{ "info": { "author": "Ingo Scholtes", "author_email": "scholtes@ifi.uzh.ch", "bugtrack_url": null, "classifiers": [ "Development Status :: 5 - Production/Stable", "Intended Audience :: Science/Research", "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Topic :: Scientific/Engineering :: Artificial Intelligence" ], "description": "Introduction\n============\n\npathpy is an OpenSource python package for the analysis of time\nseries data on networks using higher- and multi-order network models.\n\npathpy is specifically tailored to analyse temporal networks as\nwell as time series and sequence data that capture multiple short, \nindependent paths observed in an underlying graph or network. \nExamples for data that can be analysed with pathpy include time-stamped \nsocial networks, user click streams in information networks, biological \npathways, citation networks, or information cascades in social networks. \n\nUnifying the modelling and analysis of path statistics and temporal networks, \npathpy provides efficient methods to extract causal or time-respecting paths from \ntime-stamped network data. The current package distributed via the PyPI name \npathpy2 supersedes the packages pyTempnets as well as version 1.0 of pathpy.\n\npathpy facilitates the analysis of temporal correlations in time\nseries data on networks. It uses model selection and statistical\nlearning to generate optimal higher- and multi-order models that capture both\ntopological and temporal characteristics. It can help to answer the important \nquestion when a network abstraction of complex systems is\njustified and when higher-order representations are needed instead.\n\nThe theoretical foundation of this package, higher- and multi-order network\nmodels, was developed in the following published works:\n\n1. I Scholtes: When is a network a network? Multi-Order Graphical Model\n Selection in Pathways and Temporal Networks, In KDD'17 - Proceedings \n of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and \n Data Mining, Halifax, Nova Scotia, Canada, August 13-17, 2017\n http://dl.acm.org/citation.cfm?id=3098145\n2. I Scholtes, N Wider, A Garas: Higher-Order Aggregate Networks in the\n Analysis of Temporal Networks: Path structures and centralities \n In The European Physical Journal B, 89:61, March 2016 \n http://dx.doi.org/10.1140/epjb/e2016-60663-0\n3. I Scholtes, N Wider, R Pfitzner, A Garas, CJ Tessone, F Schweitzer:\n Causality-driven slow-down and speed-up of diffusion in\n non-Markovian temporal networks, In Nature Communications, 5, September 2014\n http://www.nature.com/ncomms/2014/140924/ncomms6024/full/ncomms6024.html \n4. R Pfitzner, I Scholtes, A Garas, CJ Tessone, F Schweitzer:\n Betweenness preference: Quantifying correlations in the topological\n dynamics of temporal networks, Phys Rev Lett, 110(19), 198701, May 2013\n http://journals.aps.org/prl/abstract/10.1103/PhysRevLett.110.198701\n\npathpy extends higher-order modelling approaches towards multi-order models\nfor paths that capture temporal correlations at multiple length scales\nsimultaneously. All mathematical details of the framework can be found in the \nopenly available preprint at https://arxiv.org/abs/1702.05499.\n\nA broader view on higher-order models in the analyis of complex systems can be \nfound at https://arxiv.org/abs/1806.05977.\n\npathpy is fully integrated with jupyter, providing rich and interactive in-line\nvisualisations of networks, temporal networks, higher-, and multi-order models.\nVisualisations can be exported to HTML5 files that can be shared and published\nonthe Web.\n\n\nDownload and installation\n=========================\n\npathpy is pure python code. It has no platform-specific dependencies\nand should thus work on all platforms. pathpy requires python 3.x. \nIt builds on numpy and scipy. The latest release version 2.0 of pathpy\ncan be installed by typing:\n\npip install pathpy2\n\nPlease make sure that you use the pyPI name pathpy2 as the package name pathpy is currently blocked.