Scripts Stages Added

scripts/README.md

@@ -0,0 +1,59 @@
+# Utility Scripts
+
+Simple CLI scripts for common operations.
+
+## Available Scripts
+
+### 1. Train Pipeline
+Run the complete training pipeline (all 7 stages):
+```bash
+python scripts/train.py
+```
+
+### 2. Evaluate Model
+Evaluate the trained model on test data:
+```bash
+# Use default model path
+python scripts/evaluate.py
+
+# Or specify custom model path
+python scripts/evaluate.py --model-path artifacts/model_trainer/model
+```
+
+### 3. Start API Server
+Start the FastAPI server:
+```bash
+# Default (localhost:8000)
+python scripts/serve.py
+
+# Custom host/port
+python scripts/serve.py --host 0.0.0.0 --port 8080
+
+# Development mode with auto-reload
+python scripts/serve.py --reload
+```
+
+### 4. Initialize Airflow
+Set up Airflow database and create admin user:
+```bash
+python scripts/init_db.py
+```
+
+Then start Airflow services:
+```bash
+airflow scheduler  # Terminal 1
+airflow webserver  # Terminal 2
+```
+
+## Quick Examples
+
+```bash
+# Full workflow
+python scripts/train.py          # Train model
+python scripts/evaluate.py       # Evaluate model
+python scripts/serve.py --reload # Start API server
+
+# Airflow setup
+python scripts/init_db.py        # Initialize
+airflow webserver                # Start UI
+```

scripts/evaluate.py

@@ -0,0 +1,49 @@
+"""CLI script to evaluate the trained model."""
+import sys
+from pathlib import Path
+import argparse
+
+# Add project root to path
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+from mlpipeline.components.model_evaluation import ModelEvaluation
+from mlpipeline.config.configuration import ConfigurationManager
+from mlpipeline.logging.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+def main():
+    """Evaluate the trained model."""
+    parser = argparse.ArgumentParser(description="Evaluate AutoML model")
+    parser.add_argument(
+        "--model-path",
+        type=str,
+        default=None,
+        help="Path to model directory (default: from config)"
+    )
+    args = parser.parse_args()
+
+    try:
+        logger.info("Starting model evaluation...")
+        config_manager = ConfigurationManager()
+        eval_config = config_manager.get_model_evaluation_config()
+        
+        # Override model path if provided
+        if args.model_path:
+            eval_config.model_path = Path(args.model_path)
+        
+        evaluator = ModelEvaluation(eval_config)
+        metrics = evaluator.evaluate()
+        
+        logger.info("✅ Evaluation completed!")
+        logger.info(f"Metrics: {metrics}")
+        return 0
+    except Exception as e:
+        logger.error(f"❌ Evaluation failed: {e}")
+        return 1
+
+
+if __name__ == "__main__":
+    exit(main())

scripts/init_db.py

@@ -0,0 +1,75 @@
+"""CLI script to initialize Airflow database."""
+import sys
+from pathlib import Path
+import subprocess
+import os
+
+# Add project root to path
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+from mlpipeline.logging.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+def main():
+    """Initialize Airflow database and create admin user."""
+    try:
+        airflow_home = project_root / "airflow"
+        
+        # Set AIRFLOW_HOME environment variable
+        os.environ["AIRFLOW_HOME"] = str(airflow_home)
+        logger.info(f"AIRFLOW_HOME set to: {airflow_home}")
+        
+        # Initialize database
+        logger.info("Initializing Airflow database...")
+        result = subprocess.run(
+            ["airflow", "db", "init"],
+            capture_output=True,
+            text=True
+        )
+        
+        if result.returncode != 0:
+            logger.error(f"Failed to initialize database: {result.stderr}")
+            return 1
+        
+        logger.info("✅ Database initialized successfully!")
+        
+        # Create admin user
+        logger.info("Creating admin user...")
+        result = subprocess.run(
+            [
+                "airflow", "users", "create",
+                "--username", "admin",
+                "--firstname", "Admin",
+                "--lastname", "User",
+                "--role", "Admin",
+                "--email", "admin@example.com",
+                "--password", "admin"
+            ],
+            capture_output=True,
+            text=True
+        )
+        
+        if result.returncode != 0 and "already exists" not in result.stderr:
+            logger.warning(f"User creation note: {result.stderr}")
+        else:
+            logger.info("✅ Admin user created (username: admin, password: admin)")
+        
+        logger.info("\n🚀 Next steps:")
+        logger.info("  1. Start scheduler: airflow scheduler")
+        logger.info("  2. Start webserver: airflow webserver")
+        logger.info("  3. Access UI: http://localhost:8080")
+        
+        return 0
+    except FileNotFoundError:
+        logger.error("❌ Airflow not found. Install with: pip install apache-airflow")
+        return 1
+    except Exception as e:
+        logger.error(f"❌ Initialization failed: {e}")
+        return 1
+
+
+if __name__ == "__main__":
+    exit(main())

scripts/serve.py

@@ -0,0 +1,55 @@
+"""CLI script to start the FastAPI server."""
+import sys
+from pathlib import Path
+import argparse
+import uvicorn
+
+# Add project root to path
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+from mlpipeline.logging.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+def main():
+    """Start the FastAPI server."""
+    parser = argparse.ArgumentParser(description="Start AutoML API server")
+    parser.add_argument(
+        "--host",
+        type=str,
+        default="0.0.0.0",
+        help="Host to bind (default: 0.0.0.0)"
+    )
+    parser.add_argument(
+        "--port",
+        type=int,
+        default=8000,
+        help="Port to bind (default: 8000)"
+    )
+    parser.add_argument(
+        "--reload",
+        action="store_true",
+        help="Enable auto-reload for development"
+    )
+    args = parser.parse_args()
+
+    try:
+        logger.info(f"🚀 Starting FastAPI server at {args.host}:{args.port}")
+        logger.info(f"📚 API docs: http://{args.host if args.host != '0.0.0.0' else 'localhost'}:{args.port}/docs")
+        
+        uvicorn.run(
+            "app.main:app",
+            host=args.host,
+            port=args.port,
+            reload=args.reload
+        )
+        return 0
+    except Exception as e:
+        logger.error(f"❌ Server failed to start: {e}")
+        return 1
+
+
+if __name__ == "__main__":
+    exit(main())

scripts/train.py

@@ -0,0 +1,29 @@
+"""CLI script to run the training pipeline."""
+import sys
+from pathlib import Path
+
+# Add project root to path
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+from mlpipeline.pipeline.training_pipeline import TrainingPipeline
+from mlpipeline.logging.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+def main():
+    """Run the complete training pipeline."""
+    try:
+        logger.info("Starting AutoML Training Pipeline...")
+        pipeline = TrainingPipeline()
+        pipeline.run_pipeline()
+        logger.info("✅ Training pipeline completed successfully!")
+        return 0
+    except Exception as e:
+        logger.error(f"❌ Training pipeline failed: {e}")
+        return 1
+
+
+if __name__ == "__main__":
+    exit(main())