#!/usr/bin/env python3
"""
=================================================================
TEST GPU READINESS per 1M+ RECORD - TESLA M60
=================================================================
🔧 Test rapido per verificare se il sistema è pronto per processing
   di 1.000.000+ record completamente su GPU Tesla M60
=================================================================
"""

import os
import sys
import time
import traceback

# ⚡ CONFIGURAZIONE GPU CRITICA ⚡
os.environ['TF_GPU_ALLOCATOR'] = 'legacy'  # CRITICO per Tesla M60 CC 5.2
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '1'

def test_cudf_cupy():
    """Test CuDF + CuPy per DataFrame GPU-native"""
    print("\n🔧 TEST 1: CuDF + CuPy (DataFrame 100% GPU)")
    try:
        import cudf
        import cupy as cp
        
        # Test CuDF DataFrame
        print("⚡ Creazione CuDF DataFrame test...")
        test_data = {
            'id': range(100000),
            'ip': [f"192.168.{i%256}.{(i*7)%256}" for i in range(100000)],
            'timestamp': ['2024-01-01 12:00:00'] * 100000,
            'message': [f"test_msg_{i%1000}" for i in range(100000)]
        }
        df_gpu = cudf.DataFrame(test_data)
        print(f"✅ CuDF DataFrame: {len(df_gpu):,} record su GPU")
        
        # Test CuPy arrays
        print("⚡ Test CuPy arrays...")
        arr_gpu = cp.random.random((100000, 50))
        result = cp.sum(arr_gpu, axis=1)
        print(f"✅ CuPy compute: {result.shape} array processed")
        
        # Memory info
        pool = cp.get_default_memory_pool()
        memory_mb = pool.used_bytes() / 1024**2
        print(f"✅ GPU Memory used: {memory_mb:.1f}MB")
        
        # Cleanup
        del df_gpu, arr_gpu, result
        pool.free_all_blocks()
        
        return True, f"CuDF + CuPy OK (Memory: {memory_mb:.1f}MB)"
        
    except ImportError as e:
        return False, f"CuDF/CuPy non installati: {e}"
    except Exception as e:
        return False, f"Errore CuDF/CuPy: {e}"

def test_cuml():
    """Test CuML per ML GPU-native"""
    print("\n🔧 TEST 2: CuML (ML 100% GPU)")
    try:
        import cuml
        import cupy as cp
        from cuml.ensemble import IsolationForest as IFGPU
        from cuml.neighbors import LocalOutlierFactor as LOFGPU
        from cuml.svm import OneClassSVM as SVMGPU
        
        print("⚡ Test Isolation Forest GPU...")
        X_test = cp.random.random((10000, 20))
        if_gpu = IFGPU(n_estimators=50, max_samples=5000)
        if_gpu.fit(X_test)
        predictions = if_gpu.predict(X_test)
        print(f"✅ Isolation Forest GPU: {len(predictions):,} predictions")
        
        print("⚡ Test LOF GPU...")
        lof_gpu = LOFGPU(n_neighbors=20)
        # LOF con subset per performance
        X_small = X_test[:5000]
        lof_gpu.fit(X_small)
        lof_pred = lof_gpu.predict(X_small)
        print(f"✅ LOF GPU: {len(lof_pred):,} predictions")
        
        print("⚡ Test SVM GPU...")
        svm_gpu = SVMGPU(nu=0.05)
        # SVM con subset ancora più piccolo
        X_tiny = X_test[:2000]
        svm_gpu.fit(X_tiny)
        svm_pred = svm_gpu.predict(X_tiny)
        print(f"✅ SVM GPU: {len(svm_pred):,} predictions")
        
        # Memory cleanup
        del X_test, X_small, X_tiny, if_gpu, lof_gpu, svm_gpu
        
        return True, "CuML ML completo OK"
        
    except ImportError as e:
        return False, f"CuML non installato: {e}"
    except Exception as e:
        return False, f"Errore CuML: {e}"

def test_tensorflow_gpu():
    """Test TensorFlow GPU"""
    print("\n🔧 TEST 3: TensorFlow GPU")
    try:
        import tensorflow as tf
        
