apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-06 18:42:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

using dataset wrapper on anonymizer

Browse source
This commit is contained in:
olasaadi 2022-03-01 02:28:41 +02:00
parent f2df2fcc8c
commit 1280b849f4
3 changed files with 64 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

70
tests/test_anonymizer.py
View file

@ -7,29 +7,29 @@ from apt.anonymization import Anonymize
from apt.utils.dataset_utils import get_iris_dataset, get_adult_dataset, get_nursery_dataset
from sklearn.datasets import load_diabetes
from sklearn.model_selection import train_test_split
from apt.utils.datasets import BaseDataset, Data
def test_anonymize_ndarray_iris():
(x_train, y_train), _ = get_iris_dataset()
dataset = get_iris_dataset()
model = DecisionTreeClassifier()
model.fit(x_train, y_train)
pred = model.predict(x_train)
model.fit(dataset.get_train_samples(), dataset.get_train_labels())
pred = model.predict(dataset.get_train_samples())
k = 10
QI = [0, 2]
anonymizer = Anonymize(k, QI)
anon = anonymizer.anonymize(x_train, pred)
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
anon = anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), pred))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(dataset.get_train_samples()[:, QI], axis=0)))
_, counts_elements = np.unique(anon[:, QI], return_counts=True)
assert (np.min(counts_elements) >= k)
assert ((np.delete(anon, QI, axis=1) == np.delete(x_train, QI, axis=1)).all())
assert ((np.delete(anon, QI, axis=1) == np.delete(dataset.get_train_samples(), QI, axis=1)).all())
def test_anonymize_pandas_adult():
(x_train, y_train), _ = get_adult_dataset()
encoded = OneHotEncoder().fit_transform(x_train)
dataset = get_adult_dataset()
encoded = OneHotEncoder().fit_transform(dataset.get_train_samples())
model = DecisionTreeClassifier()
model.fit(encoded, y_train)
model.fit(encoded, dataset.get_train_labels())
pred = model.predict(encoded)
k = 100
@ -38,51 +38,51 @@ def test_anonymize_pandas_adult():
categorical_features = ['workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
'native-country']
anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
anon = anonymizer.anonymize(x_train, pred)
anon = anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), pred))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
assert(anon.loc[:, QI].drop_duplicates().shape[0] < dataset.get_train_samples().loc[:, QI].drop_duplicates().shape[0])
assert (anon.loc[:, QI].value_counts().min() >= k)
assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
assert (anon.drop(QI, axis=1).equals(dataset.get_train_samples().drop(QI, axis=1)))
def test_anonymize_pandas_nursery():
(x_train, y_train), _ = get_nursery_dataset()
x_train = x_train.astype(str)
encoded = OneHotEncoder().fit_transform(x_train)
dataset = get_nursery_dataset()
encoded = OneHotEncoder().fit_transform(dataset.get_train_samples())
model = DecisionTreeClassifier()
model.fit(encoded, y_train)
model.fit(encoded, dataset.get_train_labels())
pred = model.predict(encoded)
k = 100
QI = ["finance", "social", "health"]
categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children']
anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
anon = anonymizer.anonymize(x_train, pred)
anon = anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), pred))
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
assert(anon.loc[:, QI].drop_duplicates().shape[0] < dataset.get_train_samples().loc[:, QI].drop_duplicates().shape[0])
assert (anon.loc[:, QI].value_counts().min() >= k)
assert (anon.drop(QI, axis=1).equals(x_train.drop(QI, axis=1)))
assert (anon.drop(QI, axis=1).equals(dataset.get_train_samples().drop(QI, axis=1)))
def test_regression():
dataset = load_diabetes()
x_train, x_test, y_train, y_test = train_test_split(dataset.data, dataset.target, test_size=0.5, random_state=14)
x_train, x_test, y_train, y_test = train_test_split(load_diabetes().data, load_diabetes().target, test_size=0.5, random_state=14)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
model = DecisionTreeRegressor(random_state=10, min_samples_split=2)
model.fit(x_train, y_train)
pred = model.predict(x_train)
model.fit(dataset.get_train_samples(), dataset.get_train_labels())
pred = model.predict(dataset.get_train_samples())
k = 10
QI = [0, 2, 5, 8]
anonymizer = Anonymize(k, QI, is_regression=True)
anon = anonymizer.anonymize(x_train, pred)
print('Base model accuracy (R2 score): ', model.score(x_test, y_test))
model.fit(anon, y_train)
print('Base model accuracy (R2 score) after anonymization: ', model.score(x_test, y_test))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
anon = anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), pred))
print('Base model accuracy (R2 score): ', model.score(dataset.get_test_samples(), dataset.get_test_labels()))
model.fit(anon, dataset.get_train_labels())
print('Base model accuracy (R2 score) after anonymization: ', model.score(dataset.get_test_samples(), dataset.get_test_labels()))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(dataset.get_train_samples()[:, QI], axis=0)))
_, counts_elements = np.unique(anon[:, QI], return_counts=True)
assert (np.min(counts_elements) >= k)
assert ((np.delete(anon, QI, axis=1) == np.delete(x_train, QI, axis=1)).all())
assert ((np.delete(anon, QI, axis=1) == np.delete(dataset.get_train_samples(), QI, axis=1)).all())
def test_errors():
@ -93,9 +93,9 @@ def test_errors():
with pytest.raises(ValueError):
Anonymize(2, None)
anonymizer = Anonymize(10, [0, 2])
(x_train, y_train), (x_test, y_test) = get_iris_dataset()
dataset = get_iris_dataset()
with pytest.raises(ValueError):
anonymizer.anonymize(x_train, y_test)
(x_train, y_train), _ = get_adult_dataset()
anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), dataset.get_test_labels()))
dataset = get_adult_dataset()
with pytest.raises(ValueError):
anonymizer.anonymize(x_train, y_train)
anonymizer.anonymize(BaseDataset(dataset.get_train_samples(), dataset.get_train_labels()))