clusterSimilarSSIDSets.py 文件源码

def get_similar_ssid_sets(ssid_sets, threshold):
    """Return a mapping of ssid set to similar ssid sets.
    :param ssid_sets: Iterable of SSID sets
    :param threshold: Minimum Jaccard index for two sets to be matched as similar.
    """
    ssid_set_to_matches = defaultdict(set)
    ssid_pairs = combinations(ssid_sets, r=2)

    # Distribute calulcations to worker processes
    # Significant speed-up over single process
    with multiprocessing.Pool() as pool:
        task = partial(jaccard_worker, threshold=threshold)

        # Immediately returns an iterable
        similar_ssids = pool.imap_unordered(task, ssid_pairs, chunksize=300000)

        # Consumes the iterable whenever a worker process yields
        for match in similar_ssids:
            if match:
                ssid_set_to_matches[match[0]].add(match[1])
                ssid_set_to_matches[match[1]].add(match[0])

    return ssid_set_to_matches