def get_psi_entropies(data):
bands = [0.5, 4, 7, 12, 30, 100]
fs = 125
array_length = 1024
cols = data.shape[1]
rows = math.floor(data.shape[0] / array_length)
alpha_psi_entropies = pd.DataFrame([])
temp_data = pd.DataFrame()
for x in range(cols):
alpha_psis = []
entropies = []
temp_col_alpha = 'alpha_psi ' + str(x)
temp_col_entropy = 'spectral_entropy ' + str(x)
for y in range(rows):
psis, power_ratios = bin_power(
data.iloc[(y * array_length):((y + 1) * array_length), x],
bands, fs)
alpha_psis.append(psis[2])
spec_entropies = spectral_entropy(
data.iloc[(y * array_length):((y + 1) * array_length), x],
bands, fs, power_ratios)
entropies.append(spec_entropies)
temp_data[temp_col_alpha] = alpha_psis
temp_data[temp_col_entropy] = entropies
alpha_psi_entropies = alpha_psi_entropies.append(temp_data,
ignore_index=True)
return alpha_psi_entropies
def SpectralEntropy(self): b = pyeeg.bin_power(self.channel_data,self.bands,self.samplingFrequency) resp = pyeeg.spectral_entropy(self.channel_data,self.bands,self.samplingFrequency,Power_Ratio=b) resp = [0 if math.isnan(x) else x for x in resp] label = 'SpectralEntropy_' labels = label+pd.Series(range(len(resp)),dtype=str) return [np.array(resp),labels.values]
def get_psi_entropies(data):
# Setting variables needed for for loop
band = [0.5, 4, 7, 12, 30, 100]
fs = 1024
size = 1024
columns = data.shape[1]
rows = math.floor(data.shape[0] / size)
alpha_psi_df = pd.DataFrame([])
temp_data = pd.DataFrame([])
# Creating for loop
for x in range(columns):
alpha_psis = []
entropies = []
temp_col_alpha = 'alpha_psi ' + str(x)
temp_col_entropy = 'spectral_entropy ' + str(x)
for y in range(rows):
psis, power_ratios = bin_power(data.iloc[(y * size):((y + 1) * size), x], band, fs)
alpha_psis.append(psis[2])
spec_entropies = spectral_entropy(data.iloc[(y * size):((y + 1) * size), x], band, fs, power_ratios)
entropies.append(spec_entropies)
temp_data[temp_col_alpha] = alpha_psis
temp_data[temp_col_entropy] = entropies
alpha_psi_df = alpha_psi_df.append(temp_data, ignore_index = True)
return alpha_psi_df
def set_spectral_entropy(self):
for e in xrange(self.data.shape[0]):
if np.all(self.data[e][:1000] == 0):
continue
name = 'spectral_entropy_e' + str(e)
pr = self.power_ratio['power_ratio_e' + str(e)]
value = pyeeg.spectral_entropy(self.data[e], range(len(pr)), int(self.frequency), pr)
self.features[name] = value
def mean_spectral_entropy(data):
psd_vals = all_psd(data)
power_ratio = []
sum_psd_vals = sum_psd(data)
for val in psd_vals:
power_ratio.append(val / sum_psd_vals)
bands = [0, 4, 8, 12, 30, 45]
Fs = 256
spec_entropy = p.spectral_entropy(data, bands, Fs, power_ratio)
return spec_entropy
def single_window_q_features(eeg_window, samplerate):
'''
Calculates all the features for the provided eeg sample data.
