Efficient id and id_var in C++ about dplyr HOT 2 CLOSED

def _get_compressed_labels(self):

    # These are the "factorized" integer numbers for each group key
    all_labels = [ping.labels for ping in self.groupings]

    if self._overflow_possible:

        # We're punting and doing an object hash if we're going
        # to overflow a 64-bit integer. Lame, I know

        # Convert the label arrays to Python tuples
        tups = lib.fast_zip(all_labels)

        # Pass the tuples through a hash table to compute integer labels
        labs, uniques = algos.factorize(tups)

        # Sort them if so desired
        if self.sort:
            uniques, labs = _reorder_by_uniques(uniques, labs)

        return labs, uniques
    else:
        if len(all_labels) > 1:
            # This is the "cartesian product number"
            group_index = get_group_index(all_labels, self.shape)

            # Pass the cartesian product number through the hash
            # table again to remove sparsity
            comp_ids, obs_group_ids = _compress_group_index(group_index)
        else:
            # Just use the integer labels from the only group key

            ping = self.groupings[0]
            comp_ids = ping.labels
            obs_group_ids = np.arange(len(ping.group_index))
            self.compressed = False
            self._filter_empty_groups = False

        return comp_ids, obs_group_ids