def test_basic(data):
is_pandas = isinstance(data[0], pd.Series)
pred = PredictionResults(data[0], data[1])
np.testing.assert_allclose(data[0], pred.predicted_mean)
np.testing.assert_allclose(data[1], pred.var_pred_mean)
if is_pandas:
assert isinstance(pred.predicted_mean, pd.Series)
assert isinstance(pred.var_pred_mean, pd.Series)
assert isinstance(pred.se_mean, pd.Series)
frame = pred.summary_frame()
assert isinstance(frame, pd.DataFrame)
assert list(
frame.columns == ["mean", "mean_se", "mean_ci_lower", "mean_ci_upper"])
def get_prediction(
self,
start: Optional[DateLike] = None,
end: Optional[DateLike] = None,
dynamic: Union[bool, DateLike] = False,
**kwargs: Dict[str, Any],
):
"""
In-sample prediction and out-of-sample forecasting
Parameters
----------
start : int, str, or datetime, optional
Zero-indexed observation number at which to start forecasting,
i.e., the first forecast is start. Can also be a date string to
parse or a datetime type. Default is the the zeroth observation.
end : int, str, or datetime, optional
Zero-indexed observation number at which to end forecasting, i.e.,
the last forecast is end. Can also be a date string to
parse or a datetime type. However, if the dates index does not
have a fixed frequency, end must be an integer index if you
want out of sample prediction. Default is the last observation in
the sample.
dynamic : bool, int, str, or datetime, optional
Integer offset relative to `start` at which to begin dynamic
prediction. Can also be an absolute date string to parse or a
datetime type (these are not interpreted as offsets).
Prior to this observation, true endogenous values will be used for
prediction; starting with this observation and continuing through
the end of prediction, forecasted endogenous values will be used
instead.
**kwargs
Additional arguments may required for forecasting beyond the end
of the sample. These arguments are passed into the time series
model results' ``get_prediction`` method.
Returns
-------
PredictionResults
PredictionResults instance containing in-sample predictions,
out-of-sample forecasts, and prediction intervals.
"""
pred = self._model_result.get_prediction(start=start,
end=end,
dynamic=dynamic,
**kwargs)
seasonal_prediction = self._get_seasonal_prediction(
start, end, dynamic)
mean = pred.predicted_mean + seasonal_prediction
return PredictionResults(
mean,
pred.var_pred_mean,
dist="norm",
row_labels=pred.row_labels,
)
def test_dist(data, dist):
df = 10 if dist == "t" else None
pred = PredictionResults(data[0], data[1], dist=dist, df=df)
basic = PredictionResults(data[0], data[1])
ci = pred.conf_int()
basic_ci = basic.conf_int()
if dist == "t":
assert np.all(np.asarray(ci != basic_ci))
else:
assert np.all(np.asarray(ci == basic_ci))