python機器學習之字典特徵提取

首先需要引入字典特徵提取類

from sklearn.feature_extraction import DictVectorizer

def dict_demo():
    #字典特徵提取
    data=[{'city':'北京','temperature':100},{'city':'上海','temperature':60},{'city':'深圳','temperature':30}]

    #1.實例化一個轉換器類
    transfer= DictVectorizer(sparse=False)#默認爲sparse=True，即爲稀疏矩陣

    #2.調用fit_transform()
    #轉換成one-hot編碼
    # 類別特徵比較多-》字典類型
    # DictVectorizer
    data_new=transfer.fit_transform(data)
    print("data_new:\n",data_new)
    print("特徵值名字：",transfer.get_feature_names())
    return None