python将文字转换成数字类型

import jieba
from sklearn.feature_extraction.text import CountVectorizer
def cut_work():
    word1="你好"
    word2="我好"
    word3="大家好"
    # 分词处理
    c1=" ".join(list(jieba.cut(word1)))
    c2= " ".join(list(jieba.cut(word2)))
    c3 = " ".join(list(jieba.cut(word3)))
    return c1,c2,c3
def demo():
    # 将中文抽取数字特征
    # 1获取需要抽取的数据
    c1,c2,c3=cut_work()
    data=[c1,c2,c3]
    #实例化一个转化数据的对象
    count=CountVectorizer()
    
    data=count.fit_transform(data)
    print(count.get_feature_names())
    print(data.toarray())
demo()