if self.suppress_warnings:
with warnings.catch_warnings(record=False):
warnings.simplefilter("ignore")
fit, self.arima_res_ = _fit_wrapper()
else:
fit, self.arima_res_ = _fit_wrapper()
// Set df_model attribute for SARIMAXResults object
sm_compat.bind_df_model(fit, self.arima_res_)
// if the model is fit with an exogenous array, it must
// be predicted with one as well.
self.fit_with_exog_ = exogenous is not None
// now make a forecast if we"re validating to compute the
// out-of-sample score
if cv_samples is not None:
// get the predictions (use self.predict, which calls forecast
// from statsmodels internally)
pred = self.predict(n_periods=cv, exogenous=cv_exog)
self.oob_ = scoring(cv_samples, pred, **self.scoring_args)
// If we compute out of sample scores, we have to now update the
// observed time points so future forecasts originate from the end
// of our y vec
self.add_new_observations(cv_samples, cv_exog)
else:
self.oob_ = np.nan
// Save nobs since we might change it later if using OOB
self.nobs_ = y.shape[0]
// As of version 0.7.2, start saving the version with the model so
// we can track changes over time.
After Change
self.pkg_version_ = pmdarima.__version__
return self
def fit(self, y, exogenous=None, **fit_args):
Fit an ARIMA to a vector, ``y``, of observations with an
optional matrix of ``exogenous`` variables.
Parameters
----------
y : array-like or iterable, shape=(n_samples,)
The time-series to which to fit the ``ARIMA`` estimator. This may
either be a Pandas ``Series`` object (statsmodels can internally
use the dates in the index), or a numpy array. This should be a
one-dimensional array of floats, and should not contain any
``np.nan`` or ``np.inf`` values.
exogenous : array-like, shape=[n_obs, n_vars], optional (default=None)
An optional 2-d array of exogenous variables. If provided, these
variables are used as additional features in the regression
operation. This should not include a constant or trend. Note that
if an ``ARIMA`` is fit on exogenous features, it must be provided
exogenous features for making predictions.
**fit_args : dict or kwargs
Any keyword arguments to pass to the statsmodels ARIMA fit.
y = c1d(check_array(y, ensure_2d=False, force_all_finite=False,
copy=True, dtype=DTYPE)) // type: np.ndarray
n_samples = y.shape[0]
// if exog was included, check the array...
if exogenous is not None:
exogenous = check_array(exogenous, ensure_2d=True,
force_all_finite=False,
copy=False, dtype=DTYPE)
// determine the CV args, if any
cv = self.out_of_sample_size
scoring = get_callable(self.scoring, VALID_SCORING)
// don"t allow negative, don"t allow > n_samples
cv = max(cv, 0)
// if cv is too big, raise
if cv >= n_samples:
raise ValueError("out-of-sample size must be less than number "
"of samples!")
// If we want to get a score on the out-of-sample, we need to trim
// down the size of our y vec for fitting. Addressed due to Issue /ቸ
cv_samples = None
cv_exog = None
if cv:
cv_samples = y[-cv:]
y = y[:-cv]
// This also means we have to address the exogenous matrix
if exogenous is not None:
cv_exog = exogenous[-cv:, :]
exogenous = exogenous[:-cv, :]
// Internal call
self._fit(y, exogenous, **fit_args)
// now make a forecast if we"re validating to compute the
// out-of-sample score
if cv_samples is not None:
