Delete unnecessary dependency on external dataset for tests

Author: mdbenito

.test_durations

@@ -1781,10 +1781,6 @@
     "tests/value/shapley/test_montecarlo.py::test_linear_montecarlo_with_outlier[owen-kwargs1-scorer0-0.2-2-0-21]": 6.573138832000012,
     "tests/value/shapley/test_montecarlo.py::test_linear_montecarlo_with_outlier[owen_antithetic-kwargs2-scorer0-0.2-2-0-21]": 10.124256999999972,
     "tests/value/shapley/test_montecarlo.py::test_linear_montecarlo_with_outlier[permutation_montecarlo-kwargs0-scorer0-0.2-2-0-21]": 2.7115268339999545,
-    "tests/value/shapley/test_montecarlo.py::test_montecarlo_shapley_housing_dataset[12-3-12-combinatorial_montecarlo-kwargs0]": 0.16786966001382098,
-    "tests/value/shapley/test_montecarlo.py::test_montecarlo_shapley_housing_dataset[12-3-12-owen-kwargs1]": 17.011920137971174,
-    "tests/value/shapley/test_montecarlo.py::test_montecarlo_shapley_housing_dataset[12-3-12-owen_antithetic-kwargs2]": 35.88025256394758,
-    "tests/value/shapley/test_montecarlo.py::test_montecarlo_shapley_housing_dataset[12-3-4-group_testing-kwargs3]": 0.25901710899779573,
     "tests/value/shapley/test_montecarlo.py::test_seed[combinatorial_montecarlo-kwargs0-test_game0]": 0.04085670800000685,
     "tests/value/shapley/test_montecarlo.py::test_seed[group_testing-kwargs3-test_game0]": 0.23488145900003587,
     "tests/value/shapley/test_montecarlo.py::test_seed[owen-kwargs1-test_game0]": 0.30296191700003305,

tests/conftest.py

@@ -129,15 +129,6 @@ def memcached_client(
         ) from e
 
 
-@pytest.fixture(scope="function")
-def housing_dataset(num_points, num_features) -> Dataset:
-    dataset = datasets.fetch_california_housing()
-    dataset.data = dataset.data[:num_points, :num_features]
-    dataset.feature_names = dataset.feature_names[:num_features]
-    dataset.target = dataset.target[:num_points]
-    return Dataset.from_sklearn(dataset, train_size=0.5)
-
-
 @pytest.fixture(scope="function")
 def linear_dataset(a: float, b: float, num_points: int):
     """Constructs a dataset sampling from y=ax+b + eps, with eps~Gaussian and

tests/utils/test_utility.py

@@ -6,13 +6,12 @@
 import pytest
 from sklearn.linear_model import LinearRegression
 
-from pydvl.utils import DataUtilityLearning, Scorer, Utility, powerset
+from pydvl.utils import Dataset, DataUtilityLearning, Scorer, Utility, powerset
 from pydvl.utils.caching import CachedFuncConfig, InMemoryCacheBackend
 
 
 @pytest.mark.parametrize("show_warnings", [False, True])
-@pytest.mark.parametrize("num_points, num_features", [(4, 4)])
-def test_utility_show_warnings(housing_dataset, show_warnings, recwarn):
+def test_utility_show_warnings(show_warnings, recwarn):
     class WarningModel:
         def fit(self, x, y):
             warnings.warn("Warning model fit")
@@ -28,7 +27,7 @@ def score(self, x, y):
 
     utility = Utility(
         model=WarningModel(),
-        data=housing_dataset,
+        data=Dataset.from_arrays(np.zeros((4, 4)), np.zeros(4)),
         show_warnings=show_warnings,
     )
     utility([0])