clean up types

api/scpca_portal/models/dataset.py

@@ -9,6 +9,7 @@
 from django.contrib.postgres.fields import ArrayField
 from django.db import models
 from django.db.models import Count
+from django.db.models.query import QuerySet
 from django.utils.timezone import make_aware
 
 from typing_extensions import Self
@@ -627,14 +628,14 @@ def get_includes_files_multiplexed(self) -> bool:
 
     # ASSOCIATIONS WITH OTHER MODELS
     @property
-    def projects(self) -> Iterable[Project]:
+    def projects(self) -> QuerySet[Project]:
         """Returns all project instances associated with the dataset."""
         if project_ids := self.data.keys():
             return Project.objects.filter(scpca_id__in=project_ids).order_by("scpca_id")
         return Project.objects.none()
 
     @property
-    def spatial_projects(self) -> Iterable[Project]:
+    def spatial_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances which have spatial data
         with spatial samples requested in the data attribute.
@@ -652,7 +653,7 @@ def spatial_projects(self) -> Iterable[Project]:
         return Project.objects.none()
 
     @property
-    def single_cell_projects(self) -> Iterable[Project]:
+    def single_cell_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances which have single cell data
         with single cell samples requested in the data attribute.
@@ -667,7 +668,7 @@ def single_cell_projects(self) -> Iterable[Project]:
         return Project.objects.none()
 
     @property
-    def bulk_single_cell_projects(self) -> Iterable[Project]:
+    def bulk_single_cell_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances which have bulk data
         where bulk was requested in the data attribute.
@@ -682,7 +683,7 @@ def bulk_single_cell_projects(self) -> Iterable[Project]:
         return Project.objects.none()
 
     @property
-    def cite_seq_projects(self) -> Iterable[Project]:
+    def cite_seq_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances associated with the dataset
         which have cite seq data.
@@ -694,7 +695,7 @@ def cite_seq_projects(self) -> Iterable[Project]:
         return self.projects.filter(has_cite_seq_data=True)
 
     @property
-    def merged_projects(self) -> Iterable[Project]:
+    def merged_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances which have merged data
         where merged was requested in the data attribute single cell field.
@@ -715,7 +716,7 @@ def merged_projects(self) -> Iterable[Project]:
         return Project.objects.none()
 
     @property
-    def multiplexed_projects(self) -> Iterable[Project]:
+    def multiplexed_projects(self) -> QuerySet[Project]:
         """
         Returns all project instances which have multiplexed data.
         """
@@ -738,7 +739,7 @@ def has_lockfile_projects(self) -> bool:
         return self.contains_project_ids(set(lockfile.get_locked_project_ids()))
 
     @property
-    def locked_projects(self) -> Iterable[Project]:
+    def locked_projects(self) -> QuerySet[Project]:
         """Returns a queryset of all of the dataset's locked project."""
         return self.projects.filter(is_locked=True)
 
@@ -756,7 +757,7 @@ def is_locked(self) -> bool:
         return self.has_locked_projects or self.has_lockfile_projects
 
     @property
-    def samples(self) -> Iterable[Sample]:
+    def samples(self) -> QuerySet[Sample]:
         """
         Returns a queryset of all samples contained in data attribute.
         If a sample is present in more than one modality, it will be
@@ -766,7 +767,7 @@ def samples(self) -> Iterable[Sample]:
             [Modalities.SINGLE_CELL, Modalities.SPATIAL, Modalities.BULK_RNA_SEQ]
         )
 