Data should be an ndarray with
'''
features = []
# Calculate spectral entropy
bins = [0.1, 4, 8, 12, 30, 70, 180]
spec_entropies = pyeeg.spectral_entropy(eeg_window, bins, samplerate)
def SpectralEntropy(x):
fs = 128
band = [1, 4, 8, 12, 30]
b = pyeeg.bin_power(x, band, fs)
resp = pyeeg.spectral_entropy(x, band, fs, Power_Ratio=b)
resp = [0 if math.isnan(x) else x for x in resp]
return resp
def SpectralEntropy(self):
b = pyeeg.bin_power(self.channel_data, self.bands,
self.samplingFrequency)
resp = pyeeg.spectral_entropy(self.channel_data,
self.bands,
self.samplingFrequency,
Power_Ratio=b)
resp = [0 if math.isnan(x) else x for x in resp]
label = 'SpectralEntropy_'
labels = label + pd.Series(range(len(resp)), dtype=str)
return [np.array(resp), labels.values]
def features(mat):
Kmax = 5
Tau = 4
DE = 10
M = 10
R = 0.3
Band = np.arange(1, 86)
Fs = 173
DFA = pyeeg.dfa(mat)
HFD = pyeeg.hfd(mat, Kmax)
SVD_Entropy = pyeeg.svd_entropy(mat, Tau, DE)
Fisher_Information = pyeeg.fisher_info(mat, Tau, DE)
#ApEn = pyeeg.ap_entropy(mat, M, R) # very slow
PFD = pyeeg.pfd(mat)
Spectral_Entropy = pyeeg.spectral_entropy(mat, Band, Fs, Power_Ratio=None)
sleep(0.01)
return (DFA, HFD, SVD_Entropy, Fisher_Information, PFD, Spectral_Entropy)
def get_features(signal):
#print(signal)
freq_cutoffs = [3, 8, 12, 27, 50]
features = []
features.append(rms(signal))
s = lpf(signal, SAMPLING_RATE, freq_cutoffs[0])
features.append(rms(s))
for i in range(len(freq_cutoffs) - 1):
s = bp(signal, SAMPLING_RATE, freq_cutoffs[i], freq_cutoffs[i + 1])
features.append(rms(s))
fourier = np.fft.rfft(signal * np.hamming(signal.size))
features.extend(abs(fourier))
wsize = 64
X = mne.time_frequency.stft(signal, wsize, verbose=False)
freqs = np.reshape(abs(X), X.size)
features.extend(freqs)
features.append(pyeeg.hurst(signal))
features.append(pyeeg.hfd(signal, 10))
e = pyeeg.spectral_entropy(signal, np.append(0.5, freq_cutoffs),
SAMPLING_RATE)
features.append(e)
features.extend(pyeeg.hjorth(signal))
features.append(pyeeg.pfd(signal))
features.append(pyeeg.mean(signal))
features.append(scipy.stats.skew(signal))
features.append(scipy.stats.kurtosis(signal))
#features.extend(signal)
return features
def get_features(signal):
#print(signal)
freq_cutoffs = [3, 8, 12, 27, 50]
features = []
features.append(rms(signal))
s = lpf(signal, SAMPLING_RATE, freq_cutoffs[0])
features.append(rms(s))
for i in range(len(freq_cutoffs)-1):
s = bp(signal, SAMPLING_RATE, freq_cutoffs[i], freq_cutoffs[i+1])
features.append(rms(s))
fourier = np.fft.rfft(signal * np.hamming(signal.size))
features.extend(abs(fourier))
wsize = 64
X = mne.time_frequency.stft(signal, wsize, verbose=False)
freqs = np.reshape(abs(X), X.size)
features.extend(freqs)
features.append(pyeeg.hurst(signal))
features.append(pyeeg.hfd(signal, 10))
e = pyeeg.spectral_entropy(signal, np.append(0.5, freq_cutoffs), SAMPLING_RATE)
features.append(e)
features.extend(pyeeg.hjorth(signal))
features.append(pyeeg.pfd(signal))
features.append(pyeeg.mean(signal))
features.append(scipy.stats.skew(signal))
features.append(scipy.stats.kurtosis(signal))
#features.extend(signal)
return features
def eeg_features(data):
data = np.asarray(data)
res = np.zeros([22])
Kmax = 5
# M = 10
# R = 0.3
Band = [1, 5, 10, 15, 20, 25]
Fs = 256
power, power_ratio = pyeeg.bin_power(data, Band, Fs)
f, P = welch(data, fs=Fs, window='hanning', noverlap=0,
nfft=int(256.)) # Signal power spectrum
area_freq = cumtrapz(P, f, initial=0)
res[0] = np.sqrt(np.sum(np.power(data, 2)) /
data.shape[0]) # amplitude RMS
res[1] = statistics.stdev(data)**2 # variance
res[2] = kurtosis(data) # kurtosis
res[3] = skew(data) # skewness
res[4] = max(data) # max amplitude
res[5] = min(data) # min amplitude
