def test_different_length_input(self):
T = np.arange(20)
S = np.random.random(len(T) + 7)
emd = EMD()
with self.assertRaises(ValueError):
emd.emd(S, T)
def test_unsupporter_spline(self):
emd = EMD()
emd.splineKind = "waterfall"
S = np.random.random(20)
with self.assertRaises(ValueError):
emd.emd(S)
def test_trend(self):
"""
Input is trend. Expeting no shifting process.
"""
emd = EMD()
t = np.arange(0, 1, 0.01)
S = 2 * t
# Input - linear function f(t) = 2*t
IMF = emd.emd(S, t)
self.assertEqual(IMF.shape[0], 1, "Expecting single IMF")
def test_single_imf(self):
"""
Input is IMF. Expecint single shifting.
"""
maxDiff = lambda a, b: np.max(np.abs(a - b))
emd = EMD()
emd.FIXE_H = 5
t = np.arange(0, 1, 0.001)
c1 = np.cos(4 * 2 * np.pi * t) # 2 Hz
S = c1.copy()
# Input - linear function f(t) = sin(2Hz t)
IMF = emd.emd(S, t)
self.assertEqual(IMF.shape[0], 1, "Expecting sin + trend")
diff = np.allclose(IMF[0], c1)
self.assertTrue(
diff, "Expecting 1st IMF to be sin\nMaxDiff = " +
str(maxDiff(IMF[0], c1)))
# Input - linear function f(t) = siin(2Hz t) + 2*t
c2 = 5 * (t + 2)
S += c2.copy()
IMF = emd.emd(S, t)
self.assertEqual(IMF.shape[0], 2, "Expecting sin + trend")
diff1 = np.allclose(IMF[0], c1, atol=0.2)
self.assertTrue(
diff1, "Expecting 1st IMF to be sin\nMaxDiff = " +
str(maxDiff(IMF[0], c1)))
diff2 = np.allclose(IMF[1], c2, atol=0.2)
self.assertTrue(
diff2, "Expecting 2nd IMF to be trend\nMaxDiff = " +
str(maxDiff(IMF[1], c2)))
class EEMD:
logger = logging.getLogger(__name__)
def __init__(self):
# Import libraries
from PyEMD.EMD import EMD
# Ensemble constants
self.noise_width = 0.3
self.trials = 100
self.EMD = EMD()
self.EMD.FIXE_H = 5
def eemd(self, S, T=None, max_imf=None):
if T is None: T = np.arange(len(S), dtype=S.dtype)
if max_imf is None: max_imf = -1
N = len(S)
E_IMF = np.zeros((1,N))
for trial in range(self.trials):
self.logger.debug("trial: "+str(trial))
noise = np.random.normal(loc=0, scale=self.noise_width, size=N)
IMFs = self.emd(S+noise, T, max_imf)
imfNo = IMFs.shape[0]
while(E_IMF.shape[0] < imfNo):
E_IMF = np.vstack((E_IMF, np.zeros(N)))
E_IMF[:imfNo] += IMFs
E_IMF /= self.trials
return E_IMF
def emd(self, S, T, max_imf=-1):
return self.EMD.emd(S, T, max_imf)
cutoff_l, fs, order)
y_filtrada_dislex = butter_highpass_filter(y_filtrada_dislex, cutoff_h, fs,
order)
senial_indep_2500_muestras = y_filtrada
senial_indep_2500_muestras_dislexia = y_filtrada_dislex
# from PyEMD import EMD,visualisation
from PyEMD.EMD import EMD
from PyEMD.visualisation import Visualisation
# Perform decomposition
print("Performing decomposition... ")
emd = EMD()
emd.emd(senial_indep_2500_muestras, max_imf=5)
emd_dis = EMD()
emd_dis.emd(senial_indep_2500_muestras_dislexia, max_imf=5)
imfs, res = emd.get_imfs_and_residue()
imfs_dis, res_dis = emd_dis.get_imfs_and_residue()
vis = Visualisation()
print("Sujeto Normal")
vis.plot_imfs(imfs=imfs, residue=res, t=time, include_residue=False)
vis.plot_instant_freq(time, imfs=imfs)
vis.show()
print("Sujeto Dislexia")