-    def get_selected_samples(self, modalities: Iterable[Modalities] = []) -> Iterable[Sample]:
+    def get_selected_samples(self, modalities: Iterable[Modalities] = []) -> QuerySet[Sample]:
         """
         Returns a queryset of samples for the specified modalities
         contained in data attribute.
@@ -780,7 +781,7 @@ def get_selected_samples(self, modalities: Iterable[Modalities] = []) -> Iterabl
 
     def get_project_modality_samples(
         self, project_id: str, modality: Modalities
-    ) -> Iterable[Library]:
+    ) -> QuerySet[Library]:
         """
         Takes project's scpca_id and a modality.
         Returns Sample instances defined in data attribute.
@@ -800,7 +801,7 @@ def get_project_modality_samples(
         return project_samples.filter(scpca_id__in=project_data.get(modality, []))
 
     @property
-    def libraries(self) -> Iterable[Library]:
+    def libraries(self) -> QuerySet[Library]:
         """Returns all of a Dataset's library, based on Data and Format attrs."""
         dataset_libraries = Library.objects.none()
 
@@ -812,7 +813,7 @@ def libraries(self) -> Iterable[Library]:
 
     def get_project_modality_libraries(
         self, project_id: str, modality: Modalities
-    ) -> Iterable[Library]:
+    ) -> QuerySet[Library]:
         """
         Takes project's scpca_id and a modality.
         Returns Library instances associated with Samples defined in data attribute.
@@ -832,7 +833,7 @@ def get_is_merged_project(self, project_id) -> bool:
         return self.data.get(project_id, {}).get(Modalities.SINGLE_CELL.value) == "MERGED"
 
     @property
-    def original_files(self) -> Iterable[OriginalFile]:
+    def original_files(self) -> QuerySet[OriginalFile]:
         """Returns all of a Dataset's associated OriginalFiles."""
         files = OriginalFile.objects.none()
 

api/scpca_portal/models/original_file.py

@@ -1,10 +1,11 @@
 from collections import defaultdict
 from pathlib import Path
-from typing import Dict, Iterable, List, Tuple
+from typing import Dict, List, Tuple
 
 from django.conf import settings
 from django.contrib.postgres.fields import ArrayField
 from django.db import models
+from django.db.models.query import QuerySet
 
 from typing_extensions import Self
 
@@ -164,7 +165,7 @@ def bulk_update_from_dicts(
     @staticmethod
     def purge_deleted_files(
         bucket: str, sync_timestamp, allow_bucket_wipe: bool = False
-    ) -> List[Self]:
+    ) -> QuerySet["OriginalFile"]:
         """Purge all files that no longer exist on s3."""
         # if the last_bucket_sync timestamp wasn't updated,
         # then the file has been deleted from s3, which must be reflected in the db.
@@ -297,7 +298,7 @@ def get_input_samples_metadata_file(
     @classmethod
     def get_input_library_metadata_files(
         cls, project_id: str, *, bucket: str = settings.AWS_S3_INPUT_BUCKET_NAME
-    ) -> Iterable[Self]:
+    ) -> QuerySet[Self]:
         return OriginalFile.objects.filter(
             is_metadata=True,
             project_id=project_id,

api/scpca_portal/models/project.py

@@ -1,11 +1,12 @@
 import csv
 from collections import Counter
-from typing import Dict, Iterable, List
+from typing import Dict, List
 
 from django.conf import settings
 from django.contrib.postgres.fields import ArrayField
 from django.db import models
 from django.db.models import Count, Q
+from django.db.models.query import QuerySet
 
 from typing_extensions import Self
 
@@ -111,7 +112,7 @@ def valid_download_configs(self) -> List[Dict]:
         ]
 
     @property
-    def original_files(self) -> Iterable[OriginalFile]:
+    def original_files(self) -> QuerySet[OriginalFile]:
         return OriginalFile.downloadable_objects.filter(
             project_id=self.scpca_id, is_project_file=True
         )
@@ -121,7 +122,7 @@ def original_file_paths(self) -> List[str]:
         return sorted(self.original_files.values_list("s3_key", flat=True))
 
     @property
-    def computed_files(self) -> Iterable[ComputedFile]:
+    def computed_files(self) -> QuerySet[ComputedFile]:
         return self.project_computed_files.order_by("created_at")
 
     @property