lamindb 0.69.2__py3-none-any.whl → 0.69.4__py3-none-any.whl

lamindb/_artifact.py

@@ -15,8 +15,7 @@ from lamindb_setup.core.types import UPathStr
 from lamindb_setup.core.upath import (
     create_path,
     extract_suffix_from_path,
-    get_stat_dir_gs,
-    get_stat_dir_s3,
+    get_stat_dir_cloud,
     get_stat_file_cloud,
 )
 from lnschema_core import Artifact, Run, Storage
@@ -192,10 +191,7 @@ def get_stat_or_artifact(
             if "ETag" in stat:  # is file
                 size, hash, hash_type = get_stat_file_cloud(stat)
             elif path.is_dir():
-                if path.protocol == "s3":
-                    size, hash, hash_type, n_objects = get_stat_dir_s3(path)
-                elif path.protocol == "gs":
-                    size, hash, hash_type, n_objects = get_stat_dir_gs(path)
+                size, hash, hash_type, n_objects = get_stat_dir_cloud(path)
         if hash is None:
             logger.warning(f"did not add hash for {path}")
             return size, hash, hash_type, n_objects

lamindb/_collection.py

@@ -64,7 +64,7 @@ def __init__(
     # now we proceed with the user-facing constructor
     if len(args) > 1:
         raise ValueError("Only one non-keyword arg allowed: data")
-    data: Union[pd.DataFrame, ad.AnnData, Artifact, Iterable[Artifact]] = (
+    data: Union[Artifact, Iterable[Artifact]] = (
         kwargs.pop("data") if len(args) == 0 else args[0]
     )
     meta: Optional[str] = kwargs.pop("meta") if "meta" in kwargs else None
@@ -108,57 +108,24 @@ def __init__(
         if name is None:
             name = is_new_version_of.name
     run = get_run(run)
-    data_init_complete = False
-    artifact = None
-    artifacts = None
-    # now handle potential metadata
+    if isinstance(data, Artifact):
+        data = [data]
+    else:
+        if not hasattr(data, "__getitem__"):
+            raise ValueError("Artifact or List[Artifact] is allowed.")
+        assert isinstance(data[0], Artifact)  # type: ignore
+    hash, feature_sets = from_artifacts(data)  # type: ignore
     if meta is not None:
-        if not isinstance(meta, (pd.DataFrame, ad.AnnData, Artifact)):
-            raise ValueError(
-                "meta has to be of type `(pd.DataFrame, ad.AnnData, Artifact)`"
-            )
-        data = meta
-    # init artifact - is either data or metadata
-    if isinstance(data, (pd.DataFrame, ad.AnnData, Artifact)):
-        if isinstance(data, Artifact):
-            artifact = data
-            if artifact._state.adding:
-                raise ValueError("Save artifact before creating collection!")
+        if not isinstance(meta, Artifact):
+            raise ValueError("meta has to be an Artifact")
+        if isinstance(meta, Artifact):
+            if meta._state.adding:
+                raise ValueError("Save meta artifact before creating collection!")
             if not feature_sets:
-                feature_sets = artifact.features._feature_set_by_slot
+                feature_sets = meta.features._feature_set_by_slot
             else:
-                if len(artifact.features._feature_set_by_slot) > 0:
+                if len(meta.features._feature_set_by_slot) > 0:
                     logger.info("overwriting feature sets linked to artifact")
-        else:
-            artifact_is_new_version_of = (
-                is_new_version_of.artifact if is_new_version_of is not None else None
-            )
-            artifact = Artifact(
-                data,
-                run=run,
-                description="tmp",
-                version=version,
-                is_new_version_of=artifact_is_new_version_of,
-                accessor=accessor,
