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_two_consants(time_index):
tt = TimeTrend(constant=True, order=1)
dp = DeterministicProcess(
time_index, constant=True, additional_terms=[tt], drop=True
)
assert dp.in_sample().shape[1] == 2
dp2 = DeterministicProcess(time_index, additional_terms=[tt], drop=True)
pd.testing.assert_frame_equal(dp.in_sample(), dp2.in_sample())
def test_range_casting():
idx = np.arange(120)
dp = DeterministicProcess(
idx, constant=True, order=1, seasonal=True, period=12
)
idx = pd.RangeIndex(0, 120)
dp2 = DeterministicProcess(
idx, constant=True, order=1, seasonal=True, period=12
)
pd.testing.assert_frame_equal(dp.in_sample(), dp2.in_sample())
pd.testing.assert_frame_equal(dp.range(100, 150), dp2.range(100, 150))
def test_additional_terms(time_index):
add_terms = [TimeTrend(True, order=1)]
dp = DeterministicProcess(time_index, additional_terms=add_terms)
dp2 = DeterministicProcess(time_index, constant=True, order=1)
pd.testing.assert_frame_equal(dp.in_sample(), dp2.in_sample())
with pytest.raises(ValueError,
match="One or more terms in additional_terms"):
DeterministicProcess(time_index,
additional_terms=add_terms + add_terms)
with pytest.raises(ValueError,
match="One or more terms in additional_terms"):
DeterministicProcess(time_index,
constant=True,
order=1,
additional_terms=add_terms)
def check(self, dp, X):
from statsmodels.tsa.deterministic import (CalendarFourier,
DeterministicProcess)
y = load_average_sales()['2017']
fourier = CalendarFourier(freq='M', order=4)
dp = DeterministicProcess(
index=y.index,
constant=True,
order=1,
seasonal=True,
additional_terms=[fourier],
drop=True,
)
X_true = dp.in_sample()
import pandas as pd
assert all(
dp._index == y.index
), f"`index` argument to `DeterministicProcess` should be `y.index`. You gave {dp._index}."
assert dp._constant, f"`constant` argument to `DeterministicProcess` should be `True`. You gave {dp._constant}."
assert dp._order == 1, f"`order` argument to `DeterministicProcess` should be `1`. You gave {dp._order}."
assert dp._seasonal, f"`seasonal` argument to `DeterministicProcess` should be `True`. You gave {dp._seasonal}."
assert len(
dp._additional_terms
) == 1, f"`additional_terms` argument to `DeterministicProcess` should be `[fourier]`. You gave {dp._additional_terms}."
assert isinstance(
dp._additional_terms[0], CalendarFourier
), f"`additional_terms` argument to `DeterministicProcess` should be `[fourier]`. You gave {dp._additional_terms}."
assert dp._additional_terms[
0]._order == 4, f"`order` argument to `CalendarFourier` should be `4`. You gave {dp._additional_terms[0]._order}."
assert isinstance(
dp._additional_terms[0]._freq, pd.offsets.MonthEnd
), f"`freq` argument to `CalendarFourier` should be `'M'`."
assert dp._drop, f"`additional_terms` argument to `DeterministicProcess` should be `True`. You gave {dp._drop}."
assert_equal(X, X_true, 'X')
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 process requires an index, which is the index of the full-sample (or
# in-sample).
#
# First, we initialize a deterministic process with a constant, a linear
# time trend, and a 5-period seasonal term. The `in_sample` method returns
# 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