def gen_sequence_array()

in fclib/fclib/feature_engineering/feature_utils.py [0:0]

• 15 lines of code
• 2 McCabe index (conditional complexity)

def gen_sequence_array(df_all, seq_len, seq_cols, grain1_name, grain2_name, start_timestep=0, end_timestep=None):
    """Combine feature sequences for all the combinations of (grain1_name, grain2_name) into a 
    3-dimensional array.
    
    Args:
        df_all (pd.Dataframe): Time series data of all the grains for multi-granular data
        seq_len (int): Number of previous time series values to be used to form sequences
        seq_cols (list[str]): A list of names of the feature columns 
        grain1_name (str): Name of the 1st column indicating the time series graunularity
        grain2_name (str): Name of the 2nd column indicating the time series graunularity
        start_timestep (int): First time step you can use to create feature sequences
        end_timestep (int): Last time step you can use to create feature sequences
        
    Returns:
        seq_array (np.array): An array of feature sequences for all combinations of granularities
    """
    seq_gen = (
        list(
            gen_sequence(
                df_all[(df_all[grain1_name] == grain1) & (df_all[grain2_name] == grain2)],
                seq_len,
                seq_cols,
                start_timestep,
                end_timestep,
            )
        )
        for grain1, grain2 in itertools.product(df_all[grain1_name].unique(), df_all[grain2_name].unique())
    )
    seq_array = np.concatenate(list(seq_gen)).astype(np.float32)
    return seq_array