verify_deployment.py

# Test and Verification Script for Hugging Face Deployment

import os
import sys
import json

def verify_deployment_structure():
    """Verify that all required files exist for deployment"""
    
    print("🔍 Verifying Hugging Face Spaces deployment structure...")
    
    required_files = [
        "app.py",
        "requirements.txt", 
        "README.md",
        "DEPLOYMENT_GUIDE.md"
    ]
    
    model_files = [
        "models/production_model.pkl",
        "models/smoteenn_preprocessor.pkl",
        "models/model_info.json"
    ]
    
    all_files = required_files + model_files
    
    # Check main files
    print("\n📋 Checking required files:")
    missing_files = []
    
    for file_path in all_files:
        if os.path.exists(file_path):
            size = os.path.getsize(file_path)
            print(f"   ✅ {file_path}: {size:,} bytes")
        else:
            print(f"   ❌ {file_path}: Missing")
            missing_files.append(file_path)
    
    # Check directory structure
    print("\n📁 Checking directory structure:")
    if os.path.exists("models"):
        print("   ✅ models/ directory exists")
    else:
        print("   ❌ models/ directory missing")
        missing_files.append("models/")
    
    # Validate content
    print("\n🔍 Validating file content:")
    
    # Check app.py
    if os.path.exists("app.py"):
        with open("app.py", "r") as f:
            content = f.read()
            if "HospitalReadmissionPredictor" in content:
                print("   ✅ app.py contains main predictor class")
            else:
                print("   ❌ app.py missing predictor class")
            
            if "gradio" in content:
                print("   ✅ app.py imports Gradio")
            else:
                print("   ❌ app.py missing Gradio import")
    
    # Check requirements.txt
    if os.path.exists("requirements.txt"):
        with open("requirements.txt", "r") as f:
            content = f.read()
            required_packages = ["scikit-learn", "joblib", "pandas", "numpy", "gradio"]
            for package in required_packages:
                if package in content:
                    print(f"   ✅ requirements.txt includes {package}")
                else:
                    print(f"   ❌ requirements.txt missing {package}")
    
    # Check model info
    if os.path.exists("models/model_info.json"):
        try:
            with open("models/model_info.json", "r") as f:
                model_info = json.load(f)
                print(f"   ✅ Model accuracy: {model_info.get('accuracy', 'N/A')}")
                print(f"   ✅ Model type: {model_info.get('model_type', 'N/A')}")
        except Exception as e:
            print(f"   ❌ Error reading model_info.json: {e}")
    
    # Final result
    print(f"\n🎯 Deployment Status:")
    if not missing_files:
        print("   ✅ All files present - Ready for deployment!")
        return True
    else:
        print(f"   ❌ Missing {len(missing_files)} files:")
        for file in missing_files:
            print(f"      - {file}")
        return False

def test_local_import():
    """Test if the app can be imported locally"""
    
    print("\n🧪 Testing local imports...")
    
    try:
        # Test basic imports
        import pandas as pd
        print("   ✅ pandas imported successfully")
    except ImportError as e:
        print(f"   ❌ pandas import failed: {e}")
    
    try:
        import numpy as np
        print("   ✅ numpy imported successfully")
    except ImportError as e:
        print(f"   ❌ numpy import failed: {e}")
    
    try:
        import gradio as gr
        print("   ✅ gradio imported successfully")
    except ImportError as e:
        print(f"   ❌ gradio import failed: {e}")
    
    try:
        import joblib
        print("   ✅ joblib imported successfully")
    except ImportError as e:
        print(f"   ❌ joblib import failed: {e}")
    
    try:
        import sklearn
        print(f"   ✅ scikit-learn imported successfully (version: {sklearn.__version__})")
    except ImportError as e:
        print(f"   ❌ scikit-learn import failed: {e}")

def generate_test_data():
    """Generate test data for validation"""
    
    print("\n📊 Generating test data...")
    
