lamindb 1.4.0__tar.gz → 1.5.1__tar.gz

{lamindb-1.4.0 → lamindb-1.5.1}/.github/workflows/build.yml

@@ -106,8 +106,8 @@ jobs:
         if: ${{ matrix.group == 'tutorial' || matrix.group == 'guide' || matrix.group == 'biology' || matrix.group == 'faq'}}
         run: sudo apt-get -y install graphviz
 
-      - run: nox -s lint
-        if: ${{ matrix.group == 'tutorial' }}
+      # - run: nox -s lint
+      #   if: ${{ matrix.group == 'tutorial' }}
 
       - run: nox -s "install_ci(group='${{ matrix.group }}')"
 

{lamindb-1.4.0 → lamindb-1.5.1}/.pre-commit-config.yaml

@@ -59,5 +59,6 @@ repos:
               script-to-test-versioning.py|
               tests/storage/conftest.py|
               tests/curators/conftest.py|
-              tests/permissions/conftest.py
+              tests/permissions/conftest.py|
+              tests/curators/test_curators_examples.py
           )

{lamindb-1.4.0 → lamindb-1.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.4.0
+Version: 1.5.1
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14
@@ -9,9 +9,9 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: lamin_utils==0.13.11
-Requires-Dist: lamin_cli==1.3.0
-Requires-Dist: lamindb_setup[aws]==1.5.1
+Requires-Dist: lamin_utils==0.14.0
+Requires-Dist: lamin_cli==1.4.0
+Requires-Dist: lamindb_setup[aws]==1.5.2
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
 Requires-Dist: pandera
@@ -23,7 +23,7 @@ Requires-Dist: anndata>=0.8.0,<=0.11.4
 Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
-Requires-Dist: bionty>=1.3.0 ; extra == "bionty"
+Requires-Dist: bionty>=1.3.2 ; extra == "bionty"
 Requires-Dist: cellregistry ; extra == "cellregistry"
 Requires-Dist: clinicore ; extra == "clinicore"
 Requires-Dist: tomlkit ; extra == "dev"
@@ -40,7 +40,7 @@ Requires-Dist: faker-biology ; extra == "dev"
 Requires-Dist: django-schema-graph ; extra == "erdiagram"
 Requires-Dist: readfcs>=2.0.1 ; extra == "fcs"
 Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
-Requires-Dist: nbproject==0.10.6 ; extra == "jupyter"
+Requires-Dist: nbproject==0.11.1 ; extra == "jupyter"
 Requires-Dist: jupytext ; extra == "jupyter"
 Requires-Dist: nbconvert>=7.2.1 ; extra == "jupyter"
 Requires-Dist: mistune!=3.1.0 ; extra == "jupyter"

{lamindb-1.4.0 → lamindb-1.5.1}/docs/arrays.ipynb

@@ -40,7 +40,9 @@
     "- For a use case with TileDB, see: {doc}`docs:cellxgene`\n",
     "- For a use case with DuckDB, see: {doc}`docs:rxrx`\n",
     "\n",
-    "In this notebook, we show how to subset an `AnnData` and generic `HDF5` and `zarr` collections accessed in the cloud."
+    "In this notebook, we show how to subset an `AnnData` and generic `HDF5` and `zarr` collections accessed in the cloud.\n",
+    "\n",
+    "Let us create a remote instance for testing."
    ]
   },
   {
@@ -48,23 +50,35 @@
    "execution_count": null,
    "metadata": {
     "tags": [
-     "hide-output",
-     "hide-cell"
+     "hide-output"
     ]
    },
    "outputs": [],
    "source": [
     "!lamin login testuser1\n",
-    "!lamin init --storage s3://lamindb-ci/test-array-notebook --name test-array-notebook"
+    "!lamin init --storage s3://lamindb-ci/test-arrays"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Import lamindb and track this notebook."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
-    "import lamindb as ln"
+    "import lamindb as ln\n",
+    "\n",
+    "ln.track(\"hsRyWJggf2Ca\")"
    ]
   },
   {
@@ -84,8 +98,8 @@
    },
    "outputs": [],
    "source": [
-    "ln.Artifact(\"s3://lamindb-ci/lndb-storage/pbmc68k.h5ad\").save()\n",
-    "ln.Artifact(\"s3://lamindb-ci/lndb-storage/testfile.hdf5\").save()"
+    "ln.Artifact(\"s3://lamindb-ci/test-arrays/pbmc68k.h5ad\").save()\n",
+    "ln.Artifact(\"s3://lamindb-ci/test-arrays/testfile.hdf5\").save()"
    ]
   },
   {
@@ -164,7 +178,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.get(key=\"lndb-storage/pbmc68k.h5ad\")"
+    "artifact = ln.Artifact.get(key=\"pbmc68k.h5ad\")"
    ]
   },
   {
@@ -313,7 +327,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.get(key=\"lndb-storage/testfile.hdf5\")"
+    "artifact = ln.Artifact.get(key=\"testfile.hdf5\")"
    ]
   },
   {
@@ -486,6 +500,52 @@
     "backed.to_table().to_pandas()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "By default `Artifact.open()` and `Collection.open()` use `pyarrow` to lazily open dataframes. `polars` can be also used by passing `engine=\"polars\"`. Note also that `.open(engine=\"polars\")` returns a context manager with [LazyFrame](https://docs.pola.rs/api/python/stable/reference/lazyframe/index.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "with collection.open(engine=\"polars\") as lazy_df:\n",
+    "    display(lazy_df.collect().to_pandas())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Yet another way to open several parquet files as a single dataset is via calling `.open()` directly for a query set."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "backed = ln.Artifact.filter(suffix=\".parquet\").open()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "backed"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -497,13 +557,13 @@
    "outputs": [],
    "source": [
     "# clean up test instance\n",
-    "!lamin delete --force test-array-notebook"
+    "!lamin delete --force test-arrays"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "py312",
    "language": "python",
    "name": "python3"
   },
@@ -517,7 +577,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.12.8"
   },
   "nbproject": {
    "id": "YVUCtH4GfQOy",
@@ -528,11 +588,6 @@
    "user_id": "DzTjkKse",
    "user_name": "Test User1",
    "version": "0"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "ae1fefc8646a06dd2e75004cd934adda7c5727b046986a772e3b44b0ffba9754"
-   }
   }
  },
  "nbformat": 4,

{lamindb-1.4.0 → lamindb-1.5.1}/docs/bio-registries.ipynb

@@ -789,7 +789,7 @@
     "# now you can start using this source\n",
     "\n",
     "# import all genes from this source to your Gene registry\n",
-    "source = bt.Source.get(entity=\"bionty.Gene\", name=\"ensembl\", organism=\"rabbit\", \n",
+    "source = bt.Source.get(entity=\"bionty.Gene\", name=\"ensembl\", organism=\"rabbit\", version=\"release-103\")\n",
     "bt.Gene.import_source(source=source)\n",
     "```"
    ]