cluster.py 文件源码

def cluster_service(path, service, cluster_size, prev_metadata=None):

    filename = os.path.join(path, service["preprocessed_filename"])
    df = pd.read_csv(filename, sep="\t", index_col='time', parse_dates=True)

    initial_idx = None
    if prev_metadata:
        initial_idx = get_initial_clustering(service["name"], prev_metadata, df.columns)
        # adjust cluster_size if an initial assigment has been found
        if initial_idx is not None:
            cluster_size = len(np.unique(initial_idx))

    prefix = "%s/%s-cluster-%d" % (path, service["name"], cluster_size)
    if os.path.exists(prefix + "_1.png"):
        print("skip " + prefix)
        return (None, None)

    cluster_metrics, score, filenames = do_kshape(prefix, df, cluster_size, initial_idx)
    if cluster_size < 2:
        # no silhouette_score for cluster size 1
        return (None, None)
    print("silhouette_score: %f" % score)

    # protect the write access to the metadata file
    metadata_lock.acquire()
    with metadata.update(path) as data:
        for srv in data["services"]:
            if srv["name"] == service["name"]:
                if "clusters" not in srv:
                    srv["clusters"] = {}
                d = dict(silhouette_score=score, filenames=filenames, metrics=cluster_metrics)
                srv["clusters"][cluster_size] = d
    metadata_lock.release()

    return (service["name"], cluster_size)