StatsModels 多元回归

未分类

import numpy as np
import pandas as pd
import statsmodels.api as sm
from statsmodels import regression
import matplotlib.pyplot as plt
import tushare as ts

asset1 = ts.get_k_data('000001', start='2016-01-01', end='2016-12-31', ktype='D',autype='qfq')
asset1.index = pd.to_datetime(asset1['date'], format='%Y-%m-%d')
asset1 = asset1['close']
asset2 = ts.get_k_data('000005', start='2016-01-01', end='2016-12-31', ktype='D',autype='qfq')
asset2.index = pd.to_datetime(asset2['date'], format='%Y-%m-%d')
asset2 = asset2['close']
benchmark = ts.get_hist_data('sh', start='2016-01-01', end='2016-12-31', ktype='D')[::-1]
benchmark = benchmark['close']
new = pd.concat([asset1, asset2, benchmark],join='inner', axis=1)
new.columns = ['asset1', 'asset2', 'benchmark']

# Run multiple linear regression using asset2 and SPY as independent variables
mlr = regression.linear_model.OLS(new['asset1'], sm.add_constant(np.column_stack((new['asset2'], new['benchmark'])))).fit()
prediction = mlr.params[0] + mlr.params[1]*asset2 + mlr.params[2]*new['benchmark']
prediction.name = 'Prediction'
print 'MLR beta of asset2:', mlr.params[1], '\nMLR beta of sz:', mlr.params[2]

new['asset1'].plot()
prediction.plot(color='y')
plt.xlabel('Price')
plt.legend()
plt.show()

策略多元回归
不用品种的MA策略多元回归

BrenchMark = MA200