def run_extra_tree(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Extremely Random Forest Regression'))
if not self.batch:
results = CLFManager.factory(self.patientId, model="et").predict()
return results
else:
clf = CLFManager.factory(self.patientId, model="et")
return clf.batch_predict(), clf._allFeatureDesp
def run_incremental_random_forest(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Random Forest Regression'))
results = CLFManager.factory(self.patientId,
model="incremental").predict()
return results
def run_global(self):
'''
Run global model
:return:
'''
self.log.info(
"Running global classification using algorithm '{}'".format(
self.patientId, 'Naive Bayes'))
return CLFManager.factory(model="global").predict()
def run_nb(self):
'''
Run Naive Bayes
:return:
'''
self.log.info(
"Running classification for patient {} using algorithm '{}'".
format(self.patientId, 'Naive Bayes'))
return CLFManager.factory(self.patientId, model="nb").predict()
def run_svm(self):
'''
Run SVM
:return:
'''
self.log.info(
"Running classification for patient {} using algorithm '{}'".
format(self.patientId, 'SVM'))
return CLFManager.factory(self.patientId, model="svm").predict()
def run_dummy(self):
'''
Run Dummy classifier
:return:
'''
self.log.info(
"Running classification for patient {} using algorithm '{}'".
format(self.patientId, 'Dummy'))
return CLFManager.factory(self.patientId, model="dummy").predict()
def run_extra_tree_classifier(self):
'''
Run Extr TRee Classifier
:return:
'''
self.log.info(
"Running classification for patient {} using algorithm '{}'".
format(self.patientId, 'Extremely Random Forest'))
return CLFManager.factory(self.patientId, model="etc").predict()
def run_random_forest_classifier(self):
'''
Run Random Forest Classifier
:return:
'''
self.log.info(
"Running classification for patient {} using algorithm '{}'".
format(self.patientId, 'Random Forest'))
return CLFManager.factory(self.patientId, model="rfc").predict()
def run_fixed_model(self):
"""
Runs RNN prediction.
:return:
"""
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'FixedModel'))
fixed_model = CLFManager.factory(self.patientId, model="fm")
return fixed_model.predict()
def run_rnn(self):
"""
Runs RNN prediction.
:return:
"""
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Recurrent Neural Networks'))
rnn = CLFManager.factory(self.patientId, model="rnn")
return rnn.predict()
def run_lstm(self):
"""
Runs LSTM prediction.
:return:
"""
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'LSTM-Recurrent Neural Networks'))
lstm = CLFManager.factory(self.patientId, model="lstm")
return lstm.predict()
def run_arima(self):
"""
Runs ARIMA prediction.
:return:
"""
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'ARIMA'))
arima = CLFManager.factory(self.patientId, model="arima")
return arima.predict()
def run_avg(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Avg training value'))
return CLFManager.factory(self.patientId, model="avg").predict()
def run_linear_regression(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Linear Regression'))
return CLFManager.factory(self.patientId, model="lr").predict()
def run_context_avg(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Weigted AVG in similar context'))
return CLFManager.factory(self.patientId, model="contextavg").predict()
def run_last_value(self):
self.log.info(
"Running prediction for patient {} using algorithm '{}'".format(
self.patientId, 'Last value'))
return CLFManager.factory(self.patientId, model="last").predict()
