如图所示,通过6步完成数据预处理。
此例用到的数据,代码。
import numpy as np import pandas as pd
dataset = pd.read_csv('Data.csv')//读取csv文件 X = dataset.iloc[ : , :-1].values//.iloc[行,列] Y = dataset.iloc[ : , 3].values // : 全部行 or 列;[a]第a行 or 列// [a,b,c]第 a,b,c 行 or 列
from sklearn.preprocessing import Imputer imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0) imputer = imputer.fit(X[ : , 1:3]) X[ : , 1:3] = imputer.transform(X[ : , 1:3])
from sklearn.preprocessing import LabelEncoder, OneHotEncoder labelencoder_X = LabelEncoder() X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
onehotencoder = OneHotEncoder(categorical_features = [0]) X = onehotencoder.fit_transform(X).toarray() labelencoder_Y = LabelEncoder() Y = labelencoder_Y.fit_transform(Y)
from sklearn.model_selection import train_test_split X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)
from sklearn.preprocessing import StandardScaler sc_X = StandardScaler() X_train = sc_X.fit_transform(X_train) X_test = sc_X.transform(X_test)
版权声明:本站所有资料均为网友推荐收集整理而来,仅供学习和研究交流使用。
工作时间:8:00-18:00
客服电话
电子邮件
admin@qq.com
扫码二维码
获取最新动态