pro_cluster.py 文件源码

def all_cluster():
    #????????between??
    # bet_dic = {}
    # fin = open('sort_between.txt', 'r')
    # while True:
    #     line = fin.readline()
    #     if line:
    #         line = line.strip()
    #         between, vec = line.split('^')
    #         vec = vec.strip('[')
    #         vec = vec.strip(']')
    #         vec = vec.split(',')
    #         bet_dic[between] = vec
    #
    #     else:
    #         break
    # bet_dic = pd.DataFrame(bet_dic)
    # bet_dic = bet_dic.T
    # bet_dic.to_csv('dataframe.csv')
    # fin.close()
    df = pd.read_csv('dataframe.csv')
    clf = KMeans(n_clusters=50)
    s = clf.fit(df[1:, 1:])
    print s