chrono-brush

A lightweight, modular toolkit for common time-series preprocessing tasks.

---

✨ Features

Task	Transformer	Status
Outlier detection/removal	OutlierRemover	✅
Resampling / aggregation	Resampler	✅
Trend removal (Prophet)	ProphetTrendRemover	✅
Missing-value imputation	MissingValueImputer	✅
Chaining multiple steps	Pipeline (sklearn-style)	✅
Forthcoming	STL detrending, scaling, CLI	⏳

All transformers follow a fit / transform / fit_transform API so they can be chained or used standalone.

---

🔧 Installation

Requires Python ≥ 3.10

# From source (development mode)
git clone https://github.com/davidwardan/chrono-brush.git
cd chrono-brush
pip install -e .

# Or, when released on PyPI
pip install chrono-brush

---

🚀 Quick start

from chrono_brush import (
    OutlierRemover,
    MissingValueImputer,
    Pipeline,
)

pipe = Pipeline(
    [
        ("impute", MissingValueImputer(strategy="ffill")),
        ("outliers", OutlierRemover(method="iqr")),
    ]
)

cleaned = pipe.fit_transform(series)

See the examples/ directory for richer, end-to-end walkthroughs.