def test_burg():
rnd = np.random.RandomState(12345)
e = rnd.randn(10001)
y = e[1:] + 0.5 * e[:-1]
# R, ar.burg
expected = [[0.3909931], [0.4602607, -0.1771582],
[0.47473245, -0.21475602, 0.08168813],
[0.4787017, -0.2251910, 0.1047554, -0.0485900],
[0.47975462, -0.22746106, 0.10963527, -0.05896347, 0.02167001]]
for i in range(1, 6):
ar, _ = burg(y, i)
assert_allclose(ar, expected[i - 1], atol=1e-6)
as_nodemean, _ = burg(1 + y, i, False)
assert np.all(ar != as_nodemean)
def test_burg():
rnd = np.random.RandomState(12345)
e = rnd.randn(10001)
y = e[1:] + 0.5 * e[:-1]
# R, ar.burg
expected = [
[0.3909931],
[0.4602607, -0.1771582],
[0.47473245, -0.21475602, 0.08168813],
[0.4787017, -0.2251910, 0.1047554, -0.0485900],
[0.47975462, - 0.22746106, 0.10963527, -0.05896347, 0.02167001]
]
for i in range(1, 6):
ar, _ = burg(y, i)
assert_allclose(ar, expected[i - 1], atol=1e-6)
as_nodemean, _ = burg(1 + y, i, False)
assert np.all(ar != as_nodemean)
def test_burg_errors():
with pytest.raises(ValueError):
burg(np.ones((100, 2)))
with pytest.raises(ValueError):
burg(np.random.randn(100), 0)
with pytest.raises(ValueError):
burg(np.random.randn(100), 'apple')
def test_burg_errors():
with pytest.raises(ValueError):
burg(np.ones((100, 2)))
with pytest.raises(ValueError):
burg(np.random.randn(100), 0)
with pytest.raises(ValueError):
burg(np.random.randn(100), 'apple')
def obtain_arCoeff(self, signal) -> np.ndarray:
arCoeff = np.array([])
for col in signal.columns:
val, _ = burg(signal[col], order=4)
arCoeff = np.hstack((arCoeff, val))
return arCoeff
def burg(endog, ar_order=0, demean=True):
"""
Estimate AR parameters using Burg technique.
Parameters
----------
endog : array_like or SARIMAXSpecification
Input time series array, assumed to be stationary.
ar_order : int, optional
Autoregressive order. Default is 0.
demean : bool, optional
Whether to estimate and remove the mean from the process prior to
fitting the autoregressive coefficients.
Returns
-------
parameters : SARIMAXParams object
Contains the parameter estimates from the final iteration.
other_results : Bunch
Includes one component, `spec`, which is the `SARIMAXSpecification`
instance corresponding to the input arguments.
Notes
-----
The primary reference is [1]_, section 5.1.2.
This procedure assumes that the series is stationary.
This function is a light wrapper around `statsmodels.linear_model.burg`.
References
----------
.. [1] Brockwell, Peter J., and Richard A. Davis. 2016.
Introduction to Time Series and Forecasting. Springer.
"""
spec = SARIMAXSpecification(endog, ar_order=ar_order)
endog = spec.endog
# Workaround for statsmodels.tsa.stattools.pacf_burg which doesn't work
# on integer input
# TODO: remove when possible
if np.issubdtype(endog.dtype, np.dtype(int)):
endog = endog * 1.0
if not spec.is_ar_consecutive:
raise ValueError('Burg estimation unavailable for models with'
' seasonal or otherwise non-consecutive AR orders.')
p = SARIMAXParams(spec=spec)
if ar_order == 0:
p.sigma2 = np.var(endog)
else:
p.ar_params, p.sigma2 = linear_model.burg(endog,
order=ar_order,
demean=demean)
# Construct other results
other_results = Bunch({
'spec': spec,
})
return p, other_results
