Spaces:
Sleeping
Sleeping
| import pandas as pd | |
| import torch | |
| from torch.utils.data import TensorDataset, DataLoader | |
| from sklearn.preprocessing import StandardScaler | |
| def build_features(df: pd.DataFrame): | |
| """Prepare the processed PaySim frame for training. | |
| - Splits X/y and splits chronologically by step (no leakage) | |
| - Scales features (fit on train, transform test) | |
| - Returns train/test DataLoaders and the fitted scaler | |
| """ | |
| X = df.drop(columns=['isFraud']) | |
| y = df['isFraud'] | |
| train_mask = df['step'] < 600 | |
| X_train, y_train = X[train_mask], y[train_mask] | |
| X_test, y_test = X[~train_mask], y[~train_mask] | |
| scaler = StandardScaler() | |
| X_train = scaler.fit_transform(X_train) # fit on train only | |
| X_test = scaler.transform(X_test) # transform test with train stats | |
| def to_ds(Xa, ys): | |
| return TensorDataset( | |
| torch.tensor(Xa, dtype=torch.float32), | |
| torch.tensor(ys.to_numpy(), dtype=torch.float32).unsqueeze(1), | |
| ) | |
| train_dataloader = DataLoader(to_ds(X_train, y_train), batch_size=32, shuffle=True) | |
| test_dataloader = DataLoader(to_ds(X_test, y_test), batch_size=32, shuffle=False) | |
| return train_dataloader, test_dataloader, scaler |