Adding importable helper functions

openml · mfeurer · Jan 28, 2021 · Oct 29, 2020 · Oct 29, 2020 · Oct 29, 2020
commit b45f6f20a39600ebdb6cf557e120942e7bda7128
diff --git a/doc/progress.rst b/doc/progress.rst
@@ -8,6 +8,7 @@ Changelog
 
 0.11.1
 ~~~~~~
+* MAINT #671: Improved the performance of ``check_datasets_active`` by only querying the given list of datasets in contrast to querying all datasets. Modified the corresponding unit test.
 
 0.11.0
 ~~~~~~

diff --git a/openml/datasets/functions.py b/openml/datasets/functions.py
@@ -183,7 +183,7 @@ def list_datasets(
     status: Optional[str] = None,
     tag: Optional[str] = None,
     output_format: str = "dict",
-    **kwargs
+    **kwargs,
 ) -> Union[Dict, pd.DataFrame]:
 
     """
@@ -251,7 +251,7 @@ def list_datasets(
         size=size,
         status=status,
         tag=tag,
-        **kwargs
+        **kwargs,
     )
 
 
@@ -333,14 +333,22 @@ def _load_features_from_file(features_file: str) -> Dict:
         return xml_dict["oml:data_features"]
 
 
-def check_datasets_active(dataset_ids: List[int]) -> Dict[int, bool]:
+def check_datasets_active(
+    dataset_ids: List[int], raise_error_if_not_exist: bool = True,
+) -> Dict[int, bool]:
     """
     Check if the dataset ids provided are active.
 
+    Raises an error if a dataset_id in the given list
+    of dataset_ids does not exist on the server.
+
     Parameters
     ----------
     dataset_ids : List[int]
         A list of integers representing dataset ids.
+    raise_error_if_not_exist : bool (default=True)
+        Flag that if activated can raise an error, if one or more of the
+        given dataset ids do not exist on the server.
 
     Returns
     -------
@@ -353,7 +361,8 @@ def check_datasets_active(dataset_ids: List[int]) -> Dict[int, bool]:
     for did in dataset_ids:
         dataset = dataset_list.get(did, None)
         if dataset is None:
-            raise ValueError("Could not find dataset {} in OpenML dataset list.".format(did))
+            if raise_error_if_not_exist:
+                raise ValueError(f"Could not find dataset {did} in OpenML dataset list.")
         else:
             active[did] = dataset["status"] == "active"
 

diff --git a/openml/extensions/sklearn/__init__.py b/openml/extensions/sklearn/__init__.py
@@ -7,3 +7,19 @@
 __all__ = ["SklearnExtension"]
 
 register_extension(SklearnExtension)
+
+
+def cont(X):
+    """Returns True for all non-categorical columns, False for the rest.
+    """
+    if not hasattr(X, "dtypes"):
+        raise AttributeError("Not a Pandas DataFrame with 'dtypes' as attribute!")
+    return X.dtypes != "category"
+
+
+def cat(X):
+    """Returns True for all categorical columns, False for the rest.
+    """
+    if not hasattr(X, "dtypes"):
+        raise AttributeError("Not a Pandas DataFrame with 'dtypes' as attribute!")
+    return X.dtypes == "category"
diff --git a/tests/test_datasets/test_dataset_functions.py b/tests/test_datasets/test_dataset_functions.py
@@ -227,9 +227,10 @@ def test_list_datasets_empty(self):
     def test_check_datasets_active(self):
         # Have to test on live because there is no deactivated dataset on the test server.
         openml.config.server = self.production_server
-        active = openml.datasets.check_datasets_active([2, 17])
+        active = openml.datasets.check_datasets_active([2, 17, 79], raise_error_if_not_exist=False,)
         self.assertTrue(active[2])
         self.assertFalse(active[17])
+        self.assertIsNone(active.get(79))
         self.assertRaisesRegex(
             ValueError,
             "Could not find dataset 79 in OpenML dataset list.",

diff --git a/tests/test_study/test_study_examples.py b/tests/test_study/test_study_examples.py
@@ -1,6 +1,7 @@
 # License: BSD 3-Clause
 
-from openml.testing import TestBase, SimpleImputer, CustomImputer, cat, cont
+from openml.testing import TestBase, SimpleImputer, CustomImputer
+from openml.extensions.sklearn import cat, cont
 
 import sklearn
 import unittest
-Original file line number
+Diff line change
@@ Expand Up / @@ -8,6 +8,7 @@ Changelog @@
 .11.1
     ~~~~~~
+    * MAINT #671: Improved the performance of ``check_datasets_active`` by only querying the given list of datasets in contrast to querying all datasets. Modified the corresponding unit test.
 .11.0
     ~~~~~~
@@ Expand Down @@