metricsnamecluster.py 文件源码

def cluster_words(words, service_name, size):
    stopwords = ["GET", "POST", "total", "http-requests", service_name, "-", "_"]
    cleaned_words = []
    for word in words:
        for stopword in stopwords:
            word = word.replace(stopword, "")
        cleaned_words.append(word)
    def distance(coord):
        i, j = coord
        return 1 - jaro_distance(cleaned_words[i], cleaned_words[j])
    indices = np.triu_indices(len(words), 1)
    distances = np.apply_along_axis(distance, 0, indices)
    return cluster_of_size(linkage(distances), size)