Metadata-Version: 2.4
Name: WPforcast-gnss
Version: 0.1.0
Summary: Wind farm power forecasting utilities with optional GNSS guidance
Author: Gong
License-Expression: MIT
Project-URL: Homepage, https://github.com/longjingpy/WindPowerForcast-open
Project-URL: Source, https://github.com/longjingpy/WindPowerForcast-open
Project-URL: Issues, https://github.com/longjingpy/WindPowerForcast-open/issues
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=2.0
Requires-Dist: pandas>=2.0
Requires-Dist: pyarrow>=12.0
Requires-Dist: requests>=2.31
Requires-Dist: torch>=2.0
Requires-Dist: xarray>=2023.1
Dynamic: license-file

# WPforcast-gnss

`WPforcast-gnss` provides reusable Python components for four-hour wind-farm
power forecasting with SCADA inputs and optional GNSS-derived guidance.

## Install

```bash
pip install WPforcast-gnss
```

## Core API

```python
import torch
from wpforcast_gnss import perturb_graph_direction

flow_uv = torch.tensor([[[1.0, 0.0]]])
rotated_uv = perturb_graph_direction(flow_uv, "rotated_90")
```

The package includes GNSS prior utilities, graph-direction interventions,
power forecasting baselines, model adapters, and data-window helpers. It
does not include private SCADA/GNSS/ERA5 data, site coordinates, checkpoints,
or row-level experiment outputs.

## Citation

See `CITATION.cff` and cite the associated research repository when using this
software: https://github.com/longjingpy/WindPowerForcast-open

## License

MIT. The package source code is public; data and trained model artifacts are
not distributed.