\n\nTutorial\n========\n\nA comprehensive 3 hour hands-on tutorial that shows how you can use pathpy \nto analyse data on pathways and temporal networks is available online at:\n\nhttps://ingoscholtes.github.io/kdd2018-tutorial/\n\nAn explanatory video that introduces the science behind pathpy is available here:\n\nhttps://youtu.be/CxJkVrD2ZlM\n\nA promotional video showcasing some of pathpy's features is available here:\n\nhttps://youtu.be/QIPqFaR2Z5c \n\n\nDocumentation\n=============\n\nThe code is fully documented via docstrings which are accessible through\npython's built-in help system. Just type help(SYMBOL_NAME) to see\nthe documentation of a class or method. A reference manual is available\nhere https://ingoscholtes.github.io/pathpy/hierarchy.html\n\n\nReleases and Versioning\n=======================\n\nThe first public beta release of pathpy (released February 17 2017) is\nv1.0-beta. Following versions are named MAJOR.MINOR.PATCH according to semantic\nversioning. The current version is 2.0.0.\n\nKnown Issues\n============\n\n- Depending on whether or not scipy has been compiled \n with or without the numerics package MKL, considerable \n numerical differences can occur, e.g. for eigenvalue \n centralities, PageRank, and other measures that depend \n on the eigenvectors and eigenvalues of matrices. \n Please refer to scipy.show_config() to show compilation flags.\n- Interactive visualisations in jupyter are currently only \n supported for juypter notebooks, stand-alone HTML files, \n and the jupyter display integrated in IDEs like Visual \n Studio Code (which we highly recommend to work with pathpy). \n Due to its new widget mechanism, interactive d3js \n visualisations are currently not available for jupyterLab. \n Due to the complex document object model generated by \n jupyter notebooks, visualisation performance is best in \n stand-alone HTML files and in Visual Studio Code.\n- The visualisation of temporal networks currently does \n not support the drawing of edge arrows for directed \n edges. However, a powerful templating mechanism is \n available to support custom interactive and dynamic \n visualizations of temporal networks.\n- The visualisation of paths in terms of alluvial diagrams \n within jupyter is currently unstable for networks with \n large delay. This is due to the asynchronous loading of \n external scripts.\n\n\nAcknowledgements\n================\n\nThe research behind this data analysis framework was generously funded by the Swiss\nState Secretariate for Education, Research and Innovation via Grant C14.0036. \nThe development of the predecessor package pyTempNets was further supported by the MTEC\nFoundation in the context of the project \"The Influence of Interaction Patterns on\nSuccess in Socio-Technical Systems: From Theory to Practice.\"\n\nThe further development of pathpy is currently supported by the \nSwiss National Science Foundation via Grant 176938. See details at:\n\nhttp://p3.snf.ch/Project-176938\n\n\nContributors\n============\n\nIngo Scholtes (project lead, development)\nLuca Verginer (development, test suite integration)\n\n\nPast Contributors\n=================\nRoman Cattaneo (development)\nNicolas Wider (testing)\n\n\nCopyright\n=========\n\npathpy is licensed under the GNU Affero General Public\nLicense. See https://choosealicense.com/licenses/agpl-3.0/\n\n(c) ETH Z\u00fcrich & University of Zurich, 2015 - 2018\n\n\nHistory\n=======\n\n2.2.0 (2019-09-21)\n------------------\n\n* Several Bug Fixes for API and visualisations\n\n\n2.0.0 (2018-08-17)\n------------------\n\n* PyPi Release of 2.0 release version.\n\n2.0.0a (2018-08-07)\n-------------------\n\n* First public release of 2.0 alpha on PyPI.\n\n1.2.1 (2018-02-23)\n------------------\n\n* First test release on PyPI.\n\n\n", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://www.pathpy.net", "keywords": "network analysis temporal networks pathways sequence modeling graph mining", "license": "AGPL-3.0+", "maintainer": "", "maintainer_email": "", "name": "pathpy2", "package_url": "https://pypi.org/project/pathpy2/", "platform": "", "project_url": "https://pypi.org/project/pathpy2/", "project_urls": { "Homepage": "https://www.pathpy.net" }, "release_url": "https://pypi.org/project/pathpy2/2.2.0/", "requires_dist": [ "numpy", "scipy" ], "requires_python": ">=3.5", "summary": "An OpenSource python package for the analysis and visualisation of time series data on complex networks with higher- and multi-order graphical models.", "version": "2.2.0" }, "last_serial": 5865630, "releases": { "2.0.0": [ { "comment_text": "", "digests": { "md5": "92a9a8c28f1ee4077bb1399f6fede33d", "sha256": "73c4c7372ba9b1e849e20b80d20f8375bb0a2f4f46b2965a64896261a92677b6" }, "downloads": -1, "filename": "pathpy2-2.0.0-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "92a9a8c28f1ee4077bb1399f6fede33d", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": ">=3.5", "size": 117880, "upload_time": "2018-08-17T08:55:06", "url": "https://files.pythonhosted.org/packages/dc/b0/90cb93e9045f58945d3deac8db5350ae7de86cb81d0f3d25d7cffe4673de/pathpy2-2.0.0-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "c2a002595b60a41c35393f4c5354b77a", "sha256": "aed0b9fd0d750a416ad3734347711d280e9c92346c4acbb752cff24609becc6a" }, "downloads": -1, "filename": "pathpy2-2.0.0.tar.gz", "has_sig": false, "md5_digest": "c2a002595b60a41c35393f4c5354b77a", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 90061, "upload_time": "2018-08-17T08:55:08", "url": "https://files.pythonhosted.org/packages/8a/d0/1f835de53ec5a51ce7b7eb6ca02a2b1b6d8eb52eda2617d55f4664d28e7b/pathpy2-2.0.0.tar.gz" } ], "2.0.1": [ { "comment_text": "", "digests": { "md5": "5ff02da4270e45a2e62cc0918513a91a", "sha256": "c609663a94e4c2fc8e97e30f70eaf66e58f1f917608da4cb23addfd55b5e31cb" }, "downloads": -1, "filename": "pathpy2-2.0.1-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "5ff02da4270e45a2e62cc0918513a91a", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": ">=3.5", "size": 204905, "upload_time": "2018-08-18T16:23:37", "url": "https://files.pythonhosted.org/packages/d8/46/86b67962a76ca28b5d34ca2b40742df419e0c95c99d417e044b8b4693a96/pathpy2-2.0.1-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "617443ca5a12741db4f75f1d357ca276", "sha256": "addc6eaa6addf89308f020bd81fa608f44da15ddad7252f15afa3339abd130c9" }, "downloads": -1, "filename": "pathpy2-2.0.1.tar.gz", "has_sig": false, "md5_digest": "617443ca5a12741db4f75f1d357ca276", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 91335, "upload_time": "2018-08-18T16:23:39", "url": "https://files.pythonhosted.org/packages/08/06/9e3a65c92e749b5f4989f0d3ba9d4c6d214898fea9019b51fc945f137a93/pathpy2-2.0.1.tar.gz" } ], "2.2.0": [ { "comment_text": "", "digests": { "md5": "bef1bc0a57c5378d9ca216b0889a8869", "sha256": "76a749426af0952b8f16cc80dccfef16f0553490b13f1a649069081508ce5ddf" }, "downloads": -1, "filename": "pathpy2-2.2.0-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "bef1bc0a57c5378d9ca216b0889a8869", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": ">=3.5", "size": 231283, "upload_time": "2019-09-21T09:23:30", "url": "https://files.pythonhosted.org/packages/94/e7/b3e5849db81476faea0c755f953f62a14bb6f19076f43176cbcc4193c1d5/pathpy2-2.2.0-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "8c00ba1263cd338c5491758b1101403a", "sha256": "431a5ee4826982dd450a7c1ccc76e782debca619f3bbbcd635699d6bcadb7f64" }, "downloads": -1, "filename": "pathpy2-2.2.0.tar.gz", "has_sig": false, "md5_digest": "8c00ba1263cd338c5491758b1101403a", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 101725, "upload_time": "2019-09-21T09:23:32", "url": "https://files.pythonhosted.org/packages/e6/0f/4098196225567121192a6fb736bf47d071040cd04c0d6d67a71ec2c8bc65/pathpy2-2.2.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "bef1bc0a57c5378d9ca216b0889a8869", "sha256": "76a749426af0952b8f16cc80dccfef16f0553490b13f1a649069081508ce5ddf" }, "downloads": -1, "filename": "pathpy2-2.2.0-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "bef1bc0a57c5378d9ca216b0889a8869", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": ">=3.5", "size": 231283, "upload_time": "2019-09-21T09:23:30", "url": "https://files.pythonhosted.org/packages/94/e7/b3e5849db81476faea0c755f953f62a14bb6f19076f43176cbcc4193c1d5/pathpy2-2.2.0-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "8c00ba1263cd338c5491758b1101403a", "sha256": "431a5ee4826982dd450a7c1ccc76e782debca619f3bbbcd635699d6bcadb7f64" }, "downloads": -1, "filename": "pathpy2-2.2.0.tar.gz", "has_sig": false, "md5_digest": "8c00ba1263cd338c5491758b1101403a", "packagetype": "sdist", "python_version": "source", "requires_python": ">=3.5", "size": 101725, "upload_time": "2019-09-21T09:23:32", "url": "https://files.pythonhosted.org/packages/e6/0f/4098196225567121192a6fb736bf47d071040cd04c0d6d67a71ec2c8bc65/pathpy2-2.2.0.tar.gz" } ] }