线性回归预测房价

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

from sklearn.metrics import mean_squared_error, r2_score

import seaborn as sns

 

# 加载数据集

data = pd.read_csv('housing_price.csv')

 

# 设置中文字体

plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题

 

# 计算属性之间的相关系数矩阵

correlation_matrix = data[['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms', 'Area Population', 'size', 'Price']].corr()

 

# 绘制热力图

sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm')

plt.title('属性关联矩阵', fontproperties='