cluster.py 文件源码

def adhoc_clustering(messages, dist_func=combined):
    ''' an adhoc method for clustering messages '''
    m = len(messages)

    # extract message features.
    for (mi, message) in enumerate(messages):
        if type(message) != dict:
            message = {
                'text': message
            }
        message.update(extract_all(parse_body(message['text'])))

    # run clustering (ad hoc).
    max_label = 0
    bias = 600
    labels = []

    for (mi, message) in enumerate(messages):
        min_mj = -1
        min_dist = float('inf')
        for mj in range(mi-1, -1, -1):
            dist = dist_func(messages[mi], messages[mj])
            if dist < min_dist:
                min_dist = dist
                min_mj = mj

        if (bias- 100 * worth(messages[mi])) < min_dist: # create new cluster.
            labels.append(max_label)
            max_label += 1
        else:  # assign to an old cluster.
            labels.append(labels[min_mj])

    return labels