apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-07-11 16:22:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Formatting (#68)

Browse source 
Fix most flake/lint errors and ignore a few others

Signed-off-by: abigailt <abigailt@il.ibm.com>
This commit is contained in:
abigailgold 2022-12-25 15:13:57 +02:00 • committed by GitHub
parent b47ba24906
commit d52fcd0041
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 91 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/test_anonymizer.py
View file

@ -24,7 +24,7 @@ def test_anonymize_ndarray_iris():
QI = [0, 2]
anonymizer = Anonymize(k, QI, train_only_QI=True)
anon = anonymizer.anonymize(ArrayDataset(x_train, pred))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
assert (len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
_, counts_elements = np.unique(anon[:, QI], return_counts=True)
assert (np.min(counts_elements) >= k)
assert ((np.delete(anon, QI, axis=1) == np.delete(x_train, QI, axis=1)).all())
@ -60,7 +60,7 @@ def test_anonymize_pandas_adult():
anonymizer = Anonymize(k, QI, categorical_features=categorical_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])
assert (anon.loc[:, QI].value_counts().min() >= k)
np.testing.assert_array_equal(anon.drop(QI, axis=1), x_train.drop(QI, axis=1))
@ -93,7 +93,7 @@ def test_anonymize_pandas_nursery():
anonymizer = Anonymize(k, QI, categorical_features=categorical_features, train_only_QI=True)
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])
assert (anon.loc[:, QI].value_counts().min() >= k)
np.testing.assert_array_equal(anon.drop(QI, axis=1), x_train.drop(QI, axis=1))
@ -112,7 +112,7 @@ def test_regression():
print('Base model accuracy (R2 score): ', model.score(x_test, y_test))
model.fit(anon, y_train)
print('Base model accuracy (R2 score) after anonymization: ', model.score(x_test, y_test))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
assert (len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
_, counts_elements = np.unique(anon[:, QI], return_counts=True)
assert (np.min(counts_elements) >= k)
assert ((np.delete(anon, QI, axis=1) == np.delete(x_train, QI, axis=1)).all())