2018.12.10 boston

1. 导入boston房价数据集

from sklearn.datasets import load_boston
import  pandas as pd

boston = load_boston()
df = pd.DataFrame(boston.data)　

2. 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。

from sklearn.linear_model import LinearRegression
import  matplotlib.pyplot as plt
x = boston.data[:, 5]
y = boston.target
LinR = LinearRegression()
LinR.fit(x.reshape(-1, 1), y)


plt.figure(figsize=(10,6))
plt.scatter(x, y)
w = LinR.coef_
b = LinR.intercept_
print(w, b)
plt.plot(x, w * x + b, 'orange')
plt.show()

　　

　　

系数与截距

3. 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.datasets import load_boston
import pandas as pd
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

boston = load_boston()
df = pd.DataFrame(boston.data)

x_train, x_test, y_train, y_test = train_test_split(boston.data,boston.target,test_size=0.3)
lineR = LinearRegression()
lineR.fit(x_train,y_train)

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))

x = boston.data[:,12].reshape(-1,1)
y = boston.target
plt.figure(figsize=(10,6))
plt.scatter(x,y)
lineR = LinearRegression()
lineR.fit(x,y)
y_pred = lineR.predict(x)
plt.plot(x,y_pred,'r')
print(lineR.coef_,lineR.intercept_)
plt.show()

　　

系数、截距

4.  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。

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=3)
x_poly = poly.fit_transform(x)
print(x_poly)
lrp = LinearRegression()
lrp.fit(x_poly,y)
y_poly_pred = lrp.predict(x_poly)
plt.scatter(x,y)
plt.scatter(x,y_pred)
plt.scatter(x,y_poly_pred)
plt.show()

　　

模型参数