特征处理

特征处理

from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.impute import SimpleImputer
import pandas as pd
import numpy as np


# 归一化
# def minmax():
#     mm = MinMaxScaler(feature_range=(2, 3))  默认区间为(0,1)可设置为任意区间#
#     data = mm.fit_transform([[90, 4, 20, 60], [60, 6, 80, 30], [85, 2, 50, 40]])
#     print(data)

# 标准化
# def standards():
#       std = StandardScaler()
#       data = std.fit_transform([[90, 4, 20, 60], [60, 6, 80, 30], [85, 2, 50, 40]])
#       print(data)

# 数值缺失
def impu():
    imp = SimpleImputer(missing_values=np.nan, strategy='mean')
    data = imp.fit_transform([[1, 2, 5], [np.nan, 8, 3], [7, 6, 4]])
    print(data)


if __name__ == '__main__':
    impu()