Untitled

columns_to_drop = ["TransactionID", "TransactionAmt_bin", "TransactionDT_bin",
                   "fraud_count", "stratify_label", "label", 'k1', 'k2', 'k3', 'k4', 'k5','isFraud']

# Ensure all columns exist before dropping
columns_to_drop = [col for col in columns_to_drop if col in train_fold_1.columns]

# Drop columns
train_fold_1_X = train_fold_1.drop(columns=columns_to_drop, errors='ignore')
train_fold_1_Y = train_fold_1["isFraud"]
test_fold_1_X = test_fold_1.drop(columns=columns_to_drop, errors='ignore')
test_fold_1_Y = test_fold_1["isFraud"]



from sklearn.preprocessing import LabelEncoder

# Define categorical features
categorical_features = [
    "ProductCD", "card1", "card2", "card3", "card4", "card5", "card6",
    "addr1", "addr2", "P_emaildomain", "R_emaildomain",
    "M1", "M2", "M3", "M4", "M5", "M6", "M7", "M8", "M9",
    "DeviceType", "DeviceInfo"
] + [f"id_{i}" for i in range(12, 39)]  # Adding id_12 to id_38



from sklearn.ensemble import RandomForestClassifier

rf_model = RandomForestClassifier()