{ "info": { "author": "J. Marcus Hughes", "author_email": "hughes.jmb@gmail.com", "bugtrack_url": null, "classifiers": [], "description": "# suvi-trainer\n[](https://www.codefactor.io/repository/github/jmbhughes/suvi-trainer/overview/master)\n[](https://badge.fury.io/py/suvitrainer)\n\nThe [Solar Ultraviolet Imager](https://www.goes-r.gov/spacesegment/suvi.html) (SUVI) aboard the National Oceanic \nand Atmospheric Administration's Geostationary Operational Environmental R-Series satellites is used \nin machine learning applications to create thematic maps, images showing where different features are on the Sun. This\ntool allows domain experts to load images, manipulate them, and create labeled maps, which are used in [training solar \nimage classifiers](https://github.com/jmbhughes/smachy). \n\n## Getting Started\n\nThese instructions will get you a copy of the project up and running on your local machine \nfor development and testing purposes. At the moment, it is advised to run this code in a fresh virtual environment with\nPython 3.5. Installation should only require running the `setup.py` script. \n\n### Installing\n```\npip3 install suvitrainer\n```\nYou will need to download and edit the [configuration file](config_example.json) to include your name and the upload password. Please \n[contact me](mailto:hughes.jmb@gmail.com) for the password and further information. \n\n*Please note that the [extra scripts](scripts/) may require packages that are not automatically installed. They are auxiliary\nand not fundamental for the annotation tool to run. Everything needed for [run_suvitrainer.py](run_suvitrainer.py) and the main annotation tool should be automatically\ninstalled. If you want to use an auxiliary script download the repo.*\n\n### Running\nThe [run_suvitrainer.py](run_suvitrainer.py) script should provide all needed functionality for the average user. \nIt takes a couple optional arguments: verbosity and dates.\nThe verbosity, `-v` or `--verbose` argument will print helpful status information while running. \nThe `date` option allows three methods of specifying which date to run on: \nsimply a date string (2018-08-05T17:52), a path to a local file that contains a list of date \nstrings where each one is on a different line, or a url to an online list of dates. \nThe default is to pull using the url for [dates.txt](dates.txt) stored in this repository. This is preferred to create\na large curated data-set with some repeats for validation. \n\nThe list of options for input images:\n- `halpha` (from GONG)\n- any of the AIA EUV channels listed as `aia-[WAVELENGTH]` with the wavelength in angstroms, e.g. `aia-131`\n- any of the SUVI EUV L1B channels listed as products, e.g. `suvi-l1b-fe131` \n(see the [FTP site](https://data.ngdc.noaa.gov/platforms/solar-space-observing-satellites/goes/goes16/l1b/) for a list)\n- any locally saved SUVI l2 composite images (only available internally to NOAA employees at this time), e.g. `suvi-l2-ci094`\n\n\n**For more detailed usage, see the [user guide](user-guide.pdf).**\n\n## Data\nThe output of training is saved as a FITS file which is later converted into a labeled png. Labeled data will be available shortly.\nA [couple examples](examples/) are available here. \nThis labeled data is then used in [machine learning classification of solar images](https://github.com/jmbhughes/smachy). \n\n
\n
\n