import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

from sklearn import datasets, linear_model

data = pd.read_csv('C://Users//leon//Desktop//CCPP.csv')  #导入数据

data.head()

data.shape

X = data[['AT', 'V', 'AP', 'RH']]           #用AT， V，AP和RH这4个列作为样本特征

y = data[['PE']]

from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)

print (X_train.shape)

print (y_train.shape)

print (X_test.shape)

print (y_test.shape)                         #训练

from sklearn.linear_model import LinearRegression

linreg = LinearRegression()                 #建立模型

linreg.fit(X_train, y_train)

print (linreg.intercept_)                #输出模型常量

print (linreg.coef_)                    #自变量系数

y_pred = linreg.predict(X_test)

from sklearn import metrics

print ("MSE:",metrics.mean_squared_error(y_test, y_pred))     # 通过MSE值进行模型检验

from sklearn.model_selection import cross_val_predict

predicted = cross_val_predict(linreg, X, y, cv=10)

fig, ax = plt.subplots()

ax.scatter(y, predicted)

ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)

ax.set_xlabel('Measured')

ax.set_ylabel('Predicted')

plt.show()   #作图观察