Metadata-Version: 2.4
Name: watchtower-sdk
Version: 0.1.0
Summary: Python SDK for Watchtower AI - Data Drift & Quality Monitoring
Author: Watchtower AI
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.25.0
Requires-Dist: pandas>=1.0.0
Requires-Dist: numpy>=1.19.0
Dynamic: author
Dynamic: description
Dynamic: description-content-type
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# Watchtower AI SDK

Official Python SDK for [Watchtower AI](https://github.com/aniq63/Watchtower-AI) - A comprehensive data drift and quality monitoring platform.

## Installation

```bash
pip install watchtower-sdk
```

## Usage

### 1. Configuration
Set your environment variables (recommended):

```bash
export WATCHTOWER_API_KEY="your_project_api_key"
export WATCHTOWER_API_URL="https://your-watchtower-instance.onrender.com"
```

### 2. Monitoring Data

```python
import pandas as pd
from watchtower.monitor import WatchtowerInputMonitor

# Initialize monitor (reads env vars automatically)
monitor = WatchtowerInputMonitor(project_name="Credit Scoring Model")

# Load your data
df = pd.read_csv("production_data.csv")

# Log data to Watchtower
response = monitor.log(df)
print(response)
```

## Features
- **Data Drift Detection**: Automatically detects distribution shifts in your input features.
- **Data Quality Checks**: Validates schema, null values, and duplicates.
- **Low Latency**: Async-compatible logging.
