lamindb 0.69.7__py3-none-any.whl → 0.69.9__py3-none-any.whl

lamindb/core/_data.py

@@ -1,5 +1,7 @@
+from __future__ import annotations
+
 from collections import defaultdict
-from typing import Any, Dict, Iterable, List, Optional, Union
+from typing import TYPE_CHECKING, Any, Iterable, List
 
 from lamin_utils import colors, logger
 from lamindb_setup.core._docs import doc_args
@@ -15,7 +17,6 @@ from lnschema_core.models import (
     __repr__,
     format_field_value,
 )
-from lnschema_core.types import StrField
 
 from lamindb._feature_set import (
     dict_related_model_to_related_name,
@@ -36,10 +37,13 @@ from ._label_manager import LabelManager, print_labels
 from ._run_context import run_context
 from .exceptions import ValidationError
 
+if TYPE_CHECKING:
+    from lnschema_core.types import StrField
+
 WARNING_RUN_TRANSFORM = "no run & transform get linked, consider calling ln.track()"
 
 
-def get_run(run: Optional[Run]) -> Optional[Run]:
+def get_run(run: Run | None) -> Run | None:
     if run is None:
         run = run_context.run
         if run is None and not settings.silence_file_run_transform_warning:
@@ -50,12 +54,12 @@ def get_run(run: Optional[Run]) -> Optional[Run]:
     return run
 
 
-def add_transform_to_kwargs(kwargs: Dict[str, Any], run: Run):
+def add_transform_to_kwargs(kwargs: dict[str, Any], run: Run):
     if run is not None:
         kwargs["transform"] = run.transform
 
 
-def save_feature_sets(self: Union[Artifact, Collection]) -> None:
+def save_feature_sets(self: Artifact | Collection) -> None:
     if hasattr(self, "_feature_sets"):
         saved_feature_sets = {}
         for key, feature_set in self._feature_sets.items():
@@ -73,7 +77,7 @@ def save_feature_sets(self: Union[Artifact, Collection]) -> None:
             )
 
 
-def save_feature_set_links(self: Union[Artifact, Collection]) -> None:
+def save_feature_set_links(self: Artifact | Collection) -> None:
     from lamindb._save import bulk_create
 
     Data = self.__class__
@@ -141,7 +145,7 @@ def describe(self: Data):
     logger.print(msg)
 
 
-def validate_feature(feature: Feature, records: List[Registry]) -> None:
+def validate_feature(feature: Feature, records: list[Registry]) -> None:
     """Validate feature record, set feature.registries based on labels records."""
     if not isinstance(feature, Feature):
         raise TypeError("feature has to be of type Feature")
@@ -160,7 +164,7 @@ def get_labels(
     feature: Feature,
     mute: bool = False,
     flat_names: bool = False,
-) -> Union[QuerySet, Dict[str, QuerySet], List]:
+) -> QuerySet | dict[str, QuerySet] | list:
     """{}."""
     if not isinstance(feature, Feature):
         raise TypeError("feature has to be of type Feature")
@@ -202,10 +206,10 @@ def get_labels(
 
 def add_labels(
     self,
-    records: Union[Registry, List[Registry], QuerySet, Iterable],
-    feature: Optional[Feature] = None,
+    records: Registry | list[Registry] | QuerySet | Iterable,
+    feature: Feature | None = None,
     *,
-    field: Optional[StrField] = None,
+    field: StrField | None = None,
 ) -> None:
     """{}."""
     if self._state.adding:
@@ -253,7 +257,7 @@ def add_labels(
     if feature is None:
         d = dict_related_model_to_related_name(self.__class__)
         # strategy: group records by registry to reduce number of transactions
-        records_by_related_name: Dict = {}
+        records_by_related_name: dict = {}
         for record in records:
             related_name = d.get(record.__class__.__get_name_with_schema__())
             if related_name is None:
@@ -343,9 +347,9 @@ def add_labels(
 
 
 def _track_run_input(
-    data: Union[Data, Iterable[Data]],
-    is_run_input: Optional[bool] = None,
-    run: Optional[Run] = None,
+    data: Data | Iterable[Data],
+    is_run_input: bool | None = None,
+    run: Run | None = None,
 ):
     if run is None:
         run = run_context.run
@@ -430,7 +434,7 @@ def _track_run_input(
 
