apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-08 11:32:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix tests

Browse source
This commit is contained in:
olasaadi 2022-03-24 19:35:26 +02:00
parent 66c86dc595
commit b54f0a2382
2 changed files with 5 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

6
apt/anonymization/anonymizer.py
View file

@ -45,10 +45,10 @@ class Anonymize:
:return: An array containing the anonymized training dataset. :return: An array containing the anonymized training dataset.
""" """
if dataset.features_names is not None: if dataset.features_names is not None:
self._features = dataset.features_names self.features_names = dataset.features_names
# if features is None, use numbers instead of names # if features is None, use numbers instead of names
elif dataset.get_samples().shape[0] != 0: elif dataset.get_samples().shape[0] != 0:
self._features = [i for i in range(dataset.get_samples().shape[0])] self.features_names = [i for i in range(dataset.get_samples().shape[0])]
else: else:
raise ValueError('No data provided') raise ValueError('No data provided')
if not set(self.quasi_identifiers).issubset(set(self.features_names)): if not set(self.quasi_identifiers).issubset(set(self.features_names)):
@ -63,7 +63,7 @@ class Anonymize:
transformed = self._anonymize(dataset.get_samples().copy(), dataset.get_labels()) transformed = self._anonymize(dataset.get_samples().copy(), dataset.get_labels())
if dataset.is_pandas: if dataset.is_pandas:
return pd.DataFrame(transformed, columns=self._features) return pd.DataFrame(transformed, columns=self.features_names)
else: else:
return transformed return transformed

8
tests/test_anonymizer.py
View file

@ -41,9 +41,7 @@ def test_anonymize_pandas_adult():
'native-country'] 'native-country']
categorical_features = ['workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex', categorical_features = ['workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
'native-country'] 'native-country']
QI_indexes = [i for i, v in enumerate(features) if v in QI] anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
categorical_features_indexes = [i for i, v in enumerate(features) if v in categorical_features]
anonymizer = Anonymize(k, QI_indexes, categorical_features=categorical_features_indexes)
anon = anonymizer.anonymize(ArrayDataset(x_train, pred, features)) anon = anonymizer.anonymize(ArrayDataset(x_train, pred, features))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0]) assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
@ -62,9 +60,7 @@ def test_anonymize_pandas_nursery():
k = 100 k = 100
QI = ["finance", "social", "health"] QI = ["finance", "social", "health"]
categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children'] categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children']
QI_indexes = [i for i, v in enumerate(features) if v in QI] anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
categorical_features_indexes = [i for i, v in enumerate(features) if v in categorical_features]
anonymizer = Anonymize(k, QI_indexes, categorical_features=categorical_features_indexes)
anon = anonymizer.anonymize(ArrayDataset(x_train, pred)) anon = anonymizer.anonymize(ArrayDataset(x_train, pred))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0]) assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])