mode2.py

# function to reshape features into (samples, time steps, features) 
def gen_sequence(id_df, seq_length, seq_cols):
    """ Only sequences that meet the window-length are considered, no padding is used. This means for testing
    we need to drop those which are below the window-length. An alternative would be to pad sequences so that
    we can use shorter ones """
    # for one id I put all the rows in a single matrix
    data_matrix = id_df[seq_cols].values
    num_elements = data_matrix.shape[0]
    # Iterate over two lists in parallel.
    # For example id1 have 192 rows and sequence_length is equal to 50
    # so zip iterate over two following list of numbers (0,112),(50,192)
    # 0 50 -> from row 0 to row 50
    # 1 51 -> from row 1 to row 51
    # 2 52 -> from row 2 to row 52
    # ...
    # 111 191 -> from row 111 to 191
    for start, stop in zip(range(0, num_elements-seq_length), range(seq_length, num_elements)):
        yield data_matrix[start:stop, :]