 @property  # type: ignore
 @doc_args(Data.features.__doc__)
-def features(self) -> "FeatureManager":
+def features(self) -> FeatureManager:
     """{}."""
     from lamindb.core._feature_manager import FeatureManager
 
@@ -439,7 +443,7 @@ def features(self) -> "FeatureManager":
 
 @property  # type: ignore
 @doc_args(Data.labels.__doc__)
-def labels(self) -> "LabelManager":
+def labels(self) -> LabelManager:
     """{}."""
     from lamindb.core._label_manager import LabelManager
 

lamindb/core/_feature_manager.py

@@ -1,16 +1,16 @@
+from __future__ import annotations
+
 from itertools import compress
-from typing import Dict, Iterable, Optional, Union
+from typing import TYPE_CHECKING, Iterable
 
 import anndata as ad
 from anndata import AnnData
 from lamin_utils import colors, logger
 from lamindb_setup.core.upath import create_path
 from lnschema_core.models import Artifact, Collection, Data, Feature, Registry
-from lnschema_core.types import AnnDataLike, FieldAttr
 
 from lamindb._feature import convert_numpy_dtype_to_lamin_feature_type
 from lamindb._feature_set import FeatureSet
-from lamindb._query_set import QuerySet
 from lamindb._registry import (
     REGISTRY_UNIQUE_FIELD,
     get_default_str_field,
@@ -22,8 +22,13 @@ from lamindb.core.storage import LocalPathClasses
 
 from ._settings import settings
 
+if TYPE_CHECKING:
+    from lnschema_core.types import FieldAttr
+
+    from lamindb._query_set import QuerySet
+
 
-def get_host_id_field(host: Union[Artifact, Collection]) -> str:
+def get_host_id_field(host: Artifact | Collection) -> str:
     if isinstance(host, Artifact):
         host_id_field = "artifact_id"
     else:
@@ -31,7 +36,7 @@ def get_host_id_field(host: Union[Artifact, Collection]) -> str:
     return host_id_field
 
 
-def get_accessor_by_orm(host: Union[Artifact, Collection]) -> Dict:
+def get_accessor_by_orm(host: Artifact | Collection) -> dict:
     dictionary = {
         field.related_model.__get_name_with_schema__(): field.name
         for field in host._meta.related_objects
@@ -41,7 +46,7 @@ def get_accessor_by_orm(host: Union[Artifact, Collection]) -> Dict:
     return dictionary
 
 
-def get_feature_set_by_slot(host) -> Dict:
+def get_feature_set_by_slot(host) -> dict:
     # if the host is not yet saved
     if host._state.adding:
         if hasattr(host, "_feature_sets"):
@@ -64,7 +69,7 @@ def get_feature_set_by_slot(host) -> Dict:
 
 
 def get_label_links(
-    host: Union[Artifact, Collection], registry: str, feature: Feature
+    host: Artifact | Collection, registry: str, feature: Feature
 ) -> QuerySet:
     host_id_field = get_host_id_field(host)
     kwargs = {host_id_field: host.id, "feature_id": feature.id}
@@ -76,7 +81,7 @@ def get_label_links(
     return link_records
 
 
-def get_feature_set_links(host: Union[Artifact, Collection]) -> QuerySet:
+def get_feature_set_links(host: Artifact | Collection) -> QuerySet:
     host_id_field = get_host_id_field(host)
     kwargs = {host_id_field: host.id}
     feature_set_links = host.feature_sets.through.objects.filter(**kwargs)
@@ -127,11 +132,11 @@ def print_features(self: Data) -> str:
 
 
 def parse_feature_sets_from_anndata(
-    adata: AnnDataLike,
+    adata: AnnData,
     var_field: FieldAttr,
     obs_field: FieldAttr = Feature.name,
     **kwargs,
-) -> Dict:
+) -> dict:
     data_parse = adata
     if not isinstance(adata, AnnData):  # is a path
         filepath = create_path(adata)  # returns Path for local
@@ -183,7 +188,7 @@ class FeatureManager:
     See :class:`~lamindb.core.Data` for more information.
     """
 
