fix tests

Author: ravinkohli

autoPyTorch/data/tabular_validator.py

@@ -48,7 +48,7 @@ def __init__(
         dataset_compression: Optional[DatasetCompressionSpec] = None,
         seed: int = 42,
     ) -> None:
-        self._dataset_compression = dataset_compression
+        self.dataset_compression = dataset_compression
         self._reduced_dtype: Optional[DatasetDTypeContainerType] = None
         self.is_classification = is_classification
         self.logger_port = logger_port
@@ -92,7 +92,7 @@ def _compress_dataset(
         """
         is_dataframe = hasattr(X, 'iloc')
         is_reducible_type = isinstance(X, np.ndarray) or issparse(X) or is_dataframe
-        if not is_reducible_type or self._dataset_compression is None:
+        if not is_reducible_type or self.dataset_compression is None:
             return X, y
         elif self._reduced_dtype is not None:
             X = X.astype(self._reduced_dtype)
@@ -103,7 +103,7 @@ def _compress_dataset(
                 y=y,
                 is_classification=self.is_classification,
                 random_state=self.seed,
-                **self._dataset_compression  # type: ignore [arg-type]
+                **self.dataset_compression  # type: ignore [arg-type]
             )
             self._reduced_dtype = dict(X.dtypes) if is_dataframe else X.dtype
             return X, y

test/test_data/test_utils.py

@@ -127,8 +127,8 @@ def test_unsupported_errors():
         ['a', 'b', 'c', 'a', 'b', 'c'],
         ['a', 'b', 'd', 'r', 'b', 'c']])
     with pytest.raises(ValueError, match=r'X.dtype = .*'):
-        reduce_dataset_size_if_too_large(X, 0)
+        reduce_dataset_size_if_too_large(X, is_classification=True, random_state=1, memory_allocation=0)
 
     X = [[1, 2], [2, 3]]
     with pytest.raises(ValueError, match=r'Unrecognised data type of X, expected data type to be in .*'):
-        reduce_dataset_size_if_too_large(X, 0)
+        reduce_dataset_size_if_too_large(X, is_classification=True, random_state=1, memory_allocation=0)

test/test_data/test_validation.py

@@ -163,7 +163,7 @@ def test_validation_unsupported():
     ),
     indirect=True
 )
-def test_featurevalidator_reduce_precision(input_data_featuretest):
+def test_featurevalidator_dataset_compression(input_data_featuretest):
     n_samples = input_data_featuretest.shape[0]
     input_data_targets = np.random.random_sample((n_samples))
     X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(