res[6] = len(argrelextrema(
data, np.greater)[0]) # number of local extrema or peaks
res[7] = ((data[:-1] * data[1:]) < 0).sum() # number of zero crossings
res[8] = pyeeg.hfd(data, Kmax) # Higuchi Fractal Dimension
res[9] = pyeeg.pfd(data) # Petrosian Fractal Dimension
res[10] = pyeeg.hurst(data) # Hurst exponent
res[11] = pyeeg.spectral_entropy(
data, Band, Fs, Power_Ratio=power_ratio) # spectral entropy (1.21s)
res[12] = area_freq[-1] # total power
res[13] = f[np.where(area_freq >= res[12] / 2)[0][0]] # median frequency
res[14] = f[np.argmax(P)] # peak frequency
res[15], res[16] = pyeeg.hjorth(data) # Hjorth mobility and complexity
res[17] = power_ratio[0]
res[18] = power_ratio[1]
res[19] = power_ratio[2]
res[20] = power_ratio[3]
res[21] = power_ratio[4]
# res[22] = pyeeg.samp_entropy(data, M, R) # sample entropy
# res[23] = pyeeg.ap_entropy(data, M, R) # approximate entropy (1.14s)
return (res)
def feature_wave(self, toolName=None, Fs=256):
if (toolName == None):
print('please select a tool')
return
if toolName in self.FeatureSet.dict[0]:
index = self.FeatureSet.dict[0][toolName]
else:
index = -1
print(toolName)
if toolName == 'DWT':
answer_train = DWT(self.DataSet.trainSet_data[0], 'db4')
answer_test = DWT(self.DataSet.testSet_data[0], 'db4')
print('DWT feature extraction succeed db4')
elif toolName == 'hurst':
answer_train = [
pyeeg.hurst(i) for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.hurst(i) for i in self.DataSet.testSet_data[0]
]
print('hurst feature extraction succeed')
elif toolName == 'dfa':
answer_train = [
pyeeg.dfa(i, L=[4, 8, 16, 32, 64])
for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.dfa(i, L=[4, 8, 16, 32, 64])
for i in self.DataSet.testSet_data[0]
]
print('dfa feature extraction succeed')
elif toolName == 'fisher_info':
answer_train = [
pyeeg.fisher_info(i, 2, 20)
for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.fisher_info(i, 2, 20)
for i in self.DataSet.testSet_data[0]
]
print('fisher_info feature extraction succeed')
elif toolName == 'svd_entropy':
answer_train = [
pyeeg.svd_entropy(i, 2, 20)
for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.svd_entropy(i, 2, 20)
for i in self.DataSet.testSet_data[0]
]
print('svd_entropy feature extraction succeed')
elif toolName == 'spectral_entropy':
bandlist = [0.5, 4, 7, 12, 30, 100]
answer_train = [
pyeeg.spectral_entropy(i, bandlist, Fs)
for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.spectral_entropy(i, bandlist, Fs)
for i in self.DataSet.testSet_data[0]
]
print('spectral_entropy feature extraction succeed')
elif toolName == 'hjorth':
# 得到两个量 第一个是 mobility 第二个是 complexity
answer_train = [
pyeeg.hjorth(i) for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.hjorth(i) for i in self.DataSet.testSet_data[0]
]
answer_train = np.array(answer_train)
answer_test = np.array(answer_test)
for i in answer_train:
i[1] = i[1] / 100
for i in answer_test:
i[1] = i[1] / 100
#只取Mobility
answer_train = np.array(answer_train[:, 0])
answer_test = np.array(answer_test[:, 0])
print('hjorth feature extraction succeed')
elif toolName == 'hfd':
answer_train = [
pyeeg.hfd(i, 8) for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.hfd(i, 8) for i in self.DataSet.testSet_data[0]
]
print('hfd feature extraction succeed')
elif toolName == 'pfd':
answer_train = [
pyeeg.pfd(i) for i in self.DataSet.trainSet_data[0]
]
answer_test = [pyeeg.pfd(i) for i in self.DataSet.testSet_data[0]]
print('pfd feature extraction succeed')
elif toolName == 'bin_power':
bandlist = [0.5, 4, 7, 12] #,30,100]
answer_train = [
pyeeg.bin_power(i, bandlist, Fs)
for i in self.DataSet.trainSet_data[0]
]
answer_test = [
pyeeg.bin_power(i, bandlist, Fs)
for i in self.DataSet.testSet_data[0]
]