    test_cases = [
        {
            "name": "High Risk Patient",
            "data": {
                "age": 75,
                "time_in_hospital": 8,
                "n_lab_procedures": 55,
                "n_procedures": 4,
                "n_medications": 18,
                "n_outpatient": 3,
                "n_inpatient": 2,
                "n_emergency": 2,
                "medical_specialty": "Cardiology",
                "primary_diagnosis": "Circulatory",
                "admission_type": "Emergency",
                "discharge_disposition": "Home Health Service",
                "glucose_test": ">200",
                "a1c_test": ">8",
                "diabetes_med": "Yes",
                "change_diabetes_med": "Up",
                "insulin": "Steady",
                "hemoglobin": 9.5,
                "sodium": 130
            },
            "expected_risk": "High"
        },
        {
            "name": "Low Risk Patient", 
            "data": {
                "age": 45,
                "time_in_hospital": 2,
                "n_lab_procedures": 15,
                "n_procedures": 1,
                "n_medications": 5,
                "n_outpatient": 1,
                "n_inpatient": 0,
                "n_emergency": 0,
                "medical_specialty": "Family/GeneralPractice",
                "primary_diagnosis": "Other",
                "admission_type": "Elective",
                "discharge_disposition": "Home",
                "glucose_test": "Norm",
                "a1c_test": "Norm",
                "diabetes_med": "No",
                "change_diabetes_med": "No",
                "insulin": "No",
                "hemoglobin": 13.5,
                "sodium": 142
            },
            "expected_risk": "Low"
        }
    ]
    
    for i, case in enumerate(test_cases, 1):
        print(f"\n   Test Case {i}: {case['name']}")
        print(f"   Expected Risk: {case['expected_risk']}")
        print(f"   Key features:")
        print(f"      Age: {case['data']['age']} years")
        print(f"      Length of Stay: {case['data']['time_in_hospital']} days")
        print(f"      Medications: {case['data']['n_medications']}")
        print(f"      Emergency Visits: {case['data']['n_emergency']}")
        print(f"      Hemoglobin: {case['data']['hemoglobin']} g/dL")
    
    return test_cases

def create_deployment_summary():
    """Create a deployment summary"""
    
    print("\n📋 Creating deployment summary...")
    
    summary = {
        "deployment_type": "Hugging Face Spaces",
        "model_type": "Hospital Readmission Risk Predictor",
        "framework": "Gradio",
        "files_checked": True,
        "ready_for_deployment": verify_deployment_structure(),
        "timestamp": "2025-09-10",
        "instructions": "Follow DEPLOYMENT_GUIDE.md for step-by-step deployment"
    }
    
    with open("deployment_summary.json", "w") as f:
        json.dump(summary, f, indent=2)
    
    print(f"   ✅ Deployment summary saved to deployment_summary.json")
    
    return summary

if __name__ == "__main__":
    print("🚀 Hospital Readmission Predictor - Deployment Verification")
    print("=" * 60)
    
    # Run verification
    structure_ok = verify_deployment_structure()
    test_local_import()
    test_cases = generate_test_data()
    summary = create_deployment_summary()
    
    print("\n" + "=" * 60)
    print("🎯 FINAL STATUS:")
    
    if structure_ok:
        print("✅ READY FOR HUGGING FACE SPACES DEPLOYMENT!")
        print("\n📋 Next Steps:")
        print("1. Follow DEPLOYMENT_GUIDE.md")
        print("2. Create Hugging Face Space")
        print("3. Upload files using Git or web interface")
        print("4. Test deployment with provided test cases")
    else:
        print("❌ DEPLOYMENT NOT READY")
        print("\n📋 Required Actions:")
        print("1. Fix missing files listed above")
        print("2. Run copy_models.py to copy model files")
        print("3. Re-run this verification script")
    
    print(f"\n📊 Test cases ready: {len(test_cases)}")
    print("🔗 Deployment guide: DEPLOYMENT_GUIDE.md")
    print("📋 Summary: deployment_summary.json")