def _test_same(dataset):
X, y = dataset
if X.shape[1] == 1:
# If we only have one column (which is also the sensitive one) we can't fit
return True
sensitive_cols = [0]
X_without_sens = np.delete(X, sensitive_cols, axis=1)
lr = LogisticRegression(
penalty="none",
solver="lbfgs",
multi_class="ovr",
dual=False,
tol=1e-4,
C=1.0,
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
random_state=None,
max_iter=100,
verbose=0,
warm_start=False,
n_jobs=None,
l1_ratio=None,
)
fair = EqualOpportunityClassifier(
covariance_threshold=None,
sensitive_cols=sensitive_cols,
penalty="none",
positive_target=True,
)
fair.fit(X, y)
lr.fit(X_without_sens, y)
normal_pred = lr.predict_proba(X_without_sens)
fair_pred = fair.predict_proba(X)
np.testing.assert_almost_equal(normal_pred, fair_pred, decimal=2)
assert np.sum(
lr.predict(X_without_sens) != fair.predict(X)) / len(X) < 0.01
def _test_same(dataset):
X, y = dataset
if X.shape[1] == 1:
# If we only have one column (which is also the sensitive one) we can't fit
return True
sensitive_cols = [0]
X_without_sens = np.delete(X, sensitive_cols, axis=1)
lr = LogisticRegression(penalty="none", solver="lbfgs")
fair = EqualOpportunityClassifier(
covariance_threshold=None,
sensitive_cols=sensitive_cols,
penalty="none",
positive_target=True,
)
fair.fit(X, y)
lr.fit(X_without_sens, y)
normal_pred = lr.predict_proba(X_without_sens)
fair_pred = fair.predict_proba(X)
np.testing.assert_almost_equal(normal_pred, fair_pred, decimal=2)
assert np.sum(
lr.predict(X_without_sens) != fair.predict(X)) / len(X) < 0.01