def test_determintic_term_equiv(index):
base = DeterministicProcess(pd.RangeIndex(0, 200), constant=True, order=2)
dp = DeterministicProcess(index, constant=True, order=2)
np.testing.assert_array_equal(base.in_sample(), dp.in_sample())
np.testing.assert_array_equal(base.out_of_sample(37), dp.out_of_sample(37))
np.testing.assert_array_equal(base.range(200, 237), dp.range(200, 237))
np.testing.assert_array_equal(base.range(50, 150), dp.range(50, 150))
np.testing.assert_array_equal(base.range(50, 250), dp.range(50, 250))
def test_drop():
index = pd.RangeIndex(0, 200)
dummy = DummyTerm()
str(dummy)
assert dummy != TimeTrend()
dp = DeterministicProcess(index, additional_terms=[dummy], drop=True)
in_samp = dp.in_sample()
assert in_samp.shape == (200, 4)
oos = dp.out_of_sample(37)
assert oos.shape == (37, 4)
assert list(oos.columns) == list(in_samp.columns)
valid = ("const", "trend", "dummy", "normal")
for valid_col in valid:
assert sum([1 for col in oos if valid_col in col]) == 1
def test_deterministic_process(time_index, constant, order, seasonal, fourier,
period, drop):
if seasonal and fourier:
return
dp = DeterministicProcess(
time_index,
constant=constant,
order=order,
seasonal=seasonal,
fourier=fourier,
period=period,
drop=drop,
)
terms = dp.in_sample()
pd.testing.assert_index_equal(terms.index, time_index)
terms = dp.out_of_sample(23)
assert isinstance(terms, pd.DataFrame)
# the full set of values that match the index.
from statsmodels.tsa.deterministic import DeterministicProcess
index = pd.RangeIndex(0, 100)
det_proc = DeterministicProcess(index,
constant=True,
order=1,
seasonal=True,
period=5)
det_proc.in_sample()
# The `out_of_sample` returns the next `steps` values after the end of the
# in-sample.
det_proc.out_of_sample(15)
# `range(start, stop)` can also be used to produce the deterministic terms
# over any range including in- and out-of-sample.
#
# ### Notes
#
# * When the index is a pandas `DatetimeIndex` or a `PeriodIndex`, then
# `start` and `stop` can be date-like (strings, e.g., "2020-06-01", or
# Timestamp) or integers.
# * `stop` is always included in the range. While this is not very
# Pythonic, it is needed since both statsmodels and Pandas include `stop`
# when working with date-like slices.
det_proc.range(190, 210)