lamindb 1.9.1__tar.gz → 1.10.1__tar.gz

{lamindb-1.9.1 → lamindb-1.10.1}/.github/workflows/build.yml

@@ -69,7 +69,7 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: |
-            ${{ github.ref == 'refs/heads/release' && '3.10' ||
+            ${{ github.ref == 'refs/heads/release' && '3.11' ||
                 '3.13'
                 }}
 

{lamindb-1.9.1 → lamindb-1.10.1}/.gitignore

@@ -66,6 +66,7 @@ run-tests
 test-django-validation/
 curate.tiledbsoma
 small_dataset.tiledbsoma
+registered_storage
 
 # General
 .DS_Store

{lamindb-1.9.1 → lamindb-1.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.9.1
+Version: 1.10.1
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14
@@ -10,8 +10,8 @@ Classifier: Programming Language :: Python :: 3.11
 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]==1.8.3
+Requires-Dist: lamin_cli==1.6.1
+Requires-Dist: lamindb_setup[aws]==1.9.1
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
 Requires-Dist: pandera>=0.24.0
@@ -19,7 +19,7 @@ Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: scipy<1.15.0
-Requires-Dist: anndata>=0.8.0,<=0.12.0
+Requires-Dist: anndata>=0.8.0,<=0.12.1
 Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary

{lamindb-1.9.1 → lamindb-1.10.1}/docs/arrays.ipynb

@@ -106,34 +106,32 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Note that it is also possible to register Hugging Face paths. For this `huggingface_hub` package should be installed."
+    "## AnnData"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We register a folder of `parquet` files as a single artifact."
+    "An `h5ad` artifact stored on s3:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "tags": [
-     "hide-output"
-    ]
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "ln.Artifact(\"hf://datasets/Koncopd/lamindb-test/sharded_parquet\").save()"
+    "artifact = ln.Artifact.get(key=\"pbmc68k.h5ad\")"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
+   "outputs": [],
    "source": [
-    "We also register a collection of individual `parquet` files."
+    "artifact.path"
    ]
   },
   {
@@ -146,48 +144,54 @@
    },
    "outputs": [],
    "source": [
-    "artifact_shard1 = ln.Artifact(\n",
-    "    \"hf://datasets/Koncopd/lamindb-test/sharded_parquet/louvain=0/947eee0b064440c9b9910ca2eb89e608-0.parquet\"\n",
-    ").save()\n",
-    "artifact_shard2 = ln.Artifact(\n",
-    "    \"hf://datasets/Koncopd/lamindb-test/sharded_parquet/louvain=1/947eee0b064440c9b9910ca2eb89e608-0.parquet\"\n",
-    ").save()\n",
-    "\n",
-    "ln.Collection(\n",
-    "    [artifact_shard1, artifact_shard2], key=\"sharded_parquet_collection\"\n",
-    ").save()"
+    "adata = artifact.open()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## AnnData"
+    "This object is an `AnnDataAccessor` object, an `AnnData` object backed in the cloud:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "adata"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "An `h5ad` artifact stored on s3:"
+    "Without subsetting, the `AnnDataAccessor` object references underlying lazy `h5` or `zarr` arrays:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.get(key=\"pbmc68k.h5ad\")"
+    "adata.X"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "artifact.path"
+    "You can subset it like a normal `AnnData` object:"
    ]
   },
   {
@@ -200,14 +204,18 @@
    },
    "outputs": [],
    "source": [
-    "adata = artifact.open()"
+    "obs_idx = adata.obs.cell_type.isin([\"Dendritic cells\", \"CD14+ Monocytes\"]) & (\n",
+    "    adata.obs.percent_mito <= 0.05\n",
+    ")\n",
+    "adata_subset = adata[obs_idx]\n",
+    "adata_subset"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This object is an `AnnDataAccessor` object, an `AnnData` object backed in the cloud:"
+    "Subsets load arrays into memory upon direct access:"
    ]
   },
   {
@@ -220,14 +228,14 @@
    },
    "outputs": [],
    "source": [
-    "adata"
+    "adata_subset.X"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Without subsetting, the `AnnDataAccessor` object references underlying lazy `h5` or `zarr` arrays:"
+    "To load the entire subset into memory as an actual `AnnData` object, use `to_memory()`:"
    ]
   },
   {
@@ -240,14 +248,34 @@
    },
    "outputs": [],
    "source": [
-    "adata.X"
+    "adata_subset.to_memory()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can subset it like a normal `AnnData` object:"
+    "## SpatialData"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "It is also possible to access `AnnData` objects inside `SpatialData` `tables`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "artifact = ln.Artifact.using(\"laminlabs/lamindata\").get(\n",
+    "    key=\"visium_aligned_guide_min.zarr\"\n",
+    ")\n",
+    "\n",
+    "access = artifact.open()"
    ]
   },
   {
@@ -260,18 +288,27 @@
    },
    "outputs": [],
    "source": [
-    "obs_idx = adata.obs.cell_type.isin([\"Dendritic cells\", \"CD14+ Monocytes\"]) & (\n",
-    "    adata.obs.percent_mito <= 0.05\n",
-    ")\n",
-    "adata_subset = adata[obs_idx]\n",
-    "adata_subset"
+    "access"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "access.tables"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Subsets load arrays into memory upon direct access:"
+    "This gives you the same `AnnDataAccessor` object as for a normal `AnnData`."
    ]
   },
   {
@@ -284,14 +321,16 @@
    },
    "outputs": [],
    "source": [
-    "adata_subset.X"
+    "table = access.tables[\"table\"]\n",
+    "\n",
+    "table"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To load the entire subset into memory as an actual `AnnData` object, use `to_memory()`:"
+    "You can subset it and read into memory as an actual `AnnData`:"
    ]
   },
   {
@@ -304,7 +343,18 @@
    },
    "outputs": [],
    "source": [
-    "adata_subset.to_memory()"
+    "table_subset = table[table.obs[\"clone\"] == \"diploid\"]\n",
+    "\n",
+    "table_subset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```python\n",
+    "adata = table_subset.to_memory()\n",
+    "```"
    ]
   },
   {
@@ -389,13 +439,20 @@
     "A dataframe stored as sharded `parquet`."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that it is also possible to register and access Hugging Face paths. For this `huggingface_hub` package should be installed."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.get(key=\"sharded_parquet\")"
+    "artifact = ln.Artifact.using(\"laminlabs/lamindata\").get(key=\"sharded_parquet\")"
    ]
   },
   {
@@ -466,13 +523,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "collection = ln.Collection.get(key=\"sharded_parquet_collection\")"
+    "collection = ln.Collection.using(\"laminlabs/lamindata\").get(\n",
+    "    key=\"sharded_parquet_collection\"\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "backed = collection.open()"
@@ -557,7 +620,7 @@
    "outputs": [],
    "source": [
     "# clean up test instance\n",
-    "!lamin delete --force test-arrays"
+    "ln.setup.delete(\"test-arrays\", force=True)"
    ]
   }
  ],