def test_oob_sarimax():
xreg = rs.rand(wineind.shape[0], 2)
fit = ARIMA(order=(1, 1, 1),
seasonal_order=(0, 1, 1, 12),
out_of_sample_size=15).fit(y=wineind, exogenous=xreg)
fit_no_oob = ARIMA(
order=(1, 1, 1), seasonal_order=(0, 1, 1, 12),
out_of_sample_size=0, suppress_warnings=True)\
.fit(y=wineind[:-15], exogenous=xreg[:-15, :])
# now assert some of the same things here that we did in the former test
oob = fit.oob()
# compare scores:
scoring = get_callable(fit_no_oob.scoring, VALID_SCORING)
no_oob_preds = fit_no_oob.predict(n_periods=15, exogenous=xreg[-15:, :])
assert np.allclose(oob, scoring(wineind[-15:], no_oob_preds), rtol=1e-2)
# show params are still the same
assert np.allclose(fit.params(), fit_no_oob.params(), rtol=1e-2)
# show we can add the new samples and get the exact same forecasts
xreg_test = rs.rand(5, 2)
fit_no_oob.add_new_observations(wineind[-15:], xreg[-15:, :])
assert np.allclose(fit.predict(5, xreg_test),
fit_no_oob.predict(5, xreg_test),
rtol=1e-2)
# Show we can get a confidence interval out here
preds, conf = fit.predict(5, xreg_test, return_conf_int=True)
assert all(isinstance(a, np.ndarray) for a in (preds, conf))
def test_with_oob():
# show we can fit with CV (kinda)
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=10).fit(y=hr)
assert not np.isnan(arima.oob()) # show this works
# show we can fit if ooss < 0 and oob will be nan
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=-1).fit(y=hr)
assert np.isnan(arima.oob())
# can we do one with an exogenous array, too?
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=10).fit(y=hr,
exogenous=rs.rand(hr.shape[0], 4))
assert not np.isnan(arima.oob())
def test_with_oob():
# show we can fit with CV (kinda)
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=10).fit(y=hr)
assert not np.isnan(arima.oob()) # show this works
# show we can fit if ooss < 0 and oob will be nan
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=-1).fit(y=hr)
assert np.isnan(arima.oob())
# This will raise since n_steps is not an int
assert_raises(TypeError, arima.predict, n_periods="5")
# But that we CAN forecast with an int...
_ = arima.predict(n_periods=5)
# Show we fail if cv > n_samples
assert_raises(ValueError,
ARIMA(order=(2, 1, 2), out_of_sample_size=1000).fit, hr)
def test_oob_for_issue_28():
# Continuation of above: can we do one with an exogenous array, too?
xreg = rs.rand(hr.shape[0], 4)
arima = ARIMA(order=(2, 1, 2),
suppress_warnings=True,
out_of_sample_size=10).fit(y=hr, exogenous=xreg)
oob = arima.oob()
assert not np.isnan(oob)
# Assert that the endog shapes match. First is equal to the original,
# and the second is the differenced array, with original shape - d.
assert np.allclose(arima.arima_res_.data.endog, hr, rtol=1e-2)
assert arima.arima_res_.model.endog.shape[0] == hr.shape[0] - 1
# Now assert the same for exog
assert np.allclose(arima.arima_res_.data.exog, xreg, rtol=1e-2)
assert arima.arima_res_.model.exog.shape[0] == xreg.shape[0] - 1
# Compare the OOB score to an equivalent fit on data - 10 obs, but
# without any OOB scoring, and we'll show that the OOB scoring in the
# first IS in fact only applied to the first (train - n_out_of_bag)
# samples
arima_no_oob = ARIMA(
order=(2, 1, 2), suppress_warnings=True,
out_of_sample_size=0)\
.fit(y=hr[:-10], exogenous=xreg[:-10, :])
scoring = get_callable(arima_no_oob.scoring, VALID_SCORING)
preds = arima_no_oob.predict(n_periods=10, exogenous=xreg[-10:, :])
assert np.allclose(oob, scoring(hr[-10:], preds), rtol=1e-2)
# Show that the model parameters are exactly the same
xreg_test = rs.rand(5, 4)
assert np.allclose(arima.params(), arima_no_oob.params(), rtol=1e-2)
# Now assert on the forecast differences.
with_oob_forecasts = arima.predict(n_periods=5, exogenous=xreg_test)
no_oob_forecasts = arima_no_oob.predict(n_periods=5, exogenous=xreg_test)
assert_raises(AssertionError, assert_array_almost_equal,
with_oob_forecasts, no_oob_forecasts)
# But after we update the no_oob model with the latest data, we should
# be producing the same exact forecasts
# First, show we'll fail if we try to add observations with no exogenous
assert_raises(ValueError, arima_no_oob.add_new_observations, hr[-10:],
None)
# Also show we'll fail if we try to add mis-matched shapes of data
assert_raises(ValueError, arima_no_oob.add_new_observations, hr[-10:],
xreg_test)
# Show we fail if we try to add observations with a different dim exog
assert_raises(ValueError, arima_no_oob.add_new_observations, hr[-10:],
xreg_test[:, 2])
# Actually add them now, and compare the forecasts (should be the same)
arima_no_oob.add_new_observations(hr[-10:], xreg[-10:, :])
assert np.allclose(with_oob_forecasts,
arima_no_oob.predict(n_periods=5, exogenous=xreg_test),
rtol=1e-2)