-            )
-            # do we really want to update the artifact here?
-            if feature_sets:
-                artifact._feature_sets = feature_sets
-        hash = artifact.hash  # type: ignore
-        provisional_uid = artifact.uid  # type: ignore
-        if artifact.description is None or artifact.description == "tmp":
-            artifact.description = f"See collection {provisional_uid}"  # type: ignore
-        data_init_complete = True
-    if not data_init_complete:
-        if hasattr(data, "__getitem__"):
-            assert isinstance(data[0], Artifact)  # type: ignore
-            artifacts = data
-            hash, feature_sets = from_artifacts(artifacts)  # type: ignore
-            data_init_complete = True
-        else:
-            raise ValueError(
-                "Only DataFrame, AnnData, Artifact or list of artifacts is allowed."
-            )
     # we ignore collections in trash containing the same hash
     if hash is not None:
         existing_collection = Collection.filter(hash=hash).one_or_none()
@@ -183,88 +150,19 @@ def __init__(
             description=description,
             reference=reference,
             reference_type=reference_type,
-            artifact=artifact,
+            artifact=meta,
             hash=hash,
             run=run,
             version=version,
             visibility=visibility,
             **kwargs,
         )
-    collection._artifacts = artifacts
+    collection._artifacts = data
     collection._feature_sets = feature_sets
     # register provenance
     if is_new_version_of is not None:
         _track_run_input(is_new_version_of, run=run)
-    if artifact is not None and artifact.run != run:
-        _track_run_input(artifact, run=run)
-    elif artifacts is not None:
-        _track_run_input(artifacts, run=run)
-
-
-@classmethod  # type: ignore
-@doc_args(Collection.from_df.__doc__)
-def from_df(
-    cls,
-    df: "pd.DataFrame",
-    name: Optional[str] = None,
-    description: Optional[str] = None,
-    run: Optional[Run] = None,
-    reference: Optional[str] = None,
-    reference_type: Optional[str] = None,
-    version: Optional[str] = None,
-    is_new_version_of: Optional["Artifact"] = None,
-    **kwargs,
-) -> "Collection":
-    """{}."""
-    if isinstance(df, Artifact):
-        assert not df._state.adding
-        assert df.accessor == "DataFrame"
-    collection = Collection(
-        data=df,
-        name=name,
-        run=run,
-        description=description,
-        reference=reference,
-        reference_type=reference_type,
-        version=version,
-        is_new_version_of=is_new_version_of,
-        accessor="DataFrame",
-        **kwargs,
-    )
-    return collection
-
-
-@classmethod  # type: ignore
-@doc_args(Collection.from_anndata.__doc__)
-def from_anndata(
-    cls,
-    adata: "AnnData",
-    name: Optional[str] = None,
-    description: Optional[str] = None,
-    run: Optional[Run] = None,
-    reference: Optional[str] = None,
-    reference_type: Optional[str] = None,
-    version: Optional[str] = None,
-    is_new_version_of: Optional["Artifact"] = None,
-    **kwargs,
-) -> "Collection":
-    """{}."""
-    if isinstance(adata, Artifact):
-        assert not adata._state.adding
-        assert adata.accessor == "AnnData"
-    collection = Collection(
-        data=adata,
-        run=run,
-        name=name,
-        description=description,
-        reference=reference,
-        reference_type=reference_type,
-        version=version,
-        is_new_version_of=is_new_version_of,
-        accessor="AnnData",
-        **kwargs,
-    )
-    return collection
+    _track_run_input(data, run=run)
 