        # Check GPU devices
        gpus = tf.config.list_physical_devices('GPU')
        if not gpus:
            return False, "Nessuna GPU TensorFlow rilevata"
        
        gpu = gpus[0]
        print(f"⚡ GPU rilevata: {gpu}")
        
        # Configure GPU
        tf.config.experimental.set_memory_growth(gpu, True)
        print("✅ Memory growth configurato")
        
        # Test GPU operations
        with tf.device('/GPU:0'):
            print("⚡ Test matrix operations GPU...")
            A = tf.random.normal((5000, 500))
            B = tf.random.normal((500, 200))
            C = tf.matmul(A, B)
            print(f"✅ Matrix GPU: {C.shape} = {A.shape} @ {B.shape}")
            
            print("⚡ Test neural network GPU...")
            model = tf.keras.Sequential([
                tf.keras.layers.Dense(128, activation='relu', input_shape=(500,)),
                tf.keras.layers.Dense(64, activation='relu'),
                tf.keras.layers.Dense(1, activation='sigmoid')
            ])
            
            # Compile and test
            model.compile(optimizer='adam', loss='binary_crossentropy')
            
            # Test data
            X_test = tf.random.normal((10000, 500))
            y_test = tf.random.uniform((10000, 1))
            
            # Quick training test
            model.fit(X_test, y_test, epochs=1, batch_size=1000, verbose=0)
            predictions = model.predict(X_test[:1000], verbose=0)
            print(f"✅ Neural Network GPU: {len(predictions):,} predictions")
        
        return True, f"TensorFlow GPU OK ({gpu})"
        
    except ImportError as e:
        return False, f"TensorFlow non disponibile: {e}"
    except Exception as e:
        return False, f"Errore TensorFlow GPU: {e}"

def test_memory_capacity():
    """Test capacità memoria GPU per 1M+ record"""
    print("\n🔧 TEST 4: Capacità Memoria GPU per 1M+ record")
    try:
        import cupy as cp
        
        # Simula 1M record processing
        print("⚡ Simulazione 1M record processing...")
        
        # Test 1: DataFrame equivalent (1M rows x 50 cols)
        print("⚡ Test 1M x 50 array (simula DataFrame)...")
        test_df = cp.random.random((1000000, 50), dtype=cp.float32)
        print(f"✅ 1M x 50 array: {test_df.nbytes / 1024**2:.1f}MB GPU memory")
        
        # Test 2: Feature matrix (1M rows x 500 features)
        print("⚡ Test 1M x 500 array (simula feature matrix)...")
        test_features = cp.random.random((1000000, 500), dtype=cp.float32) 
        print(f"✅ 1M x 500 array: {test_features.nbytes / 1024**2:.1f}MB GPU memory")
        
        # Test 3: Operations simulation
        print("⚡ Test operazioni massive...")
        result = cp.sum(test_features, axis=1)
        result2 = cp.mean(test_features, axis=1)
        result3 = cp.std(test_features, axis=1)
        print(f"✅ Operazioni massive: 3 calcoli su 1M record")
        
        # Memory status
        pool = cp.get_default_memory_pool()
        used_gb = pool.used_bytes() / 1024**3
        
        print(f"📊 Memoria GPU utilizzata: {used_gb:.2f}GB")
        
        # Cleanup
        del test_df, test_features, result, result2, result3
        pool.free_all_blocks()
        
        if used_gb < 7.0:  # Tesla M60 ha 8GB
            return True, f"Memoria OK: {used_gb:.2f}GB/8GB utilizzati"
        else:
            return False, f"Memoria limite: {used_gb:.2f}GB/8GB"
            
    except Exception as e:
        return False, f"Errore test memoria: {e}"

def test_analisys_04_import():
    """Test import analisys_04 with GPU support"""
    print("\n🔧 TEST 5: Import analisys_04 con supporto GPU")
    try:
        # Test import modules
        from analisys_04 import AdvancedFeatureExtractor, AdvancedEnsemble
        print("✅ Import analisys_04 OK")
        
