#!/bin/bash
# Train final production model with 10k emails and 0.55 thresholds

set -e

echo "=========================================="
echo "TRAINING FINAL MODEL"
echo "=========================================="
echo ""
echo "Config: 0.55 thresholds across all categories"
echo "Training set: 10,000 Enron emails"
echo "Calibration: 300 samples (3%)"
echo "Validation: 100 samples (1%)"
echo ""

# Backup existing model if it exists
if [ -f src/models/calibrated/classifier.pkl ]; then
    BACKUP_FILE="src/models/calibrated/classifier.pkl.backup-$(date +%Y%m%d-%H%M%S)"
    cp src/models/calibrated/classifier.pkl "$BACKUP_FILE"
    echo "Backed up existing model to: $BACKUP_FILE"
fi

# Clean old results
rm -rf results_final/ final_training.log

# Activate venv
if [ -z "$VIRTUAL_ENV" ]; then
    source venv/bin/activate
fi

# Train model
python -m src.cli run \
    --source enron \
    --limit 10000 \
    --output results_final/ \
    2>&1 | tee final_training.log

# Create timestamped backup of trained model
if [ -f src/models/calibrated/classifier.pkl ]; then
    TRAINED_BACKUP="src/models/calibrated/classifier.pkl.backup-trained-$(date +%Y%m%d-%H%M%S)"
    cp src/models/calibrated/classifier.pkl "$TRAINED_BACKUP"
    echo "Created backup of trained model: $TRAINED_BACKUP"
fi

echo ""
echo "=========================================="
echo "Training complete!"
echo "Model saved to: src/models/calibrated/classifier.pkl"
echo "Backup created with timestamp"
echo "Log: final_training.log"
echo "=========================================="