lamindb 1.2a2__tar.gz → 1.3.0__tar.gz

{lamindb-1.2a2 → lamindb-1.3.0}/.github/workflows/build.yml

@@ -68,8 +68,8 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: |
-            ${{ matrix.group == 'storage' && '3.10' ||
-                '3.12'
+            ${{ github.ref == 'refs/heads/release' && '3.10' ||
+                '3.13'
                 }}
 
       - name: cache pre-commit
@@ -163,15 +163,23 @@ jobs:
       - run: nox -s "install_ci(group='docs')"
       - uses: actions/download-artifact@v4
       - run: nox -s docs
-      - uses: nwtgck/actions-netlify@v1.2
-        with:
-          publish-dir: "_build/html"
-          production-deploy: ${{ github.event_name == 'push' }}
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          enable-commit-comment: false
-        env:
-          NETLIFY_AUTH_TOKEN: ${{ secrets.NETLIFY_AUTH_TOKEN }}
-          NETLIFY_SITE_ID: ${{ secrets.NETLIFY_SITE_ID }}
+      - run: rm -r ./_build/html/.doctrees # do not want to deploy with cloudflare
+      - uses: cloudflare/wrangler-action@v3
+        id: cloudflare
+        with:
+          apiToken: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          accountId: 472bdad691b4483dea759eadb37110bd
+          command: pages deploy "_build/html" --project-name=lamindb
+          gitHubToken: ${{ secrets.GITHUB_TOKEN }}
+      - uses: edumserrano/find-create-or-update-comment@v2
+        if: github.event_name == 'pull_request'
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          body-includes: "Deployment URL"
+          comment-author: "github-actions[bot]"
+          body: |
+            Deployment URL: ${{ steps.cloudflare.outputs.deployment-url }}
+          edit-mode: replace
 
       - uses: peter-evans/repository-dispatch@v2
         if: ${{ github.event_name == 'push' }}
@@ -187,7 +195,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: "3.13"
       - run: |
           python -m pip install -U uv
           uv pip install --system coverage[toml]

{lamindb-1.2a2 → lamindb-1.3.0}/.gitignore

@@ -215,3 +215,6 @@ _build
 
 # VSCode
 .vscode
+
+# cxg
+!lamindb/curators/_cellxgene_schemas/schema_versions.csv

{lamindb-1.2a2 → lamindb-1.3.0}/PKG-INFO

@@ -1,16 +1,17 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.2a2
+Version: 1.3.0
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
-Requires-Python: >=3.10,<3.13
+Requires-Python: >=3.10,<3.14
 Description-Content-Type: text/markdown
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: lamin_utils==0.13.10
-Requires-Dist: lamin_cli==1.1.0
-Requires-Dist: lamindb_setup[aws]==1.3.0
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: lamin_utils==0.13.11
+Requires-Dist: lamin_cli==1.2.0
+Requires-Dist: lamindb_setup[aws]==1.3.2
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
 Requires-Dist: pandera
@@ -39,7 +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==0.10.5 ; extra == "jupyter"
+Requires-Dist: nbproject==0.10.6 ; extra == "jupyter"
 Requires-Dist: jupytext ; extra == "jupyter"
 Requires-Dist: nbconvert>=7.2.1 ; extra == "jupyter"
 Requires-Dist: mistune!=3.1.0 ; extra == "jupyter"

{lamindb-1.2a2 → lamindb-1.3.0}/docs/api.md

@@ -11,15 +11,6 @@ cli
 lamindb
 ```
 
-```{toctree}
-:maxdepth: 1
-:caption: R & REST
-:hidden:
-
-laminr
-rest
-```
-
 ```{toctree}
 :maxdepth: 1
 :caption: Modules
@@ -28,6 +19,4 @@ rest
 bionty
 wetlab
 clinicore
-cellregistry
-omop
 ```

lamindb-1.2a2/docs/curate-df.ipynb → lamindb-1.3.0/docs/curate.ipynb

@@ -5,13 +5,15 @@
    "id": "0",
    "metadata": {},
    "source": [
-    "# Curate DataFrames and AnnDatas\n",
+    "# Curate datasets\n",
     "\n",
     "Curating a dataset with LaminDB means three things:\n",
     "\n",
     "1. Validate that the dataset matches a desired schema\n",
     "2. In case the dataset doesn't validate, standardize it, e.g., by fixing typos or mapping synonyms\n",
-    "3. Annotate the dataset by linking it against metadata entities so that it becomes queryable"
+    "3. Annotate the dataset by linking it against metadata entities so that it becomes queryable\n",
+    "\n",
+    "In this guide we'll curate common data structures. Here is a [guide](/faq/curate-any) for the underlying low-level API."
    ]
   },
   {
@@ -61,23 +63,8 @@
     "import pandas as pd\n",
     "\n",
     "\n",
-    "df = pd.DataFrame(\n",
-    "    {\n",
-    "        \"perturbation\": pd.Categorical([\"DMSO\", \"IFNG\", \"DMSO\"]),\n",
-    "        \"temperature\": [37.2, 36.3, 38.2],\n",
-    "        \"cell_type\": pd.Categorical(\n",
-    "            [\n",
-    "                \"cerebral pyramidal neuron\",\n",
-    "                \"astrocytic glia\",\n",
-    "                \"oligodendrocyte\",\n",
-    "            ]\n",
-    "        ),\n",
-    "        \"assay_ontology_id\": pd.Categorical(\n",
-    "            [\"EFO:0008913\", \"EFO:0008913\", \"EFO:0008913\"]\n",
-    "        ),\n",
-    "        \"donor\": [\"D0001\", \"D0002\", None],\n",
-    "    },\n",
-    "    index=[\"obs1\", \"obs2\", \"obs3\"],\n",
+    "df = ln.core.datasets.small_dataset1(\n",
+    "    with_cell_type_synonym=True, with_cell_type_typo=True\n",
     ")\n",
     "df"
    ]
@@ -87,7 +74,7 @@
    "id": "5",
    "metadata": {},
    "source": [
-    "Define a schema to validate this dataset."
+    "Define a schema to define the minimal columns we expect in such a dataset."
    ]
   },
   {
@@ -102,15 +89,15 @@
    "outputs": [],
    "source": [
     "schema = ln.Schema(\n",
-    "    name=\"My example schema\",\n",
+    "    name=\"My immuno schema\",\n",
     "    features=[\n",
     "        ln.Feature(name=\"perturbation\", dtype=ln.ULabel).save(),\n",
-    "        ln.Feature(name=\"temperature\", dtype=float).save(),\n",
-    "        ln.Feature(name=\"cell_type\", dtype=bt.CellType).save(),\n",
-    "        ln.Feature(\n",
-    "            name=\"assay_ontology_id\", dtype=bt.ExperimentalFactor.ontology_id\n",
-    "        ).save(),\n",
+    "        ln.Feature(name=\"cell_type_by_model\", dtype=bt.CellType).save(),\n",
+    "        ln.Feature(name=\"cell_type_by_expert\", dtype=bt.CellType).save(),\n",
+    "        ln.Feature(name=\"assay_oid\", dtype=bt.ExperimentalFactor.ontology_id).save(),\n",
     "        ln.Feature(name=\"donor\", dtype=str, nullable=True).save(),\n",
+    "        ln.Feature(name=\"concentration\", dtype=str).save(),\n",
+    "        ln.Feature(name=\"treatment_time_h\", dtype=float, coerce_dtype=True).save(),\n",
     "    ],\n",
     ").save()\n",
     "# display the associated features as a dataframe\n",
@@ -160,8 +147,8 @@
    "source": [
     "try:\n",
     "    curator.validate()\n",
-    "except ln.errors.ValidationError as error:\n",
-    "    print(error)"
+    "except ln.errors.ValidationError:\n",
+    "    pass"
    ]
   },
   {
@@ -193,10 +180,14 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "13",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
-    "curator.cat.standardize(\"cell_type\")"
+    "curator.cat.standardize(\"cell_type_by_expert\")"
    ]
   },
   {
@@ -251,8 +242,8 @@
    "outputs": [],
    "source": [
     "# here is an example for the \"cell_type\" column\n",
-    "cell_types = lookup[\"cell_type\"]\n",
-    "cell_types.cerebral_cortex_pyramidal_neuron"
+    "cell_types = lookup[\"cell_type_by_expert\"]\n",
+    "cell_types.cd8_positive_alpha_beta_t_cell"
    ]
   },
   {
@@ -266,9 +257,9 @@
    },
    "outputs": [],
    "source": [
-    "# fix the cell type\n",
-    "df.cell_type = df.cell_type.cat.rename_categories(\n",
-    "    {\"cerebral pyramidal neuron\": cell_types.cerebral_cortex_pyramidal_neuron.name}\n",
+    "# fix the cell type name\n",
+    "df[\"cell_type_by_expert\"] = df[\"cell_type_by_expert\"].cat.rename_categories(\n",
+    "    {\"CD8-pos alpha-beta T cell\": cell_types.cd8_positive_alpha_beta_t_cell.name}\n",
     ")"
    ]
   },
@@ -418,7 +409,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "29",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "anndata_schema.slots"
@@ -517,7 +512,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "38",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "artifact.features.slots"
@@ -558,7 +557,7 @@
    "id": "42",
    "metadata": {},
    "source": [
-    "If you need more control, you can access the underlying `\"var\"` and `\"obs\"` `DataFrameCurator` objects directly."
+    "If you need more control, you can access `DataFrameCurator` objects for the `\"var\"` and `\"obs\"` slots, respectively."
    ]
   },
   {
@@ -572,20 +571,23 @@
    },
    "outputs": [],
    "source": [
-    "curator.slots[\"var\"]\n",
-    "curator.slots[\"obs\"]"
+    "curator.slots"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "44",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "# revert the previous cell type standardization\n",
-    "df[\"cell_type\"] = df[\"cell_type\"].cat.rename_categories(\n",
-    "    {\"astrocyte\": \"astrocytic glia\"}\n",
+    "df[\"cell_type_by_expert\"] = df[\"cell_type_by_expert\"].cat.rename_categories(\n",
+    "    {\"B cell\": \"B-cell\"}\n",
     ")\n",
     "# an AnnData where a cell type matches a synonym\n",
     "adata_with_synonym = ad.AnnData(X=adata_validated.X, var=adata_validated.var, obs=df)\n",
@@ -596,31 +598,43 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "45",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "curator = ln.curators.AnnDataCurator(adata_with_synonym, anndata_schema)\n",
     "try:\n",
     "    curator.validate()\n",
-    "except ln.errors.ValidationError as error:\n",
-    "    print(error)"
+    "except ln.errors.ValidationError:\n",
+    "    pass"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "46",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
-    "curator.slots[\"obs\"].cat.standardize(\"cell_type\")"
+    "curator.slots[\"obs\"].cat.standardize(\"cell_type_by_expert\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "47",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "curator.validate()"
@@ -648,7 +662,7 @@
     "\n",
     "By following these steps, you can ensure your data is standardized and well-curated.\n",
     "\n",
-    "If you have datasets that aren't DataFrame-like or AnnData-like, read: {doc}`curate-any`."
+    "If you have other data structures, read: {doc}`/faq/curate-any`."
    ]
   },
   {