Merge branch 'main' into repr_openmlsplit

Author: JATAYU000

openml/_api_calls.py

@@ -22,8 +22,8 @@
 from . import config
 from .__version__ import __version__
 from .exceptions import (
+    OpenMLAuthenticationError,
     OpenMLHashException,
-    OpenMLNotAuthorizedError,
     OpenMLServerError,
     OpenMLServerException,
     OpenMLServerNoResult,
@@ -515,11 +515,7 @@ def __parse_server_exception(
         400,  # run/42 delete
         460,  # task/42 delete
     ]:
-        msg = (
-            f"The API call {url} requires authentication via an API key.\nPlease configure "
-            "OpenML-Python to use your API as described in this example:"
-            "\nhttps://openml.github.io/openml-python/latest/examples/Basics/introduction_tutorial/#authentication"
-        )
-        return OpenMLNotAuthorizedError(message=msg)
+        msg = f"The API call {url} requires authentication via an API key."
+        return OpenMLAuthenticationError(message=msg)
 
     return OpenMLServerException(code=code, message=full_message, url=url)

openml/cli.py

@@ -109,7 +109,7 @@ def check_server(server: str) -> str:
 
     def replace_shorthand(server: str) -> str:
         if server == "test":
-            return "https://test.openml.org/api/v1/xml"
+            return f"{config.TEST_SERVER_URL}/api/v1/xml"
         if server == "production_server":
             return "https://www.openml.org/api/v1/xml"
         return server

openml/config.py

@@ -28,6 +28,8 @@
 OPENML_TEST_SERVER_ADMIN_KEY_ENV_VAR = "OPENML_TEST_SERVER_ADMIN_KEY"
 _TEST_SERVER_NORMAL_USER_KEY = "normaluser"
 
+TEST_SERVER_URL = "https://test.openml.org"
+
 
 class _Config(TypedDict):
     apikey: str
@@ -214,7 +216,7 @@ class ConfigurationForExamples:
     _last_used_server = None
     _last_used_key = None
     _start_last_called = False
-    _test_server = "https://test.openml.org/api/v1/xml"
+    _test_server = f"{TEST_SERVER_URL}/api/v1/xml"
     _test_apikey = _TEST_SERVER_NORMAL_USER_KEY
 
     @classmethod
@@ -470,7 +472,8 @@ def get_cache_directory() -> str:
 
     """
     url_suffix = urlparse(server).netloc
-    reversed_url_suffix = os.sep.join(url_suffix.split(".")[::-1])  # noqa: PTH118
+    url_parts = url_suffix.replace(":", "_").split(".")[::-1]
+    reversed_url_suffix = os.sep.join(url_parts)  # noqa: PTH118
     return os.path.join(_root_cache_directory, reversed_url_suffix)  # noqa: PTH118
 
 

openml/exceptions.py

@@ -63,5 +63,28 @@ class OpenMLNotAuthorizedError(OpenMLServerError):
     """Indicates an authenticated user is not authorized to execute the requested action."""
 
 
+class OpenMLAuthenticationError(OpenMLServerError):
+    """Exception raised when API authentication fails.
+
+    This typically occurs when:
+    - No API key is configured
+    - The API key is invalid or expired
+    - The API key format is incorrect
+
+    This is different from authorization (OpenMLNotAuthorizedError), which occurs
+    when a valid API key lacks permissions for the requested operation.
+    """
+
+    def __init__(self, message: str):
+        help_text = (
+            "\n\nTo fix this:\n"
+            "1. Get your API key from https://www.openml.org/\n"
+            "   (you'll need to register for a free account if you don't have one)\n"
+            "2. Configure your API key by following the authentication guide:\n"
+            "   https://openml.github.io/openml-python/latest/examples/Basics/introduction_tutorial/#authentication"
+        )
+        super().__init__(message + help_text)
+
+
 class ObjectNotPublishedError(PyOpenMLError):
     """Indicates an object has not been published yet."""

openml/tasks/functions.py

@@ -415,24 +415,28 @@ def get_task(
     if not isinstance(task_id, int):
         raise TypeError(f"Task id should be integer, is {type(task_id)}")
 
-    cache_key_dir = openml.utils._create_cache_directory_for_id(TASKS_CACHE_DIR_NAME, task_id)
-    tid_cache_dir = cache_key_dir / str(task_id)
-    tid_cache_dir_existed = tid_cache_dir.exists()
+    task_cache_directory = openml.utils._create_cache_directory_for_id(
+        TASKS_CACHE_DIR_NAME, task_id
+    )
+    task_cache_directory_existed = task_cache_directory.exists()
     try:
         task = _get_task_description(task_id)
         dataset = get_dataset(task.dataset_id, **get_dataset_kwargs)
         # List of class labels available in dataset description
         # Including class labels as part of task meta data handles
         #   the case where data download was initially disabled
         if isinstance(task, (OpenMLClassificationTask, OpenMLLearningCurveTask)):
+            assert task.target_name is not None, (
+                "Supervised tasks must define a target feature before retrieving class labels."
+            )
             task.class_labels = dataset.retrieve_class_labels(task.target_name)
         # Clustering tasks do not have class labels
         # and do not offer download_split
         if download_splits and isinstance(task, OpenMLSupervisedTask):
             task.download_split()
     except Exception as e:
-        if not tid_cache_dir_existed:
-            openml.utils._remove_cache_dir_for_id(TASKS_CACHE_DIR_NAME, tid_cache_dir)
+        if not task_cache_directory_existed:
+            openml.utils._remove_cache_dir_for_id(TASKS_CACHE_DIR_NAME, task_cache_directory)
         raise e
 
     return task
@@ -598,6 +602,7 @@ def create_task(
         )
 
     return task_cls(
+        task_id=None,
         task_type_id=task_type,
         task_type="None",  # TODO: refactor to get task type string from ID.
         data_set_id=dataset_id,