apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-11 04:52:36 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Support for many new model output types (#93)

Browse source 
* General model wrappers and methods supporting multi-label classifiers
* Support for pytorch multi-label binary classifier
* New model output types + single implementation of score method that supports multiple output types. 
* Anonymization with pytorch multi-output binary model
* Support for multi-label binary models in minimizer. 
* Support for multi-label logits/probabilities
---------
Signed-off-by: abigailt <abigailt@il.ibm.com>
This commit is contained in:
abigailgold 2024-07-03 09:04:59 -04:00 • committed by GitHub
parent e00535d120
commit 57e38ea4fa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 913 additions and 172 deletions
Download patch file Download diff file Expand all files Collapse all files

14
apt/utils/models/sklearn_model.py
View file

@ -2,8 +2,8 @@ from typing import Optional
from sklearn.base import BaseEstimator
from apt.utils.models import Model, ModelOutputType, get_nb_classes, check_correct_model_output
from apt.utils.datasets import Dataset, OUTPUT_DATA_ARRAY_TYPE
from apt.utils.models import Model, ModelOutputType, get_nb_classes
from apt.utils.datasets import Dataset, ArrayDataset, OUTPUT_DATA_ARRAY_TYPE
from art.estimators.classification.scikitlearn import SklearnClassifier as ArtSklearnClassifier
from art.estimators.regression.scikitlearn import ScikitlearnRegressor
@ -48,7 +48,7 @@ class SklearnClassifier(SklearnModel):
super().__init__(model, output_type, black_box_access, unlimited_queries, **kwargs)
self._art_model = ArtSklearnClassifier(model, preprocessing=None)
def fit(self, train_data: Dataset, **kwargs) -> None:
def fit(self, train_data: ArrayDataset, **kwargs) -> None:
"""
Fit the model using the training data.
@ -58,11 +58,11 @@ class SklearnClassifier(SklearnModel):
:return: None
"""
y = train_data.get_labels()
self.nb_classes = get_nb_classes(y)
self.nb_classes = get_nb_classes(y, self.output_type)
y_encoded = check_and_transform_label_format(y, nb_classes=self.nb_classes)
self._art_model.fit(train_data.get_samples(), y_encoded, **kwargs)
def predict(self, x: Dataset, **kwargs) -> OUTPUT_DATA_ARRAY_TYPE:
def predict(self, x: ArrayDataset, **kwargs) -> OUTPUT_DATA_ARRAY_TYPE:
"""
Perform predictions using the model for input `x`.
@ -71,7 +71,7 @@ class SklearnClassifier(SklearnModel):
:return: Predictions from the model as numpy array (class probabilities, if supported).
"""
predictions = self._art_model.predict(x.get_samples(), **kwargs)
check_correct_model_output(predictions, self.output_type)
# check_correct_model_output(predictions, self.output_type)
return predictions
@ -93,7 +93,7 @@ class SklearnRegressor(SklearnModel):
"""
def __init__(self, model: BaseEstimator, black_box_access: Optional[bool] = True,
unlimited_queries: Optional[bool] = True, **kwargs):
super().__init__(model, ModelOutputType.REGRESSOR_SCALAR, black_box_access, unlimited_queries, **kwargs)
super().__init__(model, ModelOutputType.REGRESSION, black_box_access, unlimited_queries, **kwargs)
self._art_model = ScikitlearnRegressor(model)
def fit(self, train_data: Dataset, **kwargs) -> None: