How to use fairlearn - 10 common examples

l1_series = pd.Series([1.5, 0.5], index=idx)
    l2_series = pd.Series([1.0, 1.0], index=idx)
    l3_series = pd.Series([0.5, 1.5], index=idx)
    l4_series = pd.Series([0.0, 2.0], index=idx)
    grid_df = pd.concat([l0_series,
                         l1_series,
                         l2_series,
                         l3_series,
                         l4_series],
                        axis=1)

    target1 = GridSearch(copy.deepcopy(estimator),
                         constraints=GroupLossMoment(ZeroOneLoss()),
                         grid_size=5)

    target2 = GridSearch(copy.deepcopy(estimator),
                         constraints=GroupLossMoment(ZeroOneLoss()),
                         grid=grid_df)

    tradeoffs = [0, 0.25, 0.5, 0.75, 1]

    target1.fit(X, y, sensitive_features=A)
    target2.fit(X, y, sensitive_features=A)

    assert len(target1.all_results) == len(tradeoffs)
    assert len(target2.all_results) == len(tradeoffs)

    # Check we generated the same multipliers
    for i in range(len(tradeoffs)):
        lm1 = target1.all_results[i].lambda_vec
        lm2 = target2.all_results[i].lambda_vec
        assert lm1.equals(lm2)

def test_X_A_different_rows(self, transformX, transformY, transformA):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, Y, _ = self._quick_data()
        A = np.random.randint(2, size=len(Y)+1)

        message = str("X and the sensitive features must have same number of rows")
        with pytest.raises(RuntimeError) as execInfo:
            gs.fit(transformX(X),
                   transformY(Y),
                   sensitive_features=transformA(A))

        assert message == execInfo.value.args[0]

def test_Y_ternary(self, transformX, transformY, transformA):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, Y, A = self._quick_data()
        Y[0] = 0
        Y[1] = 1
        Y[2] = 2

        message = str("Supplied y labels are not 0 or 1")
        with pytest.raises(RuntimeError) as execInfo:
            gs.fit(transformX(X),
                   transformY(Y),
                   sensitive_features=transformA(A))

        assert message == execInfo.value.args[0]

def test_sensitive_feature_non_binary(self, transformX, transformY, transformA):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, Y, A = self._quick_data()
        A[0] = 0
        A[1] = 1
        A[2] = 2

        message = str("Sensitive features contain more than two unique values")
        with pytest.raises(RuntimeError) as execInfo:
            gs.fit(transformX(X),
                   transformY(Y),
                   sensitive_features=transformA(A))

        assert message == execInfo.value.args[0]

def test_Y_df_bad_columns(self, transformX, transformA):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, Y, A = self._quick_data()

        Y_two_col_df = pd.DataFrame({"a": Y, "b": Y})
        message = str("y is a DataFrame with more than one column")
        with pytest.raises(RuntimeError) as execInfo:
            gs.fit(transformX(X),
                   Y_two_col_df,
                   sensitive_features=transformA(A))

        assert message == execInfo.value.args[0]

# Do the grid search with a zero Lagrange multiplier
    idx = pd.Int64Index(sorted([a0_label, a1_label]))
    l0_series = pd.Series([2.0, 0.0], index=idx)
    l1_series = pd.Series([1.5, 0.5], index=idx)
    l2_series = pd.Series([1.0, 1.0], index=idx)
    l3_series = pd.Series([0.5, 1.5], index=idx)
    l4_series = pd.Series([0.0, 2.0], index=idx)
    grid_df = pd.concat([l0_series,
                         l1_series,
                         l2_series,
                         l3_series,
                         l4_series],
                        axis=1)

    target1 = GridSearch(copy.deepcopy(estimator),
                         constraints=GroupLossMoment(ZeroOneLoss()),
                         grid_size=5)

    target2 = GridSearch(copy.deepcopy(estimator),
                         constraints=GroupLossMoment(ZeroOneLoss()),
                         grid=grid_df)

    tradeoffs = [0, 0.25, 0.5, 0.75, 1]

    target1.fit(X, y, sensitive_features=A)
    target2.fit(X, y, sensitive_features=A)

    assert len(target1.all_results) == len(tradeoffs)
    assert len(target2.all_results) == len(tradeoffs)

    # Check we generated the same multipliers

def test_no_predict_proba_before_fit(self):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, _, _ = self._quick_data()

        message = str("Must call fit before attempting to make predictions")
        with pytest.raises(NotFittedException) as execInfo:
            gs.predict_proba(X)

        assert message == execInfo.value.args[0]

iterables = [['+', '-'], ['all'], sorted([a0_label, a1_label])]
    midx = pd.MultiIndex.from_product(iterables, names=['sign', 'event', 'group_id'])
    lagrange_negative_series = pd.Series([0.0, 0.0, 0.0, 2.0], index=midx)
    lagrange_zero_series = pd.Series(np.zeros(4), index=midx)
    lagrange_positive_series = pd.Series([0.0, 2.0, 0.0, 0.0], index=midx)
    grid_df = pd.concat([lagrange_negative_series,
                         lagrange_zero_series,
                         lagrange_positive_series],
                        axis=1)

    target1 = GridSearch(copy.deepcopy(estimator),
                         constraints=DemographicParity(),
                         grid_size=3)

    target2 = GridSearch(copy.deepcopy(estimator),
                         constraints=DemographicParity(),
                         grid=grid_df)

    # Try both ways of specifying the Lagrange multipliers
    target2.fit(X, y, sensitive_features=A)
    target1.fit(X, y, sensitive_features=A)

    assert len(target1.all_results) == 3
    assert len(target2.all_results) == 3

    # Check we generated the same multipliers
    for i in range(3):
        lm1 = target1.all_results[i].lambda_vec
        lm2 = target2.all_results[i].lambda_vec
        assert lm1.equals(lm2)

estimator = LogisticRegression(solver='liblinear',
                                   fit_intercept=True,
                                   random_state=97)

    # Train an unmitigated estimator
    unmitigated_estimator = copy.deepcopy(estimator)
    unmitigated_estimator.fit(X, y)

    # Do the grid search with a zero Lagrange multiplier
    iterables = [['+', '-'], ['all'], [a0_label, a1_label]]
    midx = pd.MultiIndex.from_product(iterables, names=['sign', 'event', 'group_id'])
    lagrange_zero_series = pd.Series(np.zeros(4), index=midx)
    grid_df = pd.DataFrame(lagrange_zero_series)

    target = GridSearch(estimator,
                        constraints=DemographicParity(),
                        grid=grid_df)
    target.fit(X, y, sensitive_features=A)
    assert len(target.all_results) == 1

    # Check coefficients
    gs_coeff = target.best_result.predictor.coef_
    um_coeff = unmitigated_estimator.coef_
    assert np.array_equal(gs_coeff, um_coeff)

def test_X_Y_different_rows(self, transformX, transformY, transformA):
        gs = GridSearch(self.estimator, self.disparity_criterion)
        X, _, A = self._quick_data()
        Y = np.random.randint(2, size=len(A)+1)

        message = str("X and y must have same number of rows")
        with pytest.raises(RuntimeError) as execInfo:
            gs.fit(transformX(X),
                   transformY(Y),
                   sensitive_features=transformA(A))

        assert message == execInfo.value.args[0]