def select_problem(self, selection, parameter=None):
"""Select a prediction problem and extract information.
Update the select_problem attribute and generate the cutoff times,
the target entity and update the entityset.
Args:
selection: Name of the chosen prediction problem.
data: Entityset representation of the data.
parameters: A variable to change the default parameters, if any.
Returns:
The updated version of the entityset and cutoff time label.
"""
# problem selection
if selection == 'LengthOfStay':
self.chosen_problem = LengthOfStay()
elif selection == 'MortalityPrediction':
self.chosen_problem = MortalityPrediction()
elif selection == 'MissedAppointmentProblemDefinition':
self.chosen_problem = MissedAppointmentProblemDefinition()
elif selection == 'ProlongedLengthOfStay' and parameter:
self.chosen_problem = ProlongedLengthOfStay(parameter)
elif selection == 'ProlongedLengthOfStay':
self.chosen_problem = ProlongedLengthOfStay()
elif selection == 'Readmission' and parameter:
self.chosen_problem = Readmission(parameter)
elif selection == 'Readmission':
self.chosen_problem = Readmission()
elif selection == 'DiagnosisPrediction' and parameter:
self.chosen_problem = DiagnosisPrediction(parameter)
elif selection == 'DiagnosisPrediction':
raise ValueError('unspecified diagnosis code')
else:
raise ValueError('{} is not a defined problem'.format(selection))
# target label calculation
self.es, self.target_entity, cutoff = self.chosen_problem.generate_cutoff_times(
self.es)
return cutoff
def test_generate_labels_success_threshold(entityset_success, cutoff_times):
es, _, generated_df = Readmission(6).generate_cutoff_times(
entityset_success)
generated_df.index = cutoff_times.index # both should have the same index
labels = list(generated_df['label'])
assert labels == [False, False, False, True, False, False]
def readmission():
return Readmission()
def select_problem(self, selection, parameter=None):
"""Select a prediction problem and extract information.
Update the select_problem attribute and generate the cutoff times,
the target entity and update the entityset.
Args:
selection (str):
Name of the chosen prediction problem.
parameters (dict):
Variables to change the default parameters, if any.
Returns:
featuretools.EntitySet, str, pandas.DataFrame:
* An updated EntitySet if a new column is generated.
* A string indicating the selected target entity.
* A dataframe of cutoff times and their target labels.
"""
LOGGER.info("Selecting %s prediction problem", selection)
# problem selection
if selection == 'LengthOfStay':
self.chosen_problem = LengthOfStay()
elif selection == 'MortalityPrediction':
self.chosen_problem = MortalityPrediction()
elif selection == 'MissedAppointment':
self.chosen_problem = MissedAppointment()
elif selection == 'ProlongedLengthOfStay' and parameter:
self.chosen_problem = ProlongedLengthOfStay(parameter)
elif selection == 'ProlongedLengthOfStay':
self.chosen_problem = ProlongedLengthOfStay()
elif selection == 'Readmission' and parameter:
self.chosen_problem = Readmission(parameter)
elif selection == 'Readmission':
self.chosen_problem = Readmission()
elif selection == 'DiagnosisPrediction' and parameter:
self.chosen_problem = DiagnosisPrediction(parameter)
elif selection == 'DiagnosisPrediction':
raise ValueError('unspecified diagnosis code')
else:
raise ValueError('{} is not a defined problem'.format(selection))
# target label calculation
self.es, self.target_entity, cutoff = self.chosen_problem.generate_cutoff_times(self.es)
# set default pipeline
if self.chosen_problem.prediction_type == "classification":
pipeline = "Random Forest"
else:
pipeline = "Random Forest Regressor"
self.modeler = Modeler(pipeline, self.chosen_problem.prediction_type)
return cutoff