citylearn.end_use_load_profiles.lstm_model.preprocessing module

citylearn.end_use_load_profiles.lstm_model.preprocessing.dataset_dataloader(x: ndarray, y: ndarray, batch_size: int, shuffle: bool = None, drop_last: bool = None) → Tuple[TensorDataset, DataLoader]

citylearn.end_use_load_profiles.lstm_model.preprocessing.preprocess_df(config: Mapping[str, Any], df: DataFrame, train_references: List[int] = None, validation_references: List[int] = None, test_references: List[int] = None) → Mapping[str, Any]

citylearn.end_use_load_profiles.lstm_model.preprocessing.sliding_windows(data: ndarray, seq_length: int, output_len: int)

Create lookback/output windows where target is the last column.

Parameters:

• data (np.ndarray) – Input array where the prediction target is the last column.

• seq_length (int) – Number of lookback time steps.

• output_len (int) – Number of future target steps to predict.

Returns:

x with shape [num_steps - lookback, lookback, num_input_features] and y with shape [num_steps - lookback, num_output_features].

Return type:

Tuple[np.ndarray, np.ndarray]