lamindb 0.65.0__py3-none-any.whl → 0.66.0__py3-none-any.whl

lamindb/__init__.py

@@ -54,7 +54,7 @@ Modules & settings:
 
 """
 
-__version__ = "0.65.0"  # denote a release candidate for 0.1.0 with 0.1rc1
+__version__ = "0.66.0"  # denote a release candidate for 0.1.0 with 0.1rc1
 
 import os as _os
 

lamindb/_collection.py

@@ -5,7 +5,7 @@ import anndata as ad
 import pandas as pd
 from lamin_utils import logger
 from lamindb_setup.dev._docs import doc_args
-from lnschema_core.models import Collection, Feature, FeatureSet
+from lnschema_core.models import Collection, CollectionArtifact, Feature, FeatureSet
 from lnschema_core.types import AnnDataLike, DataLike, FieldAttr, VisibilityChoice
 
 from lamindb._utils import attach_func_to_class_method
@@ -15,6 +15,7 @@ from lamindb.dev.versioning import get_uid_from_old_version, init_uid
 
 from . import _TESTING, Artifact, Run
 from ._artifact import parse_feature_sets_from_anndata
+from ._query_set import QuerySet
 from ._registry import init_self_from_db
 from .dev._data import (
     add_transform_to_kwargs,
@@ -312,9 +313,11 @@ def from_artifacts(artifacts: Iterable[Artifact]) -> Tuple[str, Dict[str, str]]:
 def mapped(
     self,
     label_keys: Optional[Union[str, List[str]]] = None,
-    join_vars: Optional[Literal["auto", "inner"]] = "auto",
+    join: Optional[Literal["inner", "outer"]] = "inner",
     encode_labels: bool = True,
+    cache_categories: bool = True,
     parallel: bool = False,
+    dtype: Optional[str] = None,
     stream: bool = False,
     is_run_input: Optional[bool] = None,
 ) -> "MappedCollection":
@@ -328,7 +331,15 @@ def mapped(
             path_list.append(artifact.stage())
         else:
             path_list.append(artifact.path)
-    return MappedCollection(path_list, label_keys, join_vars, encode_labels, parallel)
+    return MappedCollection(
+        path_list,
+        label_keys,
+        join,
+        encode_labels,
+        cache_categories,
+        parallel,
+        dtype,
+    )
 
 
 # docstring handled through attach_func_to_class_method
@@ -416,7 +427,14 @@ def save(self, *args, **kwargs) -> None:
     super(Collection, self).save()
     if hasattr(self, "_artifacts"):
         if self._artifacts is not None and len(self._artifacts) > 0:
-            self.artifacts.set(self._artifacts)
+            links = [
+                CollectionArtifact(collection_id=self.id, artifact_id=artifact.id)
+                for artifact in self._artifacts
+            ]
+            # the below seems to preserve the order of the list in the
+            # auto-incrementing integer primary
+            # merely using .unordered_artifacts.set(*...) doesn't achieve this
+            CollectionArtifact.objects.bulk_create(links)
     save_feature_set_links(self)
 
 
@@ -429,6 +447,14 @@ def restore(self) -> None:
         self.artifact.save()
 
 
+@property  # type: ignore
+@doc_args(Collection.artifacts.__doc__)
+def artifacts(self) -> QuerySet:
+    """{}."""
+    _track_run_input(self)
+    return self.unordered_artifacts.order_by("collectionartifact__id")
+
+
 METHOD_NAMES = [
     "__init__",
     "from_anndata",
@@ -455,3 +481,4 @@ for name in METHOD_NAMES:
 
 # this seems a Django-generated function
 delattr(Collection, "get_visibility_display")
+Collection.artifacts = artifacts

lamindb/_feature.py

@@ -9,6 +9,7 @@ from lamindb._utils import attach_func_to_class_method
 from lamindb.dev._settings import settings
 
 from . import _TESTING
+from ._query_set import RecordsList
 
 FEATURE_TYPES = {
     "int": "number",
@@ -86,7 +87,7 @@ def categoricals_from_df(df: "pd.DataFrame") -> Dict:
 
 @classmethod  # type:ignore
 @doc_args(Feature.from_df.__doc__)
-def from_df(cls, df: "pd.DataFrame") -> List["Feature"]:
+def from_df(cls, df: "pd.DataFrame") -> "RecordsList":
     """{}."""
     categoricals = categoricals_from_df(df)
 
@@ -141,7 +142,7 @@ def from_df(cls, df: "pd.DataFrame") -> List["Feature"]:
     #         f" {colors.yellow('unmapped categories')}:\n     "
     #         f" {categoricals_with_unmapped_categories_formatted}"
     #     )
-    return features
+    return RecordsList(features)
 
