Move DatasetV2 out of experimental

docs/api/dataset.md

@@ -4,6 +4,12 @@
 
 --- 
 
+::: polaris.dataset.DatasetV2
+    options:
+        filters: ["!^_"]
+
+--- 
+
 ::: polaris.dataset._base.BaseDataset
     options:
         filters: ["!^_"]
@@ -20,4 +26,4 @@
     options:
         filters: ["!^_"]
 
----
+---

polaris/competition/__init__.py

@@ -8,9 +8,8 @@
 
 from polaris.benchmark import BenchmarkSpecification
 from polaris.benchmark._base import ColumnName
-from polaris.dataset import Subset
+from polaris.dataset import DatasetV2, Subset
 from polaris.evaluate import CompetitionPredictions
-from polaris.experimental._dataset_v2 import DatasetV2
 from polaris.utils.dict2html import dict2html
 from polaris.utils.errors import InvalidCompetitionError
 from polaris.utils.misc import listit
@@ -26,7 +25,7 @@
 
 class CompetitionSpecification(DatasetV2, BenchmarkSpecification):
     """An instance of this class represents a Polaris competition. It defines fields and functionality
-    that in combination with the `polaris.experimental._dataset_v2.DatasetV2` class, allow
+    that in combination with the `polaris.dataset.DatasetV2` class, allow
     users to participate in competitions hosted on Polaris Hub.
 
     Examples:
@@ -70,7 +69,7 @@ class CompetitionSpecification(DatasetV2, BenchmarkSpecification):
         end_time: The time at which the competition stops accepting prediction submissions.
         n_classes: The number of classes within target columns that define a classification task.
 
-    For additional meta-data attributes, see the `polaris.experimental._dataset_v2.DatasetV2` class.
+    For additional meta-data attributes, see the `polaris.dataset.DatasetV2` class.
     """
 
     _artifact_type = "competition"
@@ -166,7 +165,6 @@ def _serialize_split(self, v: SplitType):
         """Convert any tuple to list to make sure it's serializable"""
         return listit(v)
 
-
     @computed_field
     @property
     def dataset_artifact_id(self) -> str:
@@ -201,9 +199,7 @@ def test_set_labels(self) -> list[str]:
     def n_test_datapoints(self) -> dict[str, int]:
         """The size of (each of) the test set(s)."""
         if self.n_test_sets == 1:
-            return {
-                "test": len(self.split[1])
-            }
+            return {"test": len(self.split[1])}
         else:
             return {k: len(v) for k, v in self.split[1].items()}
 

polaris/dataset/__init__.py

@@ -1,17 +1,19 @@
 from polaris.dataset._column import ColumnAnnotation, KnownContentType, Modality
 from polaris.dataset._dataset import DatasetV1, DatasetV1 as Dataset
+from polaris.dataset._dataset_v2 import DatasetV2
 from polaris.dataset._factory import DatasetFactory, create_dataset_from_file, create_dataset_from_files
 from polaris.dataset._subset import Subset
 
+
 __all__ = [
+    "create_dataset_from_file",
+    "create_dataset_from_files",
     "ColumnAnnotation",
     "Dataset",
-    "Subset",
-    "Modality",
-    "KnownContentType",
     "DatasetFactory",
-    "create_dataset_from_file",
-    "create_dataset_from_files",
     "DatasetV1",
-    "Dataset",
+    "DatasetV2",
+    "KnownContentType",
+    "Modality",
+    "Subset",
 ]

polaris/experimental/_benchmark_v2.py

@@ -10,8 +10,7 @@
 
 from polaris.benchmark import BenchmarkSpecification
 from polaris.benchmark._base import ColumnName
-from polaris.dataset import Subset
-from polaris.experimental._dataset_v2 import DatasetV2
+from polaris.dataset import DatasetV2, Subset
 from polaris.utils.errors import InvalidBenchmarkError
 
 

polaris/hub/client.py

@@ -22,10 +22,9 @@
     SingleTaskBenchmarkSpecification,
 )
 from polaris.competition import CompetitionSpecification
-from polaris.dataset import Dataset, DatasetV1
+from polaris.dataset import Dataset, DatasetV1, DatasetV2
 from polaris.evaluate import BenchmarkResults, CompetitionPredictions
 from polaris.experimental._benchmark_v2 import BenchmarkV2Specification
-from polaris.experimental._dataset_v2 import DatasetV2
 from polaris.hub.external_client import ExternalAuthClient
 from polaris.hub.oauth import CachedTokenAuth
 from polaris.hub.settings import PolarisHubSettings
@@ -616,7 +615,7 @@ def _upload_v1_dataset(
             # Instead of directly uploading the data, we announce to the hub that we intend to upload it.
             # We do so separately for the Zarr archive and Parquet file.
             url = f"/v1/dataset/{dataset.artifact_id}"
-            response = self._base_request_to_hub(
+            self._base_request_to_hub(
                 url=url,
                 method="PUT",
                 json={
@@ -850,8 +849,7 @@ def get_competition(self, artifact_id: str) -> CompetitionSpecification:
         """Load a competition from the Polaris Hub.
 
         Args:
-            owner: The owner of the competition. Can be either a user or organization from the Polaris Hub.
-            name: The name of the competition.
+            artifact_id: The artifact identifier for the competition
 
         Returns:
             A `CompetitionSpecification` instance, if it exists.
@@ -898,7 +896,6 @@ def submit_competition_predictions(
                 method="POST",
                 json=prediction_payload,
             )
-            response_data = response.json()
 
             # Log success and return submission response
             progress_indicator.update_success_msg(

tests/conftest.py

@@ -12,9 +12,8 @@
     SingleTaskBenchmarkSpecification,
 )
 from polaris.competition import CompetitionSpecification
-from polaris.dataset import ColumnAnnotation, DatasetFactory, DatasetV1
+from polaris.dataset import ColumnAnnotation, DatasetFactory, DatasetV1, DatasetV2
 from polaris.dataset.converters import SDFConverter
-from polaris.experimental._dataset_v2 import DatasetV2
 from polaris.utils.types import HubOwner
 
 

tests/test_dataset_v2.py

@@ -9,11 +9,11 @@
 import zarr
 from pydantic import ValidationError
 
-from polaris.dataset import Subset
+from polaris.dataset import DatasetV2, Subset
+from polaris.dataset._dataset_v2 import _INDEX_ARRAY_KEY
 from polaris.dataset._factory import DatasetFactory
 from polaris.dataset.converters._pdb import PDBConverter
 from polaris.dataset.zarr._manifest import generate_zarr_manifest
-from polaris.experimental._dataset_v2 import _INDEX_ARRAY_KEY, DatasetV2
 
 
 def test_dataset_v2_get_columns(test_dataset_v2):