案例：线性回归Linear Regression房价预测

使用scikit-learn自带的波士顿房价数据集

输入特征

from sklearn.datasets import load_boston
from matplotlib import pyplot as plt
%matplotlib inline
boston=load_boston()
X=boston.data
Y=boston.target
X.shape

(506, 13)

boston.feature_names

array(['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD',
       'TAX', 'PTRATIO', 'B', 'LSTAT'],
      dtype='<U7')

模型训练

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=3)

import time
from sklearn.linear_model import LinearRegression
model=LinearRegression(normalize=True)
start=time.clock()
model.fit(X_train,y_train)
train_score=model.score(X_train,y_train)
cv_score=model.score(X_test,y_test)
print('elaspe:{0:.6f};train score:{1:.6f};cv score:{2:.6f}'.format(time.clock()-start,train_score,cv_score))

plt.figure(figsize=(16,8))
plt.title('Linear Regression train score:{0:.6f}'.format(