{ "info": { "author": "Jeroen Janssens", "author_email": "jeroen@jeroenjanssens.com", "bugtrack_url": null, "classifiers": [], "description": "scikit-sos\n==========\n\nscikit-sos is a Python module for Stochastic Outlier Selection (SOS). It\nis compatible with scikit-learn. SOS is an unsupervised outlier selection\nalgorithm. It uses the concept of affinity to compute an outlier probability\nfor each data point.\n\n.. figure:: https://github.com/jeroenjanssens/scikit-sos/raw/master/doc/sos.png\n :alt: SOS\n\nFor more information about SOS, see the technical report: J.H.M.\nJanssens, F. Huszar, E.O. Postma, and H.J. van den Herik. `Stochastic\nOutlier\nSelection `__.\nTechnical Report TiCC TR 2012-001, Tilburg University, Tilburg, the\nNetherlands, 2012.\n\nInstall\n-------\n\n.. code:: bash\n\n pip install scikit-sos\n\n\nUsage\n-----\n\n.. code:: python\n\n >>> import pandas as pd\n >>> from sksos import SOS\n >>> iris = pd.read_csv(\"http://bit.ly/iris-csv\")\n >>> X = iris.drop(\"Name\", axis=1).values\n >>> iris[\"score\"] = detector.predict(X)\n >>> iris.sort_values(\"score\", ascending=False).head(10)\n SepalLength SepalWidth PetalLength PetalWidth Name score\n 41 4.5 2.3 1.3 0.3 Iris-setosa 0.981898\n 106 4.9 2.5 4.5 1.7 Iris-virginica 0.964381\n 22 4.6 3.6 1.0 0.2 Iris-setosa 0.957945\n 134 6.1 2.6 5.6 1.4 Iris-virginica 0.897970\n 24 4.8 3.4 1.9 0.2 Iris-setosa 0.871733\n 114 5.8 2.8 5.1 2.4 Iris-virginica 0.831610\n 62 6.0 2.2 4.0 1.0 Iris-versicolor 0.821141\n 108 6.7 2.5 5.8 1.8 Iris-virginica 0.819842\n 44 5.1 3.8 1.9 0.4 Iris-setosa 0.773301\n 100 6.3 3.3 6.0 2.5 Iris-virginica 0.765657\n\n\nSelecting outliers from the command line\n----------------------------------------\n\nThis module also includes a command-line tool called `sos`.\nTo illustrate, we apply SOS with a perplexity of 10 to the Iris dataset:\n\n.. code:: bash\n\n $ curl -sL http://bit.ly/iris-csv |\n > tail -n +2 | cut -d, -f1-4 |\n > sos -p 10 |\n > sort -nr | head\n 0.98189840\n 0.96438132\n 0.95794492\n 0.89797043\n 0.87173299\n 0.83161045\n 0.82114072\n 0.81984209\n 0.77330148\n 0.76565738\n\n\nAdding a threshold causes SOS to output 0s and 1s instead of outlier\nprobabilities. If we set the threshold to 0.8 then we see that out of\nthe 150 data points, 8 are selected as outliers:\n\n.. code:: bash\n\n $ curl -sL http://bit.ly/iris-csv |\n > tail -n +2 | cut -d, -f1-4 |\n > sos -p 10 -t 0.8 |\n > paste -sd+ | bc\n 8\n\n\nLicense\n-------\n\nAll software in this repository is distributed under the terms of the\nBSD Simplified License. The full license is in the LICENSE file.", "description_content_type": null, "docs_url": null, "download_url": "UNKNOWN", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/jeroenjanssens/scikit-sos", "keywords": null, "license": "BSD", "maintainer": null, "maintainer_email": null, "name": "scikit-sos", "package_url": "https://pypi.org/project/scikit-sos/", "platform": "UNKNOWN", "project_url": "https://pypi.org/project/scikit-sos/", "project_urls": { "Download": "UNKNOWN", "Homepage": "https://github.com/jeroenjanssens/scikit-sos" }, "release_url": "https://pypi.org/project/scikit-sos/0.1.10/", "requires_dist": null, "requires_python": null, "summary": "A