Metadata-Version: 2.4
Name: mlwatch
Version: 0.1.0
Summary: Lightweight ML monitoring — drift, performance, data quality, and alerts in one library
Requires-Python: >=3.8
Requires-Dist: httpx>=0.24.0
Requires-Dist: numpy>=1.21.0
Requires-Dist: pandas>=1.3.0
Requires-Dist: scikit-learn>=1.0.0
Requires-Dist: scipy>=1.7.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Requires-Dist: ruff>=0.1.0; extra == 'dev'
Description-Content-Type: text/markdown

# mlwatch

Lightweight ML monitoring — drift detection, performance tracking, data quality, and alerts in one library.

## Install

```bash
pip install mlwatch
```

## Quickstart

```python
import mlwatch
import numpy as np
import pandas as pd

monitor = mlwatch.Monitor(name="my_model")

result = monitor.log(
    reference=train_data,
    current=new_data,
    y_true=y_true,
    y_pred=y_pred,
)

print(result.to_dict())
```

## Features

- Drift Detection (KS test, PSI, Mean Shift)
- Performance Monitoring (accuracy, F1, AUC, MAE, RMSE)
- Data Quality (nulls, outliers, schema)
- Alerts (webhook, custom callbacks)
- History storage (SQLite)

## Why mlwatch?

| | mlwatch | Evidently | WhyLogs |
|---|---|---|---|
| Simple API | ✅ | ❌ | ❌ |
| Lightweight | ✅ | ❌ | ❌ |
| JSON output | ✅ | ❌ | ❌ |
| No setup | ✅ | ❌ | ❌ |
