scale-nucleus 0.17.8__tar.gz → 0.17.9__tar.gz

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scale-nucleus
-Version: 0.17.8
+Version: 0.17.9
 Summary: The official Python client library for Nucleus, the Data Platform for AI
 Home-page: https://scale.com/nucleus
 License: MIT

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/nucleus/annotation.py

@@ -159,7 +159,7 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
     metadata: Optional[Dict] = None
     embedding_vector: Optional[list] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -180,7 +180,7 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
             metadata=payload.get(METADATA_KEY, {}),
             embedding_vector=payload.get(EMBEDDING_VECTOR_KEY, None),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -198,7 +198,7 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
             METADATA_KEY: self.metadata,
             EMBEDDING_VECTOR_KEY: self.embedding_vector,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
 
     def __eq__(self, other):
@@ -213,7 +213,7 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
             and sorted(self.metadata.items()) == sorted(other.metadata.items())
             and self.embedding_vector == other.embedding_vector
             and self.track_reference_id == other.track_reference_id
-            and self.task_id == other.task_id
+            and self._task_id == other._task_id
         )
 
 
@@ -280,7 +280,7 @@ class LineAnnotation(Annotation):
     annotation_id: Optional[str] = None
     metadata: Optional[Dict] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -310,7 +310,7 @@ class LineAnnotation(Annotation):
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -324,7 +324,7 @@ class LineAnnotation(Annotation):
             ANNOTATION_ID_KEY: self.annotation_id,
             METADATA_KEY: self.metadata,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
         return payload
 
@@ -375,7 +375,7 @@ class PolygonAnnotation(Annotation):
     metadata: Optional[Dict] = None
     embedding_vector: Optional[list] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -406,7 +406,7 @@ class PolygonAnnotation(Annotation):
             metadata=payload.get(METADATA_KEY, {}),
             embedding_vector=payload.get(EMBEDDING_VECTOR_KEY, None),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -421,7 +421,7 @@ class PolygonAnnotation(Annotation):
             METADATA_KEY: self.metadata,
             EMBEDDING_VECTOR_KEY: self.embedding_vector,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
         return payload
 
@@ -518,7 +518,7 @@ class KeypointsAnnotation(Annotation):
     annotation_id: Optional[str] = None
     metadata: Optional[Dict] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata or {}
@@ -571,7 +571,7 @@ class KeypointsAnnotation(Annotation):
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -587,7 +587,7 @@ class KeypointsAnnotation(Annotation):
             ANNOTATION_ID_KEY: self.annotation_id,
             METADATA_KEY: self.metadata,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
         return payload
 
@@ -692,7 +692,7 @@ class CuboidAnnotation(Annotation):  # pylint: disable=R0902
     annotation_id: Optional[str] = None
     metadata: Optional[Dict] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -709,7 +709,7 @@ class CuboidAnnotation(Annotation):  # pylint: disable=R0902
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -729,7 +729,8 @@ class CuboidAnnotation(Annotation):  # pylint: disable=R0902
             payload[METADATA_KEY] = self.metadata
         if self.track_reference_id:
             payload[TRACK_REFERENCE_ID_KEY] = self.track_reference_id
-
+        if self._task_id:
+            payload[TASK_ID_KEY] = self._task_id
         return payload
 