-    def __init__(self, host: Union[Artifact, Collection]):
+    def __init__(self, host: Artifact | Collection):
         self._host = host
         self._feature_set_by_slot = get_feature_set_by_slot(host)
         self._accessor_by_orm = get_accessor_by_orm(host)
@@ -210,7 +215,7 @@ class FeatureManager:
         else:
             return getattr(feature_set, self._accessor_by_orm[orm_name]).all()
 
-    def add(self, features: Iterable[Registry], slot: Optional[str] = None):
+    def add(self, features: Iterable[Registry], slot: str | None = None):
         """Add features stratified by slot."""
         if (hasattr(self._host, "accessor") and self._host.accessor == "DataFrame") or (
             hasattr(self._host, "artifact")
@@ -246,7 +251,7 @@ class FeatureManager:
     def add_from_anndata(
         self,
         var_field: FieldAttr,
-        obs_field: Optional[FieldAttr] = Feature.name,
+        obs_field: FieldAttr | None = Feature.name,
         **kwargs,
     ):
         """Add features from AnnData."""

lamindb/core/_label_manager.py

@@ -1,4 +1,6 @@
-from typing import Dict, List, Optional, Tuple, Union
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Dict
 
 import numpy as np
 from lamin_utils import colors, logger
@@ -6,7 +8,6 @@ from lnschema_core.models import Artifact, Collection, Data, Feature, Registry
 
 from lamindb._feature_set import dict_related_model_to_related_name
 from lamindb._from_values import _print_values
-from lamindb._query_set import QuerySet
 from lamindb._registry import (
     REGISTRY_UNIQUE_FIELD,
     get_default_str_field,
@@ -17,6 +18,9 @@ from lamindb._save import save
 
 from ._settings import settings
 
+if TYPE_CHECKING:
+    from lamindb._query_set import QuerySet
+
 
 def get_labels_as_dict(self: Data):
     labels = {}
@@ -80,10 +84,10 @@ def transfer_add_labels(labels, features_lookup_self, self, row, parents: bool =
         transfer_single_registry(*result)
 
 
-def validate_labels(labels: Union[QuerySet, List, Dict], parents: bool = True):
+def validate_labels(labels: QuerySet | list | dict, parents: bool = True):
     def validate_labels_registry(
-        labels: Union[QuerySet, List, Dict], parents: bool = True
-    ) -> Tuple[List[str], List[str]]:
+        labels: QuerySet | list | dict, parents: bool = True
+    ) -> tuple[list[str], list[str]]:
         if len(labels) == 0:
             return [], []
         registry = labels[0].__class__
@@ -134,7 +138,7 @@ class LabelManager:
     See :class:`~lamindb.core.Data` for more information.
     """
 
-    def __init__(self, host: Union[Artifact, Collection]):
+    def __init__(self, host: Artifact | Collection):
         self._host = host
 
     def __repr__(self) -> str:
@@ -146,8 +150,8 @@ class LabelManager:
 
     def add(
         self,
-        records: Union[Registry, List[Registry], QuerySet],
-        feature: Optional[Feature] = None,
+        records: Registry | list[Registry] | QuerySet,
+        feature: Feature | None = None,
     ) -> None:
         """Add one or several labels and associate them with a feature.
 
@@ -165,7 +169,7 @@ class LabelManager:
         feature: Feature,
         mute: bool = False,
         flat_names: bool = False,
-    ) -> Union[QuerySet, Dict[str, QuerySet], List]:
+    ) -> QuerySet | dict[str, QuerySet] | list:
         """Get labels given a feature.
 
         Args:

lamindb/core/_mapped_collection.py

@@ -1,12 +1,13 @@
+from __future__ import annotations
+
 from collections import Counter
 from functools import reduce
 from pathlib import Path
-from typing import Dict, List, Literal, Optional, Union
+from typing import TYPE_CHECKING, Dict, List, Literal, Optional, Union
 
 import numpy as np
 import pandas as pd
 from lamin_utils import logger
-from lamindb_setup.core.types import UPathStr
 from lamindb_setup.core.upath import UPath
 
 from .storage._backed_access import (
@@ -17,6 +18,9 @@ from .storage._backed_access import (
     registry,
 )
 
+if TYPE_CHECKING:
+    from lamindb_setup.core.types import UPathStr
+
 
 class _Connect:
     def __init__(self, storage):
@@ -81,14 +85,14 @@ class MappedCollection:
 
     def __init__(
         self,
-        path_list: List[UPathStr],
-        label_keys: Optional[Union[str, List[str]]] = None,
-        join: Optional[Literal["inner", "outer"]] = "inner",
-        encode_labels: Union[bool, List[str]] = True,
-        unknown_label: Optional[Union[str, Dict[str, str]]] = None,
+        path_list: list[UPathStr],
+        label_keys: str | list[str] | None = None,
+        join: Literal["inner", "outer"] | None = "inner",
+        encode_labels: bool | list[str] = True,
+        unknown_label: str | dict[str, str] | None = None,
         cache_categories: bool = True,
         parallel: bool = False,
-        dtype: Optional[str] = None,
+        dtype: str | None = None,
     ):
         assert join in {None, "inner", "outer"}
 
@@ -248,8 +252,8 @@ class MappedCollection:
         self,
         storage: StorageType,  # type: ignore
         idx: int,
-        var_idxs_join: Optional[list] = None,
-        layer_key: Optional[str] = None,
+        var_idxs_join: list | None = None,
+        layer_key: str | None = None,
     ):
         """Get the index for the data."""
         layer = storage["X"] if layer_key is None else storage["layers"][layer_key]  # type: ignore
@@ -290,7 +294,7 @@ class MappedCollection:
         storage: StorageType,
         idx: int,
         label_key: str,
-        categories: Optional[list] = None,
+        categories: list | None = None,
     ):
         """Get the index for the label by key."""
         obs = storage["obs"]  # type: ignore
@@ -313,7 +317,7 @@ class MappedCollection:
             label = label.decode("utf-8")
         return label
 
-    def get_label_weights(self, label_keys: Union[str, List[str]]):
+    def get_label_weights(self, label_keys: str | list[str]):
         """Get all weights for the given label keys."""
         if isinstance(label_keys, str):
             label_keys = [label_keys]

lamindb/core/_run_context.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import builtins
 import hashlib
 import os
@@ -6,12 +8,11 @@ import subprocess
 import sys
 from datetime import datetime, timezone
 from pathlib import Path, PurePath
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any
 
 from lamin_utils import logger
 from lamindb_setup import settings as setup_settings
 from lamindb_setup.core import InstanceSettings
-from lamindb_setup.core.types import UPathStr
 from lnschema_core import Run, Transform, ids
 from lnschema_core.types import TransformType
 from lnschema_core.users import current_user_id
@@ -21,6 +22,9 @@ from lamindb.core._transform_settings import transform as transform_settings
 from ._settings import settings
 from ._sync_git import get_transform_reference_from_git_repo
 
+if TYPE_CHECKING:
+    from lamindb_setup.core.types import UPathStr
+
 is_run_from_ipython = getattr(builtins, "__IPYTHON__", False)
 
 msg_path_failed = (
@@ -55,7 +59,7 @@ def get_uid_ext(version: str) -> str:
     return encodebytes(hashlib.md5(version.encode()).digest())[:4]
 
 
-def get_stem_uid_and_version_from_file(file_path: Path) -> Tuple[str, str]:
+def get_stem_uid_and_version_from_file(file_path: Path) -> tuple[str, str]:
     # line-by-line matching might be faster, but let's go with this for now
     with open(file_path) as file:
         content = file.read()
@@ -215,20 +219,20 @@ def raise_transform_settings_error() -> None:
 class run_context:
     """Global run context."""
 
-    transform: Optional[Transform] = None
+    transform: Transform | None = None
     """Current transform."""
-    run: Optional[Run] = None
+    run: Run | None = None
     """Current run."""
-    path: Optional[Path] = None
+    path: Path | None = None
     """A local path to the script that's running."""
 
     @classmethod
     def _track(
         cls,
         *,
-        transform: Optional[Transform] = None,
-        new_run: Optional[bool] = None,
-        path: Optional[str] = None,
+        transform: Transform | None = None,
+        new_run: bool | None = None,
+        path: str | None = None,
     ) -> None:
         """Track notebook or script run.
 
@@ -364,8 +368,8 @@ class run_context:
     def _track_script(
         cls,
         *,
-        path: Optional[UPathStr],
-    ) -> Tuple[str, str, str, str]:
+        path: UPathStr | None,
+    ) -> tuple[str, str, str, str]:
         if path is None:
             import inspect
 
@@ -387,7 +391,7 @@ class run_context:
     def _track_notebook(
         cls,
         *,
-        path: Optional[str],
+        path: str | None,
     ):
         if path is None:
             path = get_notebook_path()
@@ -442,13 +446,13 @@ class run_context:
         cls,
         *,
         stem_uid: str,
-        version: Optional[str],
+        version: str | None,
         name: str,
-        transform_ref: Optional[str] = None,
-        transform_ref_type: Optional[str] = None,
-        key: Optional[str] = None,
+        transform_ref: str | None = None,
+        transform_ref_type: str | None = None,
+        key: str | None = None,
         transform_type: TransformType = None,
-        transform: Optional[Transform] = None,
+        transform: Transform | None = None,
     ):
         # make a new transform record
         if transform is None:

lamindb/core/_settings.py

@@ -1,16 +1,21 @@
+from __future__ import annotations
+
 import os
-from pathlib import Path
-from typing import Dict, Literal, Mapping, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Literal, Mapping
 
 import lamindb_setup as ln_setup
 from lamin_utils import logger
 from lamindb_setup._add_remote_storage import switch_default_storage
 from lamindb_setup.core._settings import settings as setup_settings
 from lamindb_setup.core._settings_instance import sanitize_git_repo_url
-from upath import UPath
 
 from ._transform_settings import TransformSettings, transform
 
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from upath import UPath
+
 VERBOSITY_TO_INT = {
     "error": 0,  # 40
     "warning": 1,  # 30
@@ -19,7 +24,7 @@ VERBOSITY_TO_INT = {
     "hint": 4,  # 15
     "debug": 5,  # 10
 }
-VERBOSITY_TO_STR: Dict[int, str] = dict(
+VERBOSITY_TO_STR: dict[int, str] = dict(
     [reversed(i) for i in VERBOSITY_TO_INT.items()]  # type: ignore
 )
 
@@ -30,10 +35,10 @@ class Settings:
     Use ``lamindb.settings`` instead of instantiating this class yourself.
     """
 
-    def __init__(self, git_repo: Optional[str]):
+    def __init__(self, git_repo: str | None):
         self._verbosity_int: int = 1  # warning-level logging
         logger.set_verbosity(self._verbosity_int)
-        self._sync_git_repo: Optional[str] = git_repo
+        self._sync_git_repo: str | None = git_repo
 
     upon_artifact_create_if_hash_exists: Literal[
         "warn_return_existing", "error", "warn_create_new"
@@ -73,16 +78,16 @@ class Settings:
     If `True`, the `key` is **not** used to construct file paths, but file paths are
     based on the `uid` of artifact.
     """
-    __using_key: Optional[str] = None
-    _using_storage: Optional[str] = None
+    __using_key: str | None = None
+    _using_storage: str | None = None
 
     @property
-    def _using_key(self) -> Optional[str]:
+    def _using_key(self) -> str | None:
         """Key for Django database settings."""
         return self.__using_key
 
     @_using_key.setter
-    def _using_key(self, value: Optional[str]):
+    def _using_key(self, value: str | None):
         ln_setup.settings._using_key = value
         self.__using_key = value
 
@@ -100,7 +105,7 @@ class Settings:
         return transform
 
     @property
-    def sync_git_repo(self) -> Optional[str]:
+    def sync_git_repo(self) -> str | None:
         """Sync transforms with scripts in git repository.
 
