Metadata-Version: 2.4
Name: atr-adaptive-laguerre
Version: 0.1.1
Summary: ATR-adaptive Laguerre RSI for non-anticipative feature engineering in seq-2-seq forecasting
Project-URL: Repository, https://github.com/eonlabs/atr-adaptive-laguerre
Project-URL: Documentation, https://github.com/eonlabs/atr-adaptive-laguerre/blob/main/docs/README.md
Author: Eon Labs Ltd.
License: MIT
License-File: LICENSE
Keywords: atr,features,laguerre,rsi,seq2seq,trading,volatility
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: gapless-crypto-data>=2.11.0
Requires-Dist: httpx>=0.27
Requires-Dist: numba>=0.59
Requires-Dist: numpy>=1.26
Requires-Dist: orjson>=3.10
Requires-Dist: pandas>=2.0
Requires-Dist: platformdirs>=4.0
Requires-Dist: pyarrow>=15.0
Requires-Dist: pydantic>=2.0
Requires-Dist: scipy>=1.10
Provides-Extra: dev
Requires-Dist: mypy>=1.8; extra == 'dev'
Requires-Dist: pytest-cov>=4.1; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.3; extra == 'dev'
Description-Content-Type: text/markdown

# ATR-Adaptive Laguerre RSI

Non-anticipative volatility-adaptive momentum indicator for sequence-to-sequence forecasting.

## Overview

This library implements the ATR-Adaptive Laguerre RSI indicator, designed for robust feature engineering in financial time series forecasting. The indicator combines:

- **True Range (TR)** - Volatility measurement including gaps
- **ATR with Min/Max Tracking** - Rolling volatility envelope
- **Adaptive Coefficient** - Volatility-normalized adaptation
- **Laguerre 4-Stage Cascade** - Low-lag smoothing filter
- **Laguerre RSI** - Momentum from filter stage differences

## Key Features

- ✅ **Non-anticipative**: Guaranteed no lookahead bias
- ✅ **O(1) Incremental**: Efficient online computation (talipp pattern)
- ✅ **Multi-interval**: Supports 1s-1d timeframes
- ✅ **Validated**: Information coefficient > 0.03 on k-step-ahead returns

## Installation

```bash
uv add atr-adaptive-laguerre
```

## Quick Start

```python
from atr_adaptive_laguerre import ATRAdaptiveLaguerreRSI, ATRAdaptiveLaguerreRSIConfig
from atr_adaptive_laguerre.data import BinanceAdapter

# Fetch data
adapter = BinanceAdapter()
df = adapter.fetch("BTCUSDT", "1h", "2024-01-01", "2024-06-30")

# Create feature
config = ATRAdaptiveLaguerreRSIConfig(atr_period=32, smoothing_period=5)
feature = ATRAdaptiveLaguerreRSI(config)

# Transform (non-anticipative)
rsi_series = feature.fit_transform(df)
```

## Documentation

- [API Reference](https://github.com/eonlabs/atr-adaptive-laguerre/blob/main/docs/API_REFERENCE.md) - Complete API documentation
- [Examples](https://github.com/eonlabs/atr-adaptive-laguerre/tree/main/examples) - Runnable usage examples
- [Changelog](https://github.com/eonlabs/atr-adaptive-laguerre/blob/main/CHANGELOG.md) - Release notes and version history

## License

MIT License - Eon Labs Ltd.
