lamindb 0.76.14__tar.gz → 0.76.16__tar.gz

{lamindb-0.76.14 → lamindb-0.76.16}/.github/workflows/build.yml

@@ -32,11 +32,15 @@ jobs:
       - uses: actions/setup-python@v5
         if: ${{ matrix.group == 'storage' }}
         with:
-          python-version: "3.9" # run just one job with a different python version
+          python-version: "3.9"
       - uses: actions/setup-python@v5
-        if: ${{ matrix.group != 'storage' }}
+        if: ${{ matrix.group == 'unit-storage' }}
         with:
-          python-version: "3.11"
+          python-version: "3.11" # there are problems with installation time with python 3.12
+      - uses: actions/setup-python@v5
+        if: ${{ matrix.group != 'storage' && matrix.group != 'unit-storage'}}
+        with:
+          python-version: "3.12"
       - name: cache pre-commit
         uses: actions/cache@v4
         with:
@@ -106,7 +110,7 @@ jobs:
           aws-region: us-east-1
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.10" # use 3.10, 3.8 and 3.11 give issues
+          python-version: "3.10" # use 3.10 because 3.11+ give issues (ablog lacks 3.12 support)
       - run: pip install "laminci@git+https://x-access-token:${{ secrets.LAMIN_BUILD_DOCS }}@github.com/laminlabs/laminci"
       - run: nox -s "install_ci(group='docs')"
       - uses: actions/download-artifact@v4
@@ -134,7 +138,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
       - run: |
           python -m pip install -U uv
           uv pip install --system coverage[toml]

{lamindb-0.76.14 → lamindb-0.76.16}/PKG-INFO

@@ -1,29 +1,30 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.76.14
+Version: 0.76.16
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
-Requires-Python: >=3.9
+Requires-Python: >=3.9,<3.13
 Description-Content-Type: text/markdown
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Dist: lnschema_core==0.76.0
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: lnschema_core==0.76.2
 Requires-Dist: lamin_utils==0.13.7
-Requires-Dist: lamin_cli==0.20.1
+Requires-Dist: lamin_cli==0.21.2
 Requires-Dist: lamindb_setup
 Requires-Dist: rapidfuzz
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
-Requires-Dist: anndata>=0.8.0,<=0.10.9
-Requires-Dist: scipy<1.13.0rc1
+Requires-Dist: anndata>=0.8.0,<=0.11.1
 Requires-Dist: fsspec
-Requires-Dist: pandas
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
 Requires-Dist: lamindb_setup[aws] ; extra == "aws"
-Requires-Dist: bionty==0.52.0 ; extra == "bionty"
+Requires-Dist: bionty==0.52.1 ; extra == "bionty"
+Requires-Dist: cellregistry ; extra == "cellregistry"
+Requires-Dist: clinicore ; extra == "clinicore"
 Requires-Dist: line_profiler ; extra == "dev"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"
@@ -35,20 +36,30 @@ Requires-Dist: mudata ; extra == "dev"
 Requires-Dist: nbproject_test>=0.5.1 ; extra == "dev"
 Requires-Dist: faker-biology ; extra == "dev"
 Requires-Dist: django-schema-graph ; extra == "erdiagram"
-Requires-Dist: readfcs>=1.1.8 ; extra == "fcs"
+Requires-Dist: readfcs>=1.1.9 ; extra == "fcs"
+Requires-Dist: findrefs ; extra == "findrefs"
 Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
 Requires-Dist: nbproject==0.10.5 ; extra == "jupyter"
 Requires-Dist: jupytext ; extra == "jupyter"
 Requires-Dist: nbconvert ; extra == "jupyter"
+Requires-Dist: omop ; extra == "omop"
+Requires-Dist: ourprojects ; extra == "ourprojects"
+Requires-Dist: wetlab ; extra == "wetlab"
 Requires-Dist: zarr>=2.16.0 ; extra == "zarr"
 Project-URL: Home, https://github.com/laminlabs/lamindb
 Provides-Extra: aws
 Provides-Extra: bionty
+Provides-Extra: cellregistry
+Provides-Extra: clinicore
 Provides-Extra: dev
 Provides-Extra: erdiagram
 Provides-Extra: fcs
+Provides-Extra: findrefs
 Provides-Extra: gcp
 Provides-Extra: jupyter
+Provides-Extra: omop
+Provides-Extra: ourprojects
+Provides-Extra: wetlab
 Provides-Extra: zarr
 
 [![Stars](https://img.shields.io/github/stars/laminlabs/lamindb?logo=GitHub&color=yellow)](https://github.com/laminlabs/lamindb)

{lamindb-0.76.14 → lamindb-0.76.16}/docs/arrays.ipynb

@@ -8,7 +8,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -16,7 +15,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -35,7 +33,9 @@
     "\n",
     "Because the artifact was validated, querying the `DataFrame` is guaranteed to succeed!\n",
     "\n",
-    "Such within-collection queries are also possible for cloud-backed collections using DuckDB, TileDB, zarr, HDF5, parquet, and other storage backends.\n",
+    "Such within-collection queries are also possible for cloud-backed collections using [DuckDB](https://duckdb.org),\n",
+    "[TileDB](https://tiledb.com), [zarr](https://zarr.readthedocs.io/en/stable), [HDF5](https://docs.h5py.org/en/stable),\n",
+    "[parquet](https://parquet.apache.org), and other storage backends.\n",
     "\n",
     "- For a use case with TileDB, see: {doc}`docs:cellxgene`\n",
     "- For a use case with DuckDB, see: {doc}`docs:rxrx`\n",
@@ -61,7 +61,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "import lamindb as ln"
@@ -87,7 +91,9 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "tags": []
+    "tags": [
+     "hide-output"
+    ]
    },
    "outputs": [],
    "source": [
@@ -96,7 +102,26 @@
    ]
   },
   {
-   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that it is also possible to register Hugging Face paths. For this `huggingface_hub` package should be installed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "ln.Artifact(\"hf://datasets/Koncopd/lamindb-test/sharded_parquet\").save()"
+   ]
+  },
+  {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -131,14 +156,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "adata = artifact.open()"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -148,14 +176,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "adata"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -165,14 +196,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "adata.X"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -182,7 +216,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "obs_idx = adata.obs.cell_type.isin([\"Dendritic cells\", \"CD14+ Monocytes\"]) & (\n",
@@ -193,7 +231,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -203,14 +240,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "adata_subset.X"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -220,14 +260,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "adata_subset.to_memory()"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -235,7 +278,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -252,7 +294,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -262,14 +303,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "backed = artifact.open()"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -294,6 +338,84 @@
     "backed.storage"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Parquet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "A dataframe stored as sharded `parquet`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "artifact = ln.Artifact.get(key=\"sharded_parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "artifact.path.view_tree()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "backed = artifact.open()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This returns a [pyarrow dataset](https://arrow.apache.org/docs/python/dataset.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "backed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "backed.head(5).to_pandas()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -325,7 +447,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.9.17"
   },
   "nbproject": {
    "id": "YVUCtH4GfQOy",

{lamindb-0.76.14 → lamindb-0.76.16}/docs/bio-registries.ipynb

@@ -8,7 +8,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -16,7 +15,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -73,7 +71,7 @@
    "outputs": [],
    "source": [
     "# populate the database with the public ontology\n",
-    "bt.CellType.import_from_source()"
+    "bt.CellType.import_source()"
    ]
   },
   {
@@ -104,8 +102,8 @@
    "outputs": [],
    "source": [
     "# similarly, let's populate the Gene registry with human and mouse genes\n",
-    "bt.Gene.import_from_source(organism=\"human\")\n",
-    "bt.Gene.import_from_source(organism=\"mouse\")"
+    "bt.Gene.import_source(organism=\"human\")\n",
+    "bt.Gene.import_source(organism=\"mouse\")"
    ]
   },
   {
@@ -215,6 +213,39 @@
     "gdt_cell.children.df()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "It is also possible to recursively query parents or children, getting direct parents (children), their parents, and so forth."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "gdt_cell.query_parents().df()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "gdt_cell.query_children().df()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -238,7 +269,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -246,7 +276,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -293,7 +322,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -322,7 +350,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -356,7 +383,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -446,7 +472,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -463,7 +488,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -598,7 +622,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -606,7 +629,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -627,7 +649,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -743,7 +764,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "py310",
+   "display_name": "lamindb",
    "language": "python",
    "name": "python3"
   },
@@ -757,7 +778,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.7"
   },
   "nbproject": {
    "id": "s7F7PezA1HdQ",

{lamindb-0.76.14 → lamindb-0.76.16}/docs/curate-df.ipynb

@@ -74,7 +74,7 @@
     "        \"temperature\": [37.2, 36.3, 38.2],\n",
     "        \"cell_type\": [\"cerebral pyramidal neuron\", \"astrocyte\", \"oligodendrocyte\"],\n",
     "        \"assay_ontology_id\": [\"EFO:0008913\", \"EFO:0008913\", \"EFO:0008913\"],\n",
-    "        \"donor\": [\"D0001\", \"D0002\", \"DOOO3\"]\n",
+    "        \"donor\": [\"D0001\", \"D0002\", \"D0003\"]\n",
     "    },\n",
     "    index = [\"obs1\", \"obs2\", \"obs3\"]\n",
     ")\n",
@@ -163,7 +163,8 @@
    },
    "outputs": [],
    "source": [
-    "# use a lookup object to get the correct spelling of categories from a public ontology via `public=True`\n",
+    "# to check the correct spelling of categories, pass `public=True` to get a lookup object from public ontologies\n",
+    "# use `lookup = curate.lookup()` to get a lookup object of existing records in your instance\n",
     "lookup = curate.lookup(public=True)\n",
     "lookup"
    ]
@@ -179,7 +180,7 @@
    },
    "outputs": [],
    "source": [
-    "# here is an example for the cell_type column\n",
+    "# here is an example for the \"cell_type\" column\n",
     "cell_types = lookup[\"cell_type\"]\n",
     "cell_types.cerebral_cortex_pyramidal_neuron"
    ]
@@ -204,7 +205,7 @@
    "id": "1dc1028a",
    "metadata": {},
    "source": [
-    "For donor, we want to add the new donoers: 'D0001', 'D0002', 'DOOO3'"
+    "For donor, we want to add the new donors: \"D0001\", \"D0002\", \"D0003\""
    ]
   },
   {
@@ -245,7 +246,7 @@
    "source": [
     "## Validate an AnnData\n",
     "\n",
-    "Here we addtionally specify which `var_index` to validate against."
+    "Here we additionally specify which `var_index` to validate against."
    ]
   },
   {
@@ -268,7 +269,7 @@
     "        \"ENSG00000198851\": [7, 8, 9], \n",
     "        \"ENSG00000010610\": [10, 11, 12], \n",
     "        \"ENSG00000153563\": [13, 14, 15],\n",
-    "        \"corrupted\": [16, 17, 18]\n",
+    "        \"ENSGcorrupted\": [16, 17, 18]\n",
     "    }, \n",
     "    index=df.index\n",
     ")\n",
@@ -414,7 +415,7 @@
    "id": "0fa20942",
    "metadata": {},
    "source": [
-    "Validated features and labels are linked to the artifact:"
+    "Saved artifact has been annotated with validated features and labels:"
    ]
   },
   {