def _extract_selection_performance_per_metric(selection_state: HPSelectionState, metric: Metric, split_count):
performance = {"setting": [], **{f"split {i + 1}": [] for i in range(split_count)}}
for hp_setting, hp_item_list in selection_state.hp_items.items():
performance['setting'].append(str(hp_setting))
for index, hp_item in enumerate(hp_item_list):
performance[f'split {index + 1}'].append(HPHTMLBuilder._print_metric(hp_item.performance, metric))
s = io.StringIO()
pd.DataFrame(performance).rename(columns={"setting": 'Hyperparameter settings (preprocessing, encoding, ML method)'}).to_csv(s, sep="\t",
index=False)
return Util.get_table_string_from_csv_string(s.getvalue(), separator="\t")
def _extract_assessment_performances_per_metric(state: TrainMLModelState, assessment_state: HPAssessmentState, label: str) -> str:
performance_metric = {"setting": [], **{metric.name.lower(): [] for metric in state.metrics}}
for hp_setting, hp_item in assessment_state.label_states[label].assessment_items.items():
performance_metric['setting'].append(str(hp_setting))
for metric in sorted(state.metrics, key=lambda metric: metric.name.lower()):
performance_metric[metric.name.lower()].append(HPHTMLBuilder._print_metric(hp_item.performance, metric))
s = io.StringIO()
pd.DataFrame(performance_metric).rename(columns={"setting": 'Hyperparameter settings (preprocessing, encoding, ML method)'})\
.to_csv(s, sep="\t", index=False)
return Util.get_table_string_from_csv_string(s.getvalue(), separator="\t")