 
 # internal function, not exposed to user
@@ -373,18 +271,6 @@ def stage(self, is_run_input: Optional[bool] = None) -> List[UPath]:
     return path_list
 
 
-# docstring handled through attach_func_to_class_method
-def backed(
-    self, is_run_input: Optional[bool] = None
-) -> Union["AnnDataAccessor", "BackedAccessor"]:
-    _track_run_input(self, is_run_input)
-    if self.artifact is None:
-        raise RuntimeError(
-            "Can only call backed() for collections with a single artifact"
-        )
-    return self.artifact.backed()
-
-
 # docstring handled through attach_func_to_class_method
 def load(
     self,
@@ -393,29 +279,25 @@ def load(
     **kwargs,
 ) -> DataLike:
     # cannot call _track_run_input here, see comment further down
-    if self.artifact is not None:
-        _track_run_input(self, is_run_input)
-        return self.artifact.load()
-    else:
-        all_artifacts = self.artifacts.all()
-        suffixes = [artifact.suffix for artifact in all_artifacts]
-        if len(set(suffixes)) != 1:
-            raise RuntimeError(
-                "Can only load collections where all artifacts have the same suffix"
-            )
-        # because we're tracking data flow on the collection-level, here, we don't
-        # want to track it on the artifact-level
-        objects = [artifact.load(is_run_input=False) for artifact in all_artifacts]
-        artifact_uids = [artifact.uid for artifact in all_artifacts]
-        if isinstance(objects[0], pd.DataFrame):
-            concat_object = pd.concat(objects, join=join)
-        elif isinstance(objects[0], ad.AnnData):
-            concat_object = ad.concat(
-                objects, join=join, label="artifact_uid", keys=artifact_uids
-            )
-        # only call it here because there might be errors during concat
-        _track_run_input(self, is_run_input)
-        return concat_object
+    all_artifacts = self.artifacts.all()
+    suffixes = [artifact.suffix for artifact in all_artifacts]
+    if len(set(suffixes)) != 1:
+        raise RuntimeError(
+            "Can only load collections where all artifacts have the same suffix"
+        )
+    # because we're tracking data flow on the collection-level, here, we don't
+    # want to track it on the artifact-level
+    objects = [artifact.load(is_run_input=False) for artifact in all_artifacts]
+    artifact_uids = [artifact.uid for artifact in all_artifacts]
+    if isinstance(objects[0], pd.DataFrame):
+        concat_object = pd.concat(objects, join=join)
+    elif isinstance(objects[0], ad.AnnData):
+        concat_object = ad.concat(
+            objects, join=join, label="artifact_uid", keys=artifact_uids
+        )
+    # only call it here because there might be errors during concat
+    _track_run_input(self, is_run_input)
+    return concat_object
 
 
 # docstring handled through attach_func_to_class_method
@@ -484,11 +366,8 @@ def artifacts(self) -> QuerySet:
 
 METHOD_NAMES = [
     "__init__",
-    "from_anndata",
-    "from_df",
     "mapped",
     "stage",
-    "backed",
     "load",
     "delete",
     "save",

lamindb/_query_set.py

@@ -243,7 +243,7 @@ class QuerySet(models.QuerySet, CanValidate, IsTree):
         self, values: ListLike, field: Optional[Union[str, StrField]] = None, **kwargs
     ):
         """{}."""
-        from ._validate import _validate
+        from ._can_validate import _validate
 
         return _validate(cls=self, values=values, field=field, **kwargs)
 
@@ -252,7 +252,7 @@ class QuerySet(models.QuerySet, CanValidate, IsTree):
         self, values: ListLike, field: Optional[Union[str, StrField]] = None, **kwargs
     ):
         """{}."""
-        from ._validate import _inspect
+        from ._can_validate import _inspect
 
         return _inspect(cls=self, values=values, field=field, **kwargs)
 
@@ -261,7 +261,7 @@ class QuerySet(models.QuerySet, CanValidate, IsTree):
         self, values: Iterable, field: Optional[Union[str, StrField]] = None, **kwargs
     ):
         """{}."""
-        from ._validate import _standardize
+        from ._can_validate import _standardize
 
         return _standardize(cls=self, values=values, field=field, **kwargs)
 

lamindb/core/__init__.py

@@ -14,6 +14,9 @@ Registries:
    LabelManager
    IsTree
    IsVersioned
+   DataFrameAnnotator
+   AnnDataAnnotator
+   AnnotateLookup
    CanValidate
    HasParents
    InspectResult
@@ -50,6 +53,7 @@ from lnschema_core.models import (
     Registry,
 )
 
+from lamindb._annotate import AnnDataAnnotator, AnnotateLookup, DataFrameAnnotator
 from lamindb._query_manager import QueryManager
 from lamindb._query_set import QuerySet, RecordsList
 from lamindb.core._feature_manager import FeatureManager

lamindb/core/_data.py

@@ -36,9 +36,7 @@ from ._label_manager import LabelManager, print_labels
 from ._run_context import run_context
 from .exceptions import ValidationError
 
-WARNING_RUN_TRANSFORM = (
-    "no run & transform get linked, consider passing a `run` or calling ln.track()"
-)
+WARNING_RUN_TRANSFORM = "no run & transform get linked, consider calling ln.track()"
 
 
 def get_run(run: Optional[Run]) -> Optional[Run]:

lamindb/core/_feature_manager.py

@@ -253,8 +253,7 @@ class FeatureManager:
         if isinstance(self._host, Artifact):
             assert self._host.accessor == "AnnData"
         else:
-            # Collection
-            assert self._host.artifact.accessor == "AnnData"
+            raise NotImplementedError()
 
         # parse and register features
         adata = self._host.load()

lamindb/integrations/__init__.py

@@ -0,0 +1,8 @@
+"""Integrations.
+
+.. autosummary::
+   :toctree: .
+
+   save_vitessce_config
+"""
+from ._vitessce import save_vitessce_config

lamindb/integrations/_vitessce.py

@@ -0,0 +1,36 @@
+import json
+from datetime import datetime, timezone
+
+import lamindb_setup as ln_setup
+from lamin_utils import logger
+
+from lamindb._artifact import Artifact
+
+
+# tested in lamin-spatial
+# can't type vitessce_config because can't assume it's installed
+def save_vitessce_config(vitessce_config, description: str) -> Artifact:
+    """Takes a ``VitessceConfig`` object and saves it as an artifact.
+
+    Args:
+        vitessce_config (``VitessceConfig``): A VitessceConfig object.
+        description: A description for the artifact.
+    """
+    from vitessce import VitessceConfig
+
+    assert isinstance(vitessce_config, VitessceConfig)
+    timestamp = datetime.now(timezone.utc).isoformat().split(".")[0]
+    vitesse_export = f"./vitessce_export_{timestamp}.vitessce"
+    vitessce_config.export(to="files", base_url="", out_dir=vitesse_export)
+    logger.important(f"local export: {vitesse_export}")
+    artifact = Artifact(vitesse_export, description=description)
+    artifact.save()
+    config_dict = vitessce_config.to_dict(base_url=artifact.path.to_url())
+    config_filename = "vitessce_config.json"
+    config_file_local_path = f"{vitesse_export}/{config_filename}"
+    with open(config_file_local_path, "w") as file:
+        json.dump(config_dict, file)
+    (artifact.path / config_filename).upload_from(config_file_local_path)
+    slug = ln_setup.settings.instance.slug
+    logger.important(f"go to: https://lamin.ai/{slug}/artifact/{artifact.uid}")
+    return artifact

{lamindb-0.69.2.dist-info → lamindb-0.69.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.69.2
+Version: 0.69.4
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.8
@@ -10,7 +10,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: lnschema_core==0.64.1
-Requires-Dist: lamindb_setup==0.68.0
+Requires-Dist: lamindb_setup==0.68.2
 Requires-Dist: lamin_utils==0.13.1
 Requires-Dist: lamin_cli==0.10.2
 Requires-Dist: rapidfuzz
@@ -26,7 +26,7 @@ Requires-Dist: urllib3<2 ; extra == "aws"
 Requires-Dist: aiobotocore[boto3]>=2.5.4,<3.0.0 ; extra == "aws"
 Requires-Dist: s3fs==2023.12.2 ; extra == "aws"
 Requires-Dist: fsspec[s3]==2023.12.2 ; extra == "aws"
-Requires-Dist: bionty==0.42.2 ; extra == "bionty"
+Requires-Dist: bionty==0.42.4 ; extra == "bionty"
 Requires-Dist: pandas<2 ; extra == "dev"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"

