openml · PGijsbers · Nov 3, 2020 · Oct 28, 2020 · Oct 30, 2020 · Oct 30, 2020
diff --git a/openml/datasets/dataset.py b/openml/datasets/dataset.py
@@ -456,12 +456,11 @@ def _parse_data_from_arff(
                     col.append(
                         self._unpack_categories(X[column_name], categories_names[column_name])
                     )
-                elif attribute_dtype[column_name] in ('floating',
-                                                      'integer'):
+                elif attribute_dtype[column_name] in ("floating", "integer"):
                     X_col = X[column_name]
                     if X_col.min() >= 0 and X_col.max() <= 255:
                         try:
-                            X_col_uint = X_col.astype('uint8')
+                            X_col_uint = X_col.astype("uint8")
                             if (X_col == X_col_uint).all():
                                 col.append(X_col_uint)
                                 continue

diff --git a/openml/extensions/extension_interface.py b/openml/extensions/extension_interface.py
@@ -229,6 +229,19 @@ def obtain_parameter_values(
             - ``oml:component`` : int: flow id to which the parameter belongs
         """
 
+    @abstractmethod
+    def check_if_model_fitted(self, model: Any) -> bool:
+        """Returns True/False denoting if the model has already been fitted/trained.
+
+        Parameters
+        ----------
+        model : Any
+
+        Returns
+        -------
+        bool
+        """
+
     ################################################################################################
     # Abstract methods for hyperparameter optimization
 

diff --git a/openml/extensions/sklearn/extension.py b/openml/extensions/sklearn/extension.py
@@ -1537,6 +1537,28 @@ def _seed_current_object(current_value):
         model.set_params(**random_states)
         return model
 
+    def check_if_model_fitted(self, model: Any) -> bool:
+        """Returns True/False denoting if the model has already been fitted/trained
+
+        Parameters
+        ----------
+        model : Any
+
+        Returns
+        -------
+        bool
+        """
+        try:
+            # check if model is fitted
+            from sklearn.exceptions import NotFittedError
+            from sklearn.utils.validation import check_is_fitted
+
+            check_is_fitted(model)  # raises a NotFittedError if the model has not been trained
+            return True
+        except NotFittedError:
+            # model is not fitted, as is required
+            return False
+
     def _run_model_on_fold(
         self,
         model: Any,

diff --git a/openml/runs/functions.py b/openml/runs/functions.py
@@ -250,6 +250,12 @@ def run_flow_on_task(
     run_environment = flow.extension.get_version_information()
     tags = ["openml-python", run_environment[1]]
 
+    if flow.extension.check_if_model_fitted(flow.model):
+        warnings.warn(
+            "The model is already fitted!"
+            " This might cause inconsistency in comparison of results."
+        )
+
     # execute the run
     res = _run_task_get_arffcontent(
         flow=flow,

diff --git a/tests/test_datasets/test_dataset.py b/tests/test_datasets/test_dataset.py
@@ -120,11 +120,11 @@ def test_get_data_no_str_data_for_nparrays(self):
 
     def _check_expected_type(self, dtype, is_cat, col):
         if is_cat:
-            expected_type = 'category'
-        elif not col.isna().any() and (col.astype('uint8') == col).all():
-            expected_type = 'uint8'
+            expected_type = "category"
+        elif not col.isna().any() and (col.astype("uint8") == col).all():
+            expected_type = "uint8"
         else:
-            expected_type = 'float64'
+            expected_type = "float64"
 
         self.assertEqual(dtype.name, expected_type)
 

diff --git a/tests/test_datasets/test_dataset_functions.py b/tests/test_datasets/test_dataset_functions.py
@@ -373,9 +373,9 @@ def test_get_dataset_by_name(self):
     def test_get_dataset_uint8_dtype(self):
         dataset = openml.datasets.get_dataset(1)
         self.assertEqual(type(dataset), OpenMLDataset)
-        self.assertEqual(dataset.name, 'anneal')
+        self.assertEqual(dataset.name, "anneal")
         df, _, _, _ = dataset.get_data()
-        self.assertEqual(df['carbon'].dtype, 'uint8')
+        self.assertEqual(df["carbon"].dtype, "uint8")
 
     def test_get_dataset(self):
         # This is the only non-lazy load to ensure default behaviour works.