print('bin_power feature extraction succeed')
else:
print('does not have this kind of mode')
answer_train = np.array(answer_train)
answer_train = answer_train.reshape(len(answer_train), -1)
answer_test = np.array(answer_test)
answer_test = answer_test.reshape(len(answer_test), -1)
if index == -1:
#print(len(self.FeatureSet.feature.trainSet_feat[0]),len(answer_train))
self.FeatureSet.feature.trainSet_feat[0] = np.column_stack(
(self.FeatureSet.feature.trainSet_feat[0], answer_train))
self.FeatureSet.feature.testSet_feat[0] = np.column_stack(
(self.FeatureSet.feature.testSet_feat[0], answer_test))
self.FeatureSet.dict[0][toolName] = [
self.FeatureSet.size[0],
self.FeatureSet.size[0] + len(answer_train[0])
]
self.FeatureSet.size[0] += len(answer_train[0])
else:
self.FeatureSet.feature.trainSet_feat[0][:, index[0]:index[1]] = [
i for i in answer_train
]
self.FeatureSet.feature.testSet_feat[0][:, index[0]:index[1]] = [
i for i in answer_test
]
"times": 10,
"name": "fisher_info",
"is_original": True,
"fun": lambda x: pyeeg.fisher_info(x, 2, 3)
},
{
"times": 100,
"name": "fisher_info",
"is_original": False,
"fun": lambda x: univ.fisher_info(x, 2, 3)
},
{
"times": 100,
"name": "spectral_entropy",
"is_original": True,
"fun": lambda x: pyeeg.spectral_entropy(x, SPECT_ENT_BANDS, 256)
},
{
"times": 100,
"name": "spectral_entropy",
"is_original": False,
"fun": lambda x: univ.spectral_entropy(x, 256, SPECT_ENT_BANDS)
},
]
def make_one_rep():
ldfs = []
for n in range(MIN_EPOCH_N, MAX_EPOCH_N + 1, EPOCH_STEP):
a = numpy.random.normal(size=n)
for fun in fun_to_test:
def myFeaturesExtractor(X): # X has to be a matrix where each row is a channel
N = len(X)
# L = len(X[0])
# here we initialize the list of features // We will transform it to an array later
featList = list()
timeList =list ()
featName =list()
for kChan in range(1):
mySig = X[kChan , :]
if kChan == 0:
start=time.perf_counter_ns()
#========== Stats ========================
myMean = np.mean(mySig)
featList.append(myMean)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append("mean")
start=end
featList.append(max(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" max")
start=end
featList.append(min(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" min")
start=end
peak =max(abs(mySig))
featList.append(peak)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" peak")
start=end
myVar = np.var(mySig)
featList.append(myVar)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" var")
start=end
myVar = np.var(mySig)
myStd = np.sqrt(myVar)
featList.append(myStd)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" std")
start=end
featList.append(sp.skew(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" skew")
start=end
featList.append(sp.kurtosis(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" kurt")
start=end
myRMS = rms(mySig)
featList.append(myRMS)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" rms")
start=end
myRMS = rms(mySig)
featList.append(peak/myRMS)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" fact")
start=end
myRMS = rms(mySig)
featList.append(myRMS/myMean)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" papr")
start=end
featList.append(totVar(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" totVar")
start=end
featList.append(pyeeg.dfa(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" dfa")
start=end
featList.append(pyeeg.hurst(mySig))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" hurst")
start=end
hMob , hComp = pyeeg.hjorth(mySig )
featList.append(hMob)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" Hmob")
timeList.append(end -start)
featName.append(" Hcomp")
start=end
featList.append(hComp)
