apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-07 02:52:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

update docstring

Browse source
This commit is contained in:
olasaadi 2022-03-28 00:07:04 +03:00
parent b54f0a2382
commit 3bc1341dad
2 changed files with 8 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
apt/anonymization/anonymizer.py
View file

@ -22,8 +22,10 @@ class Anonymize:
"""
:param k: The privacy parameter that determines the number of records that will be indistinguishable from each
other (when looking at the quasi identifiers). Should be at least 2.
:param quasi_identifiers: The features that need to be minimized.
:param categorical_features: The list of categorical features.
:param quasi_identifiers: The features that need to be minimized. It can be a list of feature name (strings) if
dataset.feature_names is set, otherwise a list of indexes (integers).
:param categorical_features: The list of categorical features. It can be a list of feature name (strings) if
dataset.feature_names is set, otherwise a list of indexes (integers).
:param is_regression: Boolean param indicates that is is a regression problem.
"""
if k < 2:
@ -48,7 +50,7 @@ class Anonymize:
self.features_names = dataset.features_names
# if features is None, use numbers instead of names
elif dataset.get_samples().shape[0] != 0:
self.features_names = [i for i in range(dataset.get_samples().shape[0])]
self.features_names = [i for i in range(dataset.get_samples().shape[1])]
else:
raise ValueError('No data provided')
if not set(self.quasi_identifiers).issubset(set(self.features_names)):

5
apt/utils/datasets/datasets.py
View file

@ -162,12 +162,13 @@ class StoredDataset(Dataset):
class ArrayDataset(Dataset):
"""Dataset that is based on x and y arrays (e.g., numpy/pandas/list...)"""
def __init__(self, x: INPUT_DATA_ARRAY_TYPE, y: Optional[INPUT_DATA_ARRAY_TYPE] = None, features_names=None,
**kwargs):
def __init__(self, x: INPUT_DATA_ARRAY_TYPE, y: Optional[INPUT_DATA_ARRAY_TYPE] = None,
features_names: Optional = None, **kwargs):
"""
ArrayDataset constructor.
:param x: collection of data samples
:param y: collection of labels (optional)
:param feature_names: list of str, The feature names, in the order that they appear in the data (optional)
:param kwargs: dataset parameters
"""
self.is_pandas = False