def run_classifier(header_file, signal_file, classifier_pickle):
signal_names, Fs, n_samples = phyc.import_signal_names(header_file)
# Get this subject's data as a dataframe
this_data = phyc.get_subject_data_test(signal_file, signal_names)
SaO2 = this_data.get(['SaO2']).values
step = Fs * 60
window_size = Fs * 60
# Initialize the X_subj and Y_subj matricies
X_subj = np.zeros([((n_samples) // step), 1])
for idx, k in enumerate(range(0, (n_samples-step+1), step)):
X_subj[idx, :] = np.var(np.transpose(SaO2[k:k+window_size]), axis=1)
# Load the classifier
my_classifier = joblib.load(classifier_pickle)
# Generate the prediction for the subjects.
predictions = my_classifier.predict_proba(X_subj)
predictions = predictions[:, 1]
predictions = [x * np.ones([window_size]) for x in predictions]
predictions = np.concatenate(predictions)
predictions = np.append(predictions, np.zeros(np.size(this_data, 0)
- np.size(predictions, 0)))
return predictions
def loaddata(record_name):
L.log_info("Loading record: " + str(record_name))
header_file = record_name + '.hea'
signal_file = record_name + '.mat'
arousal_file = record_name + '-arousal.mat'
# Get the signal names from the header file
signal_names, Fs, n_samples = phyc.import_signal_names(header_file)
signal_names = list(np.append(signal_names, 'arousals'))
print("signal_names: " + str(signal_names))
print("Fs: " + str(Fs))
print("n_samples: " + str(n_samples))
# Convert this subject's data into a pandas dataframe
this_data = phyc.get_subject_data(arousal_file, signal_file, signal_names)
# ----------------------------------------------------------------------
# Generate the Features for the classificaition model - variance of SaO2
# ----------------------------------------------------------------------
# For the baseline, let's only look at how SaO2 might predict arousals
arousals_originale = this_data.get(['arousals']).values
SaO2 = this_data.get(['ECG']).values
recordLength = SaO2.size
signals=None
arousals=None
if(p_INPUT_FEAT==1):
SaO2 = instfreq(SaO2)
SaO2 = scale(SaO2)
#SaO2 = standardize(SaO2)
signals, arousals = phyc.signalsToMatrix(SaO2, arousals_originale, recordLength, p_WINDOW_SIZE, p_INPUT_FEAT);
print("signals shape:" + str(signals.shape))
if(p_INPUT_FEAT==13):
ECG = this_data.get(['ECG']).values
print("ECG shape:"+str(ECG.shape))
ECG = instfreq(ECG)
print("ECG shape:" + str(ECG.shape))
signals = this_data[
['F3-M2', 'F4-M1', 'C3-M2', 'C4-M1', 'O1-M2', 'O2-M1', 'E1-M2', 'Chin1-Chin2', 'ABD', 'CHEST', 'AIRFLOW',
'SaO2']].values
signals = np.append(signals,ECG, axis=1)
#signals = instfreq(signals)
signals = scale(signals)
#signals = standardize(signals)
print("signals shape:" + str(signals.shape))
print("signals shape:" + str(signals[0:20,:]))
signals, arousals = phyc.signalsToMatrix(signals, arousals_originale, recordLength, p_WINDOW_SIZE, p_INPUT_FEAT);
#signals = signals.values
return signals, arousals,recordLength,arousals_originale
def preprocess_record(record_name):
header_file = record_name + '.hea'
signal_file = record_name + '.mat'
arousal_file = record_name + '-arousal.mat'
# Get the signal names from the header file
signal_names, Fs, n_samples = phyc.import_signal_names(header_file)
signal_names = list(np.append(signal_names, 'arousals'))
# Convert this subject's data into a pandas dataframe
this_data = phyc.get_subject_data(arousal_file, signal_file, signal_names)
# ----------------------------------------------------------------------
# Generate the Features for the classificaition model - variance of SaO2
# ----------------------------------------------------------------------
# For the baseline, let's only look at how SaO2 might predict arousals
SaO2 = this_data.get(['SaO2']).values
arousals = this_data.get(['arousals']).values
# We select a window size of 60 seconds with no overlap to compute
# the features
step = Fs * 60
window_size = Fs * 60
# Initialize the matrices that store our training data
X_subj = np.zeros([((n_samples) // step), 1])
Y_subj = np.zeros([((n_samples) // step), 1])
# Extract the variance of the SaO2 in 60 second windows as a feature
for idx, k in enumerate(range(0, (n_samples - step + 1), step)):
X_subj[idx, 0] = np.var(np.transpose(SaO2[k:k + window_size]), axis=1)
Y_subj[idx] = np.max(arousals[k:k + window_size])
# Ignore records that do not contain any arousals
if not np.any(Y_subj):
sys.stderr.write('no arousals found in %s\n' % record_name)
return
print("X_subj.shape: " + str(X_subj.shape))
print("np.ravel(Y_subj).shape: " + str(np.ravel(Y_subj).shape))
# ---------------------------------------------------------------------
# Train a (multi-class) Logistic Regression classifier
# ---------------------------------------------------------------------
my_classifier = LogisticRegression()
my_classifier.fit(X_subj, np.ravel(Y_subj))
# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
# Save this algorithm for submission to Physionet Challenge:
# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
model_file = 'models/%s_model.pkl' % os.path.basename(record_name)
joblib.dump(my_classifier, model_file)
def loaddata(record_name):
L.log_info("Loading record: " + str(record_name))
header_file = record_name + '.hea'
signal_file = record_name + '.mat'
arousal_file = record_name + '-arousal.mat'
# Get the signal names from the header file
signal_names, Fs, n_samples = phyc.import_signal_names(header_file)
signal_names = list(np.append(signal_names, 'arousals'))
this_data = phyc.get_subject_data(arousal_file, signal_file, signal_names)
SaO2 = this_data.get(['SaO2']).values
arousals = this_data.get(['arousals']).values
recordLength = SaO2.size
#print(this_data)
#print(this_data.values)
signals = this_data[
['F3-M2', 'F4-M1', 'C3-M2', 'C4-M1', 'O1-M2', 'O2-M1', 'E1-M2', 'Chin1-Chin2', 'ABD', 'CHEST', 'AIRFLOW',
'SaO2', 'ECG']]
signals = signals.values
arousals=arousals.astype(np.int32)
return signals,arousals, recordLength,SaO2