Function _check_dsk

dask/array/utils.py:205–229

Check that graph is well named and non-overlapping

(dsk)

def _check_dsk(dsk):
    """Check that graph is well named and non-overlapping"""
    if not isinstance(dsk, HighLevelGraph):
        return

    dsk.validate()
    assert all(isinstance(k, (tuple, str)) for k in dsk.layers)
    freqs = frequencies(concat(dsk.layers.values()))
    non_one = {k: v for k, v in freqs.items() if v != 1}
    key_collisions = set()
    # Allow redundant keys if the values are equivalent
    collisions = set()
    all_keys = set(dsk)
    layers = [convert_legacy_graph(layer, all_keys) for layer in dsk.layers.values()]
    for k in non_one.keys():
        for layer in layers:
            try:
                key_collisions.add(tokenize(layer[k]))
            except KeyError:
                pass
        if len(key_collisions) >= 2:
            collisions.add(k)
        key_collisions.clear()

    assert len(collisions) == 0, {k: non_one[k] for k in collisions}


def assert_eq_shape(a, b, check_ndim=True, check_nan=True):