cat << 'EOF' > process_data.py
import boto3
import pandas as pd
import os
import sys
import logging
from datetime import datetime

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def process_file(input_bucket, input_key, output_bucket, output_key):
    """
    Process data file from S3 and upload results back to S3.
    Includes error handling and logging.
    """
    s3 = boto3.client('s3')
    
    try:
        logger.info(f"Starting processing of s3://{input_bucket}/{input_key}")
        
        # Download input file
        local_input = f'/tmp/input_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv'
        s3.download_file(input_bucket, input_key, local_input)
        
        # Process the data
        df = pd.read_csv(local_input)
        logger.info(f"Loaded data with shape: {df.shape}")
        
        # Get numeric columns only
        numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
        
        # Calculate statistics for numeric columns only
        result = pd.DataFrame({
            'column': numeric_columns,
            'mean': df[numeric_columns].mean(),
            'median': df[numeric_columns].median(),
            'std': df[numeric_columns].std()
        })
        
        # Save and upload results
        local_output = f'/tmp/output_{datetime.now().strftime("%Y%m%d_%H%M%S")}.csv'
        result.to_csv(local_output, index=False)
        s3.upload_file(local_output, output_bucket, output_key)
        
        logger.info(f"Successfully uploaded results to s3://{output_bucket}/{output_key}")
        
        # Cleanup temporary files
        os.remove(local_input)
        os.remove(local_output)
        
    except Exception as e:
        logger.error(f"Error processing file: {str(e)}")
        raise

def main():
    if len(sys.argv) != 5:
        logger.error("Required arguments: input_bucket input_key output_bucket output_key")
        sys.exit(1)
        
    process_file(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])

if __name__ == "__main__":
    main()
EOF

cat << 'EOF' > Dockerfile
FROM python:3.9-slim

# Install dependencies
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY process_data.py .

# Set permissions
RUN chmod +x process_data.py

# Set entry point
ENTRYPOINT ["python", "process_data.py"]
EOF

cat << 'EOF' > requirements.txt
boto3==1.26.137
pandas==2.0.0
numpy==1.24.3
EOF

# Export environment variables
export AWS_ACCOUNT_ID=211125437318
export AWS_REGION=us-east-1

# ECR repository URL
export ECR_REPO="${AWS_ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com"

# Get ECR login token
aws ecr get-login-password --region ${AWS_REGION} \
   | docker login --username AWS --password-stdin ${ECR_REPO}

# Build image
docker build -t batch-demo-app .

# Tag image
docker tag batch-demo-app:latest ${ECR_REPO}/batch-demo-app:latest

# Push to ECR
docker push ${ECR_REPO}/batch-demo-app:latest

# Generate a random suffix (using timestamp)
TIMESTAMP=$(date +%Y%m%d%H%M%S)
BUCKET_NAME="batch-demo-${TIMESTAMP}"

# Create the bucket
aws s3api create-bucket \
    --bucket ${BUCKET_NAME} \
    --region us-east-1

echo "Created bucket: ${BUCKET_NAME}"

# Create input and output folders
# (by creating empty objects with trailing slashes)
aws s3api put-object --bucket ${BUCKET_NAME} --key input/
aws s3api put-object --bucket ${BUCKET_NAME} --key output/

# First create the data.csv file
cat << 'EOF' > data.csv
month,revenue,costs,units_sold,customer_count,avg_order_value
Jan_2024,120500.50,85000.75,1250,850,96.40
Feb_2024,135750.25,92500.50,1380,920,98.35
Mar_2024,142800.75,95750.25,1450,975,98.50
Apr_2024,128900.25,88250.50,1320,890,97.65
May_2024,155200.50,98500.75,1580,1050,98.25
Jun_2024,168500.75,102750.50,1720,1150,98.00
Jul_2024,172500.50,105250.25,1750,1180,98.55
Aug_2024,180250.25,108500.50,1820,1250,99.05
Sep_2024,165750.75,101250.25,1680,1120,98.65
Oct_2024,158900.50,99750.75,1620,1080,98.10
EOF

# Upload data.csv to the input folder
aws s3 cp data.csv s3://${BUCKET_NAME}/input/data.csv

# Verify the setup
echo "Listing contents of bucket ${BUCKET_NAME}:"
aws s3 ls s3://${BUCKET_NAME}/ --recursive

# Save bucket name for later use
echo ${BUCKET_NAME} > bucket_name.txt
echo "Bucket name saved to bucket_name.txt"