 
 @doc_args(Feature.save.__doc__)

lamindb/_parents.py

@@ -275,10 +275,15 @@ def _record_label(record: Registry, field: Optional[str] = None):
         )
     elif isinstance(record, Run):
         name = f'{record.transform.name.replace("&", "&")}'
+        user_display = (
+            record.created_by.handle
+            if record.created_by.name is None
+            else record.created_by.name
+        )
         return (
             rf'<{TRANSFORM_EMOJIS.get(str(record.transform.type), "💫")} {name}<BR/><FONT COLOR="GREY" POINT-SIZE="10"'
             rf' FACE="Monospace">uid={record.transform.uid}<BR/>type={record.transform.type},'
-            rf" user={record.created_by.name}<BR/>run_at={format_field_value(record.run_at)}</FONT>>"
+            rf" user={user_display}<BR/>run={format_field_value(record.run_at)}</FONT>>"
         )
     elif isinstance(record, Transform):
         name = f'{record.name.replace("&", "&amp;")}'
@@ -317,13 +322,13 @@ def _get_all_parent_runs(data: Union[Artifact, Collection]) -> List:
             inputs_run = (
                 r.__getattribute__(f"input_{name}s").all().filter(visibility=1).list()
             )
-            if name == "file":
+            if name == "artifact":
                 inputs_run += r.input_collections.all().filter(visibility=1).list()
             run_inputs_outputs += [(inputs_run, r)]
             outputs_run = (
                 r.__getattribute__(f"output_{name}s").all().filter(visibility=1).list()
             )
-            if name == "file":
+            if name == "artifact":
                 outputs_run += r.output_collections.all().filter(visibility=1).list()
             run_inputs_outputs += [(r, outputs_run)]
             inputs += inputs_run
@@ -337,8 +342,11 @@ def _get_all_child_runs(data: Union[Artifact, Collection]) -> List:
     all_runs: Set[Run] = set()
     run_inputs_outputs = []
 
-    runs = {f.run for f in data.run.__getattribute__(f"output_{name}s").all()}
-    if name == "file":
+    if data.run is not None:
+        runs = {f.run for f in data.run.__getattribute__(f"output_{name}s").all()}
+    else:
+        runs = set()
+    if name == "artifact" and data.run is not None:
         runs.update(
             {
                 f.run
@@ -352,13 +360,13 @@ def _get_all_child_runs(data: Union[Artifact, Collection]) -> List:
             inputs_run = (
                 r.__getattribute__(f"input_{name}s").all().filter(visibility=1).list()
             )
-            if name == "file":
+            if name == "artifact":
                 inputs_run += r.input_collections.all().filter(visibility=1).list()
             run_inputs_outputs += [(inputs_run, r)]
             outputs_run = (
                 r.__getattribute__(f"output_{name}s").all().filter(visibility=1).list()
             )
-            if name == "file":
+            if name == "artifact":
                 outputs_run += r.output_collections.all().filter(visibility=1).list()
             run_inputs_outputs += [(r, outputs_run)]
             child_runs.update(
@@ -366,7 +374,7 @@ def _get_all_child_runs(data: Union[Artifact, Collection]) -> List:
                     **{f"input_{name}s__id__in": [i.id for i in outputs_run]}
                 ).list()
             )
-            if name == "file":
+            if name == "artifact":
                 child_runs.update(
                     Run.filter(
                         input_collections__id__in=[i.id for i in outputs_run]

lamindb/_query_set.py

@@ -1,4 +1,5 @@
-from typing import Iterable, List, NamedTuple, Optional, Union
+from collections import UserList
+from typing import Dict, Iterable, List, NamedTuple, Optional, Union
 
 import pandas as pd
 from django.db import models
@@ -21,6 +22,40 @@ class MultipleResultsFound(Exception):
 #     return (series + timedelta).dt.strftime("%Y-%m-%d %H:%M:%S %Z")
 
 
+def get_keys_from_df(data: List, registry: Registry) -> List[str]:
+    if len(data) > 0:
+        if isinstance(data[0], dict):
+            keys = list(data[0].keys())
+        else:
+            keys = list(data[0].__dict__.keys())
+            if "_state" in keys:
+                keys.remove("_state")
+    else:
+        keys = [
+            field.name
+            for field in registry._meta.fields
+            if not isinstance(field, models.ForeignKey)
+        ]
+        keys += [
+            f"{field.name}_id"
+            for field in registry._meta.fields
+            if isinstance(field, models.ForeignKey)
+        ]
+    return keys
+
+
+class RecordsList(UserList):
+    """Is ordered, can't be queried, but has `.df()`."""
+
+    def __init__(self, records: List[Registry]):
+        super().__init__(record for record in records)
+
+    def df(self) -> pd.DataFrame:
+        keys = get_keys_from_df(self.data, self.data[0].__class__)
+        values = [record.__dict__ for record in self.data]
+        return pd.DataFrame(values, columns=keys)
+
+
 class QuerySet(models.QuerySet, CanValidate, IsTree):
     """Lazily loaded queried records returned by queries.
 
