Я изучаю анализ данных временных рядов.Данные взяты с сайта - www.quandl.com .
Я использую модель ARIMA для прогнозирования будущих прогнозов.Тем не менее, я думаю, что я сделал ошибку в коде, но я не знаю, что я пропустил.Я проверил код, но это правильно, насколько я знаю.
Это мой код:
import quandl
import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.arima_model import ARIMA
data = quandl.get('EIA/PET_RWTC_D')
# converting the dataframe into series for Time Series Analysis
dataset = pd.Series(data = data['Value'], index = data.index)
# I am creating a hold_out_data. This data is removed from the training data. This is the test data.
hold_out_data = dataset['2019-09']
train_data = dataset.drop(dataset['2019-09'].index, axis = 0)
# ARIMA model to predict the hold out data
model = ARIMA(endog = train_data, order = (5, 1, 0)).fit(transparams = False)
# predicting the values for the dates 2019-09-02 to 2019-09-16.
prediction = model.predict('2019-09-02', '2019-09-16')
Ошибка появляется при попытке запустить последнюю строку:
prediction = model.predict('2019-09-02', '2019-09-16').
Полный вывод
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
TypeError: an integer is required
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2896 try:
-> 2897 return self._engine.get_loc(key)
2898 except KeyError:
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine._date_check_type()
KeyError: '2019-09-02'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
TypeError: an integer is required
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\datetimes.py in get_loc(self, key, method, tolerance)
1056 try:
-> 1057 return Index.get_loc(self, key, method, tolerance)
1058 except (KeyError, ValueError, TypeError):
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2898 except KeyError:
-> 2899 return self._engine.get_loc(self._maybe_cast_indexer(key))
2900 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine._date_check_type()
KeyError: '2019-09-02'
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 1567382400000000000
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2896 try:
-> 2897 return self._engine.get_loc(key)
2898 except KeyError:
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
KeyError: Timestamp('2019-09-02 00:00:00')
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 1567382400000000000
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\datetimes.py in get_loc(self, key, method, tolerance)
1069 stamp = stamp.tz_localize(self.tz)
-> 1070 return Index.get_loc(self, stamp, method, tolerance)
1071 except KeyError:
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2898 except KeyError:
-> 2899 return self._engine.get_loc(self._maybe_cast_indexer(key))
2900 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.DatetimeEngine.get_loc()
KeyError: Timestamp('2019-09-02 00:00:00')
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\base\tsa_model.py in _get_index_label_loc(self, key, base_index)
425 if not isinstance(key, (int, long, np.integer)):
--> 426 loc = self.data.row_labels.get_loc(key)
427 else:
~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\indexes\datetimes.py in get_loc(self, key, method, tolerance)
1071 except KeyError:
-> 1072 raise KeyError(key)
1073 except ValueError as e:
KeyError: '2019-09-02'
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
<ipython-input-366-2fff9dcc06e2> in <module>
----> 1 prediction = model.predict('2019-09-02', '2019-09-16')
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\base\wrapper.py in wrapper(self, *args, **kwargs)
93 obj = data.wrap_output(func(results, *args, **kwargs), how[0], how[1:])
94 elif how:
---> 95 obj = data.wrap_output(func(results, *args, **kwargs), how)
96 return obj
97
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\arima_model.py in predict(self, start, end, exog, typ, dynamic)
1816 def predict(self, start=None, end=None, exog=None, typ='linear',
1817 dynamic=False):
-> 1818 return self.model.predict(self.params, start, end, exog, typ, dynamic)
1819 predict.__doc__ = _arima_results_predict
1820
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\arima_model.py in predict(self, params, start, end, exog, typ, dynamic)
1163 if isinstance(start, (string_types, datetime)):
1164 # start = _index_date(start, self.data.dates)
-> 1165 start, _, _ = self._get_index_label_loc(start)
1166 if isinstance(start, slice):
1167 start = start.start
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\base\tsa_model.py in _get_index_label_loc(self, key, base_index)
456 index_was_expanded = False
457 except:
--> 458 raise e
459 return loc, index, index_was_expanded
460
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\base\tsa_model.py in _get_index_label_loc(self, key, base_index)
420 try:
421 loc, index, index_was_expanded = (
--> 422 self._get_index_loc(key, base_index))
423 except KeyError as e:
424 try:
~\Anaconda3\envs\tensorflow\lib\site-packages\statsmodels\tsa\base\tsa_model.py in _get_index_loc(self, key, base_index)
370 # (as of Pandas 0.22)
371 except (IndexError, ValueError) as e:
--> 372 raise KeyError(str(e))
373 loc = key
374 else:
KeyError: 'only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices'
Я проверил, и в StackOverflow есть много ответов, но я не могу найти ответа относительно анализа временных рядов.Большинство ответов состоит в том, чтобы изменить индекс на int32 с float64. Однако мой индекс - DateTime, и я не могу изменить его на целое число.
Может ли кто-нибудь помочь мне, где я допустил ошибку здесь?
Примечание. Возможно, вы захотите получить ключ API для доступа к наборам данных из quandl.
Заранее спасибо:)