Metadata-Version: 2.5
Name: foundationforecast
Version: 0.1.1
Summary: Foundation time series forecasting models
Author-email: Azul Garza <azul.garza.r@gmail.com>
License-Expression: MIT
License-File: LICENSE
Requires-Python: >=3.10
Requires-Dist: gluonts[torch]
Requires-Dist: huggingface-hub<2.0,>=0.36.2
Requires-Dist: nixtla>=0.7.0
Requires-Dist: pandas>=2.2.0; python_full_version >= '3.13'
Requires-Dist: scipy
Requires-Dist: tabpfn-time-series==1.0.3; python_full_version < '3.13'
Requires-Dist: tfc-t0>=0.2.3; python_full_version >= '3.11' and python_full_version < '3.14'
Requires-Dist: timecopilot-chronos-forecasting>=0.2.2
Requires-Dist: timecopilot-granite-tsfm>=0.2.1; python_full_version >= '3.11' and python_full_version < '3.14'
Requires-Dist: timecopilot-timesfm>=0.3.0
Requires-Dist: timecopilot-tirex2>=0.1.0; python_full_version >= '3.11'
Requires-Dist: timecopilot-tirex>=0.1.1; python_full_version >= '3.11'
Requires-Dist: timecopilot-toto-2>=0.1.1
Requires-Dist: timecopilot-toto>=0.1.7
Requires-Dist: timecopilot-uni2ts>=0.1.3; python_full_version < '3.14'
Requires-Dist: torch
Requires-Dist: transformers<6,>=4.41; python_full_version < '3.13'
Requires-Dist: transformers<6,>=4.48; python_full_version >= '3.13'
Requires-Dist: utilsforecast>=0.2.15
Provides-Extra: plot
Requires-Dist: matplotlib>=3.10.6; extra == 'plot'
Requires-Dist: plotly>=6.3.1; extra == 'plot'
Description-Content-Type: text/markdown

# foundationforecast

Foundation time series forecasting models, extracted from [TimeCopilot](https://github.com/TimeCopilot/timecopilot).

Run state-of-the-art pretrained models (Chronos, Moirai, TimesFM, Toto, TiRex, TimeGPT, and more) through a single unified API.

## Installation

```bash
pip install foundationforecast
```

Requires Python 3.10+. Some models have additional version requirements — see the [Model Hub](model-hub.md).

Optional plotting support:

```bash
pip install "foundationforecast[plot]"
```

## Quick example

```python
import pandas as pd
from foundationforecast import FoundationForecast
from foundationforecast.models import Chronos, Toto

df = pd.read_csv(
    "https://timecopilot.s3.amazonaws.com/public/data/air_passengers.csv",
    parse_dates=["ds"],
)

ff = FoundationForecast(models=[Chronos(), Toto(context_length=256)])
fcst = ff.forecast(df, h=12, freq="MS")
cv = ff.cross_validation(df, h=12, freq="MS")
```

## Supported models

Chronos, FlowState, Moirai, PatchTST-FM, Sundial, T0, TabPFN, TiRex, TimeGPT, TimesFM, Toto

## Documentation

Build and serve docs locally:

```bash
uv sync --group docs
uv run --group docs mkdocs serve
```

See [Getting Started](getting-started/quickstart.md) and [Examples](examples/index.md).

## Development

```bash
uv sync --group dev --group docs
pre-commit install --install-hooks
uv run pytest
```

## License

MIT