# ## ======== fractal ========================
# # Now we need to get the embeding time lag Tau and embeding dmension
# ac=delay.acorr(mySig, maxtau=maxTauLag, norm=True, detrend=True)
# Tau = firstTrue(ac < corrThresh) # embeding delay
# featList.append(Tau)
# if kChan == 0:
# end=time.perf_counter_ns()
#
# timeList.append(end -start)
# featName.append(" dCorrTime")
# start=end
# f1 , f2 , f3 = dimension.fnn(mySig, dim=dim, tau=Tau, R=10.0, A=2.0, metric='chebyshev', window=10,maxnum=None, parallel=True)
# myEmDim = firstTrue(f3 < fracThresh)
## if kChan == 0:
## end=time.perf_counter_ns()
## timeList.append(end -start)
## featName.append(" embDim")
## start=end
# # Here we construct the Embeding Matrix Em
# Em = pyeeg.embed_seq(mySig, Tau, myEmDim)
# U, s, Vh = linalg.svd(Em)
# W = s/np.sum(s) # list of singular values in decreasing order
#
# FInfo = pyeeg.fisher_info(X, Tau, myEmDim , W=W)
# featList.append(FInfo)
# if kChan == 0:
# end=time.perf_counter_ns()
#
# timeList.append(end -start)
# featName.append(" FInfo")
# start=end
#
# featList.append(myEmDim)
PFD = pyeeg.pfd(mySig, D=None)
featList.append(PFD)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" pfd")
start=end
hfd6 = pyeeg.hfd(mySig , 6)
featList.append(hfd6)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" hfd6")
start=end
hfd10 = pyeeg.hfd(mySig , 10)
featList.append(hfd10)
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" hfd10")
start=end
# Now we fit aline and get its slope to have Lyapunov exponent
# divAvg = lyapunov.mle(Em, maxt=maxtLyap, window= 3 * Tau, metric='euclidean', maxnum=None)
# poly = np.polyfit(lyapLags, divAvg, 1, rcond=None, full=False, w=None, cov=False)
# LyapExp = poly[0]
# featList.append(np.mean(LyapExp))
# if kChan == 0:
# end=time.perf_counter_ns()
#
# timeList.append(end -start)
# featName.append("Lyapunov")
# start=end
## ======== Entropy ========================
# here we compute bin power
power, power_Ratio = pyeeg.bin_power(mySig , freqBins , Fs )
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append("Spectral")
start=end
featList.append( pyeeg.spectral_entropy(mySig, freqBins, Fs, Power_Ratio=power_Ratio))
if kChan == 0:
end=time.perf_counter_ns()
timeList.append(end -start)
featName.append(" specEn")
start=end
# tolerance = myStd / 4
# entropyDim = max([myEmDim , PFD])
# featList.append( pyeeg.samp_entropy(mySig , entropyDim , tolerance ) )
# if kChan == 0:
# end=time.perf_counter_ns()
#
# timeList.append(end -start)
# featName.append(" sampEn")
# start=end
# featList.append( pyeeg.svd_entropy(mySig, Tau, myEmDim , W=W) )
# if kChan == 0:
# end=time.perf_counter_ns()
#
# timeList.append(end -start)
# featName.append(" svdEn")
# start=end
## ======== Spectral ========================
appendArray2List(featList , power )
appendArray2List(featList , power_Ratio )
start=time.perf_counter_ns()
connectome(X , featList)
end=time.perf_counter_ns()
timeList.append((end -start)/N/(N-1)*2)
featName.append("connectivity")
ll=list()
ll.append(featName)
ll.append(timeList)
return np.asarray(featList) , ll
def calculate_features(samples):
data = samples
if not samples:
print("no samples")
return []
band = [0.5, 4, 7, 12, 30]
a = randn(4097)
# approx = pyeeg.ap_entropy(data, 5, 1)
approx = 0
DFA = pyeeg.dfa(data)
first_order_diff = [data[i] - data[i - 1] for i in range(1, len(data))]
fisher_info = pyeeg.fisher_info(data, 1, 1, W=None)
embed_seq = pyeeg.embed_seq(data, 1, 1)
hfd = pyeeg.hfd(data, 6)
hjorth = pyeeg.hjorth(data, D=None)
hurst = pyeeg.hurst(data)
PFD = pyeeg.pfd(data)
sam_ent = pyeeg.samp_entropy(data, 1, 2)
spectral_entropy = pyeeg.spectral_entropy(data,
band,
256,
Power_Ratio=None)
svd = pyeeg.svd_entropy(data, 6, 4, W=None)
PSI = pyeeg.bin_power(data, band, 256)
