#!/bin/bash

# Run data processing pipeline

set -e

echo "🔄 Starting data processing pipeline..."

# Activate virtual environment if exists
if [ -d "venv" ]; then
    source venv/bin/activate
fi

# Install dependencies if needed
if [ -f "requirements.txt" ]; then
    pip install -q -r requirements.txt
fi

# Run data pipeline
python -m src.pipelines.data_pipeline \
    --input data/raw/metadata.csv \
    --output data/processed

echo "✅ Data pipeline complete!"
echo "Processed data saved to data/processed/"