python实现-回归分析

python实现-回归分析

import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error,r2_score

data = pd.read_csv('/Users/huangqiankun/Downloads/汽车销售数据.csv')
data.head()

data.isnull().any()

data = data.dropna()

X = data.iloc[:,3:]
Y = data.iloc[:,2]
x_train,x_test,y_train,y_test = train_test_split(X,Y,test_size = 0.2,random_state = 1234)


ss = StandardScaler()
ss.fit(x_train)
x_train_ss = ss.transform(x_train)
x_test_ss = ss.transform(x_test)


lr = LinearRegression()
lr.fit(x_train_ss,y_train)

out:
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

lr.coef_

out:
array([-14.97630252,   2.32553882,   1.41436362, 237.23659298,
         3.42730138,   1.80472323,  -4.99775286])

lr.intercept_
out:
430.7574509803923


y_pred = lr.predict(x_test_ss)
mean_squared_error(y_test,y_pred)

out:
19.500348658914437

r2_score(y_test,y_pred)

out:
0.9995192568677627

来源：CSDN

作者：yxjwhhhh

链接：https://blog.csdn.net/yxjwhhhh/article/details/104348778