def get_feature_pipelines(sort_by=FeaturePipeline.start_time,
response_type="json",
**kwargs):
assert_response_type(response_type)
q = session.query(FeaturePipeline)
q = sort_and_filter(q, sort_by=sort_by, **kwargs)
return build_response(q.all(), response_type)
def get_predictor_details(predictor_id=None, response_type="json"):
assert_response_type(response_type)
predictor_id = predictor_id or request.args.get('predictor', type=int)
predictor = Predictor.load(id=predictor_id)
if response_type == 'object':
return predictor
else:
return build_response(cohort.as_dict(), response_type)
def get_predictors(sort_by=Predictor.created_at,
response_type="json",
**kwargs):
assert_response_type(response_type)
q = session.query(Predictor)
q = sort_and_filter(q, sort_by=sort_by, **kwargs)
if response_type == 'object':
return q.all()
else:
return build_response(q.all(), response_type)
def get_training_configuration(
pipeline_id=None,
response_type="json",
config=None
):
assert_response_type(response_type)
pipeline_id = pipeline_id or request.args.get('pipeline', type=int)
config = config or request.args
tc = TrainingConfiguration.load_by_config(pipeline_id, config)
return build_response(tc, response_type)
def predict_outcome(predictor_id=None,
features=[],
patient_id=None,
response_type="json"):
"""
Load predictor and predict outcome for patient
"""
assert_response_type(response_type)
predictor_id = predictor_id or request.args.get('predictor', type=int)
predictor = Predictor.load(id=predictor_id)
if not features:
if patient_id is None:
# special case, because patient_id could be 0 (evaluates False)
patient_id = request.args.get('patient', type=int)
df = predictor.get_data()
del df[predictor.training_configuration.target]
features = list(df.iloc[patient_id])
prediction = {
'predicted_label': predictor.clf.predict([features])[0],
'class_probabilities':
predictor.clf.predict_proba([features])[0].tolist()
}
return build_response(prediction, response_type)
def get_training_results(
pipeline_id=None,
columns=DEFAULT_COLUMNS,
metrics=DEFAULT_METRICS,
response_type="json",
**kwargs
):
assert_response_type(response_type)
pipeline_id = pipeline_id or request.args.get('pipeline', type=int)
assert pipeline_id is not None
q = session.query(
TrainingResult
).join(
TrainingConfiguration,
TrainingResult.training_configuration_id == TrainingConfiguration.id
).filter(
TrainingConfiguration.training_pipeline_id == pipeline_id
).with_entities(
*columns,
*metrics
)
q = sort_and_filter(q, **kwargs)
results = [row._asdict() for row in q]
return build_response(results, response_type)
def get_cohort_details(cohort_id=None, response_type="json"):
assert_response_type(response_type)
cohort_id = cohort_id or request.args.get('cohort', type=int)
assert cohort_id is not None
cohort = Cohort.load(id=cohort_id)
return build_response(cohort.as_dict(), response_type)
def get_cohorts(sort_by=Cohort.created_at, response_type="json", **kwargs):
assert_response_type(response_type)
q = session.query(Cohort)
q = sort_and_filter(q, sort_by=sort_by, **kwargs)
return build_response(q.all(), response_type)