def describe_pipeline(self, pipeline_id, return_dict=False):
"""Describe a pipeline
Arguments:
pipeline_id (int): pipeline to describe
return_dict (bool): If True, return dictionary of information
about pipeline. Defaults to False.
Returns:
Description of specified pipeline. Includes information such as
type of pipeline components, problem, training time, cross validation, etc.
"""
if pipeline_id not in self._results['pipeline_results']:
raise PipelineNotFoundError("Pipeline not found")
pipeline = self.get_pipeline(pipeline_id)
pipeline_results = self._results['pipeline_results'][pipeline_id]
pipeline.describe()
log_subtitle(logger, "Training")
logger.info("Training for {} problems.".format(pipeline.problem_type))
if self.optimize_thresholds and self.objective.is_defined_for_problem_type(
ProblemTypes.BINARY) and self.objective.can_optimize_threshold:
logger.info(
"Objective to optimize binary classification pipeline thresholds for: {}"
.format(self.objective))
logger.info("Total training time (including CV): %.1f seconds" %
pipeline_results["training_time"])
log_subtitle(logger, "Cross Validation", underline="-")
all_objective_scores = [
fold["all_objective_scores"]
for fold in pipeline_results["cv_data"]
]
all_objective_scores = pd.DataFrame(all_objective_scores)
for c in all_objective_scores:
if c in ["# Training", "# Validation"]:
all_objective_scores[c] = all_objective_scores[c].astype(
"object")
continue
mean = all_objective_scores[c].mean(axis=0)
std = all_objective_scores[c].std(axis=0)
all_objective_scores.loc["mean", c] = mean
all_objective_scores.loc["std", c] = std
all_objective_scores.loc[
"coef of var", c] = std / mean if abs(mean) > 0 else np.inf
all_objective_scores = all_objective_scores.fillna("-")
with pd.option_context('display.float_format', '{:.3f}'.format,
'expand_frame_repr', False):
logger.info(all_objective_scores)
if return_dict:
return pipeline_results
def test_logger_title(capsys, caplog, logger_env_cleanup):
logger = get_logger(TEST_LOGGER_NAME)
log_title(logger, "Log title")
assert "Log title" in caplog.text
caplog.clear()
log_subtitle(logger, "Log subtitle")
assert "Log subtitle" in caplog.text