lamindb 0.77.2__tar.gz → 0.77.3__tar.gz

{lamindb-0.77.2 → lamindb-0.77.3}/.github/workflows/build.yml

@@ -29,23 +29,28 @@ jobs:
         with:
           submodules: recursive
           fetch-depth: 0
+
       - uses: actions/setup-python@v5
         if: ${{ matrix.group == 'storage' }}
         with:
           python-version: "3.9"
+
       - uses: actions/setup-python@v5
         if: ${{ matrix.group == 'unit-storage' }}
         with:
           python-version: "3.11" # there are problems with installation time with python 3.12
+
       - uses: actions/setup-python@v5
         if: ${{ matrix.group != 'storage' && matrix.group != 'unit-storage'}}
         with:
           python-version: "3.12"
+
       - name: cache pre-commit
         uses: actions/cache@v4
         with:
           path: ~/.cache/pre-commit
           key: pre-commit-${{ runner.os }}-${{ hashFiles('.pre-commit-config.yaml') }}
+
       - name: cache postgres
         if: ${{ matrix.group == 'faq' || matrix.group == 'unit-core' || matrix.group == 'unit-storage' }}
         id: cache-postgres
@@ -63,9 +68,11 @@ jobs:
       - name: install postgres
         if: ${{ matrix.group == 'faq' }}
         run: sudo apt-get install libpq-dev
+
       - name: install graphviz
         if: ${{ matrix.group == 'tutorial' || matrix.group == 'guide' || matrix.group == 'biology' }}
         run: sudo apt-get -y install graphviz
+
       - run: nox -s lint
         if: ${{ matrix.group == 'tutorial' }} # choose a fast-running a group
       - run: nox -s "install_ci(group='${{ matrix.group }}')"
@@ -75,12 +82,14 @@ jobs:
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           aws-region: us-east-1
       - run: nox -s "build(group='${{ matrix.group }}')"
+
       - name: upload coverage
         uses: actions/upload-artifact@v4
         with:
           name: coverage--${{ matrix.group }}
           path: .coverage
           include-hidden-files: true
+
       - name: upload docs
         if: ${{ matrix.group == 'tutorial' || matrix.group == 'guide' || matrix.group == 'biology' || matrix.group == 'faq' || matrix.group == 'storage' }}
         uses: actions/upload-artifact@v4
@@ -96,6 +105,7 @@ jobs:
         with:
           submodules: recursive
           fetch-depth: 0
+
       - name: checkout lndocs
         uses: actions/checkout@v4
         with:
@@ -103,11 +113,13 @@ jobs:
           ssh-key: ${{ secrets.READ_LNDOCS }}
           path: lndocs
           ref: main
+
       - uses: aws-actions/configure-aws-credentials@v4
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           aws-region: us-east-1
+
       - uses: actions/setup-python@v5
         with:
           python-version: "3.10" # use 3.10 because 3.11+ give issues (ablog lacks 3.12 support)
@@ -124,6 +136,7 @@ jobs:
         env:
           NETLIFY_AUTH_TOKEN: ${{ secrets.NETLIFY_AUTH_TOKEN }}
           NETLIFY_SITE_ID: ${{ secrets.NETLIFY_SITE_ID }}
+
       - uses: peter-evans/repository-dispatch@v2
         if: ${{ github.event_name == 'push' }}
         with:
@@ -143,6 +156,7 @@ jobs:
           python -m pip install -U uv
           uv pip install --system coverage[toml]
           uv pip install --system --no-deps .
+
       - uses: actions/download-artifact@v4
       - name: run coverage
         run: |

{lamindb-0.77.2 → lamindb-0.77.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.77.2
+Version: 0.77.3
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.9,<3.13
@@ -10,12 +10,13 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: lnschema_core==0.77.1
-Requires-Dist: lamin_utils==0.13.9
+Requires-Dist: lamin_utils==0.13.10
 Requires-Dist: lamin_cli==0.22.0
-Requires-Dist: lamindb_setup==0.81.2
+Requires-Dist: lamindb_setup==0.81.3
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
+Requires-Dist: pandas>=2.0.0
 Requires-Dist: anndata>=0.8.0,<=0.11.1
 Requires-Dist: fsspec
 Requires-Dist: graphviz

