2024.7.7

初步了解 机器学习 

 """
    sklearn数据集使用
    :return:
    """

def dict_demo():
    """
    字典特征抽取
    :return:
    """
    data = [{'city': '北京','temperature':100}, {'city': '上海','temperature':60}, {'city': '深圳','temperature':30}]
    # 1、实例化一个转换器类
    transfer = DictVectorizer(sparse=False)

    # 2、调用fit_transform()
    data_new = transfer.fit_transform(data)

    print("data_new:\n", data_new.toarray(), type(data_new))
    print("特征名字：\n", transfer.get_feature_names_out_out())

    return None

 transfer = CountVectorizer(stop_words=["is", "too"])

  # 1、实例化一个转换器类
    transfer = CountVectorizer()

def cut_word(text):
    """
    进行中文分词："我爱北京天安门" --> "我 爱 北京 天安门"
    :param text:
    :return:
    """
    return " ".join(list(jieba.cut(text)))