def test_emd_FIXE(self):
T = np.linspace(0, 1, 100)
c = np.sin(9 * 2 * np.pi * T)
offset = 4
S = c + offset
emd = EMD()
# Default state: converge
self.assertTrue(emd.FIXE == 0)
self.assertTrue(emd.FIXE_H == 0)
# Set 1 iteration per each sift,
# same as removing offset
FIXE = 1
emd.FIXE = FIXE
# Check flags correctness
self.assertTrue(emd.FIXE == FIXE)
self.assertTrue(emd.FIXE_H == 0)
# Extract IMFs
IMFs = emd.emd(S)
# Check that IMFs are correct
self.assertTrue(np.allclose(IMFs[0], c))
self.assertTrue(np.allclose(IMFs[1], offset))
def test_emd_FIXE(self):
T = np.linspace(0, 1, 100)
c = np.sin(9*2*np.pi*T)
offset = 4
S = c + offset
emd = EMD()
# Default state: converge
self.assertTrue(emd.FIXE==0)
self.assertTrue(emd.FIXE_H==0)
# Set 1 iteration per each sift,
# same as removing offset
FIXE = 1
emd.FIXE = FIXE
# Check flags correctness
self.assertTrue(emd.FIXE==FIXE)
self.assertTrue(emd.FIXE_H==0)
# Extract IMFs
IMFs = emd.emd(S)
# Check that IMFs are correct
self.assertTrue(np.allclose(IMFs[0], c))
self.assertTrue(np.allclose(IMFs[1], offset))
def emd_csi(csi, imfn=10):
# Execute EMD on signal
emd = EMD()
emd.FIXE = 10
IMF = emd(csi)
csi_emd = np.zeros((csi.shape[0], imfn))
for n, imf in enumerate(IMF):
if n < imfn:
csi_emd[:, n - 1] = imf
return csi_emd
def test_max_iteration_flag(self):
S = np.random.random(200)
emd = EMD()
emd.MAX_ITERATION = 10
emd.FIXE = 20
imfs = emd.emd(S)
# There's not much to test, except that it doesn't fail.
# With low MAX_ITERATION value for random signal it's
# guaranteed to have at least 2 imfs.
self.assertTrue(imfs.shape[0]>1)
def _emd(self, data, label):
f_0 = self._random_pick(label)
d = load(f_0)
if self.pretransform is not None:
d = self.pretransform(d)
data, d = match_length(data, d)
emd = EMD()
emd.FIXE = 5
imf_0 = emd(data, max_imf=5)
imf_1 = emd(d, max_imf=5)
imf = [*imf_0[:3], *imf_1[3:]]
data = np.sum(imf, 0)
return data
def test_EMD_max_execution_time(self):
t_min, t_max = 0, 1
N = 100
T = np.linspace(t_min, t_max, N)
all_test_signals = []
# These are local values. I'd be veeerrry surprised if everyone had such performance.
# In case your test is failing: ignore and carry on.
expected_times = np.array(
[0.015, 0.04, 0.04, 0.05, 0.04, 0.05, 0.05, 0.05, 0.03, 0.05])
received_times = [0] * len(expected_times)
# Detect whether run on Travis CI
# Performance test should be run on same machine with
# same setting. Travis cannot guarantee that.
if "TRAVIS" in os.environ:
expected_times *= 10 # Conservative.
all_w = np.arange(10, 20)
for w in all_w:
signal = np.sin(w * 2 * np.pi * T)
signal[:] = signal[:] + 2 * np.cos(5 * 2 * np.pi * T)
all_test_signals.append(signal)
emd = EMD()
emd.FIXE = 10
for idx, signal in enumerate(all_test_signals):
avg_t = self._timeit(emd.emd, signal, T, N=15)
self.logger.info("{}. t = {:.4} (exp. {})".format(
idx, avg_t, expected_times[idx]))
received_times[idx] = avg_t
# allclose = np.allclose(received_times, expected_times, atol=1e-2)
# self.assertTrue(allclose)
less_than = received_times <= expected_times
self.assertTrue(np.all(less_than))
