Bug of adfuller test with zipline

Question

I've tested ADF with stattools, my code is

import statsmodels.tsa.stattools as ts  
from datetime import datetime

import zipline  
from zipline import TradingAlgorithm  
from zipline.api import order_target, record, symbol, history, add_history

data = get_pricing(['AAPL'],start_date='2015-01-13',end_date = '2015-02-13',frequency='daily')  
result = ts.adfuller(data.price.values,1)

However, I've got the following error,

ValueError                                Traceback (most recent call last)  
<ipython-input-45-44774ff05797> in <module>()  
      7  
      8 data = get_pricing(['AAPL'],start_date='2015-01-13',end_date = '2015-02-13',frequency='daily')  
----> 9 result = ts.adfuller(data.price.values,1)

/usr/local/lib/python2.7/dist-packages/statsmodels/tsa/stattools.pyc in adfuller(x, maxlag, regression, autolag, store, regresults)
    209  
    210     xdiff = np.diff(x)  
--> 211     xdall = lagmat(xdiff[:, None], maxlag, trim='both', original='in')  
    212     nobs = xdall.shape[0]  # pylint: disable=E1103  
    213 

/usr/local/lib/python2.7/dist-packages/statsmodels/tsa/tsatools.pyc in lagmat(x, maxlag, trim, original)
    322     if x.ndim == 1:  
    323         x = x[:,None]  
--> 324     nobs, nvar = x.shape  
    325     if original in ['ex','sep']:  
    326         dropidx = nvar

ValueError: too many values to unpack

I couldn't see the problem. I think the parameters of adfullter is ok.

Anyone could help?? Thanks a lot...

What's the shape of your `data.price.values`? From the traceback it looks like it's strictly larger than 2 dimensions, while the code can handle only 1-D or 2-D. (My guess is that this should be reported to the statsmodels issue tracker to raise a more informative error message if it's a shape mismatch.) — Josef, Jul 09 '15 at 21:43
Thanks for your reply, it's one dimension. For example, [[ 110.225]..... [ 127.08 ]]. I've already checked the dimension. — Lucas, Jul 09 '15 at 21:49
`[[ 110.225]..... [ 127.08 ]]` is 2-dim AFAICS, shape (nobs, 1). To check, try to ravel: `result = ts.adfuller(data.price.values.ravel(),1)` — Josef, Jul 09 '15 at 22:02

Bug of adfuller test with zipline

0 Answers0