Metadata-Version: 2.4
Name: ionis-validate
Version: 0.1.0
Summary: IONIS V20 — HF Propagation Model Validation Suite
Project-URL: Homepage, https://ionis-ai.com/
Project-URL: Repository, https://github.com/IONIS-AI/ionis-validate
Project-URL: Issues, https://github.com/IONIS-AI/ionis-validate/issues
Project-URL: Documentation, https://ionis-ai.com/testing/
Author: Greg Beam, KI7MT
License: GPL-3.0-or-later
License-File: LICENSE
Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Physics
Requires-Python: >=3.9
Requires-Dist: numpy>=1.24
Requires-Dist: torch>=2.0
Description-Content-Type: text/markdown

# ionis-validate

Validation suite for the IONIS V20 HF propagation model. Run 62 physics
tests, predict SNR for any HF path, or validate the model against your
own QSO log — all from the command line, on any platform.

IONIS (Ionospheric Neural Inference System) predicts HF radio signal
strength from WSPR, RBN, and contest data. The V20 model was trained on
31 million propagation observations spanning 2008-2025.

## Install

```
pip install ionis-validate
```

Requires Python 3.9+ and PyTorch 2.0+. Works on Windows, macOS, and Linux.

## Quick Start

```bash
# Show model and system info
ionis-validate info

# Run the full 62-test validation suite
ionis-validate test

# Predict SNR for a single path
ionis-validate predict \
    --tx-grid FN20 --rx-grid IO91 --band 20m \
    --sfi 150 --kp 2 --hour 14 --month 6
```

## Validate Your Log

Export your QSO log from eQSL, LoTW, or QRZ as an ADIF (.adi) file,
then check how often the model agrees the band was open for each contact.

```bash
ionis-validate adif my_log.adi --my-grid DN26
```

All processing happens locally. Callsigns are stripped at parse time and
never leave your machine. The tool extracts only grid pairs, band, mode,
and time — no personal information.

## Batch Predictions

Define a set of paths in a JSON file and run them all at once:

```bash
ionis-validate custom my_paths.json
```

See the [documentation](https://ionis-ai.com/testing/) for the JSON format.

## Beta Test Reports

Generate a structured report for filing as a GitHub Issue:

```bash
ionis-validate report
```

## Privacy

IONIS processes only grid-pair geometry, band, time, and solar indices.
No callsigns, names, or personal data are used by the model or stored
by this tool. ADIF log validation strips all PII at parse time.

Full privacy policy: <https://ionis-ai.com/ethos/>

## License

GPL-3.0-or-later. See [LICENSE](LICENSE).

## Links

- Documentation: <https://ionis-ai.com/testing/>
- Source: <https://github.com/IONIS-AI/ionis-validate>
- Issues: <https://github.com/IONIS-AI/ionis-validate/issues>
- IONIS Project: <https://ionis-ai.com/>
