import pandas as pd
data = pd.read_csv('house_price.csv')  # 修正了pdread_csv为pd.read_csv，变量名date改为data
print("数据集中的前10条记录:")
print(data.head(10))
print("")

from matplotlib import pyplot as plt
fig = plt.figure(figsize=(20,5))

fig1 = plt.subplot(131)
plt.scatter(data.loc[:,'面积'], data.loc[:,'价格'])
plt.title('Price VS Size')

fig2 = plt.subplot(132)
plt.scatter(data.loc[:,'人均收入'], data.loc[:,'价格'])
plt.title('Price VS Income')

fig3 = plt.subplot(133)
plt.scatter(data.loc[:,'平均房龄'], data.loc[:,'价格'])
plt.title('Price VS House_age')
plt.show()

import numpy as np
X = data.drop(['价格'], axis=1)
y = data.loc[:,'价格']

X = np.array(X)
y = np.array(y)
print(X.shape, y.shape)
y = y.reshape(-1, 1)
print(X.shape, y.shape)

from sklearn.linear_model import LinearRegression
model_multi = LinearRegression()
model_multi.fit(X, y)

# 测试数据：面积150，人均收入60000，平均房龄5
X_test = np.array([[150, 60000, 5]])
y_test_predict = model_multi.predict(X_test)
print(f"预测价格: {y_test_predict}")