Metadata-Version: 2.5
Name: alphatonic
Version: 0.2.0
Summary: Evaluate predictive signals with cross-sectional and time-series information coefficients, dependence-aware uncertainty, and offline tearsheets.
Project-URL: Homepage, https://github.com/mblum/alphatonic
Project-URL: Documentation, https://mblum.github.io/alphatonic/
Project-URL: Source, https://github.com/mblum/alphatonic
Project-URL: Issues, https://github.com/mblum/alphatonic/issues
Project-URL: Changelog, https://github.com/mblum/alphatonic/blob/HEAD/CHANGELOG.md
Author: Manuel Blum
License-Expression: MIT
License-File: LICENSE
Keywords: alpha,backtesting,factor,finance,information coefficient,quant,signal
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Office/Business :: Financial :: Investment
Classifier: Topic :: Scientific/Engineering
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: jinja2>=3.1
Requires-Dist: numpy>=1.26
Requires-Dist: pandas>=2.2.2
Requires-Dist: pydantic>=2.6
Provides-Extra: report
Description-Content-Type: text/markdown

# alphatonic

[![CI](https://github.com/mblum/alphatonic/actions/workflows/ci.yml/badge.svg)](https://github.com/mblum/alphatonic/actions/workflows/ci.yml)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/mblum/alphatonic/blob/master/LICENSE)

alphatonic is a Python library for testing trading signals. Give alphatonic your scores 
and prices, and it measures how well the scores predict future returns. 

With alphatonic you can:

- Measure cross-sectional and time-series information coefficients, including single-asset signals.
- Estimate uncertainty with Newey–West standard errors and a block bootstrap.
- Assess how costly a signal would be to trade, using rank-persistence and bucket-turnover
  statistics.
- Render an offline HTML tearsheet, and browse your trials with `alphatonic serve`.

Start with the
[tutorial](https://mblum.github.io/alphatonic/tutorials/first-evaluation/),
or browse the [docs](https://mblum.github.io/alphatonic/).

alphatonic evaluates predictive association; it does not build factors or simulate portfolios,
costs or P&L. See [scope and alternatives](https://mblum.github.io/alphatonic/explanation/scope/).

## Try it

Python 3.11 or newer. Install from [PyPI](https://pypi.org/project/alphatonic/):

```sh
python -m pip install alphatonic
```

```python
from alphatonic import evaluate
from alphatonic.demo import synthetic_market

factor, prices = synthetic_market(n_assets=30, n_bars=500, ic=0.04, seed=7)  # or your own tables
result = evaluate(factor, prices, horizons=[1, 5])

result.summary.query("method == 'spearman'")[["horizon", "mean", "ci95_lower", "ci95_upper"]]
result.tearsheet("tearsheet.html")
```

Open `tearsheet.html` in your browser.

## Changelog

See the [changelog](https://github.com/mblum/alphatonic/blob/master/CHANGELOG.md) for what
changed in each release.

## Development

```sh
uv sync --all-extras --locked
uv run pytest
uv run ruff check . && uv run ruff format --check .
uv run pyright
```

See [Contributing](https://github.com/mblum/alphatonic/blob/master/CONTRIBUTING.md)
for setup, tests and the release process.

## License

[MIT License](https://github.com/mblum/alphatonic/blob/master/LICENSE). Copyright 2026 Manuel Blum.
