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

Support regression models (#19)

Browse source 
* support DecisionTreeRegressor

* support regression models

* Update membership_inference_dp_diabetes_reg.ipynb
This commit is contained in:
olasaadi 2022-01-26 14:30:58 +02:00 • committed by GitHub
parent a9a93c8a3a
commit cb9278ddb5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 273 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

32
tests/test_anonymizer.py
View file

@ -1,10 +1,12 @@
import pytest
import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from sklearn.preprocessing import OneHotEncoder
from apt.anonymization import Anonymize
from apt.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
def test_anonymize_ndarray_iris():
@ -17,8 +19,7 @@ def test_anonymize_ndarray_iris():
QI = [0, 2]
anonymizer = Anonymize(k, QI)
anon = anonymizer.anonymize(x_train, pred)
assert(len(np.unique(anon, axis=0)) < len(np.unique(x_train, axis=0)))
assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, 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())
@ -39,7 +40,7 @@ def test_anonymize_pandas_adult():
anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
anon = anonymizer.anonymize(x_train, pred)
assert(anon.drop_duplicates().shape[0] < x_train.drop_duplicates().shape[0])
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.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)))
@ -58,11 +59,32 @@ def test_anonymize_pandas_nursery():
anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
anon = anonymizer.anonymize(x_train, pred)
assert(anon.drop_duplicates().shape[0] < x_train.drop_duplicates().shape[0])
assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.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)))
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)
model = DecisionTreeRegressor(random_state=10, min_samples_split=2)
model.fit(x_train, y_train)
pred = model.predict(x_train)
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)))
_, 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())
def test_errors():
with pytest.raises(ValueError):
Anonymize(1, [0, 2])