# # Power Spectral Intensity (PSI) and Relative Intensity Ratio (RIR) Two 1- D v ec t o rs
# # print("bin_power = ", PSI)
# # Petrosian Fractal Dimension (PFD) Ascalar
# print("PFD = ", PFD)
# # Higuchi Fractal Dimension (HFD) Ascalar
# print("hfd = ", hfd)
# # Hjorth mobility and complexity Two s c a la rs
# print("hjorth = ", hjorth)
# # Spectral Entropy (Shannon’s entropy of RIRs) Ascalar
# print("spectral_entropy = ", spectral_entropy)
# # SVD Entropy Ascalar
# print("svd = ", svd)
# # Fisher Information Ascalar
# print("fisher_info = ", fisher_info)
# # Approximate Entropy (ApEn) Ascalar
# print("approx entrophy = ", approx)
# # Detrended Fluctuation Analysis (DFA) Ascalar
# print("DFA = ", DFA)
# # HurstExponent(Hurst) Ascalar
# print("Hurst_Exponent = ", hurst)
# # Build a set of embedding sequences from given time series X with lag Tau and embedding dimension
# print("embed_seq = ", embed_seq)
# # Compute the first order difference of a time series.
# print("first_order_diff = ", first_order_diff)
return {
'approximate': approx,
'DFA': DFA,
'fisher_info': fisher_info,
'embed_seq': embed_seq,
'hfd': hfd,
'hjorth': hjorth,
'hurst': hurst,
'PFD': PFD,
'sam_ent': sam_ent,
'spectral_entropy': spectral_entropy,
'svd': svd,
'PSI': PSI,
'first_order_diff': first_order_diff
}
##print i
h = hjorth(X_train[i,])
hjorth_features_train.append(h)
hjorth_features_test = []
for i in range(X_test.shape[0]):
##print i
h = hjorth(X_test[i,])
hjorth_features_test.append(h)
"""Spectral Entropy """ ##Okay
spectral_entropy_features_train = []
for i in range(X_train.shape[0]):
##print i
h = spectral_entropy(X_train[i,], [0.54, 5, 7, 12, 50], 173, Power_Ratio=None)
spectral_entropy_features_train.append(h)
spectral_entropy_features_test = []
for i in range(X_test.shape[0]):
##print i
h = spectral_entropy(X_test[i,], [0.54, 5, 7, 12, 50], 173, Power_Ratio=None)
spectral_entropy_features_test.append(h)
"""SVD Entropy """ ## Okay
svd_entropy_features_train = []
for i in range(X_train.shape[0]):
##print i
h = svd_entropy(X_train[i,], 4, 10, W=None)
svd_entropy_features_train.append(h)
def myFeaturesExtractor(
X, myM, myV): # X has to be a matrix where each row is a channel
N = len(X) # number of channels
L = len(X[0])
maxtLyap = min(500, L // 2 + L // 4)
lyapLags = np.arange(maxtLyap) / Fs
# get number of features
nFeatures = nMono * N + N * (N - 1) / 2
# here we initialize the list of features // We will transform it to an array later
featList = np.zeros((int(nFeatures)))
# deal with monovariate features first
for kChan in range(N):
kFeat = 0
mySig = X[kChan, :]
#========== Stats ========================
myMean = myM[kChan]
featList[nMono * kChan + kFeat] = myMean
kFeat += 1
myMax = max(mySig)
featList[nMono * kChan + kFeat] = myMax
kFeat += 1
myMin = min(mySig)
featList[nMono * kChan + kFeat] = myMin
kFeat += 1
peak = max(abs(np.array([myMin, myMax])))
featList[nMono * kChan + kFeat] = peak
kFeat += 1
myVar = myV[kChan]
featList[nMono * kChan + kFeat] = myVar
kFeat += 1
featList[nMono * kChan + kFeat] = sp.skew(mySig)
kFeat += 1
featList[nMono * kChan + kFeat] = sp.kurtosis(mySig)
kFeat += 1
myRMS = rms(mySig)
featList[nMono * kChan + kFeat] = myRMS
kFeat += 1
featList[nMono * kChan + kFeat] = peak / myRMS
kFeat += 1
featList[nMono * kChan + kFeat] = totVar(mySig)
kFeat += 1
featList[nMono * kChan + kFeat] = pyeeg.dfa(mySig)
kFeat += 1
featList[nMono * kChan + kFeat] = pyeeg.hurst(mySig)
kFeat += 1
hMob, hComp = pyeeg.hjorth(mySig)
featList[nMono * kChan + kFeat] = hMob
kFeat += 1
featList[nMono * kChan + kFeat] = hComp
kFeat += 1
## ======== fractal ========================
# Now we need to get the embeding time lag Tau and embeding dmension
ac = delay.acorr(mySig, maxtau=maxTauLag, norm=True, detrend=True)
Tau = firstTrue(ac < corrThresh) # embeding delay
f1 , f2 , f3 = dimension.fnn(mySig, dim=dim, tau=Tau, R=10.0, A=2.0, metric='euclidean',\
window=10,maxnum=None, parallel=True)
myEmDim = firstTrue(f3 < fracThresh)
# Here we construct the Embeding Matrix Em
Em = pyeeg.embed_seq(mySig, Tau, myEmDim)
U, s, Vh = linalg.svd(Em)
W = s / np.sum(s) # list of singular values in decreasing order
