60a6af4bc3d3",
                    "sha256": "3dda02c79401a4c33c675b11746ee31c4e9df5170bc30bdf719b62269a82245e"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b440c5d9132c68f74f4e60a6af4bc3d3",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9765,
                "upload_time": "2018-05-25T07:23:36",
                "url": "https://files.pythonhosted.org/packages/f1/77/4ff0e8329f12e33b5f33b28b2f03cecd55e3f3d606caeb8a53f211b665c0/soyclustering-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "13644de38b55f2c345702d257037536d",
                    "sha256": "73daf4346f3a0bc90ee41e7784b22a07f5efcb06c81db86b95749086401d65f2"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "13644de38b55f2c345702d257037536d",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7917,
                "upload_time": "2018-05-25T07:23:37",
                "url": "https://files.pythonhosted.org/packages/c4/f1/ca3f2805e272f8c74bdb59322df6dacfe629c9814ec4779d089811737c8a/soyclustering-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a24e562202cacc434ba2f89e02576b90",
                    "sha256": "a60a19abfa8df10a59d7b8ab2b3bcad66f97ba05a8b9dc54f599047d2b03f600"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a24e562202cacc434ba2f89e02576b90",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9792,
                "upload_time": "2018-05-25T07:25:41",
                "url": "https://files.pythonhosted.org/packages/2b/63/f1d94dc0644538f89402e3ac2f931cc669b4cc651924de09775ed368931c/soyclustering-0.0.2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "20fe891264349f29e13641b76d1f3c41",
                    "sha256": "f4bab693c38c0d19e322b66452488f41cb1e1eb14e70448fb49eea11f783cde6"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "20fe891264349f29e13641b76d1f3c41",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7933,
                "upload_time": "2018-05-25T07:25:42",
                "url": "https://files.pythonhosted.org/packages/0e/72/d864d575d8e91de8e2b8d200b4c69f18c0c0ab03c825b2dcb1c1b28dc782/soyclustering-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "86c53fe5058e0050ff4c355c721c8f9c",
                    "sha256": "f2a359e4c391ee4d3fa31a296f2b12bde6447d45e7447f29add8b10e83ae894b"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "86c53fe5058e0050ff4c355c721c8f9c",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9694,
                "upload_time": "2018-05-25T07:28:28",
                "url": "https://files.pythonhosted.org/packages/9e/19/4e9390eef2ae60018fb6ff8ad0a7ca41359fb5c46c87f17473a05af3be9c/soyclustering-0.0.3-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "cdf58a06441a4b98e6e38404751ed207",
                    "sha256": "1c3744ed7ecdac2b9f7d8ac760a05ed7eba9d0fafc02319a515a848324a4a101"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "cdf58a06441a4b98e6e38404751ed207",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7871,
                "upload_time": "2018-05-25T07:28:30",
                "url": "https://files.pythonhosted.org/packages/3a/16/047e316684a6df0fe5efed372481f17d84813371f8b228f62b5529dcf30a/soyclustering-0.0.3.tar.gz"
            }
        ],
        "0.0.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f280757f281ee94ae70def7dc29708a4",
                    "sha256": "456e29f33b3ccede17a12563dfe09111252c0d4bbdec28b0e68701ae7d9b43a4"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.4-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "f280757f281ee94ae70def7dc29708a4",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9754,
                "upload_time": "2018-05-25T07:32:07",
                "url": "https://files.pythonhosted.org/packages/97/c9/47941bf456d96fbc874dca02032d3106c8876734e5be305041b4551950fe/soyclustering-0.0.4-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "bc2fbf89b1d98ba34d829eddda5b862f",
                    "sha256": "e4c120f66030819721bb48b57ef079c83cc924dcba37ca53262cdb5d2af2c585"
                },
                "downloads": -1,
                "filename": "soyclustering-0.0.4.tar.gz",
                "has_sig": false,
                "md5_digest": "bc2fbf89b1d98ba34d829eddda5b862f",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7907,
                "upload_time": "2018-05-25T07:32:08",
                "url": "https://files.pythonhosted.org/packages/8b/4f/84587dbe1f1fc2743db8a1ae5bf1eccd8a6a7aeb2da5ad346a1cd523f61f/soyclustering-0.0.4.tar.gz"
            }
        ],
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "0a5268ce7629e59e660e794539bec43f",
                    "sha256": "276f68dd7858cb893622cf8f232de4085cb7953152196af20d8a160379801c7d"
                },
                "downloads": -1,
                "filename": "soyclustering-0.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "0a5268ce7629e59e660e794539bec43f",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 28435,
                "upload_time": "2019-08-20T17:49:13",
                "url": "https://files.pythonhosted.org/packages/dc/57/674a06e265fb3a90f060271d5e258a9c671890c01d7e99c7cd639d5d029a/soyclustering-0.1.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "49bd86fad4c8df188508dc9e0b05d8d7",
                    "sha256": "3e2d1e4672bc97827c3c5948ee16e7626211f43a19221ce4d193d791ba2d2351"
                },
                "downloads": -1,
                "filename": "soyclustering-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "49bd86fad4c8df188508dc9e0b05d8d7",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 17820,
                "upload_time": "2019-08-20T17:49:14",
                "url": "https://files.pythonhosted.org/packages/1f/79/a3a2ce7f00c7dabf179056d403337a6a5b96f2cb2d3fefc944e47333372a/soyclustering-0.1.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "0a5268ce7629e59e660e794539bec43f",
                "sha256": "276f68dd7858cb893622cf8f232de4085cb7953152196af20d8a160379801c7d"
            },
            "downloads": -1,
            "filename": "soyclustering-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "0a5268ce7629e59e660e794539bec43f",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 28435,
            "upload_time": "2019-08-20T17:49:13",
            "url": "https://files.pythonhosted.org/packages/dc/57/674a06e265fb3a90f060271d5e258a9c671890c01d7e99c7cd639d5d029a/soyclustering-0.1.0-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "49bd86fad4c8df188508dc9e0b05d8d7",
                "sha256": "3e2d1e4672bc97827c3c5948ee16e7626211f43a19221ce4d193d791ba2d2351"
            },
            "downloads": -1,
            "filename": "soyclustering-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "49bd86fad4c8df188508dc9e0b05d8d7",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 17820,
            "upload_time": "2019-08-20T17:49:14",
            "url": "https://files.pythonhosted.org/packages/1f/79/a3a2ce7f00c7dabf179056d403337a6a5b96f2cb2d3fefc944e47333372a/soyclustering-0.1.0.tar.gz"
        }
    ]
}