振幅和成交量的关系

# coding=utf-8
from pandas import Series,DataFrame
import pandas as pd
import numpy as np
from datetime import datetime
import tushare as ts
from sklearn import datasets, linear_model

df=pd.read_csv('data.csv')
X=df[['open','volume']]
y=df['high']-df['low']

from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)

from sklearn.linear_model import LinearRegression
linreg = LinearRegression()
linreg.fit(X_train,y_train)

print linreg.intercept_
print linreg.coef_

print "振幅=%f+%f价格+%f成交量"%(linreg.intercept_,linreg.coef_[0],linreg.coef_[1])

#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))

-0.542840729241
[  2.91283661e-02   1.89720767e-05]
振幅=-0.542841+0.029128价格+0.000019成交量
MSE:
 
1.16361481737
RMSE:
 
1.07870979293