{lamindb-0.69.2.dist-info → lamindb-0.69.4.dist-info}/RECORD

@@ -1,6 +1,8 @@
-lamindb/__init__.py,sha256=hJStNsXJq-qclYj7tDUz2t-4j5sDhkZdBen5URQ1_dA,2051
-lamindb/_artifact.py,sha256=3H8hemGysZLlyHkb02MEXCie1FluQ60LdGIBXOv13uc,35999
-lamindb/_collection.py,sha256=03CQ0u8eCY_dx31pIT5ZMZsmxbbj6J5dJ9zUqJLrDGY,18427
+lamindb/__init__.py,sha256=3kVakyBIty4I2C-69S114uW3z9lnEOgpnOz3LsZb2ro,2163
+lamindb/_annotate.py,sha256=BopvJvzUlNKiTzOELg6MXeXQNUVMUTk-FcRoV9mfZdo,27682
+lamindb/_artifact.py,sha256=RV36tcHMZ6wH6u65jOAQ_H4rfmFiIzZmAr8IY7kFhm0,35817
+lamindb/_can_validate.py,sha256=w7lrUGTWldpvwaRiXBRrjfU_ZRidA7CooOu_r5MbocY,14569
+lamindb/_collection.py,sha256=SdNNhhMh2O4q0hG4Hf_y1bcwcbkMF_sqk6MIYc-hLZo,14525
 lamindb/_feature.py,sha256=ahRv87q1tcRLQ0UM5FA3KtcMQvIjW__fZq1yAdRAV7s,6728
 lamindb/_feature_set.py,sha256=G_Ss6mKh4D0Eji-xSfLRbKVFXwgUE82YOqIUmkV0CAA,8767
 lamindb/_filter.py,sha256=_PjyQWQBR3ohDAvJbR3hMvZ-2p2GvzFxLfKGC-gPnHI,1320
@@ -9,7 +11,7 @@ lamindb/_from_values.py,sha256=Ei11ml77Q1xubVekt2C4-mbox2-qnC7kP18B-LhCdSc,11886
 lamindb/_is_versioned.py,sha256=DXp5t-1DwErpqqMc9eb08kpQPCHOC2fNzaozMoBunR4,1337
 lamindb/_parents.py,sha256=pTDsW8HjQ_txFbPKrBU0WjjtCNH6sx2LASUuGWpJuYE,14742
 lamindb/_query_manager.py,sha256=lyYMEsstUQlns2H01oZXN5Ly0X6ug2VOPebyu9fHn4s,4008
-lamindb/_query_set.py,sha256=OXL5meaGoWHV5aPhT-LYUboPHFB0i1BPWfmvKTSeYF4,11306
+lamindb/_query_set.py,sha256=DafHKwufvWQaWWSZsuxq24wpxae5Vfw7wD_3KCr7kLc,11318
 lamindb/_registry.py,sha256=vEsjn33BV2vxlanE3fyvDiy7AJoq7RKqEn_Sspo4_Dc,19232
 lamindb/_run.py,sha256=CvH6cAFUb83o38iOdpBsktF3JGAwmuZrDZ4p4wvUr0g,1853
 lamindb/_save.py,sha256=uIzHfNulzn7rpSKyAvUHT1OuN294OWFGC04gLmwrScY,11452
@@ -17,11 +19,10 @@ lamindb/_storage.py,sha256=VW8xq3VRv58-ciholvOdlcgvp_OIlLxx5GxLt-e2Irs,614
 lamindb/_transform.py,sha256=oZq-7MgyCs4m6Bj901HwDlbvF0JuvTpe3RxN0Zb8PgE,3515
 lamindb/_ulabel.py,sha256=euXsDPD7wC99oopLXVkT-vq7f3E6-zP4Z4akI-yh0aM,1913
 lamindb/_utils.py,sha256=LGdiW4k3GClLz65vKAVRkL6Tw-Gkx9DWAdez1jyA5bE,428
-lamindb/_validate.py,sha256=w7lrUGTWldpvwaRiXBRrjfU_ZRidA7CooOu_r5MbocY,14569
 lamindb/_view.py,sha256=yFMu4vnt0YqvN1q11boAkwigxCH1gdliDUSbzh3IuDw,2175
-lamindb/core/__init__.py,sha256=RYNsg2foVZRawpCW2J5J82vHZt6ub_Tze8wiDMxXCH8,988
-lamindb/core/_data.py,sha256=Q8w1I8pXXOaLVIxfjWBkLV6GGnzaQxCXamu9tplFgsA,17287
-lamindb/core/_feature_manager.py,sha256=II0nuxtjOdEtU_9a7eB18_Clw9d1n5k1JOqk_vHisRw,13940
+lamindb/core/__init__.py,sha256=Mw4sI-xgnMXNsu84oYFQBZOF8mxxxhp6-e3BjTQqjlA,1131
+lamindb/core/_data.py,sha256=SCyUjS9bL7MMqyZTJl8PxnNtLKL7eNiUcLvmwFrqP-k,17260
+lamindb/core/_feature_manager.py,sha256=_Bicjal2DQbpl6tR7p5o7Alb9rq0XYzAxrF_bV9sTjE,13894
 lamindb/core/_label_manager.py,sha256=zrWDSd2AkR6fKsGDxLSWqHC9fz9BcGlavPZEh92Wzjg,9063
 lamindb/core/_mapped_collection.py,sha256=e4P3AoykIMjD4_88BWbISWvKyWWTklwHl-_WLa72ZG4,16841
 lamindb/core/_run_context.py,sha256=EK0lFJWx32NY2FdqFR1YozR9zioC-BjA394nPu-KwLQ,17510
@@ -43,15 +44,11 @@ lamindb/core/storage/_backed_access.py,sha256=DUJIDjkGkemjmKLD05blndP_rO5DpUD0EZ
 lamindb/core/storage/_zarr.py,sha256=bMQSCsTOCtQy4Yo3KwCVpbUkKdWRApN9FM1rM-d2_G0,2839
 lamindb/core/storage/file.py,sha256=WTeC4ENn_O6HEoinmTviB89W81UrJT3bSGtnpqPpIyE,7242
 lamindb/core/storage/object.py,sha256=MPUb2M8Fleq2j9x1Ryqr3BETmvsDKyf11Ifvbxd3NpA,1097
+lamindb/integrations/__init__.py,sha256=aH2PmO2m4-vwIifMYTB0Fyyr_gZWtVnV71jT0tVWSw0,123
+lamindb/integrations/_vitessce.py,sha256=NHOiDJzn2QtzfkThhHEuDJuTTcSkem9x5d_wrQ-8nPI,1474
 lamindb/setup/__init__.py,sha256=OwZpZzPDv5lPPGXZP7-zK6UdO4FHvvuBh439yZvIp3A,410
 lamindb/setup/core/__init__.py,sha256=LqIIvJNcONxkqjbnP6CUaP4d45Lbd6TSMAcXFp4C7_8,231
-lamindb/validation/__init__.py,sha256=AuonqVEhyYDXAoRqXnM9JweTUnYfAoExza8A5mQuM7Q,347
-lamindb/validation/_anndata_validator.py,sha256=lFCVLE4F4VN-9DTEwY9RUqSw8I2C6eTPYvXotGdKgvU,3782
-lamindb/validation/_lookup.py,sha256=HIGwk85e-c8yaVg4NkcvBdW4LIhnxwRI02km8uYOiFY,1545
-lamindb/validation/_register.py,sha256=UKsNVwXZhBl-spheZX1nkugjLF8g1yANT2vumcyzx6Y,9765
-lamindb/validation/_validate.py,sha256=FPQ4e_qDcP3tlKsYOVyo7-yb8nIbKyzoZHwgMbJJog0,4588
-lamindb/validation/_validator.py,sha256=6vzOfKIPQdA0pWwtXlRJWvjgLIjpivkBeLtgD6QODvY,7861
-lamindb-0.69.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-0.69.2.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-lamindb-0.69.2.dist-info/METADATA,sha256=ly2Nwd236G0yxp4sX3DStxyzFFzqSv7sJuccmnc142Y,2856
-lamindb-0.69.2.dist-info/RECORD,,
+lamindb-0.69.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-0.69.4.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lamindb-0.69.4.dist-info/METADATA,sha256=lGw_OTGbviwuQbwwav9IVSHfblR8bwUNC1weeEx6Eok,2856
+lamindb-0.69.4.dist-info/RECORD,,

lamindb/validation/__init__.py

@@ -1,19 +0,0 @@
-"""Validators built on LaminDB.
-
-Import the package::
-
-   from lamindb.validation import Validator, AnnDataValidator
-
-This is the complete API reference:
-
-.. autosummary::
-   :toctree: .
-
-   Validator
-   AnnDataValidator
-   Lookup
-"""
-
-from ._anndata_validator import AnnDataValidator
-from ._lookup import Lookup
-from ._validator import Validator

lamindb/validation/_anndata_validator.py

@@ -1,117 +0,0 @@
-from typing import Dict, Optional
-
-import anndata as ad
-from lnschema_core.types import FieldAttr
-from pandas.core.api import DataFrame as DataFrame
-
-import lamindb as ln
-
-from ._lookup import Lookup
-from ._register import register_artifact, register_labels
-from ._validate import validate_anndata
-from ._validator import ValidationError, Validator
-
-
-class AnnDataValidator(Validator):
-    """Lamin AnnData validator.
-
-    Args:
-        adata: The AnnData object to validate.
-        var_field: The registry field to validate variables index against.
-        obs_fields: A dictionary mapping obs_column to registry_field.
-            For example:
-            {"cell_type_ontology_id": bt.CellType.ontology_id, "donor_id": ln.ULabel.name}
-        using: The reference instance containing registries to validate against.
-    """
-
-    def __init__(
-        self,
-        adata: ad.AnnData,
-        var_field: FieldAttr,
-        obs_fields: Dict[str, FieldAttr],
-        using: str = "default",
-        verbosity: str = "hint",
-        **kwargs,
-    ) -> None:
-        self._adata = adata
-        self._var_field = var_field
-        super().__init__(
-            df=self._adata.obs,
-            fields=obs_fields,
-            using=using,
-            verbosity=verbosity,
-            **kwargs,
-        )
-        self._obs_fields = obs_fields
-        self._register_variables()
-
-    @property
-    def var_field(self) -> FieldAttr:
-        """Return the registry field to validate variables index against."""
-        return self._var_field
-
-    @property
-    def obs_fields(self) -> Dict:
-        """Return the obs fields to validate against."""
-        return self._obs_fields
-
-    def lookup(self, using: Optional[str] = None) -> Lookup:
-        """Lookup features and labels."""
-        fields = {
-            **{"feature": ln.Feature.name, "variables": self.var_field},
-            **self.obs_fields,
-        }
-        return Lookup(fields=fields, using=using or self._using)
-
-    def _register_variables(self, validated_only: bool = True, **kwargs):
-        """Register variable records."""
-        self._kwargs.update(kwargs)
-        register_labels(
-            values=self._adata.var_names,
-            field=self.var_field,
-            feature_name="variables",
-            using=self._using,
-            validated_only=validated_only,
-            kwargs=self._kwargs,
-        )
-
-    def validate(self, **kwargs) -> bool:
-        """Validate variables and categorical observations."""
-        self._kwargs.update(kwargs)
-        self._validated = validate_anndata(
-            self._adata,
-            var_field=self.var_field,
-            obs_fields=self.obs_fields,
-            **self._kwargs,
-        )
-        return self._validated
-
-    def register_labels(self, feature: str, validated_only: bool = True, **kwargs):
-        """Register labels for a feature."""
-        if feature == "variables":
-            self._register_variables(validated_only=validated_only, **kwargs)
-        else:
-            super().register_labels(feature, validated_only, **kwargs)
-
-    def register_artifact(self, description: str, **kwargs) -> ln.Artifact:
-        """Register the validated AnnData and metadata.
-
-        Args:
-            description: Description of the AnnData object.
-            **kwargs: Object level metadata.
-
-        Returns:
-            A registered artifact record.
-        """
-        self._kwargs.update(kwargs)
-        if not self._validated:
-            raise ValidationError("Please run `validate()` first!")
-
-        self._artifact = register_artifact(
-            self._adata,
-            description=description,
-            feature_field=self.var_field,
-            fields=self.obs_fields,
-            **self._kwargs,
-        )
-        return self._artifact

lamindb/validation/_lookup.py

@@ -1,42 +0,0 @@
-from typing import Dict, Optional
-
-from lamin_utils import colors, logger
-from lnschema_core.types import FieldAttr
-
-import lamindb as ln
-
-from ._validate import get_registry_instance
-
-
-class Lookup:
-    """Lookup features and labels from the reference instance."""
-
-    def __init__(
-        self, fields: Dict[str, FieldAttr], using: Optional[str] = None
-    ) -> None:
-        self._fields = fields
-        self._using = None if using == "default" else using
-        self._using_name = using or ln.setup.settings.instance.slug
-        logger.debug(f"Lookup objects from the {colors.italic(self._using_name)}")
-
-    def __getitem__(self, name):
-        if name in self._fields:
-            registry = self._fields[name].field.model
-            if self._using == "public":
-                return registry.public().lookup()
-            else:
-                return get_registry_instance(registry, self._using).lookup()
-        raise AttributeError(
-            f"'{self.__class__.__name__}' object has no attribute '{name}'"
-        )
-
-    def __repr__(self) -> str:
-        if len(self._fields) > 0:
-            fields = "\n ".join([str([key]) for key in self._fields.keys()])
-            return (
-                f"Lookup objects from the {colors.italic(self._using_name)}:\n {colors.green(fields)}\n\n"
-                "Example:\n    → categories = validator.lookup().['cell_type']\n"
-                "    → categories.alveolar_type_1_fibroblast_cell"
-            )
-        else:
-            return colors.warning("No fields are found!")