 
@@ -942,7 +943,7 @@ class CategoryAnnotation(Annotation):
     taxonomy_name: Optional[str] = None
     metadata: Optional[Dict] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -955,7 +956,7 @@ class CategoryAnnotation(Annotation):
             taxonomy_name=payload.get(TAXONOMY_NAME_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -966,7 +967,7 @@ class CategoryAnnotation(Annotation):
             REFERENCE_ID_KEY: self.reference_id,
             METADATA_KEY: self.metadata,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
         if self.taxonomy_name is not None:
             payload[TAXONOMY_NAME_KEY] = self.taxonomy_name
@@ -982,7 +983,7 @@ class MultiCategoryAnnotation(Annotation):
     taxonomy_name: Optional[str] = None
     metadata: Optional[Dict] = None
     track_reference_id: Optional[str] = None
-    task_id: Optional[str] = None
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     def __post_init__(self):
         self.metadata = self.metadata if self.metadata else {}
@@ -995,7 +996,7 @@ class MultiCategoryAnnotation(Annotation):
             taxonomy_name=payload.get(TAXONOMY_NAME_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
             track_reference_id=payload.get(TRACK_REFERENCE_ID_KEY, None),
-            task_id=payload.get(TASK_ID_KEY, None),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -1006,7 +1007,7 @@ class MultiCategoryAnnotation(Annotation):
             REFERENCE_ID_KEY: self.reference_id,
             METADATA_KEY: self.metadata,
             TRACK_REFERENCE_ID_KEY: self.track_reference_id,
-            TASK_ID_KEY: self.task_id,
+            TASK_ID_KEY: self._task_id,
         }
         if self.taxonomy_name is not None:
             payload[TAXONOMY_NAME_KEY] = self.taxonomy_name
@@ -1045,6 +1046,7 @@ class SceneCategoryAnnotation(Annotation):
     reference_id: str
     taxonomy_name: Optional[str] = None
     metadata: Optional[Dict] = field(default_factory=dict)
+    _task_id: Optional[str] = field(default=None, repr=False)
 
     @classmethod
     def from_json(cls, payload: dict):
@@ -1053,6 +1055,7 @@ class SceneCategoryAnnotation(Annotation):
             reference_id=payload[REFERENCE_ID_KEY],
             taxonomy_name=payload.get(TAXONOMY_NAME_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
+            _task_id=payload.get(TASK_ID_KEY, None),
         )
 
     def to_payload(self) -> dict:
@@ -1062,6 +1065,7 @@ class SceneCategoryAnnotation(Annotation):
             GEOMETRY_KEY: {},
             REFERENCE_ID_KEY: self.reference_id,
             METADATA_KEY: self.metadata,
+            TASK_ID_KEY: self._task_id,
         }
         if self.taxonomy_name is not None:
             payload[TAXONOMY_NAME_KEY] = self.taxonomy_name
@@ -1079,9 +1083,7 @@ class AnnotationList:
         default_factory=list
     )
     cuboid_annotations: List[CuboidAnnotation] = field(default_factory=list)
-    category_annotations: List[CategoryAnnotation] = field(
-        default_factory=list
-    )
+    category_annotations: List[CategoryAnnotation] = field(default_factory=list)
     multi_category_annotations: List[MultiCategoryAnnotation] = field(
         default_factory=list
     )

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/nucleus/annotation_uploader.py

@@ -176,9 +176,7 @@ class AnnotationUploader:
         """
 
         def fn():
-            request_json = construct_segmentation_payload(
-                segmentations, update
-            )
+            request_json = construct_segmentation_payload(segmentations, update)
             form_data = [
                 FileFormField(
                     name=SERIALIZED_REQUEST_KEY,
@@ -212,15 +210,17 @@ class AnnotationUploader:
 
         return fn
 
-    @staticmethod
-    def check_for_duplicate_ids(annotations: Iterable[Annotation]):
+    def check_for_duplicate_ids(self, annotations: Iterable[Annotation]):
         """Do not allow annotations to have the same (annotation_id, reference_id, task_id) tuple"""
 
-        # some annotations like CategoryAnnotation do not have annotation_id attribute, and as such, we allow duplicates
         tuple_ids = [
-            (ann.reference_id, ann.annotation_id, ann.task_id)  # type: ignore
+            (
+                ann.reference_id,
+                ann.annotation_id,
+                getattr(ann, "_task_id", None),
+            )
             for ann in annotations
-            if hasattr(ann, "annotation_id") and hasattr(ann, "task_id")
+            if hasattr(ann, "annotation_id")
         ]
         tuple_count = Counter(tuple_ids)
         duplicates = {key for key, value in tuple_count.items() if value > 1}
@@ -255,3 +255,20 @@ class PredictionUploader(AnnotationUploader):
             self._route = (
                 f"dataset/{dataset_id}/model/{model_id}/uploadPredictions"
             )
+
+    def check_for_duplicate_ids(self, annotations: Iterable[Annotation]):
+        """Do not allow predictions to have the same (annotation_id, reference_id) tuple"""
+        tuple_ids = [
+            (pred.annotation_id, pred.reference_id)  # type: ignore
+            for pred in annotations
+            if hasattr(pred, "annotation_id") and hasattr(pred, "reference_id")
+        ]
+        tuple_count = Counter(tuple_ids)
+        duplicates = {key for key, value in tuple_count.items() if value > 1}
+        if len(duplicates) > 0:
+            raise DuplicateIDError(
+                f"Duplicate predictions with the same (annotation_id, reference_id) properties found.\n"
+                f"Duplicates: {duplicates}\n"
+                f"To fix this, avoid duplicate predictions, or specify a different annotation_id attribute "
+                f"for the failing items."
+            )