@@ -59,24 +94,7 @@ class QuerySet(models.QuerySet, CanValidate, IsTree):
             >>> ln.ULabel.filter().df(include=["labels__name", "labels__created_by_id"])
         """
         data = self.values()
-        if len(data) > 0:
-            keys = list(data[0].keys())
-            if "created_at" in keys:
-                keys.remove("created_at")
-        else:
-            keys = [
-                field.name
-                for field in self.model._meta.fields
-                if (
-                    not isinstance(field, models.ForeignKey)
-                    and field.name != "created_at"
-                )
-            ]
-            keys += [
-                f"{field.name}_id"
-                for field in self.model._meta.fields
-                if isinstance(field, models.ForeignKey)
-            ]
+        keys = get_keys_from_df(data, self.model)
         df = pd.DataFrame(self.values(), columns=keys)
         # if len(df) > 0 and "updated_at" in df:
         #     df.updated_at = format_and_convert_to_local_time(df.updated_at)

lamindb/_registry.py

@@ -469,7 +469,11 @@ def save(self, *args, **kwargs) -> None:
     if result is not None:
         init_self_from_db(self, result)
     else:
-        super(Registry, self).save(*args, **kwargs)
+        # here, we can't use the parents argument
+        save_kwargs = kwargs.copy()
+        if "parents" in save_kwargs:
+            save_kwargs.pop("parents")
+        super(Registry, self).save(*args, **save_kwargs)
     if db is not None and db != "default":
         if hasattr(self, "labels"):
             from copy import copy

lamindb/dev/__init__.py

@@ -14,6 +14,7 @@ Queries of registries:
 
    QuerySet
    QueryManager
+   RecordsList
 
 Functionality of data registries:
 
@@ -24,6 +25,7 @@ Functionality of data registries:
    FeatureManager
    LabelManager
    IsTree
+   IsVersioned
 
 Functionality of metadata registries:
 
@@ -51,10 +53,17 @@ Auxiliary tools:
 """
 
 from lamin_utils._inspect import InspectResult
-from lnschema_core.models import CanValidate, Data, HasParents, IsTree, Registry
+from lnschema_core.models import (
+    CanValidate,
+    Data,
+    HasParents,
+    IsTree,
+    IsVersioned,
+    Registry,
+)
 
 from lamindb._query_manager import QueryManager
-from lamindb._query_set import QuerySet
+from lamindb._query_set import QuerySet, RecordsList
 from lamindb.dev._feature_manager import FeatureManager
 from lamindb.dev._label_manager import LabelManager
 

lamindb/dev/_data.py

@@ -113,8 +113,7 @@ def describe(self: Data):
         "created_by": "👤",
         "transform": _transform_emoji(self.transform),
         "run": "👣",
-        "initial_version": "🔖",
-        "file": "📄",
+        "artifact": "📄",
     }
     if len(foreign_key_fields) > 0:  # always True for Artifact and Collection
         record_msg = f"{colors.green(model_name)}{__repr__(self, include_foreign_keys=False).lstrip(model_name)}"
@@ -209,7 +208,7 @@ def add_labels(
 ) -> None:
     """{}."""
     if self._state.adding:
-        raise ValueError("Please save the file/collection before adding a label!")
+        raise ValueError("Please save the artifact/collection before adding a label!")
 
     if isinstance(records, (QuerySet, QuerySet.__base__)):  # need to have both
         records = records.list()
@@ -331,7 +330,7 @@ def add_labels(
                             id=old_feature_set_link.feature_set_id
                         ).one()
                         logger.info(
-                            "no file links to it anymore, deleting feature set"
+                            "nothing links to it anymore, deleting feature set"
                             f" {old_feature_set}"
                         )
                         old_feature_set.delete()
@@ -368,7 +367,7 @@ def _track_run_input(
         if run is None:
             if settings.track_run_inputs:
                 logger.hint(
-                    "you can auto-track this file as a run input by calling"
+                    "you can auto-track these data as a run input by calling"
                     " `ln.track()`"
                 )
         # assume we have a run record
@@ -390,7 +389,7 @@ def _track_run_input(
                     track_run_input = True
                 else:
                     logger.hint(
-                        "track this file as a run input by passing `is_run_input=True`"
+                        "track these data as a run input by passing `is_run_input=True`"
                     )
     else:
         track_run_input = is_run_input

