publish,tag methods need testing

Author: JATAYU000

openml/_api/resources/dataset.py

@@ -18,7 +18,6 @@
 from openml.datasets.dataset import OpenMLDataset
 from openml.exceptions import (
     OpenMLHashException,
-    OpenMLMinioRequiredError,
     OpenMLPrivateDatasetError,
     OpenMLServerException,
 )
@@ -466,9 +465,7 @@ def parse_features_file(
     ) -> dict[int, OpenMLDataFeature]:
         if features_pickle_file is None:
             features_pickle_file = features_file.with_suffix(features_file.suffix + ".pkl")
-        if features_file.suffix != ".xml":
-            # TODO (Shrivaths) can only parse xml warn/ raise exception
-            raise NotImplementedError()
+        assert features_file.suffix == ".xml"
 
         with Path(features_file).open("r", encoding="utf8") as fh:
             features_xml = fh.read()
@@ -485,9 +482,7 @@ def parse_qualities_file(
     ) -> dict[str, float]:
         if qualities_pickle_file is None:
             qualities_pickle_file = qualities_file.with_suffix(qualities_file.suffix + ".pkl")
-        if qualities_file.suffix != ".xml":
-            # TODO (Shrivaths) can only parse xml warn/ raise exception
-            raise NotImplementedError()
+        assert qualities_file.suffix == ".xml"
 
         with Path(qualities_file).open("r", encoding="utf8") as fh:
             qualities_xml = fh.read()
@@ -582,25 +577,19 @@ def __handler(response: Response, path: Path, encoding: str) -> Path:
 
     def download_features_file(self, dataset_id: int) -> Path:
         path = f"data/features/{dataset_id}"
-        file = self._download_file(path, "features.xml")
-        _ = self.parse_features_file(file)
-        return file
+        return self._download_file(path, "features.xml")
 
     def download_qualities_file(self, dataset_id: int) -> Path:
         path = f"data/qualities/{dataset_id}"
-        file = self._download_file(path, "qualities.xml")
-        _ = self.parse_qualities_file(file)
-        return file
+        return self._download_file(path, "qualities.xml")
 
     def download_dataset_parquet(
         self,
         description: dict | OpenMLDataset,
         download_all_files: bool = False,  # noqa: FBT002
     ) -> Path | None:
-        if self._minio is None:
-            raise OpenMLMinioRequiredError(
-                "A minio object is required for Dataset, but none was provided"
-            )
+        assert self._minio is not None  # for mypy
+
         if isinstance(description, dict):
             url = str(description.get("oml:parquet_url"))
         elif isinstance(description, OpenMLDataset):
@@ -1026,25 +1015,19 @@ def __handler(response: Response, path: Path, encoding: str) -> Path:
 
     def download_features_file(self, dataset_id: int) -> Path:
         path = f"datasets/features/{dataset_id}"
-        file = self._download_file(path, "features.json")
-        _ = self.parse_features_file(file)
-        return file
+        return self._download_file(path, "features.json")
 
     def download_qualities_file(self, dataset_id: int) -> Path:
         path = f"datasets/qualities/{dataset_id}"
-        file = self._download_file(path, "qualities.json")
-        _ = self.parse_qualities_file(file)
-        return file
+        return self._download_file(path, "qualities.json")
 
     def download_dataset_parquet(
         self,
         description: dict | OpenMLDataset,
         download_all_files: bool = False,  # noqa: FBT002
     ) -> Path | None:
-        if self._minio is None:
-            raise OpenMLMinioRequiredError(
-                "A minio object is required for Dataset, but none was provided"
-            )
+        assert self._minio is not None  # for mypy
+
         if isinstance(description, dict):
             url = str(description.get("parquet_url"))
         elif isinstance(description, OpenMLDataset):
@@ -1095,7 +1078,7 @@ def delete_topic(self, data_id: int, topic: str) -> int:
         raise NotImplementedError(self._not_supported(method="delete_topic"))
 
     def get_online_dataset_format(self, dataset_id: int) -> str:
-        dataset_json = self._http.get(f"datasets/{dataset_id}").text
+        dataset_json = self._http.get(f"datasets/{dataset_id}").json()
         # build a dict from the xml and get the format from the dataset description
         return dataset_json["data_set_description"]["format"].lower()  # type: ignore
 

openml/datasets/dataset.py

@@ -949,6 +949,49 @@ def _parse_publish_response(self, xml_response: dict) -> None:
         """Parse the id from the xml_response and assign it to self."""
         self.dataset_id = int(xml_response["oml:upload_data_set"]["oml:id"])
 
+    def publish(self) -> OpenMLDataset:
+        """Publish this flow to OpenML server.
+
+        Returns
+        -------
+        self : OpenMLFlow
+        """
+        file_elements = self._get_file_elements()
+        if "description" not in file_elements:
+            file_elements["description"] = self._to_xml()
+
+        dataset_id = openml._backend.dataset.publish(path="data", files=file_elements)
+        self.dataset_id = dataset_id
+        return self
+
+    def push_tag(self, tag: str) -> None:
+        """Annotates this dataset with a tag on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to attach to the dataset.
+        """
+        if self.dataset_id is None:
+            raise ValueError(
+                "Dataset does not have an ID. Please publish the dataset before tagging."
+            )
+        openml._backend.dataset.tag(self.dataset_id, tag)
+
+    def remove_tag(self, tag: str) -> None:
+        """Removes a tag from this dataset on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to remove from the dataset.
+        """
+        if self.dataset_id is None:
+            raise ValueError(
+                "Dataset does not have an ID. Please publish the dataset before untagging."
+            )
+        openml._backend.dataset.untag(self.dataset_id, tag)
+
     def _to_dict(self) -> dict[str, dict]:
         """Creates a dictionary representation of self."""
         props = [

openml/exceptions.py

@@ -73,7 +73,3 @@ class OpenMLNotSupportedError(PyOpenMLError):
 
 class OpenMLCacheRequiredError(PyOpenMLError):
     """Raised when a cache object is required but not provided."""
-
-
-class OpenMLMinioRequiredError(PyOpenMLError):
-    """Raised when a minio object is required but not provided"""