python - 使用 ARMA 的统计模型

Question

这里有点新，但试图让 statsmodel ARMA 预测工具起作用。我从 Yahoo 导入了一些股票数据，并让 ARMA 给我拟合参数。然而，当我使用预测代码时，我收到的只是一个我似乎无法弄清楚的错误列表。不太确定我在这里做错了什么:

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)

错误是:

---------------------------------------------------------------------------
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

在我看来像是一个错误。我会调查一下。

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

编辑:作为解决方法，您可以从 DataFrame 中删除 DatetimeIndex 并将其传递给 numpy 数组。它使预测在日期方面变得有点棘手，但在没有频率的情况下使用日期进行预测已经非常棘手，因此仅具有开始日期和结束日期基本上没有意义。

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)