{"id":13948997,"url":"https://github.com/djgagne/hagelslag","last_synced_at":"2025-05-08T05:54:59.614Z","repository":{"id":3418953,"uuid":"37555335","full_name":"djgagne/hagelslag","owner":"djgagne","description":"Hagelslag supports segmentation and tracking of weather fields and scalable verification, including performance diagrams and reliability diagrams.","archived":false,"fork":false,"pushed_at":"2024-02-10T00:50:36.000Z","size":95698,"stargazers_count":70,"open_issues_count":6,"forks_count":25,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-04-25T14:07:51.933Z","etag":null,"topics":["geojson","hail","hrrr","machine-learning","mrms","netcdf","performance","performance-diagram","python","reliability","segmentation","storms","tracking","verification","weather","zarr"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/djgagne.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2015-06-16T20:48:43.000Z","updated_at":"2025-04-24T19:52:07.000Z","dependencies_parsed_at":"2024-03-17T06:59:44.583Z","dependency_job_id":null,"html_url":"https://github.com/djgagne/hagelslag","commit_stats":{"total_commits":619,"total_committers":20,"mean_commits":30.95,"dds":"0.41518578352180935","last_synced_commit":"fb443b79834aad9bcb58f99d09ba59d029370225"},"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djgagne%2Fhagelslag","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djgagne%2Fhagelslag/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djgagne%2Fhagelslag/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djgagne%2Fhagelslag/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/djgagne","download_url":"https://codeload.github.com/djgagne/hagelslag/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251001804,"owners_count":21521026,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["geojson","hail","hrrr","machine-learning","mrms","netcdf","performance","performance-diagram","python","reliability","segmentation","storms","tracking","verification","weather","zarr"],"created_at":"2024-08-08T05:01:36.012Z","updated_at":"2025-05-08T05:54:59.594Z","avatar_url":"https://github.com/djgagne.png","language":"Jupyter Notebook","funding_links":[],"categories":["Machine Learning","Climate Change"],"sub_categories":["Natural Hazard and Storms"],"readme":"# Hagelslag\n## Storm tracking, machine learning, and probabilistic evaluation\n[![NSF-1261776](https://img.shields.io/badge/NSF-1261776-blue)](https://www.nsf.gov/awardsearch/showAward?AWD_ID=1261776\u0026HistoricalAwards=false)\n\nHagelslag is an object-based severe storm forecasting system that utilizing image processing and machine learning tools\nto derive calibrated probabilities of severe hazards from convection-allowing numerical weather prediction model output.\nThe package contains modules for storm identification and tracking, spatio-temporal data extraction, and \nmachine learning model training to predict hazard intensity as well as space and time translations.\n\n### Citation\nIf you employ hagelslag in your research, please acknowledge its use with the following citations:\n\n    Gagne, D. J., A. McGovern, S. E. Haupt, R. A. Sobash, J. K. Williams, M. Xue, 2017: Storm-Based Probabilistic Hail\n    Forecasting with Machine Learning Applied to Convection-Allowing Ensembles, Wea. Forecasting, 32, 1819-1840. \n    https://doi.org/10.1175/WAF-D-17-0010.1. \n    \n    Gagne II, D. J., A. McGovern, N. Snook, R. Sobash, J. Labriola, J. K. Williams, S. E. Haupt, and M. Xue, 2016: \n    Hagelslag: Scalable object-based severe weather analysis and forecasting. Proceedings of the Sixth Symposium on \n    Advances in Modeling and Analysis Using Python, New Orleans, LA, Amer. Meteor. Soc., 447.\n\nIf you discover any issues, please post them to the Github issue tracker page. Questions and comments should be sent to\ndjgagne at ou dot edu.\n\n### Requirements\n\nHagelslag is compatible with Python 3.6 or newer. Hagelslag is easiest to install with the help of the [Miniconda \nPython Distribution](https://docs.conda.io/en/latest/miniconda.html), but it should work with other\nPython setups as well. Hagelslag requires the following packages and recommends the following versions:\n\n* numpy \u003e= 1.10\n* scipy \u003e= 0.15\n* matplotlib \u003e= 1.4\n* scikit-learn \u003e= 0.16\n* pandas \u003e= 0.15\n* arrow \u003e= 0.8.0\n* pyproj\n* netCDF4-python\n* xarray\n* jupyter\n* ncepgrib2\n* pygrib\n* cython\n* pip\n* sphinx\n* mock\n\nInstall dependencies with the following commands:\n```\ngit clone https://github.com/djgagne/hagelslag.git\ncd ~/hagelslag\nconda env create -f environment.yml\nconda activate hagelslag\n```\n\n### Installation\nInstall the latest version of hagelslag with the following command from the top-level hagelslag directory (where setup.py\nis):\n`pip install .`\n\n\nHagelslag will install the libraries in site-packages and will also install 3 applications into the `bin` directory\nof your Python installation.\n\n### Use\nA Jupyter notebook is located in the demos directory that showcases the functionality of the package. For larger scale \nuse, 3 scripts are provided in the bin directory. \n\n* `hsdata` performs object tracking and matching as well as data processing.\n* `hsfore` trains and applies machine learning models.\n* `hseval` performs forecast verification.\n\nAll scripts take input from a config file. The config file should be valid Python code and contain a dictionary called\nconfig. Custom machine learning models and parameters should be contained within the config files. Examples of them can\nbe found in the config directory.\n\n### Documentation\nAPI Documentation is available [here](http://hagelslag.readthedocs.io/en/latest/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdjgagne%2Fhagelslag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdjgagne%2Fhagelslag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdjgagne%2Fhagelslag/lists"}