apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-06-08 15:05:13 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tests and support for additional model output types

Browse source 
Signed-off-by: abigailt <abigailt@il.ibm.com>
This commit is contained in:
abigailt 2024-05-02 15:17:51 +03:00
parent a8ec87f922
commit 0f5a1bcaa0
2 changed files with 20 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
apt/utils/models/model.py
View file

@ -227,6 +227,8 @@ class Model(metaclass=ABCMeta):
count += np.count_nonzero(np.argmax(y[:, i], axis=1) == np.argmax(predicted[:, i], axis=1))
sum += predicted.shape[0] * predicted.shape[-1]
return count / sum
elif self.output_type == ModelOutputType.CLASSIFIER_MULTI_OUTPUT_CATEGORICAL:
return np.count_nonzero(y == predicted) / (predicted.shape[0] * y.shape[1])
elif is_binary(self.output_type):
if is_logits(self.output_type):
if apply_non_linearity:

19
tests/test_model.py
View file

@ -189,7 +189,7 @@ def test_blackbox_classifier_predictions_multi_label_cat():
train = DatasetWithPredictions(y_train, x_train, y_train)
test = DatasetWithPredictions(y_test, x_test, y_test)
data = Data(train, test)
model = BlackboxClassifierPredictions(data, ModelOutputType.CLASSIFIER_SINGLE_OUTPUT_CATEGORICAL)
model = BlackboxClassifierPredictions(data, ModelOutputType.CLASSIFIER_MULTI_OUTPUT_CATEGORICAL)
pred = model.predict(test)
assert (pred.shape[0] == x_test.shape[0])
@ -335,6 +335,23 @@ def test_blackbox_classifier_probabilities():
assert (score == 1.0)
def test_blackbox_classifier_multi_label_probabilities():
(x_train, _), (_, _) = dataset_utils.get_iris_dataset_np()
y_train = np.array([[0.23, 0.56, 0.21] for i in range(105)])
# make multi-label categorical
y_train = np.column_stack((y_train, y_train, y_train))
train = ArrayDataset(x_train, y_train)
data = Data(train)
model = BlackboxClassifierPredictions(data, ModelOutputType.CLASSIFIER_MULTI_OUTPUT_CLASS_PROBABILITIES)
pred = model.predict(train)
assert (pred.shape[0] == x_train.shape[0])
assert (0.0 < pred).all()
assert (pred < 1.0).all()
def test_blackbox_classifier_predict():
def predict(x):
return np.array([[0.23, 0.56, 0.21] for i in range(x.shape[0])])