        # Test feature extractor
        extractor = AdvancedFeatureExtractor()
        print("✅ AdvancedFeatureExtractor creato")
        
        # Test ensemble
        ensemble = AdvancedEnsemble()
        print("✅ AdvancedEnsemble creato")
        
        return True, "analisys_04 modules OK"
        
    except ImportError as e:
        return False, f"Import analisys_04 fallito: {e}"
    except Exception as e:
        return False, f"Errore analisys_04: {e}"

def main():
    """Test completo GPU readiness"""
    print("="*80)
    print("🚀 TEST GPU READINESS per 1M+ RECORD - TESLA M60")
    print("="*80)
    
    results = []
    total_start = time.time()
    
    # Run all tests
    tests = [
        ("CuDF + CuPy", test_cudf_cupy),
        ("CuML", test_cuml),
        ("TensorFlow GPU", test_tensorflow_gpu),
        ("Memoria 1M+ record", test_memory_capacity),
        ("analisys_04 import", test_analisys_04_import)
    ]
    
    for test_name, test_func in tests:
        try:
            start_time = time.time()
            success, message = test_func()
            elapsed = time.time() - start_time
            
            results.append({
                'name': test_name,
                'success': success,
                'message': message,
                'time': elapsed
            })
            
            status = "✅ PASS" if success else "❌ FAIL"
            print(f"{status} {test_name}: {message} ({elapsed:.1f}s)")
            
        except Exception as e:
            results.append({
                'name': test_name,
                'success': False,
                'message': f"Exception: {e}",
                'time': 0
            })
            print(f"❌ FAIL {test_name}: Exception {e}")
            traceback.print_exc()
    
    total_time = time.time() - total_start
    
    # Summary
    print("\n" + "="*80)
    print("📊 SUMMARY RESULTS")
    print("="*80)
    
    passed = sum(1 for r in results if r['success'])
    total = len(results)
    
    print(f"📈 TESTS PASSED: {passed}/{total}")
    print(f"⏱️ TOTAL TIME: {total_time:.1f}s")
    
    # Detailed results
    for result in results:
        status = "✅" if result['success'] else "❌"
        print(f"{status} {result['name']}: {result['message']}")
    
    # GPU Readiness verdict
    print("\n" + "="*80)
    if passed == total:
        print("🎉 GPU SYSTEM READY per 1M+ RECORD!")
        print("✅ Tutte le librerie GPU sono installate e funzionanti")
        print("✅ Memoria GPU sufficiente per 1M+ record")
        print("✅ Performance attese: 5-10x superiori vs CPU")
        print("\n🚀 NEXT STEPS:")
        print("   python train_gpu_native_1M.py --max-records 1000000")
    elif passed >= 3:
        print("⚠️ GPU SYSTEM PARZIALMENTE READY")
        print("✅ Componenti base GPU funzionanti")
        print("⚠️ Alcune librerie mancanti - performance ridotte")
        print("\n💡 AZIONI:")
        print("   - Installa librerie mancanti (vedi INSTALL_GPU_LIBRARIES.md)")
        print("   - Testa con: python train_gpu_native_1M.py --max-records 500000")
    else:
        print("❌ GPU SYSTEM NOT READY")
        print("❌ Troppe librerie mancanti per 1M+ record")
        print("\n💡 AZIONI NECESSARIE:")
        print("   1. Installa CUDA toolkit")
        print("   2. pip install cudf-cu11 cupy-cuda11x")
        print("   3. pip install cuml-cu11")
        print("   4. Verifica GPU drivers")
    
    print("="*80)
    
    return passed == total

if __name__ == "__main__":
    main()