sklearn字典数据特征抽取

本人git仓库地址 ：https://gitee.com/wangxuewaii/MachineLearning

from sklearn.feature_extraction import DictVectorizer


def dictvec():
    """
    字典数据抽取
    :return:
    """
    # 实例化
    dict = DictVectorizer(sparse=False) # 默认返回的是sparse的矩阵格式,为了节约内存看的时候不用，关掉
    # 调用fit_transform
    data = dict.fit_transform([{"city":"北京","temperature":100},{"city":"上海","temperature":50},{"city":"东京","temperature":10}])
    print(dict.get_feature_names())
    print(data)



if __name__ == "__main__":
    dictvec()