def test_adult_no_drop():
ad = AdultDataset(protected_attribute_names=['sex'],
privileged_classes=[['Male']],
categorical_features=[],
features_to_keep=['age', 'education-num'])
bldm = BinaryLabelDatasetMetric(ad)
assert bldm.num_instances() == 48842
def test_adult():
ad = AdultDataset()
# print(ad.feature_names)
assert np.isclose(ad.labels.mean(), 0.2478, atol=5e-5)
bldm = BinaryLabelDatasetMetric(ad)
assert bldm.num_instances() == 45222
def explain(self, request: Dict) -> Dict:
inputs = request["instances"]
predictions = np.array(request["outputs"])
dataframe_predicted = pd.DataFrame(inputs, columns=self.feature_names)
dataframe_predicted[self.label_names[0]] = predictions
dataset_predicted = BinaryLabelDataset(
favorable_label=self.favorable_label,
unfavorable_label=self.unfavorable_label,
df=dataframe_predicted,
label_names=self.label_names,
protected_attribute_names=['age'])
metrics = BinaryLabelDatasetMetric(
dataset_predicted,
unprivileged_groups=self.unprivileged_groups,
privileged_groups=self.privileged_groups)
return {
"predictions": predictions.tolist(),
"metrics": {
"base_rate":
metrics.base_rate(),
"consistency":
metrics.consistency().tolist(),
"disparate_impact":
metrics.disparate_impact(),
"num_instances":
metrics.num_instances(),
"num_negatives":
metrics.num_negatives(),
"num_positives":
metrics.num_positives(),
"statistical_parity_difference":
metrics.statistical_parity_difference(),
}
}
def test_german():
gd = GermanDataset()
bldm = BinaryLabelDatasetMetric(gd)
assert bldm.num_instances() == 1000
