apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-07-05 16:02:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

categorical features and QI passed by indexes

Browse source 
dataset include feature names and is_pandas param
This commit is contained in:
olasaadi 2022-03-21 21:57:11 +02:00
parent 3263f92bee
commit 8aa7bb8281
3 changed files with 26 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

15
tests/test_anonymizer.py
View file

@ -29,6 +29,7 @@ def test_anonymize_ndarray_iris():
def test_anonymize_pandas_adult():
(x_train, y_train), _ = get_adult_dataset()
print(type(x_train['hours-per-week'][0]))
encoded = OneHotEncoder().fit_transform(x_train)
model = DecisionTreeClassifier()
model.fit(encoded, y_train)
@ -41,13 +42,15 @@ def test_anonymize_pandas_adult():
'native-country']
categorical_features = ['workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
'native-country']
anonymizer = Anonymize(k, QI, categorical_features=categorical_features, features=features)
QI_indexes = [i for i, v in enumerate(features) if v in QI]
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))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
assert (anon.loc[:, QI].value_counts().min() >= k)
assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
# print(type(x_train['hours-per-week'][0]))
#assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
print(type(x_train['hours-per-week'][0]))
@ -63,12 +66,14 @@ def test_anonymize_pandas_nursery():
k = 100
QI = ["finance", "social", "health"]
categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children']
anonymizer = Anonymize(k, QI, categorical_features=categorical_features, features=features)
QI_indexes = [i for i, v in enumerate(features) if v in QI]
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))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
assert (anon.loc[:, QI].value_counts().min() >= k)
assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
# assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
def test_regression():