Delete preprocess.py

preprocess.py

@@ -1,108 +0,0 @@
-# create_demo_data.py - Cria dados de demonstração e modelos base
-import pandas as pd
-import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
-from sklearn.linear_model import LogisticRegression
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.svm import SVC
-from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
-import joblib
-
-def create_demo_dataset():
-    """Cria dataset de demonstração realístico"""
-    np.random.seed(42)
-    n_samples = 2000
-    
-    # Features baseadas no dataset real de hotéis
-    features = {
-        'lead_time': np.random.gamma(2, 50, n_samples),
-        'adr': np.random.normal(100, 30, n_samples),
-        'adults': np.random.poisson(2, n_samples),
-        'children': np.random.poisson(0.3, n_samples),
-        'previous_cancellations': np.random.poisson(0.1, n_samples),
-        'is_repeated_guest': np.random.binomial(1, 0.1, n_samples),
-        'required_car_parking_spaces': np.random.binomial(1, 0.2, n_samples),
-        'total_of_special_requests': np.random.poisson(0.5, n_samples),
-        'booking_changes': np.random.poisson(0.3, n_samples),
-    }
-    
-    X = pd.DataFrame(features)
-    
-    # Criar target com relação realística
-    cancellation_prob = 1 / (1 + np.exp(-(
-        X['lead_time'] * 0.01 +
-        X['adr'] * 0.005 -
-        X['is_repeated_guest'] * 0.8 -
-        X['required_car_parking_spaces'] * 0.3 +
-        X['total_of_special_requests'] * -0.4 +
-        np.random.normal(0, 0.5, n_samples)
-    )))
-    
-    y = (cancellation_prob > 0.5).astype(int)
-    
-    return X, y
-
-def train_and_save_models():
-    """Treina e salva modelos de demonstração"""
-    # Criar dados
-    X, y = create_demo_dataset()
-    
-    # Split dos dados
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.3, random_state=42, stratify=y
-    )
-    
-    # Normalizar
-    scaler = StandardScaler()
-    X_train_scaled = scaler.fit_transform(X_train)
-    X_test_scaled = scaler.transform(X_test)
-    
-    # Treinar modelos
-    models = {}
-    results = {}
-    
-    # Regressão Logística
-    lr = LogisticRegression(random_state=42, max_iter=1000)
-    lr.fit(X_train_scaled, y_train)
-    models['RL_Padrao'] = lr
-    
-    # KNN
-    knn = KNeighborsClassifier(n_neighbors=5)
-    knn.fit(X_train_scaled, y_train)
-    models['KNN_Padrao'] = knn
-    
-    # SVM
-    svm = SVC(probability=True, random_state=42)
-    svm.fit(X_train_scaled, y_train)
-    models['SVM_Padrao'] = svm
-    
-    # Avaliar modelos
-    for name, model in models.items():
-        y_pred = model.predict(X_test_scaled)
-        y_proba = model.predict_proba(X_test_scaled)[:, 1]
-        
-        results[name] = {
-            'Acurácia': accuracy_score(y_test, y_pred),
-            'Precisão': precision_score(y_test, y_pred, zero_division=0),
-            'Recall': recall_score(y_test, y_pred, zero_division=0),
-            'F1-Score': f1_score(y_test, y_pred, zero_division=0),
-            'AUC-ROC': roc_auc_score(y_test, y_proba),
-            'Tempo Treino (s)': 0
-        }
-    
-    # Salvar dados
-    data_to_save = {
-        'models': models,
-        'X_train': X_train_scaled,
-        'X_test': X_test_scaled,
-        'y_train': y_train,
-        'y_test': y_test,
-        'results': results
-    }
-    
-    joblib.dump(data_to_save, 'modelos_treinados.pkl')
-    print("✅ Dados de demonstração e modelos salvos em 'modelos_treinados.pkl'")
-
-if __name__ == "__main__":
-    train_and_save_models()