def fmax(param_dict):
print(param_dict)
support, confidence = param_dict["support"] / 1000, param_dict[
"confidence"] / 1000
print(dict(support=support, confidence=confidence))
cba = CBA(support=support, confidence=confidence)
cba.fit(txns)
cba_clf = cba.clf
ids = IDS()
ids_clf = IDSClassifier(
IDSRuleSet.from_cba_rules(cba_clf.rules).ruleset)
ids_clf.quant_dataframe_train = quant_df
ids_clf.calculate_default_class()
ids.clf = ids_clf
metrics = ids.score_interpretability_metrics(quant_df_test)
if not is_solution_interpretable(metrics):
distance = solution_interpretability_distance(metrics)
print(-distance)
return -distance
auc = ids.score_auc(quant_df_test)
print(auc)
return auc
def fmax(param_dict):
print(param_dict)
support, confidence = param_dict["support"] / 1000, param_dict["confidence"] / 1000
print(dict(support=support, confidence=confidence))
cba = CBA(support=support, confidence=confidence)
cba.fit(txns)
cba_clf = cba.clf
ids = IDS()
ids_clf = IDSClassifier(IDSRuleSet.from_cba_rules(cba_clf.rules).ruleset)
ids_clf.quant_dataframe_train = quant_df
ids_clf.calculate_default_class()
ids.clf = ids_clf
auc = ids.score_auc(quant_df_test)
print(auc)
return auc
best_pars = coord_asc.fit()
print("best_pars:", best_pars)
support, confidence = best_pars[0] / 1000, best_pars[1] / 1000
cba = CBA(support=support, confidence=confidence)
cba.fit(txns)
cba_clf = cba.clf
ids = IDS()
ids_clf = IDSClassifier(
IDSRuleSet.from_cba_rules(cba_clf.rules).ruleset)
ids_clf.quant_dataframe_train = quant_df
ids_clf.calculate_default_class()
ids.clf = ids_clf
data = dict(dataset_name=dataset_name,
algorithm="pyARC",
auc=ids.score_auc(quant_df_test, order_type="cba"),
rule_cutoff=rule_cutoff)
data.update(ids.score_interpretability_metrics(quant_df_test))
print(data)
benchmark_data.append(data)
benchmark_data_df = pd.DataFrame(benchmark_data)
benchmark_data_df.to_csv(
"output_data/cba_auc_interpretability_distance_coats_benchmark_lymph_anneal.csv"
df_train = pd.read_csv(os.path.join(dataset_path_train, dataset_filename))
df_test = pd.read_csv(os.path.join(dataset_path_test, dataset_filename))
txns_train = TransactionDB.from_DataFrame(df_train)
txns_test = TransactionDB.from_DataFrame(df_test)
quant_df_train = QuantitativeDataFrame(df_train)
quant_df_test = QuantitativeDataFrame(df_test)
cba = CBA(support=0.1, confidence=0.1)
cba.fit(txns_train)
rules = cba.clf.rules
ids_ruleset = IDSRuleSet.from_cba_rules(rules)
ids = IDS()
ids.clf = IDSClassifier(ids_ruleset.ruleset)
ids.clf.default_class = cba.clf.default_class
metrics_dict = ids.score_interpretability_metrics(quant_df_test)
benchmark_dict = dict(dataset_filename=dataset_filename, algorithm="cba")
benchmark_dict.update(metrics_dict)
print(benchmark_dict)
benchmark_list.append(benchmark_dict)
benchmark_df = pd.DataFrame(benchmark_list)
benchmark_df.to_csv("output_data/cba_interpretability_benchmark.csv",
index=False)