scikit-learn compatible implementation of Stochastic Outlier Selection (SOS) for detecting outliers.", "version": "0.1.10" }, "last_serial": 2400918, "releases": { "0.1.0": [ { "comment_text": "", "digests": { "md5": "44a04bf0948f66534bd39a03b7320e92", "sha256": "3c402a1ceba273cdfd345cad8c430e621a57d5aa7e526ba9808182a3f9d2ee3e" }, "downloads": -1, "filename": "scikit-sos-0.1.0.tar.gz", "has_sig": false, "md5_digest": "44a04bf0948f66534bd39a03b7320e92", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4476, "upload_time": "2016-09-22T09:41:10", "url": "https://files.pythonhosted.org/packages/e5/16/3d0a7cd308007933ee85a5841e0d636899354c4a2a54c8d6e3e93c2378eb/scikit-sos-0.1.0.tar.gz" } ], "0.1.1": [ { "comment_text": "", "digests": { "md5": "34666df91a53d93c212ee5eb25071c3f", "sha256": "440dc1e9089a37079e5ac6be11a3aec887e85415cba3f468253dedbb7e6d7eea" }, "downloads": -1, "filename": "scikit-sos-0.1.1.tar.gz", "has_sig": false, "md5_digest": "34666df91a53d93c212ee5eb25071c3f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4456, "upload_time": "2016-09-22T09:45:44", "url": "https://files.pythonhosted.org/packages/f4/0d/465796332c9e303c0f2cc58c284a85392c676d988325b81467f8602b5289/scikit-sos-0.1.1.tar.gz" } ], "0.1.10": [ { "comment_text": "", "digests": { "md5": "0c783ee23859ffeb9729cf8c2d129703", "sha256": "a64de8e093b6bd340a2fed6d48078def54cc997aaae591a330f45e16e30bbf94" }, "downloads": -1, "filename": "scikit-sos-0.1.10.tar.gz", "has_sig": false, "md5_digest": "0c783ee23859ffeb9729cf8c2d129703", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4877, "upload_time": "2016-10-15T09:14:50", "url": "https://files.pythonhosted.org/packages/f8/27/3fe58a96f5b0695026b8662082e65782010ae227c521a5e9ebd1be34599d/scikit-sos-0.1.10.tar.gz" } ], "0.1.2": [ { "comment_text": "", "digests": { "md5": "4cd2359b70aee0768393e8dce769078d", "sha256": "c745559b2de7444cd514920775de2d0eb74130bd0a5d2ea8c46978760dc337fc" }, "downloads": -1, "filename": "scikit-sos-0.1.2.tar.gz", "has_sig": false, "md5_digest": "4cd2359b70aee0768393e8dce769078d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4456, "upload_time": "2016-09-22T10:09:31", "url": "https://files.pythonhosted.org/packages/5a/aa/9590d64720d6b3cd51d7f1b511a7158a4241f7bcd59b516ed0e3b4fe1cb7/scikit-sos-0.1.2.tar.gz" } ], "0.1.3": [ { "comment_text": "", "digests": { "md5": "097c834a187eeb0feda23226bc78bf0e", "sha256": "0ac38732cd1c83480fe89ed9031c1b0471daffddc37cf5aa3a91bd956385f783" }, "downloads": -1, "filename": "scikit-sos-0.1.3.tar.gz", "has_sig": false, "md5_digest": "097c834a187eeb0feda23226bc78bf0e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4442, "upload_time": "2016-09-22T10:27:58", "url": "https://files.pythonhosted.org/packages/cc/41/d36d43ea2afc73f1647c12d086626fd995aea3491b344032a61e516ad036/scikit-sos-0.1.3.tar.gz" } ], "0.1.4": [ { "comment_text": "", "digests": { "md5": "18d5d6927a04b65733b2750e5eeed934", "sha256": "e3b046795e3c54e9e8a7bebe9571a898da3dab29aedd13e146422093a2b01cdb" }, "downloads": -1, "filename": "scikit-sos-0.1.4.tar.gz", "has_sig": false, "md5_digest": "18d5d6927a04b65733b2750e5eeed934", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4444, "upload_time": "2016-09-22T10:42:14", "url": "https://files.pythonhosted.org/packages/d6/cc/bd93c829b96630845f5fe4038c8243f18af559b10d9c9523d64dab81a744/scikit-sos-0.1.4.tar.gz" } ], "0.1.6": [ { "comment_text": "", "digests": { "md5": "fe8ceae6954246ebd897593db64f3c60", "sha256": "888b2e42c128f5c06d92f43ad844464f7b73b588d15bbd09f1145fee8b97313a" }, "downloads": -1, "filename": "scikit-sos-0.1.6.tar.gz", "has_sig": false, "md5_digest": "fe8ceae6954246ebd897593db64f3c60", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4406, "upload_time": "2016-09-22T11:50:10", "url": "https://files.pythonhosted.org/packages/b1/e8/f65bbcdc20d7243fea8522186ef882abe67a8fd7c5a6fc8e0302890e10ef/scikit-sos-0.1.6.tar.gz" } ], "0.1.7": [ { "comment_text": "", "digests": { "md5": "d4aa2771f911634fcafc8e62bd91076b", "sha256": "45d4a8eb81cb05383d186db113c55ed5650834d90f9bc1cc73262f73997b4368" }, "downloads": -1, "filename": "scikit-sos-0.1.7.tar.gz", "has_sig": false, "md5_digest": "d4aa2771f911634fcafc8e62bd91076b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4835, "upload_time": "2016-09-22T12:19:42", "url": "https://files.pythonhosted.org/packages/cc/ee/5ebe27375c8a9506493b53b7fddcd6c8253bb803f615ca70bee0a7edceae/scikit-sos-0.1.7.tar.gz" } ], "0.1.8": [ { "comment_text": "", "digests": { "md5": "fc0428ccb6d76feec599040076a117cd", "sha256": "f2c13a45adde9e71d3eed0b8cad4d43e1ccaee881f879dce475c8382d0554ac4" }, "downloads": -1, "filename": "scikit-sos-0.1.8.tar.gz", "has_sig": false, "md5_digest": "fc0428ccb6d76feec599040076a117cd", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4830, "upload_time": "2016-09-22T12:24:57", "url": "https://files.pythonhosted.org/packages/91/cb/7a4962ffb7e6efb1acb463694fc95ceaffaa4d809cb3fc7678d1f3affe51/scikit-sos-0.1.8.tar.gz" } ], "0.1.9": [ { "comment_text": "", "digests": { "md5": "859f7ecac0f84c75be232130b3a678e6", "sha256": "91404f0a97d543faeeaa459499203ddeee0349a2cbd49c4ff65db26aac258b9b" }, "downloads": -1, "filename": "scikit-sos-0.1.9.tar.gz", "has_sig": false, "md5_digest": "859f7ecac0f84c75be232130b3a678e6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4829, "upload_time": "2016-09-22T12:26:01", "url": "https://files.pythonhosted.org/packages/c9/58/f47115e00f776d51a1b660480893cc6e9105eeed2045bb277c74b134e349/scikit-sos-0.1.9.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "0c783ee23859ffeb9729cf8c2d129703", "sha256": "a64de8e093b6bd340a2fed6d48078def54cc997aaae591a330f45e16e30bbf94" }, "downloads": -1, "filename": "scikit-sos-0.1.10.tar.gz", "has_sig": false, "md5_digest": "0c783ee23859ffeb9729cf8c2d129703", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4877, "upload_time": "2016-10-15T09:14:50", "url": "https://files.pythonhosted.org/packages/f8/27/3fe58a96f5b0695026b8662082e65782010ae227c521a5e9ebd1be34599d/scikit-sos-0.1.10.tar.gz" } ] }