FInfo = pyeeg.fisher_info(X, Tau, myEmDim, W=W)
featList[nMono * kChan + kFeat] = FInfo
kFeat += 1
featList[nMono * kChan + kFeat] = Tau
kFeat += 1
featList[nMono * kChan + kFeat] = myEmDim
kFeat += 1
#========================================
PFD = pyeeg.pfd(mySig, D=None)
hfd6 = pyeeg.hfd(mySig, 6)
hfd10 = pyeeg.hfd(mySig, 10)
# Now we fit aline and get its slope to have Lyapunov exponent
divAvg = lyapunov.mle(Em,
maxt=maxtLyap,
window=3 * Tau,
metric='euclidean',
maxnum=None)
poly = np.polyfit(lyapLags,
divAvg,
1,
rcond=None,
full=False,
w=None,
cov=False)
LyapExp = poly[0]
featList[nMono * kChan + kFeat] = PFD
kFeat += 1
featList[nMono * kChan + kFeat] = hfd6
kFeat += 1
featList[nMono * kChan + kFeat] = hfd10
kFeat += 1
featList[nMono * kChan + kFeat] = LyapExp
kFeat += 1
## ======== Entropy ========================
tolerance = 1 / 4
entropyDim = max([myEmDim, PFD])
featList[nMono * kChan + kFeat] = pyeeg.samp_entropy(
mySig, entropyDim, tolerance)
kFeat += 1
featList[nMono * kChan + kFeat] = pyeeg.svd_entropy(mySig,
Tau,
myEmDim,
W=W)
kFeat += 1
# here we compute bin power
power, power_Ratio = pyeeg.bin_power(mySig, freqBins, Fs)
featList[nMono * kChan + kFeat] = pyeeg.spectral_entropy(
mySig, freqBins, Fs, Power_Ratio=power_Ratio)
kFeat += 1
## ======== Spectral ========================
for kBin in range(len(freqBins) - 1):
featList[nMono * kChan + kFeat] = power[kBin]
kFeat += 1
featList[nMono * kChan + kFeat] = power_Ratio[kBin]
kFeat += 1
# deal with multivariate features first
#============ connectivity ==================
corrList = connectome(X)
nConnect = len(corrList)
if N * (N - 1) / 2 != nConnect:
raise ValueError('incorrect number of correlation coeffs')
for kC in range(nConnect):
featList[-nConnect + kC] = corrList[kC]
return featList
#print vibration_list #vibration_array = np.zeros(fft_size) #for i in range(len(vibration_list)): # index = (vibration_list[i]-1) * sampling_rate # vibration_array[index:index+sampling_rate] = 1 (power_xf, power_xf_filtered, freqs, xfp) = return_filtered_epoch(time_series) dominant_f = return_dominant_freq(freqs, power_xf_filtered) (delta_ratio, theta_ratio, alpha_ratio, sigma_ratio, beta_ratio) = return_power_ratio(freqs, power_xf_filtered) (A5_mean, D5_mean, D4_mean, D3_mean, A5_std, D5_std, D4_std, D3_std, A5_pm, D5_pm, D4_pm, D3_pm, \ A5_ratio_mean, D5_ratio_mean, D4_ratio_mean, D3_ratio_mean) = return_DWT_feature(time_series) hurst_index = pyeeg.hurst(time_series) pfd_index = pyeeg.pfd(time_series) sp_entropy = pyeeg.spectral_entropy(time_series, [0.5, 3, 8, 12, 16, 30], sampling_rate, Power_Ratio = None) hj_activity, hj_mobility, hj_complexity = pyeeg.hjorth(time_series) fmax=getfmax(time_series) fmin=getfmin(time_series) fmean=getfmean(time_series) fstd=getfstd(time_series) fvar=getfvar(time_series) fskew=getfskew(time_series) fkur=getfkur(time_series) fmd=getfmd(time_series) zcnum=getzcnum(time_series) print [fmax, fmin, fmean, fstd, fvar, fskew, fkur, fmd, zcnum, dominant_f[0], delta_ratio, \ theta_ratio, alpha_ratio, sigma_ratio, beta_ratio, A5_mean, D5_mean, D4_mean, D3_mean, \ A5_std, D5_std, D4_std, D3_std, A5_pm, D5_pm, D4_pm, D3_pm, A5_ratio_mean, D5_ratio_mean, \
fun_to_test = [
{"times":100,"name":"hfd", "is_original":True,"fun": lambda x: pyeeg.hfd(x,2**3)},
{"times":100,"name":"hfd", "is_original":False,"fun": lambda x: univ.hfd(x,2**3)},
{"times":100,"name":"hjorth", "is_original":True,"fun": lambda x: pyeeg.hjorth(x)},
{"times":100,"name":"hjorth", "is_original":False,"fun": lambda x: univ.hjorth(x)},
{"times":100,"name":"pfd", "is_original":True, "fun":lambda x: pyeeg.pfd(x)},
{"times":100,"name":"pfd", "is_original":False, "fun":lambda x: pyeeg.pfd(x)},
{"times":2,"name":"samp_ent", "is_original":True, "fun":lambda x: pyeeg.samp_entropy(x,2,1.5)},
{"times":10,"name":"samp_ent", "is_original":False, "fun":lambda x: univ.samp_entropy(x,2,1.5,relative_r=False)},
{"times":2,"name":"ap_ent", "is_original":True, "fun":lambda x: pyeeg.ap_entropy(x,2,1.5)},
{"times":10,"name":"ap_ent", "is_original":False, "fun":lambda x: univ.ap_entropy(x,2,1.5)},
