代码:
from sklearn import datasets
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
# 使用以后的数据集进行线性回归(这里是波士顿房价数据)
##1 数据的加载
from sklearn.model_selection import train_test_split
loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_y = loaded_data.target
X_train,X_test,y_train,y_test=train_test_split(data_X,data_y,test_size=0.2,random_state=33)
##2 模型的加载
model = LinearRegression()
##3 模型的训练
model.fit(X_train, y_train)
print(model.score(X_test,y_test))
0.6923688459535136
调参:
LinearRegression(fit_intercept=True, normalize=False, copy_X=True, n_jobs=None)
fit_intercept:是否有截据,如果没有则直线过原点;
normalize:是否将数据归一化;
copy_X:默认为True,当为True时,X会被copied,否则X将会被覆写;
n_jobs:默认值为1。计算时使用的核数