def test_class_decision_tree(self):
job = self.get_classification_job(
PredictiveModels.CLASSIFICATION.value,
ClassificationMethods.DECISION_TREE.value)
results, _, _ = calculate_hyperopt(job)
self.assertIsNotNone(results)
def test_regression_xgboost(self):
job = self.get_job(PredictiveModels.REGRESSION.value,
RegressionMethods.XGBOOST.value,
HyperOptLosses.RMSE.value)
results, _, _ = calculate_hyperopt(job)
self.assertIsNotNone(results)
def test_class_xgboost(self):
job = self.get_classification_job(
PredictiveModels.CLASSIFICATION.value,
ClassificationMethods.XGBOOST.value)
results, _, _ = calculate_hyperopt(job)
self.assertIsNotNone(results)
def prediction_task(job_id, do_publish_result=True):
logger.info("Start prediction task ID {}".format(job_id))
job = Job.objects.get(id=job_id)
try:
if (job.status == JobStatuses.CREATED.value and job.type != JobTypes.UPDATE.value) or \
(job.status == JobStatuses.CREATED.value and job.type == JobTypes.UPDATE.value and
job.incremental_train.status == JobStatuses.COMPLETED.value):
job.status = JobStatuses.RUNNING.value
job.save()
job_start_time = time.time()
if job.hyperparameter_optimizer is not None and \
job.hyperparameter_optimizer.optimization_method != HyperparameterOptimizationMethods.NONE.value:
result, _, model_split = calculate_hyperopt(job)
else:
result, model_split = calculate(job)
job_elapsed_time = time.time() - job_start_time
logger.info('\tJob took: {} in HH:MM:ss'.format(
time.strftime("%H:%M:%S", time.gmtime(job_elapsed_time))))
if job.create_models:
save_models(model_split, job)
job.result = result
# Evaluation.init(
# job.predictive_model.predictive_model,
# results
# )
job.status = JobStatuses.COMPLETED.value
elif job.status in [
JobStatuses.COMPLETED.value, JobStatuses.ERROR.value,
JobStatuses.RUNNING.value
]:
django_rq.enqueue(prediction_task, job.id)
except Exception as e:
logger.error(e)
job.status = JobStatuses.ERROR.value
job.error = str(e.__repr__())
raise e
finally:
job.save()
if do_publish_result:
publish(job)
def hyperopt_task(job):
# job_dict = job.to_dict()
results, config, model_split = calculate_hyperopt(job)
# method_conf_name = "{}.{}".format(job_dict['type'], job_dict['method'])
# job.config[method_conf_name] = config
return results, model_split
def test_class_randomForest(self):
job = self.get_job(PredictiveModels.CLASSIFICATION.value,
ClassificationMethods.RANDOM_FOREST.value)
results, _, _ = calculate_hyperopt(job)
self.assertIsNotNone(results)
def calculate_helper_hyperopt(job):
start_time = time.time()
calculate_hyperopt(job)
print('Total for %s %s seconds' %
(job['method'], time.time() - start_time))
def setUp(self):
self.job = self.get_regression_job(PredictiveModels.REGRESSION.value,
RegressionMethods.XGBOOST.value)
_, _, _ = calculate_hyperopt(self.job)
def setUp(self):
self.job = self.get_classification_job(
PredictiveModels.CLASSIFICATION.value,
ClassificationMethods.PERCEPTRON.value)
_, _, _ = calculate_hyperopt(self.job)