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/delete.ipynb

@@ -40,7 +40,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.from_df(pd.DataFrame({\"a\": [1, 2], \"b\": [3, 4]}), description=\"mydf\")\n",
+    "artifact = ln.Artifact.from_df(\n",
+    "    pd.DataFrame({\"a\": [1, 2], \"b\": [3, 4]}), description=\"mydf\"\n",
+    ")\n",
     "artifact.save()"
    ]
   },

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/keep-artifacts-local.ipynb

@@ -253,7 +253,9 @@
    "source": [
     "assert artifact.path.exists()\n",
     "assert not local_path.exists()\n",
-    "assert artifact.path.as_posix().startswith(ln.setup.settings.instance.storage.root.as_posix())"
+    "assert artifact.path.as_posix().startswith(\n",
+    "    ln.setup.settings.instance.storage.root.as_posix()\n",
+    ")"
    ]
   },
   {
@@ -364,7 +366,9 @@
    },
    "outputs": [],
    "source": [
-    "my_existing_file = ln.Artifact(\"./my_storage_local/output.bam\", description=\"my existing file\").save()\n",
+    "my_existing_file = ln.Artifact(\n",
+    "    \"./my_storage_local/output.bam\", description=\"my existing file\"\n",
+    ").save()\n",
     "ln.UPath(\"my_storage_local/\").view_tree()"
    ]
   },

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/key.ipynb

@@ -834,7 +834,8 @@
    "outputs": [],
    "source": [
     "ds = ln.Collection(\n",
-    "    [artifact_from_raw, artifact_from_preprocessed], name=\"raw_and_processed_collection_2\"\n",
+    "    [artifact_from_raw, artifact_from_preprocessed],\n",
+    "    name=\"raw_and_processed_collection_2\",\n",
     ")\n",
     "ds.save()"
    ]

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/search.ipynb

@@ -20,6 +20,7 @@
    "outputs": [],
    "source": [
     "from laminci.db import setup_local_test_postgres\n",
+    "\n",
     "pgurl = setup_local_test_postgres()\n",
     "!lamin init --name benchmark_search --db {pgurl} --schema bionty --storage ./benchmark_search"
    ]
@@ -42,13 +43,30 @@
     "import lamindb as ln\n",
     "import bionty as bt\n",
     "\n",
-    "SEARCH_QUERIES_EXACT = (\"t cell\", \"stem cell\", \"b cell\", \"regulatory B cell\", \"Be2 cell\", \"adipocyte\")\n",
+    "SEARCH_QUERIES_EXACT = (\n",
+    "    \"t cell\",\n",
+    "    \"stem cell\",\n",
+    "    \"b cell\",\n",
+    "    \"regulatory B cell\",\n",
+    "    \"Be2 cell\",\n",
+    "    \"adipocyte\",\n",
+    ")\n",
     "SEARCH_QUERIES_CONTAINS = (\"t cel\", \"t-cel\", \"neural\", \"kidney\", \"kidne\")\n",
     "TOP_N = 20\n",
     "\n",
     "bt.CellType.import_source()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a95bcef6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ln.ULabel(name=\"cat[*_*]\").save()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "799b528e",
@@ -72,7 +90,7 @@
     "    print(\"Query:\", query)\n",
     "    qs = bt.CellType.search(query)\n",
     "    display(qs.df())\n",
-    "    \n",
+    "\n",
     "    assert query.lower() == qs[0].name.lower()"
    ]
   },
@@ -97,6 +115,34 @@
     "    assert query in top_record.name.lower() or query in top_record.synonyms.lower()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "00427176",
+   "metadata": {},
+   "source": [
+    "Check escaping of special characters."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cea360c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assert len(ln.ULabel.search(\"cat[\")) == 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "04f1e84a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assert len(ln.ULabel.search(\"*_*\")) == 1"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f4e41c9b",

