apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-07-02 16:01:00 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix notebook and add features_names to ArrayDataset

Browse source 
and allow providing features names in QI and Cat features not just indexes
This commit is contained in:
olasaadi 2022-03-24 19:32:24 +02:00
parent 137167fb0c
commit 66c86dc595
5 changed files with 89 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/test_anonymizer.py
View file

@ -44,7 +44,7 @@ def test_anonymize_pandas_adult():
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))
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].value_counts().min() >= k)