apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-04-27 13:56:22 +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

8
apt/utils/datasets/datasets.py
View file

@ -29,10 +29,9 @@ def array2numpy(self, arr: INPUT_DATA_ARRAY_TYPE) -> OUTPUT_DATA_ARRAY_TYPE:
converts from INPUT_DATA_ARRAY_TYPE to numpy array
"""
if type(arr) == np.ndarray:
self.is_numpy = True
return arr
if type(arr) == pd.DataFrame or type(arr) == pd.Series:
self.is_numpy = False
self.is_pandas = True
return arr.to_numpy()
if isinstance(arr, list):
return np.array(arr)
@ -171,9 +170,12 @@ class ArrayDataset(Dataset):
:param y: collection of labels (optional)
:param kwargs: dataset parameters
"""
self.is_numpy = True
self.is_pandas = False
self.features_names = None
self._y = array2numpy(self, y) if y is not None else None
self._x = array2numpy(self, x)
if self.is_pandas:
self.features_names = x.columns
if y is not None and len(self._x) != len(self._y):
raise ValueError('Non equivalent lengths of x and y')