lamindb 1.9.0__tar.gz → 1.9.1__tar.gz

{lamindb-1.9.0 → lamindb-1.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.9.0
+Version: 1.9.1
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14
@@ -11,7 +11,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: lamin_utils==0.15.0
 Requires-Dist: lamin_cli==1.6.0
-Requires-Dist: lamindb_setup[aws]==1.8.2
+Requires-Dist: lamindb_setup[aws]==1.8.3
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
 Requires-Dist: pandera>=0.24.0

{lamindb-1.9.0 → lamindb-1.9.1}/docs/faq/keep-artifacts-local.ipynb

@@ -47,7 +47,7 @@
    },
    "outputs": [],
    "source": [
-    "# !pip install 'lamindb[jupyter]'\n",
+    "# pip install 'lamindb[jupyter]'\n",
     "import lamindb as ln\n",
     "\n",
     "ln.track(\"l9lFf83aPwRc0000\")"
@@ -132,6 +132,23 @@
     "ln.Storage.df()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can now set it as a local default storage location.\n",
+    "Next time you connect to the instance, this won't be necessary and the location will be automatically detected as the local default."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ln.settings.local_storage = \"./our_local_storage\""
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -336,7 +353,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "artifact.save(upload=True)"
@@ -352,7 +373,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "ln.settings.storage.root.view_tree()"
@@ -368,7 +393,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "assert artifact.path.exists()\n",
@@ -394,7 +423,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "filepath = ln.core.datasets.file_mini_csv()\n",
@@ -412,7 +445,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "ln.Artifact.df(include=\"storage__root\")"
@@ -435,7 +472,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "storage_record = ln.Storage.get(root__endswith=\"our_local_storage\")\n",
@@ -461,7 +502,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-ouput"
+    ]
+   },
    "outputs": [],
    "source": [
     "artifact.delete(permanent=True)\n",

{lamindb-1.9.0 → lamindb-1.9.1}/lamindb/__init__.py

@@ -108,7 +108,7 @@ Backwards compatibility.
 
 # ruff: noqa: I001
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.9.0"
+__version__ = "1.9.1"
 
 import warnings
 

{lamindb-1.9.0 → lamindb-1.9.1}/lamindb/curators/core.py

@@ -1236,6 +1236,9 @@ class CatVector:
         registry = self._field.field.model
         field_name = self._field.field.name
         non_validated_records: SQLRecordList[Any] = []  # type: ignore
+        type_record = None
+        if self._subtype_str != "" and "=" not in self._subtype_str:
+            type_record = registry.get(name=self._subtype_str)
         if df is not None and registry == Feature:
             nonval_columns = Feature.inspect(df.columns, mute=True).non_validated
             non_validated_records = Feature.from_df(df.loc[:, nonval_columns])
@@ -1252,6 +1255,9 @@ class CatVector:
                 init_kwargs = {field_name: value}
                 if registry == Feature:
                     init_kwargs["dtype"] = "cat" if dtype is None else dtype
+                if type_record is not None:
+                    # if subtype_str is set, we need to set the type for new records
+                    init_kwargs["type"] = type_record
                 non_validated_records.append(registry(**init_kwargs, **create_kwargs))
         if len(non_validated_records) > 0:
             ln_save(non_validated_records)

{lamindb-1.9.0 → lamindb-1.9.1}/lamindb/models/artifact.py

@@ -1382,7 +1382,10 @@ class Artifact(SQLRecord, IsVersioned, TracksRun, TracksUpdates):
         skip_check_exists = kwargs.pop("skip_check_exists", False)
         if "storage" in kwargs:
             storage = kwargs.pop("storage")
-        elif setup_settings.instance.keep_artifacts_local:
+        elif (
+            setup_settings.instance.keep_artifacts_local
+            and setup_settings.instance._local_storage is not None
+        ):
             storage = setup_settings.instance.local_storage.record
         else:
             storage = setup_settings.instance.storage.record

{lamindb-1.9.0 → lamindb-1.9.1}/lamindb/models/transform.py

@@ -317,10 +317,17 @@ class Transform(SQLRecord, IsVersioned):
 
     def delete(self) -> None:
         """Delete."""
+        from .project import TransformProject
+
         # query all runs and delete their artifacts
         runs = Run.filter(transform=self)
         for run in runs:
             delete_run_artifacts(run)
+        # CASCADE doesn't do the job below because run_id might be protected through run__transform=self
+        # hence, proactively delete the labels
+        qs = TransformProject.filter(transform=self)
+        if qs.exists():
+            qs.delete()
         # at this point, all artifacts have been taken care of
         # we can now leverage CASCADE delete
         super().delete()

{lamindb-1.9.0 → lamindb-1.9.1}/pyproject.toml

@@ -18,7 +18,7 @@ dependencies = [
     # Lamin PINNED packages
     "lamin_utils==0.15.0",
     "lamin_cli==1.6.0",
-    "lamindb_setup[aws]==1.8.2",
+    "lamindb_setup[aws]==1.8.3",
     # others
     "pyyaml",
     "pyarrow",

{lamindb-1.9.0 → lamindb-1.9.1}/tests/curators/test_curators_general.py

@@ -580,3 +580,35 @@ def test_hash_index_feature(df):
     schema_index.delete()
     schema.delete()
     ln.Feature.filter().delete()
+
+
+def test_add_new_from_subtype(df):
+    """Test that add_new_from works with subtypes."""
+    sample_type = ln.Record(name="SampleType", is_type=True).save()
+    ln.Record(name="Type A", type=sample_type).save()
+    schema = ln.Schema(
+        name="sample schema",
+        features=[
+            ln.Feature(name="sample_id", dtype="str").save(),
+            ln.Feature(name="sample_name", dtype="str").save(),
+            ln.Feature(name="sample_type", dtype="cat[Record[SampleType]]").save(),
+        ],
+        coerce_dtype=True,
+    ).save()
+
+    curator = ln.curators.DataFrameCurator(df, schema)
+    try:
+        curator.validate()
+    except ln.errors.ValidationError as error:
+        assert "1 term not validated in feature 'sample_type': 'Type B'" in str(error)
+
+    # add new from subtype
+    curator.cat.add_new_from("sample_type")
+    curator.validate()
+    assert sample_type.records.list("name") == ["Type A", "Type B"]
+
+    # clean up
+    schema.delete()
+    ln.Feature.filter().delete()
+    ln.Record.filter().update(type=None)
+    ln.Record.filter().delete()