utils.py 文件源码

def numpy_groupby(values, keys):
    """ Group a collection of numpy arrays by key arrays.
        Yields (key_tuple, view_tuple) where key_tuple is the key grouped on and view_tuple is a tuple of views into the value arrays.
          values: tuple of arrays to group
          keys: tuple of sorted, numeric arrays to group by """

    if len(values) == 0:
        return
    if len(values[0]) == 0:
        return

    for key_array in keys:
        assert len(key_array) == len(keys[0])
    for value_array in values:
        assert len(value_array) == len(keys[0])

    # The indices where any of the keys differ from the previous key become group boundaries
    key_change_indices = np.logical_or.reduce(tuple(np.concatenate(([1], np.diff(key))) != 0 for key in keys))
    group_starts = np.flatnonzero(key_change_indices)
    group_ends = np.roll(group_starts, -1)
    group_ends[-1] = len(keys[0])

    for group_start, group_end in itertools.izip(group_starts, group_ends):
        yield tuple(key[group_start] for key in keys), tuple(value[group_start:group_end] for value in values)