similar_posts.py 文件源码

def KmeansWrapper(true_k, data, load=False):
    from sklearn.externals import joblib

    modelName = 'doc_cluster.%s.plk' % true_k

    if load:
        km = joblib.load(modelName)
        labels = km.labels_
    else:
        km = KMeans(n_clusters=true_k,
                    init='k-means++',
                    # max_iter=1000,
                    n_init=10,
                    n_jobs=-1,
                    random_state=0,
                    verbose=0)
        km.fit_predict(data)
        labels = km.labels_
        joblib.dump(km,  modelName)

    return labels, km.cluster_centers_