lamindb/dev/_label_manager.py

@@ -23,11 +23,12 @@ def get_labels_as_dict(self: Data):
     ).items():
         if related_name in {
             "feature_sets",
-            "files",
+            "artifacts",
             "input_of",
             "collections",
             "source_of",
             "report_of",
+            "environment_of",
         }:
             continue
         if self.id is not None:

lamindb/dev/_mapped_collection.py

@@ -5,6 +5,7 @@ from typing import List, Literal, Optional, Union
 
 import numpy as np
 import pandas as pd
+from lamin_utils import logger
 from lamindb_setup.dev.upath import UPath
 
 from .storage._backed_access import (
@@ -57,10 +58,14 @@ class MappedCollection:
         self,
         path_list: List[Union[str, PathLike]],
         label_keys: Optional[Union[str, List[str]]] = None,
-        join_vars: Optional[Literal["auto", "inner"]] = "auto",
+        join: Optional[Literal["inner", "outer"]] = "outer",
         encode_labels: bool = True,
+        cache_categories: bool = True,
         parallel: bool = False,
+        dtype: Optional[str] = None,
     ):
+        assert join in {None, "inner", "outer"}
+
         self.storages = []  # type: ignore
         self.conns = []  # type: ignore
         self.parallel = parallel
@@ -79,16 +84,22 @@ class MappedCollection:
         self.indices = np.hstack([np.arange(n_obs) for n_obs in self.n_obs_list])
         self.storage_idx = np.repeat(np.arange(len(self.storages)), self.n_obs_list)
 
-        self.join_vars = join_vars if len(path_list) > 1 else None
+        self.join_vars = join if len(path_list) > 1 else None
         self.var_indices = None
         if self.join_vars is not None:
             self._make_join_vars()
 
         self.encode_labels = encode_labels
         self.label_keys = [label_keys] if isinstance(label_keys, str) else label_keys
-        if self.label_keys is not None and self.encode_labels:
-            self._make_encoders(self.label_keys)
+        if self.label_keys is not None:
+            if cache_categories:
+                self._cache_categories(self.label_keys)
+            else:
+                self._cache_cats: dict = {}
+            if self.encode_labels:
+                self._make_encoders(self.label_keys)
 
+        self._dtype = dtype
         self._closed = False
 
     def _make_connections(self, path_list: list, parallel: bool):
@@ -104,6 +115,18 @@ class MappedCollection:
             self.conns.append(conn)
             self.storages.append(storage)
 
+    def _cache_categories(self, label_keys: list):
+        self._cache_cats = {}
+        decode = np.frompyfunc(lambda x: x.decode("utf-8"), 1, 1)
+        for label in label_keys:
+            self._cache_cats[label] = []
+            for storage in self.storages:
+                with _Connect(storage) as store:
+                    cats = self.get_categories(store, label)
+                    if cats is not None:
+                        cats = decode(cats) if isinstance(cats[0], bytes) else cats[...]
+                    self._cache_cats[label].append(cats)
+
     def _make_encoders(self, label_keys: list):
         self.encoders = []
         for label in label_keys:
@@ -115,20 +138,38 @@ class MappedCollection:
         for storage in self.storages:
             with _Connect(storage) as store:
                 var_list.append(_safer_read_index(store["var"]))
+
+        self.var_joint = None
         if self.join_vars == "auto":
             vars_eq = all(var_list[0].equals(vrs) for vrs in var_list[1:])
             if vars_eq:
                 self.join_vars = None
+                logger.info("The variables are same, no virtual join is performed.")
                 return
             else:
-                self.join_vars = "inner"
+                self.var_joint = reduce(pd.Index.intersection, var_list)
+                if len(self.var_joint) > 0:
+                    self.join_vars = "inner"
+                    logger.info(
+                        "The intersection of variables is not empty, using virtual inner join."
+                    )
+                else:
+                    self.join_vars = "outer"
+                    logger.info(
+                        "The intersection of variables is empty, using virtual outer join."
+                    )
+
         if self.join_vars == "inner":
-            self.var_joint = reduce(pd.Index.intersection, var_list)
-            if len(self.var_joint) == 0:
-                raise ValueError(
-                    "The provided AnnData objects don't have shared varibales."
-                )
+            if self.var_joint is None:
+                self.var_joint = reduce(pd.Index.intersection, var_list)
+                if len(self.var_joint) == 0:
+                    raise ValueError(
+                        "The provided AnnData objects don't have shared varibales."
+                    )
             self.var_indices = [vrs.get_indexer(self.var_joint) for vrs in var_list]
+        elif self.join_vars == "outer":
+            self.var_joint = reduce(pd.Index.union, var_list)
+            self.var_indices = [self.var_joint.get_indexer(vrs) for vrs in var_list]
 
