机器学习特征处理

0导入库

import sklearn.preprocessing
from sklearn.feature_extraction import  DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer
import jieba
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.preprocessing import MinMaxScaler
import numpy as np
from sklearn.preprocessing import StandardScaler

1 字典数据抽取

def dictvec():
    """字典数据抽取"""
    # 实例化
    dict = DictVectorizer()
    # 调用方法
    date = [{'city': '北京','temperature':100},{'city': '上海','temperature':60},{'city': '深圳','temperature':30}]
    data_fea = dict.fit_transform(date)
    print(data_fea)
    dict2 = DictVectorizer(sparse=False)
    # False代表不用ｓｐａｒｓｅ矩阵
    date2 = [{'city': '北京','temperature':100},{'city': '上海','temperature':60