Statsmodel using ARMA

Question

A bit new here but trying to get a statsmodel ARMA prediction tool to work. I've imported some stock data from Yahoo and gotten the ARMA to give me fitting parameters. However when I use the predict code all I receive is a list of errors that I don't seem to be able to figure out. Not quite sure what I'm doing wrong here:

import pandas
import statsmodels.tsa.api as tsa
from pandas.io.data import DataReader

start = pandas.datetime(2013,1,1)
end = pandas.datetime.today()

data = DataReader('GOOG','yahoo')
arma =tsa.ARMA(data['Close'], order =(2,2))
results= arma.fit()
results.predict(start=start,end=end)

The errors are:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
C:\Windows\system32\<ipython-input-84-25a9b6bc631d> in <module>()
     13 results= arma.fit()
     14 results.summary()
---> 15 results.predict(start=start,end=end)

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\base\wrapp
er.pyc in wrapper(self, *args, **kwargs)
     88         results = object.__getattribute__(self, '_results')
     89         data = results.model.data
---> 90         return data.wrap_output(func(results, *args, **kwargs), how)
     91
     92     argspec = inspect.getargspec(func)

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\arima_
model.pyc in predict(self, start, end, exog, dynamic)
   1265
   1266         """
-> 1267         return self.model.predict(self.params, start, end, exog, dynamic
)
   1268
   1269     def forecast(self, steps=1, exog=None, alpha=.05):

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\arima_
model.pyc in predict(self, params, start, end, exog, dynamic)
    497
    498         # will return an index of a date

--> 499         start = self._get_predict_start(start, dynamic)
    500         end, out_of_sample = self._get_predict_end(end, dynamic)
    501         if out_of_sample and (exog is None and self.k_exog > 0):

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\arima_
model.pyc in _get_predict_start(self, start, dynamic)
    404             #elif 'mle' not in method or dynamic: # should be on a date

    405             start = _validate(start, k_ar, k_diff, self.data.dates,
--> 406                               method)
    407             start = super(ARMA, self)._get_predict_start(start)
    408         _check_arima_start(start, k_ar, k_diff, method, dynamic)

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\arima_
model.pyc in _validate(start, k_ar, k_diff, dates, method)
    160     if isinstance(start, (basestring, datetime)):
    161         start_date = start
--> 162         start = _index_date(start, dates)
    163         start -= k_diff
    164     if 'mle' not in method and start < k_ar - k_diff:

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\base\d
atetools.pyc in _index_date(date, dates)
     37         freq = _infer_freq(dates)
     38         # we can start prediction at the end of endog

---> 39         if _idx_from_dates(dates[-1], date, freq) == 1:
     40             return len(dates)
     41

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\base\d
atetools.pyc in _idx_from_dates(d1, d2, freq)
     70         from pandas import DatetimeIndex
     71         return len(DatetimeIndex(start=d1, end=d2,
---> 72                                  freq = _freq_to_pandas[freq])) - 1
     73     except ImportError, err:
     74         from pandas import DateRange

D:\Python27\lib\site-packages\statsmodels-0.5.0-py2.7.egg\statsmodels\tsa\base\d
atetools.pyc in __getitem__(self, key)
     11         # being lazy, don't want to replace dictionary below

     12         def __getitem__(self, key):
---> 13             return get_offset(key)
     14     _freq_to_pandas = _freq_to_pandas_class()
     15 except ImportError, err:

D:\Python27\lib\site-packages\pandas\tseries\frequencies.pyc in get_offset(name)

    484     """
    485     if name not in _dont_uppercase:
--> 486         name = name.upper()
    487
    488         if name in _rule_aliases:

AttributeError: 'NoneType' object has no attribute 'upper'

Answer 1

Looks like a bug to me. I'll look into it.

https://github.com/statsmodels/statsmodels/issues/712

Edit: As a workaround, you can just drop the DatetimeIndex from the DataFrame and pass it the numpy array. It makes prediction a little trickier date-wise, but it's already pretty tricky to use dates for prediction when there is no frequency, so just having the starting and ending dates is essentially meaningless.

import pandas
import statsmodels.tsa.api as tsa
from pandas.io.data import DataReader
import pandas

data = DataReader('GOOG','yahoo')
dates = data.index

# start at a date on the index
start = dates.get_loc(pandas.datetools.parse("1-2-2013"))
end = start + 30 # "steps"

# NOTE THE .values
arma =tsa.ARMA(data['Close'].values, order =(2,2))
results= arma.fit()
results.predict(start, end)