     def __len__(self):
         return self.n_obs
@@ -137,15 +178,21 @@ class MappedCollection:
         obs_idx = self.indices[idx]
         storage_idx = self.storage_idx[idx]
         if self.var_indices is not None:
-            var_idxs = self.var_indices[storage_idx]
+            var_idxs_join = self.var_indices[storage_idx]
         else:
-            var_idxs = None
+            var_idxs_join = None
 
         with _Connect(self.storages[storage_idx]) as store:
-            out = [self.get_data_idx(store, obs_idx, var_idxs)]
+            out = [self.get_data_idx(store, obs_idx, var_idxs_join)]
             if self.label_keys is not None:
                 for i, label in enumerate(self.label_keys):
-                    label_idx = self.get_label_idx(store, obs_idx, label)
+                    if label in self._cache_cats:
+                        cats = self._cache_cats[label][storage_idx]
+                        if cats is None:
+                            cats = []
+                    else:
+                        cats = None
+                    label_idx = self.get_label_idx(store, obs_idx, label, cats)
                     if self.encode_labels:
                         label_idx = self.encoders[i][label_idx]
                     out.append(label_idx)
@@ -155,26 +202,50 @@ class MappedCollection:
         self,
         storage: StorageType,  # type: ignore
         idx: int,
-        var_idxs: Optional[list] = None,
+        var_idxs_join: Optional[list] = None,
         layer_key: Optional[str] = None,
     ):
         """Get the index for the data."""
         layer = storage["X"] if layer_key is None else storage["layers"][layer_key]  # type: ignore
         if isinstance(layer, ArrayTypes):  # type: ignore
-            # todo: better way to select variables
-            return layer[idx] if var_idxs is None else layer[idx][var_idxs]
+            layer_idx = layer[idx]
+            if self.join_vars is None:
+                result = layer_idx
+                if self._dtype is not None:
+                    result = result.astype(self._dtype, copy=False)
+            elif self.join_vars == "outer":
+                dtype = layer_idx.dtype if self._dtype is None else self._dtype
+                result = np.zeros(len(self.var_joint), dtype=dtype)
+                result[var_idxs_join] = layer_idx
+            else:  # inner join
+                result = layer_idx[var_idxs_join]
+                if self._dtype is not None:
+                    result = result.astype(self._dtype, copy=False)
+            return result
         else:  # assume csr_matrix here
             data = layer["data"]
             indices = layer["indices"]
             indptr = layer["indptr"]
             s = slice(*(indptr[idx : idx + 2]))
-            # this requires more memory than csr_matrix when var_idxs is not None
-            # but it is faster
-            layer_idx = np.zeros(layer.attrs["shape"][1])
-            layer_idx[indices[s]] = data[s]
-            return layer_idx if var_idxs is None else layer_idx[var_idxs]
+            data_s = data[s]
+            dtype = data_s.dtype if self._dtype is None else self._dtype
+            if self.join_vars == "outer":
+                layer_idx = np.zeros(len(self.var_joint), dtype=dtype)
+                layer_idx[var_idxs_join[indices[s]]] = data_s
+            else:
+                layer_idx = np.zeros(layer.attrs["shape"][1], dtype=dtype)
+                layer_idx[indices[s]] = data_s
+                if self.join_vars == "inner":
+                    layer_idx = layer_idx[var_idxs_join]
+            return layer_idx
 
