线性回归模型（预测房价）

#线性回归档案

from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression
import pandas as pd
from sklearn.model_selection import train_test_split

# 读数据
boston = load_boston()
# print(boston)


X = boston['data'] # 数据集数据
y = boston['target'] # 数据集的标签

names = boston['feature_names']

# 将数据导入.xls文件中:
# df = pd.DataFrame(columns=names,data=X)
# df['label'] = y
# df.to_excel('boston.xls',index=False)


# 分测试集与训练集
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2)

# 建立线性回归模型
clf = LinearRegression().fit(X_train,y_train)

# print('回归系数',clf.coef_)
# print('截距',clf.intercept_)

# 预测训练集
y_predict = clf.predict(X_test)
print(y_predict[:5])
print(y_test[:5])

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
plt.figure(figsize=(10,6))
plt.plot(range(len(y_test)),y_test,color='blue',linewidth=1.5,linestyle='-')
plt.plot(range(len(y_test)),y_predict,color='hotpink',linewidth=1.5,linestyle='-.')

plt.plot(range(len(y_test)),(y_test-y_predict),color='k',linestyle=':')
plt.legend(['真实放假','预测房价','损耗'])
plt.show()