from sklearn.datasets import load_boston#导入数据集 boston=load_boston() #住宅平均房数与房价之间的关系 import matplotlib.pyplot as plt from sklearn.linear_model import LinearRegression lineR=LinearRegression() x=boston.data[:,6] y=boston.target plt.figure(figsize=(10,6)) plt.scatter(x,y) lineR.fit(x.reshape(-1,1),y) w=lineR.coef_ b=lineR.intercept_ plt.plot(x,w*x+b,'r') plt.show()
# 多元线性回归模型，建立13个变量与房价之间的预测模型，并检测模型好坏
# 划分数据集
from sklearn.cross_validation import train_test_split
x_train, x_test, y_train, y_test = train_test_split(boston.data,boston.target,test_size=0.3)
# 建立多项式性回归模型
lineR = LinearRegression()
lineR.fit(x_train,y_train)
# 检测模型好坏
import numpy as np
x_predict = lineR.predict(x_test)
# 打印预测的均方误差
print("预测的均方误差：", np.mean(x_predict - y_test)**2)
# 打印模型的分数
print("模型的分数：",lineR.score(x_test, y_test))
import matplotlib.pyplot as plt
x=boston.data[:,12].reshape(-1,1)
y=boston.target
plt.figure(figsize=(10,6))
plt.scatter(x,y)
from sklearn.linear_model import LinearRegression
lineR=LinearRegression()
lineR.fit(x,y)
y_pred=lineR.predict(x)
plt.plot(x,y_pred)
print(lineR.coef_,lineR.intercept_)
plt.show()
#一元多项式回归模型，建立一个变量与房价之间的预测模型， from sklearn.preprocessing import PolynomialFeatures poly = PolynomialFeatures(degree=2) x_poly = poly.fit_transform(x) lp = LinearRegression()#G构建模型 lp.fit(x_poly,y) y_poly_pred = lp.predict(x_poly) plt.scatter(x,y) plt.plot(x,y_poly_pred,'r') plt.show() lrp = LinearRegression() lrp.fit(x_poly,y) plt.scatter(x,y) plt.scatter(x,y_pred) plt.scatter(x,y_poly_pred) #多项回归 plt.show()