-    def get_label_idx(self, storage: StorageType, idx: int, label_key: str):  # type: ignore
+    def get_label_idx(
+        self,
+        storage: StorageType,
+        idx: int,
+        label_key: str,
+        categories: Optional[list] = None,
+    ):
         """Get the index for the label by key."""
         obs = storage["obs"]  # type: ignore
         # how backwards compatible do we want to be here actually?
@@ -186,9 +257,11 @@ class MappedCollection:
                 label = labels[idx]
             else:
                 label = labels["codes"][idx]
-
-        cats = self.get_categories(storage, label_key)
-        if cats is not None:
+        if categories is not None:
+            cats = categories
+        else:
+            cats = self.get_categories(storage, label_key)
+        if cats is not None and len(cats) > 0:
             label = cats[label]
         if isinstance(label, bytes):
             label = label.decode("utf-8")
@@ -215,11 +288,14 @@ class MappedCollection:
         """Get merged labels."""
         labels_merge = []
         decode = np.frompyfunc(lambda x: x.decode("utf-8"), 1, 1)
-        for storage in self.storages:
+        for i, storage in enumerate(self.storages):
             with _Connect(storage) as store:
                 codes = self.get_codes(store, label_key)
                 labels = decode(codes) if isinstance(codes[0], bytes) else codes
-                cats = self.get_categories(store, label_key)
+                if label_key in self._cache_cats:
+                    cats = self._cache_cats[label_key][i]
+                else:
+                    cats = self.get_categories(store, label_key)
                 if cats is not None:
                     cats = decode(cats) if isinstance(cats[0], bytes) else cats
                     labels = cats[labels]
@@ -230,9 +306,12 @@ class MappedCollection:
         """Get merged categories."""
         cats_merge = set()
         decode = np.frompyfunc(lambda x: x.decode("utf-8"), 1, 1)
-        for storage in self.storages:
+        for i, storage in enumerate(self.storages):
             with _Connect(storage) as store:
-                cats = self.get_categories(store, label_key)
+                if label_key in self._cache_cats:
+                    cats = self._cache_cats[label_key][i]
+                else:
+                    cats = self.get_categories(store, label_key)
                 if cats is not None:
                     cats = decode(cats) if isinstance(cats[0], bytes) else cats
                     cats_merge.update(cats)

lamindb/dev/_run_context.py

@@ -33,7 +33,9 @@ msg_manual_init = (
 )
 
 
-class UpdateNbWithNonInteractiveEditorError(Exception):
+# we don't want a real error here, as this is so frequent
+# in VSCode
+class UpdateNbWithNonInteractiveEditor(SystemExit):
     pass
 
 
@@ -230,7 +232,7 @@ class run_context:
                             "it looks like you are running ln.track() from a "
                             "notebook!\nplease install nbproject: pip install nbproject"
                         )
-                    elif isinstance(e, UpdateNbWithNonInteractiveEditorError):
+                    elif isinstance(e, UpdateNbWithNonInteractiveEditor):
                         raise e
                     elif isinstance(e, (NotebookNotSavedError, NoTitleError)):
                         raise e
@@ -435,7 +437,7 @@ class run_context:
                 cls._notebook_meta = metadata  # type: ignore
             else:
                 msg = msg_manual_init.format(notebook_path=notebook_path_str)
-                raise UpdateNbWithNonInteractiveEditorError(msg)
+                raise UpdateNbWithNonInteractiveEditor(msg)
 
         if _env in ("lab", "notebook"):
             # save the notebook in case that title was updated
@@ -450,7 +452,7 @@ class run_context:
             is_interactive = _seconds_modified(_filepath) < 1.5  # should be ~1 sec
             if not is_interactive and needs_init:
                 msg = msg_manual_init.format(notebook_path=_filepath)
-                raise UpdateNbWithNonInteractiveEditorError(msg)
+                raise UpdateNbWithNonInteractiveEditor(msg)
 
             nbproject_id = metadata["id"]
             nbproject_version = metadata["version"]
@@ -509,7 +511,7 @@ class run_context:
                 cls._notebook_meta = metadata  # type: ignore
             else:
                 msg = msg_manual_init.format(notebook_path=filepath)
-                raise UpdateNbWithNonInteractiveEditorError(msg)
+                raise UpdateNbWithNonInteractiveEditor(msg)
         else:
             from lamin_cli._transform import update_transform_source_metadata
 

lamindb/dev/_track_environment.py

@@ -6,9 +6,13 @@ from lnschema_core.models import Run
 
 
 def track_environment(run: Run) -> None:
-    filepath = ln_setup.settings.storage.cache_dir / f"run_env_pip_{run.uid}"
+    filepath = ln_setup.settings.storage.cache_dir / f"run_env_pip_{run.uid}.txt"
     # create a requirements.txt
     # we don't create a conda environment.yml mostly for its slowness
-    result = subprocess.run(f"pip freeze > {str(filepath)}", shell=True)
-    if result.returncode == 0:
+    try:
+        result = subprocess.run(f"pip freeze > {str(filepath)}", shell=True)
+    except OSError as e:
+        result = None
+        logger.warning(f"could not run pip freeze with error {e}")
+    if result is not None and result.returncode == 0:
         logger.info(f"tracked pip freeze > {str(filepath)}")

