apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-03 08:42:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Documentation updates (#29)

Browse source 
* Bump version to 0.1.0 (breaking changes to some APIs)

* Update documentation

* Update requirements

* gitignore
This commit is contained in:
abigailgold 2022-05-02 11:46:18 +03:00 • committed by GitHub
parent 014aed9670
commit fd6be8e778
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 640 additions and 298 deletions
Download patch file Download diff file Expand all files Collapse all files

63
apt/utils/models/sklearn_model.py
View file

@ -22,6 +22,7 @@ class SklearnModel(Model):
:param test_data: Test data.
:type train_data: `Dataset`
:return: the score as float (for classifiers, between 0 and 1)
"""
return self.model.score(test_data.get_samples(), test_data.get_labels(), **kwargs)
@ -29,23 +30,23 @@ class SklearnModel(Model):
class SklearnClassifier(SklearnModel):
"""
Wrapper class for scikitlearn classification models.
:param model: The original sklearn model object.
:type model: scikitlearn classifier object
:param output_type: The type of output the model yields (vector/label only)
:type output_type: `ModelOutputType`
:param black_box_access: Boolean describing the type of deployment of the model (when in production).
Set to True if the model is only available via query (API) access, i.e.,
only the outputs of the model are exposed, and False if the model internals
are also available. Default is True.
:type black_box_access: boolean, optional
:param unlimited_queries: If black_box_access is True, this boolean indicates whether a user can perform
unlimited queries to the model API or whether there is a limit to the number of
queries that can be submitted. Default is True.
:type unlimited_queries: boolean, optional
"""
def __init__(self, model: BaseEstimator, output_type: ModelOutputType, black_box_access: Optional[bool] = True,
unlimited_queries: Optional[bool] = True, **kwargs):
"""
Initialize a `SklearnClassifier` wrapper object.
:param model: The original sklearn model object.
:param output_type: The type of output the model yields (vector/label only for classifiers,
value for regressors)
:param black_box_access: Boolean describing the type of deployment of the model (when in production).
Set to True if the model is only available via query (API) access, i.e.,
only the outputs of the model are exposed, and False if the model internals
are also available. Optional, Default is True.
:param unlimited_queries: If black_box_access is True, this boolean indicates whether a user can perform
unlimited queries to the model API or whether there is a limit to the number of
queries that can be submitted. Optional, Default is True.
"""
super().__init__(model, output_type, black_box_access, unlimited_queries, **kwargs)
self._art_model = ArtSklearnClassifier(model)
@ -55,6 +56,7 @@ class SklearnClassifier(SklearnModel):
:param train_data: Training data.
:type train_data: `Dataset`
:return: None
"""
encoder = OneHotEncoder(sparse=False)
y_encoded = encoder.fit_transform(train_data.get_labels().reshape(-1, 1))
@ -65,8 +67,8 @@ class SklearnClassifier(SklearnModel):
Perform predictions using the model for input `x`.
:param x: Input samples.
:type x: `np.ndarray` or `pandas.DataFrame`
:return: Predictions from the model (class probabilities, if supported).
:type x: `Dataset`
:return: Predictions from the model as numpy array (class probabilities, if supported).
"""
return self._art_model.predict(x, **kwargs)
@ -74,21 +76,21 @@ class SklearnClassifier(SklearnModel):
class SklearnRegressor(SklearnModel):
"""
Wrapper class for scikitlearn regression models.
:param model: The original sklearn model object.
:type model: scikitlearn regressor object
:param black_box_access: Boolean describing the type of deployment of the model (when in production).
Set to True if the model is only available via query (API) access, i.e.,
only the outputs of the model are exposed, and False if the model internals
are also available. Default is True.
:type black_box_access: boolean, optional
:param unlimited_queries: If black_box_access is True, this boolean indicates whether a user can perform
unlimited queries to the model API or whether there is a limit to the number of
queries that can be submitted. Default is True.
:type unlimited_queries: boolean, optional
"""
def __init__(self, model: BaseEstimator, black_box_access: Optional[bool] = True,
unlimited_queries: Optional[bool] = True, **kwargs):
"""
Initialize a `SklearnRegressor` wrapper object.
:param model: The original sklearn model object.
:param black_box_access: Boolean describing the type of deployment of the model (when in production).
Set to True if the model is only available via query (API) access, i.e.,
only the outputs of the model are exposed, and False if the model internals
are also available. Optional, Default is True.
:param unlimited_queries: If black_box_access is True, this boolean indicates whether a user can perform
unlimited queries to the model API or whether there is a limit to the number of
queries that can be submitted. Optional, Default is True.
"""
super().__init__(model, ModelOutputType.REGRESSOR_SCALAR, black_box_access, unlimited_queries, **kwargs)
self._art_model = ScikitlearnRegressor(model)
@ -98,6 +100,7 @@ class SklearnRegressor(SklearnModel):
:param train_data: Training data.
:type train_data: `Dataset`
:return: None
"""
self._art_model.fit(train_data.get_samples(), train_data.get_labels(), **kwargs)
@ -106,7 +109,7 @@ class SklearnRegressor(SklearnModel):
Perform predictions using the model for input `x`.
:param x: Input samples.
:type x: `np.ndarray` or `pandas.DataFrame`
:return: Predictions from the model.
:type x: `Dataset`
:return: Predictions from the model as numpy array.
"""
return self._art_model.predict(x, **kwargs)