{"times":10,"name":"svd_ent", "is_original":True, "fun":lambda x: pyeeg.svd_entropy(x,2,3)},
{"times":100,"name":"svd_ent", "is_original":False, "fun":lambda x: univ.svd_entropy(x,2,3)},
{"times":10,"name":"fisher_info", "is_original":True, "fun":lambda x: pyeeg.fisher_info(x,2,3)},
{"times":100, "name":"fisher_info", "is_original":False, "fun":lambda x: univ.fisher_info(x,2,3)},
{"times":100,"name":"spectral_entropy", "is_original":True, "fun":lambda x: pyeeg.spectral_entropy(x,SPECT_ENT_BANDS,256)},
{"times":100, "name":"spectral_entropy", "is_original":False, "fun":lambda x: univ.spectral_entropy(x,256, SPECT_ENT_BANDS)},
]
def make_one_rep():
ldfs = []
for n in range(MIN_EPOCH_N, MAX_EPOCH_N + 1, EPOCH_STEP):
a = numpy.random.normal(size=n)
for fun in fun_to_test:
f = lambda : fun["fun"](a)
t=Timer(f)
numb = fun["times"]
dt = t.timeit(number=numb)
fun["log10_dt"] = np.log10(dt/float(numb))
for i in range(X_train.shape[0]):
##print i
h = hjorth(X_train[i, ])
hjorth_features_train.append(h)
hjorth_features_test = []
for i in range(X_test.shape[0]):
##print i
h = hjorth(X_test[i, ])
hjorth_features_test.append(h)
'''Spectral Entropy ''' ##Okay
spectral_entropy_features_train = []
for i in range(X_train.shape[0]):
##print i
h = spectral_entropy(X_train[i, ], [0.54, 5, 7, 12, 50],
173,
Power_Ratio=None)
spectral_entropy_features_train.append(h)
spectral_entropy_features_test = []
for i in range(X_test.shape[0]):
##print i
h = spectral_entropy(X_test[i, ], [0.54, 5, 7, 12, 50],
173,
Power_Ratio=None)
spectral_entropy_features_test.append(h)
'''SVD Entropy ''' ## Okay
svd_entropy_features_train = []
for i in range(X_train.shape[0]):
##print i
h = svd_entropy(X_train[i, ], 4, 10, W=None)
def myFeaturesExtractor1(
X, myM, myV, myMin,
myMax): # X has to be a matrix where each row is a channel
N = len(X) # number of channels
# L = len(X[0])
# get number of features
nFeatures = nMono * N + N * (N - 1) / 2
# here we initialize the list of features // We will transform it to an array later
featList = np.zeros((int(nFeatures)))
# deal with monovariate features first
for kChan in range(N):
kFeat = 0
mySig = X[kChan, :]
#========== Stats ========================
myMean = myM[kChan]
featList[nMono * kChan + kFeat] = myMean
kFeat += 1
featList[nMono * kChan + kFeat] = myMax[kChan]
kFeat += 1
featList[nMono * kChan + kFeat] = myMin[kChan]
kFeat += 1
myVar = myV[kChan]
featList[nMono * kChan + kFeat] = myVar
kFeat += 1
featList[nMono * kChan + kFeat] = sp.skew(mySig)
kFeat += 1
featList[nMono * kChan + kFeat] = sp.kurtosis(mySig)
kFeat += 1
featList[nMono * kChan + kFeat] = pyeeg.dfa(mySig)
kFeat += 1
hMob, hComp = pyeeg.hjorth(mySig)
featList[nMono * kChan + kFeat] = hMob
kFeat += 1
featList[nMono * kChan + kFeat] = hComp
kFeat += 1
## ======== fractal ========================
# Now we need to get the embeding time lag Tau and embeding dmension
ac = delay.acorr(mySig, maxtau=maxTauLag, norm=True, detrend=True)
Tau = firstTrue(ac < corrThresh) # embeding delay
featList[nMono * kChan + kFeat] = Tau
kFeat += 1
PFD = pyeeg.pfd(mySig, D=None)
hfd10 = pyeeg.hfd(mySig, 10)
featList[nMono * kChan + kFeat] = PFD
kFeat += 1
featList[nMono * kChan + kFeat] = hfd10
kFeat += 1
## ======== Entropy ========================
# here we compute bin power
power, power_Ratio = pyeeg.bin_power(mySig, freqBins, Fs)
featList[nMono * kChan + kFeat] = pyeeg.spectral_entropy(
mySig, freqBins, Fs, Power_Ratio=power_Ratio)
kFeat += 1
## ======== Spectral ========================
for kBin in range(len(freqBins) - 1):
featList[nMono * kChan + kFeat] = power[kBin]
kFeat += 1
featList[nMono * kChan + kFeat] = power_Ratio[kBin]
kFeat += 1
# deal with multivariate features first
#============ connectivity ==================
corrList = connectome(X)
nConnect = len(corrList)
if N * (N - 1) / 2 != nConnect:
raise ValueError('incorrect number of correlation coeffs')
for kC in range(nConnect):
featList[-nConnect + kC] = corrList[kC]
return featList
def specEntropy4(X):
frequencyBands = [0.1, 4, 8, 12, 30]
power, powerRatio = pyeeg.bin_power(X[3], frequencyBands, glb.fs)
return pyeeg.spectral_entropy(X[3], [0.1, 4, 7, 12, 30], 250, powerRatio)