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/symbol-mapping.ipynb

@@ -64,9 +64,25 @@
     "# create example AnnData object with gene symbols\n",
     "rng = np.random.default_rng(42)\n",
     "X = rng.integers(0, 100, size=(5, 10))\n",
-    "var = pd.DataFrame(index=pd.Index(['BRCA1', 'TP53', 'EGFR', 'KRAS', 'PTEN', 'MYC', 'VEGFA', 'IL6', 'TNF', 'GAPDH'], name=\"symbol\"))\n",
+    "var = pd.DataFrame(\n",
+    "    index=pd.Index(\n",
+    "        [\n",
+    "            \"BRCA1\",\n",
+    "            \"TP53\",\n",
+    "            \"EGFR\",\n",
+    "            \"KRAS\",\n",
+    "            \"PTEN\",\n",
+    "            \"MYC\",\n",
+    "            \"VEGFA\",\n",
+    "            \"IL6\",\n",
+    "            \"TNF\",\n",
+    "            \"GAPDH\",\n",
+    "        ],\n",
+    "        name=\"symbol\",\n",
+    "    )\n",
+    ")\n",
     "adata = ad.AnnData(X=X, var=var)\n",
-    "adata.var\n"
+    "adata.var"
    ]
   },
   {
@@ -85,10 +101,12 @@
     "    field=bt.Gene.symbol,\n",
     "    return_field=bt.Gene.ensembl_gene_id,\n",
     "    return_mapper=True,\n",
-    "    organism=\"human\"\n",
+    "    organism=\"human\",\n",
+    ")\n",
+    "adata.var[\"ensembl_id\"] = adata.var.index.map(\n",
+    "    lambda gene_id: gene_mapper.get(gene_id, gene_id)\n",
     ")\n",
-    "adata.var[\"ensembl_id\"] = adata.var.index.map(gene_mapper)\n",
-    "adata.var\n"
+    "adata.var"
    ]
   },
   {
@@ -102,9 +120,20 @@
    "outputs": [],
    "source": [
     "standardized_genes = bt.Gene.from_values(\n",
-    "    ['ENSG00000141510', 'ENSG00000133703', 'ENSG00000111640', 'ENSG00000171862', 'ENSG00000204490', 'ENSG00000112715', 'ENSG00000146648', 'ENSG00000136997', 'ENSG00000012048', 'ENSG00000136244'],\n",
+    "    [\n",
+    "        \"ENSG00000141510\",\n",
+    "        \"ENSG00000133703\",\n",
+    "        \"ENSG00000111640\",\n",
+    "        \"ENSG00000171862\",\n",
+    "        \"ENSG00000204490\",\n",
+    "        \"ENSG00000112715\",\n",
+    "        \"ENSG00000146648\",\n",
+    "        \"ENSG00000136997\",\n",
+    "        \"ENSG00000012048\",\n",
+    "        \"ENSG00000136244\",\n",
+    "    ],\n",
     "    field=bt.Gene.ensembl_gene_id,\n",
-    "    organism=\"human\"\n",
+    "    organism=\"human\",\n",
     ")\n",
     "ln.save(standardized_genes)"
    ]

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/track-run-inputs.ipynb

@@ -72,7 +72,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.track(\"Rx2s9aPTMQLY0000\")\n"
+    "ln.track(\"Rx2s9aPTMQLY0000\")"
    ]
   },
   {

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/validate-fields.ipynb

@@ -8,7 +8,7 @@
     "\n",
     "[Django field validation](https://docs.djangoproject.com/en/5.1/ref/validators/) are enabled for models that inherit the `ValidateFields` class.\n",
     "\n",
-    "For instance: [`findrefs.Reference`](https://docs.lamin.ai/findrefs.reference)"
+    "For instance: [`ourprojects.Reference`](https://docs.lamin.ai/ourprojects.reference)"
    ]
   },
   {
@@ -17,8 +17,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# !pip install lamindb, findrefs\n",
-    "!lamin init --storage ./test-django-validation --schema findrefs"
+    "# !pip install lamindb[ourprojects]\n",
+    "!lamin init --storage ./test-django-validation --schema ourprojects"
    ]
   },
   {
@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import findrefs as fr\n",
+    "import ourprojects as pj\n",
     "from lnschema_core.validation import FieldValidationError"
    ]
   },
@@ -38,7 +38,7 @@
    "outputs": [],
    "source": [
     "try:\n",
-    "    fr.Reference(name=\"my ref\", doi=\"abc.ef\", url='myurl.com')\n",
+    "    pj.Reference(name=\"my ref\", doi=\"abc.ef\", url=\"myurl.com\")\n",
     "except FieldValidationError as e:\n",
     "    print(e)"
    ]

