用 Scikit-Learn 和 Pandas 学习线性回归

代码如下：

#encoding:utf-8
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import datasets,linear_model

data=pd.read_csv('ccpp1.csv')#导入数据
#print(data.head())#打印前五行数据
print(data.shape)#查看数据的维度

X=data[['AT','V','AP','RH']]
print(X.head())#打印X的前五行数据

y=data[['PE']]
print(y.head())#打印y的前五行数据

#对数据进行分类，分为训练数据和测试数据
from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=1)
#查看训练数据和测试数据的维度
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)

#使用最小二乘法来训练模型
from sklearn.linear_model import LinearRegression
linreg=LinearRegression()
linreg.fit(X_train,y_train)
#打印模型系数结果
print(linreg.intercept_)
print(linreg.coef_)

#模型评价
#模型拟合测试集
y_pred=linreg.predict(X_test)
from sklearn import metrics
#用scikit-learn计算MSE
print("MSE:",metrics.mean_squared_error(y_test,y_pred))
#用scikit-learn计算RMSE
print("RMSE:",np.sqrt(metrics.mean_squared_error(y_test,y_pred)))

#使用交叉验证来持续优化模型
X=data[['AT','V','AP','RH']]
y=data[['PE']]
from sklearn.model_selection import cross_val_predict
predicted=cross_val_predict(linreg,X,y,cv=10)
#用scikit-learn计算MSE
print("MSE:",metrics.mean_squared_error(y,predicted))
#用scikit-learn计算RMSE
print("RMSE:",np.sqrt(metrics.mean_squared_error(y,predicted)))

#画图
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('Predicter')
plt.show()

运行效果图如下：