# 导入库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# 导入数据
from sklearn.datasets import load_boston
boston = load_boston()

boston.data.shape

boston.feature_names

data = pd.DataFrame(boston.data)
data.columns = boston.feature_names
data.head(10)

# 在数据中添加“Price"(目标)列
boston.target.shape

data['Price'] = boston.target
data.head()

data.describe()

data.info()

# 输入数据
x = boston.data
# 输出数据
y = boston.target
# 将数据拆分为训练和测试数据集.
from sklearn.cross_validation import train_test_split
xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size =0.2,
                                                    random_state = 0)
print("xtrain shape : ", xtrain.shape)
print("xtest shape  : ", xtest.shape)
print("ytrain shape : ", ytrain.shape)
print("ytest shape  : ", ytest.shape)

# 将多元线性回归模型拟合到训练模型
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(xtrain, ytrain)
# 预测测试集结果
y_pred = regressor.predict(xtest)

# 绘制散点图以显示“ytrue"值与“y_pred"值
plt.scatter(ytest, y_pred, c = 'green')
plt.xlabel("Price: in $1000's")
plt.ylabel("Predicted value")
plt.title("True value vs predicted value : Linear Regression")
plt.show()

# Results of Linear Regression.
from sklearn.metrics import mean_squared_error
mse = mean_squared_error(ytest, y_pred)
print("Mean Square Error : ", mse)