import random import uuid import os import csv from typing import List from models import TransactionWithLabel CSV_PATH = "creditcard.csv" def generate_mock_kaggle_data(filename: str, num_transactions: int = 500): """Creates a mock Kaggle creditcard.csv file if the real one isn't present.""" print("Generating mock Kaggle data since actual CSV wasn't found...") with open(filename, mode='w', newline='') as f: writer = csv.writer(f) header = ["Time"] + [f"V{i}" for i in range(1, 29)] + ["Amount", "Class"] writer.writerow(header) for i in range(num_transactions): time_val = float(i * 10) is_fraud = random.random() < 0.15 # 15% fraud in mock features = [] for j in range(1, 29): # Anomaly/fraud signals in V1, V2, V3 if is_fraud and j in [1, 2, 3]: val = random.uniform(5.0, 15.0) * random.choice([-1, 1]) else: val = random.gauss(0, 1) # Normal distribution around 0 features.append(round(val, 6)) amount = round(random.uniform(1.0, 1000.0) if not is_fraud else random.uniform(500.0, 5000.0), 2) cls = 1 if is_fraud else 0 row = [time_val] + features + [amount, cls] writer.writerow(row) def load_kaggle_data(num_transactions: int = 100) -> List[TransactionWithLabel]: """Loads transactions from creditcard.csv""" if not os.path.exists(CSV_PATH): generate_mock_kaggle_data(CSV_PATH, num_transactions=max(500, num_transactions * 2)) transactions = [] with open(CSV_PATH, mode='r') as f: reader = csv.DictReader(f) for i, row in enumerate(reader): if i >= num_transactions: break time_val = float(row["Time"]) amount_val = float(row["Amount"]) cls_val = int(row["Class"]) is_fraud = (cls_val == 1) # Extract V1-V28 features = [] for j in range(1, 29): key = f"V{j}" features.append(float(row[key])) t = TransactionWithLabel( transaction_id=f"TXN-{i+1:06d}-{hex(int(time_val))[2:].upper()}", Time=time_val, features=features, Amount=amount_val, is_fraud=is_fraud, fraud_reason="Class 1 (Fraud)" if is_fraud else None ) transactions.append(t) return transactions