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_intercept(order, seasonal):
n_params = None
for intercept in (False, True):
modl = ARIMA(order=order,
seasonal_order=seasonal,
with_intercept=intercept).fit(lynx)
if not intercept: # first time
n_params = modl.params().shape[0]
else:
# With an intercept, should be 1 more
assert modl.params().shape[0] == n_params + 1
def test_the_r_src():
# this is the test the R code provides
fit = ARIMA(order=(2, 0, 1), trend='c', suppress_warnings=True).fit(abc)
# the R code's AIC = ~135
assert abs(135 - fit.aic()) < 1.0
# the R code's AICc = ~ 137
assert abs(137 - fit.aicc()) < 1.0
# the R code's BIC = ~145
assert abs(145 - fit.bic()) < 1.0
# R's coefficients:
# ar1 ar2 ma1 mean
# -0.6515 -0.2449 0.8012 5.0370
# note that statsmodels' mean is on the front, not the end.
params = fit.params()
assert_almost_equal(params, np.array([5.0370, -0.6515, -0.2449, 0.8012]),
decimal=2)
# > fit = forecast::auto.arima(abc, max.p=5, max.d=5,
# max.q=5, max.order=100, stepwise=F)
fit = auto_arima(abc, max_p=5, max_d=5, max_q=5, max_order=100,
seasonal=False, trend='c', suppress_warnings=True,
error_action='ignore')
# this differs from the R fit with a slightly higher AIC...
assert abs(137 - fit.aic()) < 1.0 # R's is 135.28
def test_oob_sarimax():
xreg = rs.rand(wineind.shape[0], 2)
fit = ARIMA(order=(1, 1, 1),
seasonal_order=(0, 1, 1, 12),
maxiter=5,
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,
maxiter=5,
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 = val.get_scoring_metric(fit_no_oob.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 no longer the same
assert not 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.update(wineind[-15:], xreg[-15:, :])
assert np.allclose(fit.predict(5, xreg_test),
fit_no_oob.predict(5, xreg_test),
rtol=1e-2)
# And also the params should be close now after updating
assert np.allclose(fit.params(), fit_no_oob.params())
# 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_basic_arma():
arma = ARIMA(order=(0, 0, 0), suppress_warnings=True)
preds = arma.fit_predict(y) # fit/predict for coverage
# No OOB, so assert none
assert arma.oob_preds_ is None
# test some of the attrs
assert_almost_equal(arma.aic(), 11.201, decimal=3) # equivalent in R
# intercept is param 0
intercept = arma.params()[0]
assert_almost_equal(intercept, 0.441, decimal=3) # equivalent in R
assert_almost_equal(arma.aicc(), 11.74676, decimal=5)
assert_almost_equal(arma.bic(), 13.639060053303311, decimal=5)
# get predictions
expected_preds = np.array([0.44079876, 0.44079876, 0.44079876,
0.44079876, 0.44079876, 0.44079876,
0.44079876, 0.44079876, 0.44079876,
0.44079876])
# generate predictions
assert_array_almost_equal(preds, expected_preds)
# Make sure we can get confidence intervals
expected_intervals = np.array([
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139],
[-0.10692387, 0.98852139]
])
_, intervals = arma.predict(n_periods=10, return_conf_int=True,
alpha=0.05)
assert_array_almost_equal(intervals, expected_intervals)
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)