{lamindb-0.77.2 → lamindb-0.77.3}/docs/faq/visibility.ipynb

@@ -38,7 +38,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact = ln.Artifact.from_df(pd.DataFrame({\"a\": [1, 2], \"b\": [3, 4]}), description=\"mydf\")\n",
+    "artifact = ln.Artifact.from_df(\n",
+    "    pd.DataFrame({\"a\": [1, 2], \"b\": [3, 4]}), description=\"mydf\"\n",
+    ")\n",
     "artifact.save()"
    ]
   },

{lamindb-0.77.2 → lamindb-0.77.3}/docs/registries.ipynb

@@ -620,9 +620,49 @@
    },
    "outputs": [],
    "source": [
+    "ln.Artifact.filter().order_by(\"created_at\").df()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec39c7ff",
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "# reverse ordering\n",
     "ln.Artifact.filter().order_by(\"-created_at\").df()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e9830119",
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "ln.Artifact.filter().order_by(\"key\").df()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a705b47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# reverse ordering\n",
+    "ln.Artifact.filter().order_by(\"-key\").df()"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",

{lamindb-0.77.2 → lamindb-0.77.3}/docs/storage/prepare-transfer-local-to-cloud.ipynb

@@ -34,7 +34,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.setup.init(storage=\"./test-transfer-to-cloud\", schema=\"bionty,wetlab,findrefs\")\n",
+    "ln.setup.init(storage=\"./test-transfer-to-cloud\", schema=\"bionty,wetlab,ourprojects\")\n",
     "ln.setup.settings.auto_connect = False"
    ]
   },

{lamindb-0.77.2 → lamindb-0.77.3}/lamindb/__init__.py

@@ -43,7 +43,7 @@ Modules and settings.
 """
 
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "0.77.2"
+__version__ = "0.77.3"
 
 import os as _os
 

{lamindb-0.77.2 → lamindb-0.77.3}/lamindb/_can_curate.py

@@ -10,7 +10,7 @@ from lamin_utils import colors, logger
 from lamindb_setup.core._docs import doc_args
 from lnschema_core import CanCurate, Record
 
-from ._from_values import _has_organism_field, _print_values, get_or_create_records
+from ._from_values import _format_values, _has_organism_field, get_or_create_records
 from ._record import _queryset, get_name_field
 from ._utils import attach_func_to_class_method
 from .core.exceptions import ValidationError
@@ -168,7 +168,7 @@ def _inspect(
             bionty_mapper = bionty_result.synonyms_mapper
             hint = False
             if len(bionty_validated) > 0 and not mute:
-                print_values = _print_values(bionty_validated)
+                print_values = _format_values(bionty_validated)
                 s = "" if len(bionty_validated) == 1 else "s"
                 labels = colors.yellow(f"{len(bionty_validated)} {model_name} term{s}")
                 logger.print(
@@ -178,7 +178,7 @@ def _inspect(
                 hint = True
 
             if len(bionty_mapper) > 0 and not mute:
-                print_values = _print_values(list(bionty_mapper.keys()))
+                print_values = _format_values(list(bionty_mapper.keys()))
                 s = "" if len(bionty_mapper) == 1 else "s"
                 labels = colors.yellow(f"{len(bionty_mapper)} {model_name} term{s}")
                 logger.print(
@@ -199,7 +199,7 @@ def _inspect(
             logger.warning("no Bionty source found, skipping Bionty validation")
 
     if len(nonval) > 0 and not mute:
-        print_values = _print_values(list(nonval))
+        print_values = _format_values(list(nonval))
         s = "" if len(nonval) == 1 else "s"
         labels = colors.red(f"{len(nonval)} term{s}")
         logger.print(f"   couldn't validate {labels}: {colors.red(print_values)}")
@@ -383,6 +383,8 @@ def _standardize(
         organism = (
             organism_record.name if organism_record is not None else organism_record
         )
+    else:
+        organism = None
 
     # only perform synonym mapping if field is the name field
     if hasattr(registry, "_name_field") and field != registry._name_field: