lamindb 1.5.0__py3-none-any.whl → 1.5.2__py3-none-any.whl

lamindb/__init__.py

@@ -94,7 +94,7 @@ Low-level functionality.
 
 # ruff: noqa: I001
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.5.0"
+__version__ = "1.5.2"
 
 import warnings
 

lamindb/core/_context.py

@@ -259,8 +259,8 @@ class Context:
         self,
         transform: str | Transform | None = None,
         *,
-        project: str | None = None,
-        space: str | None = None,
+        project: str | Project | None = None,
+        space: str | Space | None = None,
         params: dict | None = None,
         new_run: bool | None = None,
         path: str | None = None,
@@ -273,9 +273,10 @@ class Context:
 
         Args:
             transform: A transform (stem) `uid` (or record). If `None`, auto-creates a `transform` with its `uid`.
-            project: A project `name` or `uid` for labeling entities created during the run.
-            space: A space `name` or `uid` to identify where potentially sensitive entities are created during the run.
-                This doesn't affect `Storage`, `ULabel`, `Feature`, `Schema`, `Param` and bionty entities as these provide mere structure that should typically be commonly accessible.
+            project: A project, its `name` or `uid` for labeling entities created during the run.
+            space: A restricted space, its `name` or `uid` for creating sensitive entities are created during the run.
+                The default is the common `"All"` space that every LaminDB instance has.
+                The `space` argument doesn't affect `Storage`, `ULabel`, `Feature`, `Schema`, `Param` and bionty entities as these provide structure that should typically be commonly accessible.
                 If you want to manually move entities to a different space, set the `.space` field (:doc:`docs:access`).
             params: A dictionary of parameters to track for the run.
             new_run: If `False`, loads the latest run of transform
@@ -309,20 +310,32 @@ class Context:
         if project is None:
             project = os.environ.get("LAMIN_CURRENT_PROJECT")
         if project is not None:
-            project_record = Project.filter(
-                Q(name=project) | Q(uid=project)
-            ).one_or_none()
-            if project_record is None:
-                raise InvalidArgument(
-                    f"Project '{project}' not found, either create it with `ln.Project(name='...').save()` or fix typos."
+            if isinstance(project, Project):
+                assert project._state.adding is False, (  # noqa: S101
+                    "Project must be saved before passing it to track()"
                 )
+                project_record = project
+            else:
+                project_record = Project.filter(
+                    Q(name=project) | Q(uid=project)
+                ).one_or_none()
+                if project_record is None:
+                    raise InvalidArgument(
+                        f"Project '{project}' not found, either create it with `ln.Project(name='...').save()` or fix typos."
+                    )
             self._project = project_record
         if space is not None:
-            space_record = Space.filter(Q(name=space) | Q(uid=space)).one_or_none()
-            if space_record is None:
-                raise InvalidArgument(
-                    f"Space '{space}', please check on the hub UI whether you have the correct `uid` or `name`."
+            if isinstance(space, Space):
+                assert space._state.adding is False, (  # noqa: S101
+                    "Space must be saved before passing it to track()"
                 )
+                space_record = space
+            else:
+                space_record = Space.filter(Q(name=space) | Q(uid=space)).one_or_none()
+                if space_record is None:
+                    raise InvalidArgument(
+                        f"Space '{space}', please check on the hub UI whether you have the correct `uid` or `name`."
+                    )
             self._space = space_record
         self._logging_message_track = ""
         self._logging_message_imports = ""

lamindb/core/storage/_tiledbsoma.py

@@ -110,7 +110,7 @@ def save_tiledbsoma_experiment(
 ) -> Artifact:
     """Write `AnnData` to `tiledbsoma.Experiment`.
 
-    Reads `AnnData` objects, writes them to `tiledbsoma.Experiment`, creates & saves an {class}`~lamindb.Artifact`.
+    Reads `AnnData` objects, writes them to `tiledbsoma.Experiment`, creates & saves an :class:`~lamindb.Artifact`.
 
     Populates a column `lamin_run_uid` column in `obs` with the current `run.uid`.
 
@@ -202,28 +202,44 @@ def save_tiledbsoma_experiment(
             context=ctx,
         )
 
+    prepare_experiment = False
     resize_experiment = False
     if registration_mapping is not None:
-        if version.parse(soma.__version__) < version.parse("1.15.0rc4"):
+        soma_version_parsed = version.parse(soma.__version__)
+        if soma_version_parsed < version.parse("1.15.0rc4"):
             n_observations = len(registration_mapping.obs_axis.data)
         else:
             n_observations = registration_mapping.get_obs_shape()
-            resize_experiment = True
+            prepare_experiment = soma_version_parsed >= version.parse("1.16.2")
+            resize_experiment = not prepare_experiment
     else:  # happens only if not appending and only one adata passed
         assert len(adata_objects) == 1  # noqa: S101
         n_observations = adata_objects[0].n_obs
 
     logger.important(f"Writing the tiledbsoma store to {storepath_str}")
+    experiment_exists: bool | None = None
     for adata_obj in adata_objects:
-        if resize_experiment and soma.Experiment.exists(storepath_str, context=ctx):
-            # can only happen if registration_mapping is not None
-            soma_io.resize_experiment(
-                storepath_str,
-                nobs=n_observations,
-                nvars=registration_mapping.get_var_shapes(),
-                context=ctx,
-            )
-            resize_experiment = False
+        # do not recheck if True
+        if not experiment_exists and (resize_experiment or prepare_experiment):
+            experiment_exists = soma.Experiment.exists(storepath_str, context=ctx)
+        if experiment_exists:
+            # both can only happen if registration_mapping is not None
+            if resize_experiment:
+                soma_io.resize_experiment(
+                    storepath_str,
+                    nobs=n_observations,
+                    nvars=registration_mapping.get_var_shapes(),
+                    context=ctx,
+                )
+                resize_experiment = False
+            elif prepare_experiment:
+                registration_mapping.prepare_experiment(storepath_str, context=ctx)
+                prepare_experiment = False
+        registration_mapping_write = (
+            registration_mapping.subset_for_anndata(adata_obj)
+            if hasattr(registration_mapping, "subset_for_anndata")
+            else registration_mapping
+        )
         soma_io.from_anndata(
             storepath_str,
             adata_obj,
@@ -231,7 +247,7 @@ def save_tiledbsoma_experiment(
             context=ctx,
             obs_id_name=obs_id_name,
             var_id_name=var_id_name,
-            registration_mapping=registration_mapping,
+            registration_mapping=registration_mapping_write,
             **kwargs,
         )
 

lamindb/curators/core.py

@@ -305,6 +305,8 @@ class SlotsCurator(Curator):
         for slot, curator in self._slots.items():
             logger.info(f"validating slot {slot} ...")
             curator.validate()
+        # set _is_validated to True as no slot raised an error
+        self._is_validated = True
 
     @doc_args(SAVE_ARTIFACT_DOCSTRING)
     def save_artifact(
@@ -510,7 +512,7 @@ class DataFrameCurator(Curator):
             categoricals=categoricals,
             index=schema.index,
             slot=slot,
-            schema_maximal_set=schema.maximal_set,
+            maximal_set=schema.maximal_set,
         )
 
     @property
@@ -836,7 +838,7 @@ class SpatialDataCurator(SlotsCurator):
                     sub_slot = split_result[1]
                     data_object = self._dataset.attrs[split_result[1]]
                 data_object = pd.DataFrame([data_object])
-            self._slots[slot] = DataFrameCurator(data_object, slot_schema)
+            self._slots[slot] = DataFrameCurator(data_object, slot_schema, slot)
             _assign_var_fields_categoricals_multimodal(
                 modality=table_key,
                 slot_type=sub_slot,
@@ -850,27 +852,20 @@ class SpatialDataCurator(SlotsCurator):
 
 
 class CatVector:
-    """Categorical vector for `DataFrame`.
-
-    Args:
-        values_getter: A callable or iterable that returns the values to validate.
-        field: The field to validate against.
-        key: The name of the column to validate. Only used for logging.
-        values_setter: A callable that sets the values.
-        source: The source to validate against.
-    """
+    """Vector with categorical values."""
 
     def __init__(
         self,
-        values_getter: Callable | Iterable[str],
-        field: FieldAttr,
-        key: str,
-        values_setter: Callable | None = None,
-        source: Record | None = None,
+        values_getter: Callable
+        | Iterable[str],  # A callable or iterable that returns the values to validate.
+        field: FieldAttr,  # The field to validate against.
+        key: str,  # The name of the vector to validate. Only used for logging.
+        values_setter: Callable | None = None,  # A callable that sets the values.
+        source: Record | None = None,  # The ontology source to validate against.
         feature: Feature | None = None,
         cat_manager: DataFrameCatManager | None = None,
         subtype_str: str = "",
-        maximal_set: bool = False,  # Passed during validation. Whether unvalidated categoricals cause validation failure.
+        maximal_set: bool = True,  # whether unvalidated categoricals cause validation failure.
     ) -> None:
         self._values_getter = values_getter
         self._values_setter = values_setter
@@ -912,18 +907,20 @@ class CatVector:
     @property
     def is_validated(self) -> bool:
         """Whether the vector is validated."""
-        # ensembl gene IDs pass even if they were not validated
-        # this is a simple solution to the ensembl gene version problem
-        if self._field.field.attname == "ensembl_gene_id":
-            # if none of the ensembl gene ids were validated, we are probably not looking at ensembl gene IDs
-            if len(self.values) == len(self._non_validated):
-                return False
-            # if maximal set, we do not allow additional unvalidated genes
-            elif len(self._non_validated) != 0 and self._maximal_set:
-                return False
-            return True
-        else:
-            return len(self._non_validated) == 0
+        # if nothing was validated, something likely is fundamentally wrong
+        # should probably add a setting `at_least_one_validated`
+        result = True
+        if len(self.values) > 0 and len(self.values) == len(self._non_validated):
+            result = False
+        # len(self._non_validated) != 0
+        #     if maximal_set is True, return False
+        #     if maximal_set is False, return True
+        # len(self._non_validated) == 0
+        #     return True
+        if len(self._non_validated) != 0:
+            if self._maximal_set:
+                result = False
+        return result
 
     def _replace_synonyms(self) -> list[str]:
         """Replace synonyms in the vector with standardized values."""
@@ -1078,11 +1075,6 @@ class CatVector:
         field_name = self._field.field.name
         model_field = f"{registry.__name__}.{field_name}"
 
-        def _log_mapping_info():
-            logger.indent = ""
-            logger.info(f'mapping "{self._key}" on {colors.italic(model_field)}')
-            logger.indent = "  "
-
         kwargs_current = get_current_filter_kwargs(
             registry, {"organism": self._organism, "source": self._source}
         )
@@ -1121,7 +1113,6 @@ class CatVector:
         non_validated = [i for i in non_validated if i not in values_validated]
         n_non_validated = len(non_validated)
         if n_non_validated == 0:
-            logger.indent = ""
             logger.success(
                 f'"{self._key}" is validated against {colors.italic(model_field)}'
             )
@@ -1143,14 +1134,12 @@ class CatVector:
                 warning_message += f"    → fix typos, remove non-existent values, or save terms via: {colors.cyan(non_validated_hint_print)}"
                 if self._subtype_query_set is not None:
                     warning_message += f"\n    → a valid label for subtype '{self._subtype_str}' has to be one of {self._subtype_query_set.list('name')}"
-            if logger.indent == "":
-                _log_mapping_info()
+            logger.info(f'mapping "{self._key}" on {colors.italic(model_field)}')
             logger.warning(warning_message)
             if self._cat_manager is not None:
                 self._cat_manager._validate_category_error_messages = strip_ansi_codes(
                     warning_message
                 )
-            logger.indent = ""
             return non_validated, syn_mapper
 
     def validate(self) -> None:
@@ -1218,7 +1207,7 @@ class DataFrameCatManager:
         sources: dict[str, Record] | None = None,
         index: Feature | None = None,
         slot: str | None = None,
-        schema_maximal_set: bool = False,
+        maximal_set: bool = False,
     ) -> None:
         self._non_validated = None
         self._index = index
@@ -1235,7 +1224,7 @@ class DataFrameCatManager:
         self._validate_category_error_messages: str = ""
         self._cat_vectors: dict[str, CatVector] = {}
         self._slot = slot
-        self._maximal_set = schema_maximal_set
+        self._maximal_set = maximal_set
 
         if columns_names is None:
             columns_names = []
@@ -1280,7 +1269,6 @@ class DataFrameCatManager:
                 feature=feature,
                 cat_manager=self,
                 subtype_str=subtype_str,
-                maximal_set=self._maximal_set,
             )
         if index is not None and index.dtype.startswith("cat"):
             result = parse_dtype(index.dtype)[0]
@@ -1292,7 +1280,6 @@ class DataFrameCatManager:
                 key=key,
                 feature=index,
                 cat_manager=self,
-                maximal_set=self._maximal_set,
             )
 
     @property
@@ -1330,7 +1317,7 @@ class DataFrameCatManager:
 
         validated = True
         for key, cat_vector in self._cat_vectors.items():
-            logger.info(f"validating column {key}")
+            logger.info(f"validating vector {key}")
             cat_vector.validate()
             validated &= cat_vector.is_validated
         self._is_validated = validated
@@ -1493,6 +1480,9 @@ def annotate_artifact(
                 else "columns"
             )
             features = slot_curator.cat._cat_vectors[name].records
+            if features is None:
+                logger.warning(f"no features found for slot {slot}")
+                continue
             itype = parse_cat_dtype(artifact.schema.slots[slot].itype, is_itype=True)[
                 "field"
             ]

lamindb/migrations/0093_alter_schemacomponent_unique_together.py

@@ -0,0 +1,16 @@
+# Generated by Django 5.2 on 2025-05-07 12:16
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("lamindb", "0092_alter_artifactfeaturevalue_artifact_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterUniqueTogether(
+            name="schemacomponent",
+            unique_together={("composite", "slot"), ("composite", "slot", "component")},
+        ),
+    ]

lamindb/models/_feature_manager.py

@@ -49,7 +49,7 @@ from ._label_manager import _get_labels, describe_labels
 from ._relations import (
     dict_related_model_to_related_name,
 )
-from .feature import Feature, FeatureValue
+from .feature import Feature, FeatureValue, parse_dtype
 from .record import Record
 from .run import Param, ParamManager, ParamManagerRun, ParamValue, Run
 from .ulabel import ULabel
@@ -649,13 +649,22 @@ def filter_base(cls, _skip_validation: bool = True, **expression) -> QuerySet:
                 if cls == FeatureManager:
                     from .artifact import ArtifactFeatureValue
 
-                    return Artifact.objects.exclude(
-                        id__in=Subquery(
-                            ArtifactFeatureValue.objects.filter(
-                                featurevalue__feature=feature
-                            ).values("artifact_id")
+                    if value:  # True
+                        return Artifact.objects.exclude(
+                            id__in=Subquery(
+                                ArtifactFeatureValue.objects.filter(
+                                    featurevalue__feature=feature
+                                ).values("artifact_id")
+                            )
+                        )
+                    else:
+                        return Artifact.objects.exclude(
+                            id__in=Subquery(
+                                ArtifactFeatureValue.objects.filter(
+                                    featurevalue__feature=feature
+                                ).values("artifact_id")
+                            )
                         )
-                    )
             if comparator in {"__startswith", "__contains"}:
                 logger.important(
                     f"currently not supporting `{comparator}`, using `__icontains` instead"
@@ -667,7 +676,14 @@ def filter_base(cls, _skip_validation: bool = True, **expression) -> QuerySet:
         elif isinstance(value, (str, Record, bool)):
             if comparator == "__isnull":
                 if cls == FeatureManager:
-                    return Artifact.objects.exclude(links_ulabel__feature=feature)
+                    result = parse_dtype(feature.dtype)[0]
+                    kwargs = {
+                        f"links_{result['registry'].__name__.lower()}__feature": feature
+                    }
+                    if value:  # True
+                        return Artifact.objects.exclude(**kwargs)
+                    else:
+                        return Artifact.objects.filter(**kwargs)
             else:
                 # because SQL is sensitive to whether querying with __in or not
                 # and might return multiple equivalent records for the latter

lamindb/models/artifact.py

@@ -17,7 +17,6 @@ from django.db.models import CASCADE, PROTECT, Q
 from lamin_utils import colors, logger
 from lamindb_setup import settings as setup_settings
 from lamindb_setup._init_instance import register_storage_in_instance
-from lamindb_setup.core import doc_args
 from lamindb_setup.core._settings_storage import init_storage
 from lamindb_setup.core.hashing import HASH_LENGTH, hash_dir, hash_file
 from lamindb_setup.core.types import UPathStr
@@ -99,8 +98,6 @@ WARNING_RUN_TRANSFORM = "no run & transform got linked, call `ln.track()` & re-r
 
 WARNING_NO_INPUT = "run input wasn't tracked, call `ln.track()` and re-run"
 
-DEBUG_KWARGS_DOC = "**kwargs: Internal arguments for debugging."
-
 try:
     from ..core.storage._zarr import identify_zarr_type
 except ImportError:
@@ -914,7 +911,7 @@ def add_labels(
         for registry_name, records in records_by_registry.items():
             if not from_curator and feature.name in internal_features:
                 raise ValidationError(
-                    "Cannot manually annotate internal feature with label. Please use ln.Curator"
+                    "Cannot manually annotate a feature measured *within* the dataset. Please use a Curator."
                 )
             if registry_name not in feature.dtype:
                 if not feature.dtype.startswith("cat"):
@@ -1236,7 +1233,7 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
         default=None,
         related_name="validated_artifacts",
     )
-    """The schema that validated this artifact in a :class:`~lamindb.curators.Curator`."""
+    """The schema that validated this artifact in a :class:`~lamindb.curators.core.Curator`."""
     feature_sets: Schema = models.ManyToManyField(
         Schema, related_name="artifacts", through="ArtifactSchema"
     )
@@ -2363,6 +2360,11 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
 
         if hasattr(self, "_memory_rep") and self._memory_rep is not None:
             access_memory = self._memory_rep
+            # SpatialData objects zarr stores are moved when saved
+            # SpatialData's __repr__ method attempts to access information from the old path
+            # Therefore, we need to update the in-memory path to the now moved Artifact storage path
+            if access_memory.__class__.__name__ == "SpatialData":
+                access_memory.path = self._cache_path
         else:
             filepath, cache_key = filepath_cache_key_from_artifact(
                 self, using_key=settings._using_key
@@ -2395,9 +2397,9 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
                 access_memory = load_to_memory(cache_path, **kwargs)
         # only call if load is successfull
         _track_run_input(self, is_run_input)
+
         return access_memory
 
-    @doc_args(DEBUG_KWARGS_DOC)
     def cache(
         self, *, is_run_input: bool | None = None, mute: bool = False, **kwargs
     ) -> Path:
@@ -2410,7 +2412,6 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
         Args:
             mute: Silence logging of caching progress.
             is_run_input: Whether to track this artifact as run input.
-            {}
 
         Example::
 
@@ -2560,13 +2561,11 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
                 if delete_msg != "did-not-delete":
                     logger.success(f"deleted {colors.yellow(f'{path}')}")
 
-    @doc_args(DEBUG_KWARGS_DOC)
     def save(self, upload: bool | None = None, **kwargs) -> Artifact:
         """Save to database & storage.
 
         Args:
             upload: Trigger upload to cloud storage in instances with hybrid storage mode.
-            {}
 
         Example::
 
@@ -2763,8 +2762,8 @@ def _track_run_input(
                 # record is on another db
                 # we have to save the record into the current db with
                 # the run being attached to a transfer transform
-                logger.important(
-                    f"completing transfer to track {data.__class__.__name__}('{data.uid[:8]}') as input"
+                logger.info(
+                    f"completing transfer to track {data.__class__.__name__}('{data.uid[:8]}...') as input"
                 )
                 data.save()
                 is_valid = True

lamindb/models/has_parents.py

@@ -84,10 +84,44 @@ class HasParents:
         return view_parents(
             record=self,  # type: ignore
             field=field,
+            with_parents=True,
             with_children=with_children,
             distance=distance,
         )
 
+    def view_children(
+        self,
+        field: StrField | None = None,
+        distance: int = 5,
+    ):
+        """View children in an ontology.
+
+        Args:
+            field: Field to display on graph
+            distance: Maximum distance still shown.
+
+        Ontological hierarchies: :class:`~lamindb.ULabel` (project & sub-project), :class:`~bionty.CellType` (cell type & subtype).
+
+        Examples:
+            >>> import bionty as bt
+            >>> bt.Tissue.from_source(name="subsegmental bronchus").save()
+            >>> record = bt.Tissue.get(name="respiratory tube")
+            >>> record.view_parents()
+            >>> tissue.view_parents(with_children=True)
+        """
+        if field is None:
+            field = get_name_field(self)
+        if not isinstance(field, str):
+            field = field.field.name
+
+        return view_parents(
+            record=self,  # type: ignore
+            field=field,
+            with_parents=False,
+            with_children=True,
+            distance=distance,
+        )
+
     def query_parents(self) -> QuerySet:
         """Query parents in an ontology."""
         return _query_relatives([self], "parents", self.__class__)  # type: ignore
@@ -210,6 +244,7 @@ def view_lineage(
 def view_parents(
     record: Record,
     field: str,
+    with_parents: bool = True,
     with_children: bool = False,
     distance: int = 100,
     attr_name: Literal["parents", "predecessors"] = "parents",
@@ -223,11 +258,12 @@ def view_parents(
     import pandas as pd
 
     df_edges = None
-    df_edges_parents = _df_edges_from_parents(
-        record=record, field=field, distance=distance, attr_name=attr_name
-    )
-    if df_edges_parents is not None:
-        df_edges = df_edges_parents
+    df_edges_parents = None
+    df_edges_children = None
+    if with_parents:
+        df_edges_parents = _df_edges_from_parents(
+            record=record, field=field, distance=distance, attr_name=attr_name
+        )
     if with_children:
         df_edges_children = _df_edges_from_parents(
             record=record,
@@ -236,13 +272,32 @@ def view_parents(
             children=True,
             attr_name=attr_name,
         )
-        if df_edges_children is not None:
-            if df_edges is not None:
-                df_edges = pd.concat(
-                    [df_edges_parents, df_edges_children]
-                ).drop_duplicates()
-            else:
-                df_edges = df_edges_children
+        # Rename the columns to swap source and target
+        df_edges_children = df_edges_children.rename(
+            columns={
+                "source": "temp_target",
+                "source_label": "temp_target_label",
+                "source_record": "temp_target_record",
+                "target": "source",
+                "target_label": "source_label",
+                "target_record": "source_record",
+            }
+        )
+        df_edges_children = df_edges_children.rename(
+            columns={
+                "temp_target": "target",
+                "temp_target_label": "target_label",
+                "temp_target_record": "target_record",
+            }
+        )
+    if df_edges_parents is not None and df_edges_children is not None:
+        df_edges = pd.concat([df_edges_parents, df_edges_children]).drop_duplicates()
+    elif df_edges_parents is not None:
+        df_edges = df_edges_parents
+    elif df_edges_children is not None:
+        df_edges = df_edges_children
+    else:
+        return None
 
     record_label = _record_label(record, field)
 

lamindb/models/query_set.py

@@ -430,8 +430,9 @@ def reshape_annotate_result(
     """
     cols_from_include = cols_from_include or {}
 
-    # initialize result with basic fields
-    result = df[field_names]
+    # initialize result with basic fields, need a copy as we're modifying it
+    # will give us warnings otherwise
+    result = df[field_names].copy()
     # process features if requested
     if feature_names:
         # handle feature_values

lamindb/models/record.py

@@ -596,9 +596,8 @@ class Registry(ModelBase):
 
         target_modules = setup_settings.instance.modules
         if missing_members := source_modules - target_modules:
-            logger.warning(
-                f"source modules has additional modules: {missing_members}\n"
-                "consider mounting these registry modules to transfer all metadata"
+            logger.info(
+                f"in transfer, source lamindb instance has additional modules: {', '.join(missing_members)}"
             )
 
         add_db_connection(db, instance)
@@ -839,7 +838,7 @@ class BasicRecord(models.Model, metaclass=Registry):
                 self.features._add_from(self_on_db, transfer_logs=transfer_logs)
                 self.labels.add_from(self_on_db, transfer_logs=transfer_logs)
             for k, v in transfer_logs.items():
-                if k != "run":
+                if k != "run" and len(v) > 0:
                     logger.important(f"{k} records: {', '.join(v)}")
 
         if (

lamindb/models/schema.py

@@ -439,7 +439,7 @@ class Schema(Record, CanCurate, TracksRun):
     artifacts: Artifact
     """The artifacts that measure a feature set that matches this schema."""
     validated_artifacts: Artifact
-    """The artifacts that were validated against this schema with a :class:`~lamindb.curators.Curator`."""
+    """The artifacts that were validated against this schema with a :class:`~lamindb.curators.core.Curator`."""
     projects: Project
     """Linked projects."""
     _curation: dict[str, Any] = JSONField(default=None, db_default=None, null=True)
@@ -457,7 +457,7 @@ class Schema(Record, CanCurate, TracksRun):
     # For instance, the set of measured features might be a superset of the minimally required set of features.
     # """
     # validated_schemas: Schema
-    # """The schemas that were validated against this schema with a :class:`~lamindb.curators.Curator`."""
+    # """The schemas that were validated against this schema with a :class:`~lamindb.curators.core.Curator`."""
     composite: Schema | None = ForeignKey(
         "self", PROTECT, related_name="+", default=None, null=True
     )
@@ -538,7 +538,6 @@ class Schema(Record, CanCurate, TracksRun):
             optional_features,
             features_registry,
             flexible,
-            list_for_hashing,
         ) = self._validate_kwargs_calculate_hash(
             features=features,
             index=index,
@@ -562,7 +561,6 @@ class Schema(Record, CanCurate, TracksRun):
             .filter(hash=validated_kwargs["hash"])
             .one_or_none()
         )
-        self._list_for_hashing = list_for_hashing
         if schema is not None:
             logger.important(f"returning existing schema with same hash: {schema}")
             init_self_from_db(self, schema)
@@ -609,7 +607,7 @@ class Schema(Record, CanCurate, TracksRun):
         coerce_dtype: bool,
         n_features: int | None,
         optional_features_manual: list[Feature] | None = None,
-    ) -> tuple[list[Feature], dict[str, Any], list[Feature], Registry, bool, list[str]]:
+    ) -> tuple[list[Feature], dict[str, Any], list[Feature], Registry, bool]:
         optional_features = []
         features_registry: Registry = None
         if itype is not None:
@@ -729,7 +727,6 @@ class Schema(Record, CanCurate, TracksRun):
             optional_features,
             features_registry,
             flexible,
-            list_for_hashing,
         )
 
     @classmethod
@@ -865,26 +862,24 @@ class Schema(Record, CanCurate, TracksRun):
                 if hasattr(self, "_features")
                 else (self.members.list() if self.members.exists() else [])
             )
-            _, validated_kwargs, _, _, _, list_for_hashing = (
-                self._validate_kwargs_calculate_hash(
-                    features=features,  # type: ignore
-                    index=None,  # need to pass None here as otherwise counting double
-                    slots=self._slots if hasattr(self, "_slots") else self.slots,
-                    name=self.name,
-                    description=self.description,
-                    itype=self.itype,
-                    flexible=self.flexible,
-                    type=self.type,
-                    is_type=self.is_type,
-                    otype=self.otype,
-                    dtype=self.dtype,
-                    minimal_set=self.minimal_set,
-                    ordered_set=self.ordered_set,
-                    maximal_set=self.maximal_set,
-                    coerce_dtype=self.coerce_dtype,
-                    n_features=self.n,
-                    optional_features_manual=self.optionals.get(),
-                )
+            _, validated_kwargs, _, _, _ = self._validate_kwargs_calculate_hash(
+                features=features,  # type: ignore
+                index=None,  # need to pass None here as otherwise counting double
+                slots=self.slots,
+                name=self.name,
+                description=self.description,
+                itype=self.itype,
+                flexible=self.flexible,
+                type=self.type,
+                is_type=self.is_type,
+                otype=self.otype,
+                dtype=self.dtype,
+                minimal_set=self.minimal_set,
+                ordered_set=self.ordered_set,
+                maximal_set=self.maximal_set,
+                coerce_dtype=self.coerce_dtype,
+                n_features=self.n,
+                optional_features_manual=self.optionals.get(),
             )
             if validated_kwargs["hash"] != self.hash:
                 from .artifact import Artifact
@@ -896,7 +891,6 @@ class Schema(Record, CanCurate, TracksRun):
                     )
                 self.hash = validated_kwargs["hash"]
                 self.n = validated_kwargs["n"]
-            self._list_for_hashing = list_for_hashing
         super().save(*args, **kwargs)
         if hasattr(self, "_slots"):
             # analogous to save_schema_links in core._data.py
@@ -910,6 +904,7 @@ class Schema(Record, CanCurate, TracksRun):
                 }
                 links.append(Schema.components.through(**kwargs))
             bulk_create(links, ignore_conflicts=True)
+            delattr(self, "_slots")
         if hasattr(self, "_features"):
             assert self.n > 0  # noqa: S101
             using: bool | None = kwargs.pop("using", None)
@@ -1188,7 +1183,7 @@ class SchemaComponent(BasicRecord, LinkORM, TracksRun):
     slot: str | None = CharField(null=True)
 
     class Meta:
-        unique_together = (("composite", "component"), ("composite", "slot"))
+        unique_together = (("composite", "slot", "component"), ("composite", "slot"))
 
 
 Schema._get_related_name = _get_related_name

{lamindb-1.5.0.dist-info → lamindb-1.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.5.0
+Version: 1.5.2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14

{lamindb-1.5.0.dist-info → lamindb-1.5.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-lamindb/__init__.py,sha256=PvttGVLvK5zlO9ZI651ZzH36fKKUpaj2fAyOCKRnAoE,2676
+lamindb/__init__.py,sha256=yrNn0pSKCbdmvx_KKQ98PZraCdjzqMPwcwlHR3IoDvg,2676
 lamindb/_finish.py,sha256=Wqb846pCErsx5ZPulAfdF5PJbWzgAdfbuYuf4FndfhY,20124
 lamindb/_tracked.py,sha256=fse_H0ehc9WvU_l1572g7qya0sRdWCh22LZkq0XU4ic,4445
 lamindb/_view.py,sha256=kSmG8X4ULQZEKxY7ESnthQqsUf1DEzoYGeTLYRU1I7s,4938
@@ -11,7 +11,7 @@ lamindb/base/uids.py,sha256=cLBi5mIlsf1ltkTb17r1FLzlOjlGmjvsCygoVJHQ-A8,2116
 lamindb/base/users.py,sha256=8MSmAvCKoUF15YsDE6BGLBXsFWpfoEEg8iDTKZ7kD48,848
 lamindb/core/__init__.py,sha256=aaBq0UVjNolMynbT1V5hB6UrJm1tK0M6WHu_r6em9_4,604
 lamindb/core/_compat.py,sha256=NLnKk1qk4xdgMV-QwFDnBnbio02ujjlF86icvhpdv4c,2029
-lamindb/core/_context.py,sha256=JOvz3YbzZy3zGq_0giLHFZIGl04dMq-0hneUdJMTZes,33989
+lamindb/core/_context.py,sha256=xKj4YGpgM3Dx8H7_rNf6EI3sC5JHScSYVgHw-QYbMp4,34679
 lamindb/core/_mapped_collection.py,sha256=dxyZ1ZHFn5SBl1xILqN9N6TTUJP0PptVBV-2O0EdZww,25751
 lamindb/core/_settings.py,sha256=DAeEN2Qswj6VDlM7OE5YtoteMfFZ61CmMwcS056_scE,6211
 lamindb/core/_sync_git.py,sha256=Z7keuyS5X7CAj285sEbZIFExZF9mtjGH8DzKwz3xhHw,5881
@@ -30,7 +30,7 @@ lamindb/core/storage/_anndata_sizes.py,sha256=aXO3OB--tF5MChenSsigW6Q-RuE8YJJOUT
 lamindb/core/storage/_backed_access.py,sha256=LlpRDZ0skseZA5tBFu3-cH1wJwuXm7-NS2RgnTK7wgc,7382
 lamindb/core/storage/_polars_lazy_df.py,sha256=Z0KMp0OU5S36L5g8EuJk7V_nn-spgG1lFeEFnkTOLcw,1350
 lamindb/core/storage/_pyarrow_dataset.py,sha256=lRYYt7edUtwauhxd7RwFud6YPDbz2PFvYYgqLhfapfk,1398
-lamindb/core/storage/_tiledbsoma.py,sha256=gOcfgMHToI142KqyOYWJMOzmFMLos660k6ZFaAooYPc,10308
+lamindb/core/storage/_tiledbsoma.py,sha256=QLMOPjdxv9JFs9JR0Kqg1UTkJKNgwIDMeHAewB0-Lqg,11124
 lamindb/core/storage/_valid_suffixes.py,sha256=vUSeQ4s01rdhD_vSd6wKmFBsgMJAKkBMnL_T9Y1znMg,501
 lamindb/core/storage/_zarr.py,sha256=cisYXU4_QXMF_ZY2pV52Incus6365mMxRphLaHO76W0,6801
 lamindb/core/storage/objects.py,sha256=n1Kj1soxF-_iLFyNnHriVFcngw6nqEAd7aVm0Hm8Tcw,3017
@@ -40,7 +40,7 @@ lamindb/core/subsettings/_annotation_settings.py,sha256=o-yTYw-NmjFmtehbKU8qnf7t
 lamindb/core/subsettings/_creation_settings.py,sha256=NGHWKqCFSzVNBxAr2VnmdYguiFdW29XUK7T9wRsVshg,906
 lamindb/curators/__init__.py,sha256=ZexikeaVunT24TqsR1NsSOCSBXDBigfGtFT55tBwqS8,371
 lamindb/curators/_legacy.py,sha256=dTim3YFvdYyMsn6y8qSYkbCnnEI4tlaevN2-OO_qEx8,76174
-lamindb/curators/core.py,sha256=Kd9XAow7DR0BxrjFZ3zH469_11FItoD7RyqkW2zg4vA,60184
+lamindb/curators/core.py,sha256=YwMcKV2rAEhTav_fBixMM_sON2iUeu8JHGgxgcTjBn4,59915
 lamindb/curators/_cellxgene_schemas/__init__.py,sha256=zqlFzMNMDGEBe6DV0gBsBMpfc9UHvNv1EpBsz_ktMoA,7502
 lamindb/curators/_cellxgene_schemas/schema_versions.csv,sha256=X9rmO88TW1Fht1f5mJs0JdW-VPvyKSajpf8lHNeECj4,1680
 lamindb/examples/__init__.py,sha256=DGImiuWYDvwxh78p5FCwQWClEwsE3ODLU49i_NqbW0c,533
@@ -74,35 +74,36 @@ lamindb/migrations/0090_runproject_project_runs.py,sha256=Ab9wyGxc6xjBfj-36cqdTl
 lamindb/migrations/0090_squashed.py,sha256=kx_A_25BYantikxCbGhJughFpv_lqyHH86pMh5YevEE,160823
 lamindb/migrations/0091_alter_featurevalue_options_alter_space_options_and_more.py,sha256=Df4EYAQlLKZ4BpFcsRRF52pGN3hDSo94laiO-V90Kn4,607
 lamindb/migrations/0092_alter_artifactfeaturevalue_artifact_and_more.py,sha256=x-2Pvi0GJugkLrR--Fw9PBzV-HxqXjl0NktxRtRFJno,2459
+lamindb/migrations/0093_alter_schemacomponent_unique_together.py,sha256=p6pCGU3xzOo5FuHE_COxVn6qLgRUAdfWXJjl4_euEKU,424
 lamindb/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lamindb/models/__init__.py,sha256=IFYoZfly3m0Me5Fr8sk6-KdYpVzkuug0lo8jvci00Kg,2080
 lamindb/models/_describe.py,sha256=4PxaavWidEL8cyV2idbpC_7Zo0Jmjam3X1Bwe71IMaY,5489
 lamindb/models/_django.py,sha256=2LFaTvIPtxIV8_T6Kx0cvquTetj7C3OcnKukUyC9msY,7705
-lamindb/models/_feature_manager.py,sha256=FCZ9Tv0sJv1NPnTanK5O1duIN0MsPVmcIive53nEc1M,53899
+lamindb/models/_feature_manager.py,sha256=uMIcQMYrH1bHCqzovDbkDUOsBre_-mrg_7OS4RdoR8c,54666
 lamindb/models/_from_values.py,sha256=-8l3_d2Nm14kzi1FjEYvBwyuucL-ZcDSjlMufIb4XoQ,13324
 lamindb/models/_is_versioned.py,sha256=Th2_cBf9UWh27E6ANxg6LGmjBOumXFy7AjH0GG4FoXA,7601
 lamindb/models/_label_manager.py,sha256=QOT6mz_rzPJ5p7hM1l-XzDWzyWUERpmAan2n_ma5wpI,12112
 lamindb/models/_relations.py,sha256=ONjHPiWIa_Ur7zMNTa_9Uw7K-366GORyPvGoVjf4EQs,3681
-lamindb/models/artifact.py,sha256=MHEKV-8xuzc5n5-aSyhpGdja2S-ALr0FhsBwhuhhpJw,110368
+lamindb/models/artifact.py,sha256=6F_jcZiG1LeLT5HKSPCBiKUU-ItFM24aHyqWrwl1egc,110565
 lamindb/models/artifact_set.py,sha256=VOZEGDo3m_9Yg_ftx3I2fwdydjHN61X_qV18N6xG4kM,4117
 lamindb/models/can_curate.py,sha256=5dXHCRoJzLg2y9YDhpH7CyWexxliFHilwJ_UPjjZwRI,29188
 lamindb/models/collection.py,sha256=TNXnrR86ZgsSfEvaOuAEItgZ947klTXXZspa7hpyVmw,27288
 lamindb/models/core.py,sha256=A-W_Hdg4AmbBFBU38SEEVhOwSIzww5oNgYAQFnwOO7A,4018
 lamindb/models/feature.py,sha256=WoT29eZ8DR6MTZgnztbRye3-zX4BRYfJ8HlhdenX2qA,28186
 lamindb/models/flextable.py,sha256=ET9j0fTFYQIdXOZfwCnosXOag7nYD1DUV6_wZNqhvOs,5400
-lamindb/models/has_parents.py,sha256=U-UDu4C3C_lwZo7XA0UbH4bg2kia2Lu16YTPb28cEpw,18456
+lamindb/models/has_parents.py,sha256=A8OWsNotWlFrZB2pURRxp8EcHJ1kIlyV5eMnajGgkh4,20328
 lamindb/models/project.py,sha256=Hm-5hLn-FffFK3J_68gt-AxVc6bo26fegwGFRw0Gp50,15225
 lamindb/models/query_manager.py,sha256=mqsULCmUQf5ibpSXazca9ZYxyZwiDLuzSm8s6dPrl_M,10712
-lamindb/models/query_set.py,sha256=T8aeXV8W-Wdma_t5eTBeDj54NIlYGimvfEGEh7o2INo,30305
-lamindb/models/record.py,sha256=XM5TEnwNgzUJGZYC1n9w499-QVGeYLQ9eYUwVY6msQw,61395
+lamindb/models/query_set.py,sha256=xKh5QjAlHunktB1S4x9f42Fg0SP_-sK7XlyxStIRDSo,30385
+lamindb/models/record.py,sha256=fomXuOcqkfiYF3zEdiUkYw9x00qP5flM7oseUUomhIo,61354
 lamindb/models/run.py,sha256=FzqVQhYj4DXqlnmHvNIziOCAlx9K0wISXBLpom1Yb74,20688
 lamindb/models/save.py,sha256=JTAaorKECx0ZeHaX0H9Yt4MDwOsT9F813WbSJkBIPaU,13339
-lamindb/models/schema.py,sha256=9RUuHTiFGJAGsxMyyzJ79HrAEDfJ8OmjXGXD7G3yXm4,48040
+lamindb/models/schema.py,sha256=5_31iIPh19eJn0rm1OTeFk0gtD0YUPrTbiPsglKWOeo,47753
 lamindb/models/transform.py,sha256=LGnTR7g_rAx3YFAFv4l4_UzabruKQlnui1Y3tlWHwXk,12731
 lamindb/models/ulabel.py,sha256=yn9ttz28MqDBh6ZgwH7cty6GHCJOzLJn2IEpspYosDo,8793
 lamindb/setup/__init__.py,sha256=OwZpZzPDv5lPPGXZP7-zK6UdO4FHvvuBh439yZvIp3A,410
 lamindb/setup/core/__init__.py,sha256=SevlVrc2AZWL3uALbE5sopxBnIZPWZ1IB0NBDudiAL8,167
-lamindb-1.5.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-1.5.0.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-lamindb-1.5.0.dist-info/METADATA,sha256=g1M_VmflzJYLeuY2Ac_fGLjKZeJtQk19MrK65fOc3EY,2782
-lamindb-1.5.0.dist-info/RECORD,,
+lamindb-1.5.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-1.5.2.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+lamindb-1.5.2.dist-info/METADATA,sha256=d13GwaEiF6_3iCOJIBVB3XVQJTt5wQhptuk77Te4JZM,2782
+lamindb-1.5.2.dist-info/RECORD,,