         Provide the full git repo URL.
@@ -117,7 +122,7 @@ class Settings:
         assert self._sync_git_repo.startswith("https://")
 
     @property
-    def storage(self) -> Union[Path, UPath]:
+    def storage(self) -> Path | UPath:
         """Default storage location (a path to its root).
 
         Examples:
@@ -137,9 +142,7 @@ class Settings:
         return self._storage_settings.root
 
     @storage.setter
-    def storage(
-        self, path_kwargs: Union[str, Path, UPath, Tuple[Union[str, UPath], Mapping]]
-    ):
+    def storage(self, path_kwargs: str | Path | UPath | tuple[str | UPath, Mapping]):
         logger.warning(
             "you'll no longer be able to set arbitrary storage locations soon"
         )
@@ -165,7 +168,7 @@ class Settings:
         return VERBOSITY_TO_STR[self._verbosity_int]
 
     @verbosity.setter
-    def verbosity(self, verbosity: Union[str, int]):
+    def verbosity(self, verbosity: str | int):
         if isinstance(verbosity, str):
             verbosity_int = VERBOSITY_TO_INT[verbosity]
         else:

lamindb/core/_sync_git.py

@@ -1,6 +1,7 @@
+from __future__ import annotations
+
 import subprocess
 from pathlib import Path
-from typing import Optional
 
 from lamin_utils import logger
 from lamindb_setup import settings as setup_settings
@@ -52,9 +53,7 @@ def check_local_git_repo() -> bool:
             return False
 
 
-def get_git_commit_hash(
-    blob_hash: str, repo_dir: Optional[Path] = None
-) -> Optional[str]:
+def get_git_commit_hash(blob_hash: str, repo_dir: Path | None = None) -> str | None:
     command = f"git log --find-object={blob_hash} --pretty=format:%H"
     result = subprocess.run(
         command,
@@ -71,7 +70,7 @@ def get_git_commit_hash(
 
 
 def get_filepath_within_git_repo(
-    commit_hash: str, blob_hash: str, repo_dir: Optional[Path]
+    commit_hash: str, blob_hash: str, repo_dir: Path | None
 ) -> str:
     # repo_dir might not point to the root of the
     # the git repository because git log --find-object works

lamindb/core/_track_environment.py

@@ -1,8 +1,13 @@
+from __future__ import annotations
+
 import subprocess
+from typing import TYPE_CHECKING
 
 import lamindb_setup as ln_setup
 from lamin_utils import logger
-from lnschema_core.models import Run
+
+if TYPE_CHECKING:
+    from lnschema_core.models import Run
 
 
 def track_environment(run: Run) -> None:

lamindb/core/_transform_settings.py

@@ -1,9 +1,9 @@
-from typing import Optional
+from __future__ import annotations
 
 
 class TransformSettings:
-    stem_uid: Optional[None] = None
-    version: Optional[None] = None
+    stem_uid: None | None = None
+    version: None | None = None
 
 
 transform = TransformSettings()

lamindb/core/_view_tree.py

@@ -1,4 +1,5 @@
-import os
+from __future__ import annotations
+
 from collections import defaultdict
 from pathlib import Path
 from typing import Iterable

lamindb/core/datasets/_core.py

@@ -1,5 +1,6 @@
+from __future__ import annotations
+
 from pathlib import Path
-from typing import Union
 from urllib.request import urlretrieve
 
 import anndata as ad
@@ -448,7 +449,7 @@ def df_iris_in_meter_study2() -> pd.DataFrame:
 
 
 def dir_scrnaseq_cellranger(
-    sample_name: str, basedir: Union[str, Path] = "./", output_only: bool = True
+    sample_name: str, basedir: str | Path = "./", output_only: bool = True
 ):  # pragma: no cover
     """Generate mock cell ranger outputs.
 

lamindb/core/datasets/_fake.py

@@ -1,7 +1,7 @@
-from typing import List
+from __future__ import annotations
 
 
-def fake_bio_notebook_titles(n=100) -> List[str]:
+def fake_bio_notebook_titles(n=100) -> list[str]:
     """A fake collection of study titles."""
     from faker import Faker