回归模型与房价预测

Posted 2021-01-26 yan668

 

 

1.导入数据集

from sklearn.datasets import load_boston
boston = load_boston()
boston.keys()

2.查看数据集

#介绍
print(boston.DESCR)
#查看数据
data = boston.data
#查看房价
boston.target
#特征
boston.feature_names

3.一元线性回归模型，建立一个变量与房价之间的预测模型，并图形化显示

import pandas as pd #导包
pd.DataFrame(boston.data)
#预处理获取斜率
from sklearn.linear_model import LinearRegression
LineR = LinearRegression()
LineR.fit(x.reshape(-1,1),y)
w=LineR.coef_
#获取截距
b=LineR.intercept_
#图形化显示
x = data[:,5]
y = boston.target
 
import matplotlib.pyplot as plt
plt.scatter(x,y)
plt.plot(x,w*x+b,‘G‘)
plt.show()

4.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，并图形化显示检查结果

from sklearn.linear_model import LinearRegression 
lineR = LinearRegression()
lineR.fit(boston.data,y)
w = lineR.coef_
b = lineR.intercept_
import matplotlib.pyplot as plt
x=boston.data[:,12].reshape(-1,1)
y=boston.target
plt.figure(figsize=(10,6)) #指定显示图大小
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,‘G‘)
print(lineR.coef_,lineR.intercept_)
plt.show()

5. 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，并图形化显示

xx = data[:,12].reshape(-1,1)
plt.scatter(xx,y)
plt.show()
lr12 = LinearRegression()
lr12.fit(xx,y)
w = lr12.coef_
b = lr12.intercept_
plt.scatter(xx,y)
plt.plot(xx,w*xx+b,‘G‘)
plt.show()
from sklearn.preprocessing import PolynomialFeatures
p = PolynomialFeatures()
p.fit(xx)
x_poly = p.transform(xx)
lrp = LinearRegression()
lrp.fit(x_poly,y)
lrp.coef_
lrp.intercept_
lrp = LinearRegression()
lrp.fit(x_poly,y)
y_poly = lrp.predict(x_poly)
plt.scatter(xx,y)
plt.plot(xx,w*xx+b,‘G‘)
plt.scatter(xx,y_poly)
plt.show()
lrp.coef_