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/nucleus/dataset.py

@@ -332,8 +332,7 @@ class Dataset:
         dataset_item_jsons = response.get(DATASET_ITEMS_KEY, None)
 
         return [
-            DatasetItem.from_json(item_json)
-            for item_json in dataset_item_jsons
+            DatasetItem.from_json(item_json) for item_json in dataset_item_jsons
         ]
 
     @property
@@ -699,9 +698,7 @@ class Dataset:
                 asynchronous
             ), "In order to avoid timeouts, you must set asynchronous=True when uploading videos."
 
-            return self._append_video_scenes(
-                video_scenes, update, asynchronous
-            )
+            return self._append_video_scenes(video_scenes, update, asynchronous)
 
         if len(dataset_items) > WARN_FOR_LARGE_UPLOAD and not asynchronous:
             print(
@@ -2361,10 +2358,7 @@ class Dataset:
         )
 
         if len(items) > 0:
-            if (
-                len(items) > GLOB_SIZE_THRESHOLD_CHECK
-                and not skip_size_warning
-            ):
+            if len(items) > GLOB_SIZE_THRESHOLD_CHECK and not skip_size_warning:
                 raise Exception(
                     f"Found over {GLOB_SIZE_THRESHOLD_CHECK} items in {dirname}. If this is intended,"
                     f" set skip_size_warning=True when calling this function."
@@ -2411,3 +2405,26 @@ class Dataset:
             route=f"dataset/{self.id}/model/{model.id}/pointcloud/{pointcloud_ref_id}/uploadLSSPrediction",
             requests_command=requests.post,
         )
+
+    def export_class_labels(self, slice_id: Optional[str] = None):
+        """Fetches a list of class labels for the dataset.
+
+        Args:
+            slice_id (str | None): The ID of the slice to export class labels for. If None, export class labels for the entire dataset.
+
+        Returns:
+            A list of class labels for the dataset.
+        """
+        if slice_id:
+            api_payload = self._client.make_request(
+                payload=None,
+                route=f"slice/{slice_id}/class_labels",
+                requests_command=requests.get,
+            )
+        else:
+            api_payload = self._client.make_request(
+                payload=None,
+                route=f"dataset/{self.id}/class_labels",
+                requests_command=requests.get,
+            )
+        return api_payload.get("data", [])

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/nucleus/slice.py

@@ -168,9 +168,7 @@ class Slice:
     @property
     def pending_job_count(self) -> Optional[int]:
         if self._pending_job_count is None:
-            self._pending_job_count = self.info().get(
-                "pending_job_count", None
-            )
+            self._pending_job_count = self.info().get("pending_job_count", None)
         return self._pending_job_count
 
     @classmethod
@@ -705,6 +703,15 @@ class Slice:
         )
         return api_payload
 
+    def export_class_labels(self):
+        """Fetches a list of class labels for the slice."""
+        api_payload = self._client.make_request(
+            payload=None,
+            route=f"slice/{self.id}/class_labels",
+            requests_command=requests.get,
+        )
+        return api_payload.get("data", [])
+
 
 def check_annotations_are_in_slice(
     annotations: List[Annotation], slice_to_check: Slice

{scale_nucleus-0.17.8 → scale_nucleus-0.17.9}/pyproject.toml

@@ -25,7 +25,7 @@ ignore = ["E501", "E741", "E731", "F401"]  # Easy ignore for getting it running
 
 [tool.poetry]
 name = "scale-nucleus"
-version = "0.17.8"
+version = "0.17.9"
 description = "The official Python client library for Nucleus, the Data Platform for AI"
 license =  "MIT"
 authors = ["Scale AI Nucleus Team <nucleusapi@scaleapi.com>"]