{lamindb-0.65.0.dist-info → lamindb-0.66.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.65.0
+Version: 0.66.0
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.8
@@ -9,10 +9,10 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Dist: lnschema_core==0.60.0
-Requires-Dist: lamindb_setup==0.63.0
+Requires-Dist: lnschema_core==0.61.0
+Requires-Dist: lamindb_setup==0.64.0
 Requires-Dist: lamin_utils==0.13.0
-Requires-Dist: lamin_cli==0.5.0
+Requires-Dist: lamin_cli==0.6.0
 Requires-Dist: rapidfuzz
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
@@ -62,14 +62,14 @@ Provides-Extra: zarr
 
 # LaminDB - A data framework for biology
 
-LaminDB is an open-source Python framework to manage biological data & analyses in generic backends:
+LaminDB is an open-source Python framework to manage biological data & analyses:
 
-- Access data & metadata across storage (files, arrays) & database (SQL) backends.
-- Track data flow across notebooks, pipelines & UI.
-- Manage registries for experimental metadata & in-house ontologies, import public ontologies.
-- Validate, standardize & annotate data using registries.
+- Access data & metadata across storage & databases.
+- Track data lineage across notebooks & pipelines.
+- Manage registries for experimental metadata & in-house ontologies.
+- Validate, standardize & annotate data.
 - Organize and share data across a mesh of LaminDB instances.
-- Manage data access with an auditable system of record.
+- Manage data access, leverage an auditable system of record.
 
 ## Documentation
 

{lamindb-0.65.0.dist-info → lamindb-0.66.0.dist-info}/RECORD

@@ -1,15 +1,15 @@
-lamindb/__init__.py,sha256=-_IG5yZQ4fWBdgSG1qMl8oCQJf5WgAol6keJ2PuFh5I,2691
+lamindb/__init__.py,sha256=rgCY0tETrHKyB7V5f2Y3BhY4BAJicGUUYzSRwIdRlmI,2691
 lamindb/_artifact.py,sha256=eWsLj8x6Cqy8MR7LxKyScxozM52MaqOTCK8gplloP2c,38087
-lamindb/_collection.py,sha256=ZGzx58Tm76wGxMBU9nzKRkme9IduLmiuL0H-8byPkdY,16812
+lamindb/_collection.py,sha256=gVcs3A200JZilfdYd0zrX29UrAmhP9Eovu6r_SIxXQ4,17634
 lamindb/_delete.py,sha256=jO6kcIoxY6EFgqiVF2vlbXaCaqlI25AvBo7nre3JXkQ,1968
-lamindb/_feature.py,sha256=AqQZTOL38aElT3-e7WCj8Fm2Xcso0uJO0oE72fQCScU,5989
+lamindb/_feature.py,sha256=tEcqFoEj5yp4LSJfMGyiVvxDUuLoZaik6lo05ZKcCtE,6036
 lamindb/_feature_set.py,sha256=KYgdmMdXb21pfpir1J1O21in3nJvUeznECOB38qfTvk,8654
 lamindb/_filter.py,sha256=YwWqviJ34kHTMJ8NYlrEw-vsrXkKrVIPsEZSBVvMcrI,1163
 lamindb/_from_values.py,sha256=dKz4cTUBRkXOOzFX2Ix2cKhK2Lw9PyTgi7d0PI-kh3c,11869
-lamindb/_parents.py,sha256=lDNuOys4OW5wSHzH6fxEcHPsOjwVgXFq0q-I-noPO5A,13907
+lamindb/_parents.py,sha256=hyoN92YnfJFmRWmQMLLUjTKKwnIOJci5z6csMjsdYDE,14165
 lamindb/_query_manager.py,sha256=m4WUScviuNlMHeNEPZ8H8y0YsMXSbwWyfIgS4L00wBY,4332
-lamindb/_query_set.py,sha256=nacnkFaVYDmuFkpXr0fb3uNcWP6XahbMeIvJic0YCSk,9967
-lamindb/_registry.py,sha256=UX4O3Ne9QajcfG2FGXyVkyF6b-McPPxJmRQ2MwXZy3w,17254
+lamindb/_query_set.py,sha256=tItL2YNdycpbXklYd8aW4jJX6Z-kGcNclscg0v3l8t4,10495
+lamindb/_registry.py,sha256=MxYpJUKD6Qu5eO2jO6JOcQBBGxfQpiEGPJrFaXau_jw,17421
 lamindb/_run.py,sha256=659lqY32GW7F41rFUUo37OftUa38-p8yaV9Z0oF32CE,1120
 lamindb/_save.py,sha256=UlRHJGUiHGOXv90wmawZVsOqhJIqk8f1wj8MW3Rlq_c,10535
 lamindb/_storage.py,sha256=mz2Cy0CTaeJGA03A1FPQmmH0Vt2ib_KlXklaLqtN1mU,394
@@ -18,14 +18,14 @@ lamindb/_ulabel.py,sha256=HALoy6HerRnehR-u8zPH-qmiFQHWxeAwkZ31jxjrfgI,1893
 lamindb/_utils.py,sha256=LGdiW4k3GClLz65vKAVRkL6Tw-Gkx9DWAdez1jyA5bE,428
 lamindb/_validate.py,sha256=fS2685MYX9h6iAWymEorJJmDYA2CGNOSmJpesbG6faU,14400
 lamindb/_view.py,sha256=yFMu4vnt0YqvN1q11boAkwigxCH1gdliDUSbzh3IuDw,2175
-lamindb/dev/__init__.py,sha256=Sm1-zkgy_7MKwFheXDrUKiY7ZBKX_VUQVfbr_hEPVqE,1089
-lamindb/dev/_data.py,sha256=C7Z3mygwx4IGoFOtjvnmA_-O7VXZqNvJJh6QAgN2MBM,17091
+lamindb/dev/__init__.py,sha256=LLqivujL8c-oKWC15SJepAYyrTlLNvql5Vdwunc0qvE,1174
+lamindb/dev/_data.py,sha256=YPZ664qGKMl34LbZCMCEFIxQ-E81iAt_b3lvMiTe-oc,17066
 lamindb/dev/_feature_manager.py,sha256=jn8x_JbrtLFelmaFh4noOXqGSCfqVuVX0quoa7gTJtM,9366
-lamindb/dev/_label_manager.py,sha256=q8rlFA_KgyVL_rE7h52dA6whCxGu72YTj62cilKWXGM,8706
-lamindb/dev/_mapped_collection.py,sha256=Woz5iUnCzQGraF-pjzZF0fQHEJlXnL6lpkIXq_k_d64,11129
-lamindb/dev/_run_context.py,sha256=Hgmq0yYQsLHK3cUVKR3V2bFUSllaIWO5S7a8GQcjEl0,22919
+lamindb/dev/_label_manager.py,sha256=6E_pSQicqfTWDGEGe4WPn_3GZl_CCIMTZ6xJDh4EkC0,8740
+lamindb/dev/_mapped_collection.py,sha256=NRjOYnC1d3IcVyqhT_Yp0xycepmeytlngYnw-5Xcnw4,14445
+lamindb/dev/_run_context.py,sha256=4eBZsbfcFpW5nqmRLbRZxuA5oeRW17XVHMzVtMH0bKA,22965
 lamindb/dev/_settings.py,sha256=nixk8lVijCbq_fRlUpkX5gvO9AdgUFjbXzFThAJhGBA,3824
-lamindb/dev/_track_environment.py,sha256=GelTuDF_k9dXTLV5AcibfzXllmTXXorBy2RqJyb6GuI,508
+lamindb/dev/_track_environment.py,sha256=QjHWbyl2u8J4hbJG8Q_ToFaZIgS-H15Ej6syJgk-dvY,662
 lamindb/dev/_view_tree.py,sha256=K-C1BsOiEupwgkhyrsGxLFxHU45SAkiKsQbeOV9PbaY,3421
 lamindb/dev/exceptions.py,sha256=PHk5lyBdJPrrEQcid3ItfdNzz3fgiQsUmsEDdz063F0,197
 lamindb/dev/fields.py,sha256=0f0wai2aCjQYAQgI04UlCOAHo2MQknp4AsOKFDmE9iU,163
@@ -43,7 +43,7 @@ lamindb/dev/storage/file.py,sha256=jalzFQ8q110UUu_GGQBkU-g3M04h5g4LJ3nLjCzJ4pU,5
 lamindb/dev/storage/object.py,sha256=KGuOwwYuN2yCJxTXn9v0LanC0fjKwy_62P-WksHcf40,1140
 lamindb/setup/__init__.py,sha256=WaWKO-2XT67S65lSbS80hUojL-Mr_Wms9UxH6U54TsY,289
 lamindb/setup/dev/__init__.py,sha256=tBty426VGF2PGqqt2XuNU-WgvOrbOp1aZBDowjLuzgA,242
-lamindb-0.65.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-0.65.0.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-lamindb-0.65.0.dist-info/METADATA,sha256=OPOAcrY3znOQE4q664MuFvFEN30kOwunGfrup364TUE,3165
-lamindb-0.65.0.dist-info/RECORD,,
+lamindb-0.66.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-0.66.0.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lamindb-0.66.0.dist-info/METADATA,sha256=d9S5mPiFAzV1EhN7KB_VnugNCy7vdeivGqtxZsZPD60,3076
+lamindb-0.66.0.dist-info/RECORD,,