lamindb 1.5.3__tar.gz → 1.6a2__tar.gz

{lamindb-1.5.3 → lamindb-1.6a2}/.github/workflows/doc-changes.yml

@@ -4,6 +4,7 @@ on:
   pull_request_target:
     branches:
       - main
+      - release
     types:
       - closed
 

{lamindb-1.5.3 → lamindb-1.6a2}/.gitignore

@@ -62,6 +62,8 @@ test.ipynb
 test2.ipynb
 run-tests
 test-django-validation/
+curate.tiledbsoma
+small_dataset.tiledbsoma
 
 # General
 .DS_Store

{lamindb-1.5.3 → lamindb-1.6a2}/.pre-commit-config.yaml

@@ -60,5 +60,7 @@ repos:
               tests/storage/conftest.py|
               tests/curators/conftest.py|
               tests/permissions/conftest.py|
+              tests/writelog/conftest.py|
+              tests/writelog_sqlite/conftest.py|
               tests/curators/test_curators_examples.py
           )

{lamindb-1.5.3 → lamindb-1.6a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.5.3
+Version: 1.6a2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14
@@ -10,21 +10,20 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: lamin_utils==0.14.0
-Requires-Dist: lamin_cli==1.4.0
-Requires-Dist: lamindb_setup[aws]==1.5.2
+Requires-Dist: lamin_cli==1.4.1
+Requires-Dist: lamindb_setup[aws]==1.6.0
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
-Requires-Dist: pandera
+Requires-Dist: pandera>=0.24.0
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
-Requires-Dist: scipy<1.15.0
 Requires-Dist: pandas>=2.0.0
+Requires-Dist: scipy<1.15.0
 Requires-Dist: anndata>=0.8.0,<=0.11.4
 Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
-Requires-Dist: bionty>=1.3.2 ; extra == "bionty"
-Requires-Dist: cellregistry ; extra == "cellregistry"
+Requires-Dist: bionty>=1.4a1 ; extra == "bionty"
 Requires-Dist: clinicore ; extra == "clinicore"
 Requires-Dist: tomlkit ; extra == "dev"
 Requires-Dist: line_profiler ; extra == "dev"
@@ -37,7 +36,6 @@ Requires-Dist: pytest-cov ; extra == "dev"
 Requires-Dist: mudata ; extra == "dev"
 Requires-Dist: nbproject_test>=0.6.0 ; extra == "dev"
 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==0.11.1 ; extra == "jupyter"
@@ -45,15 +43,13 @@ Requires-Dist: jupytext ; extra == "jupyter"
 Requires-Dist: nbconvert>=7.2.1 ; extra == "jupyter"
 Requires-Dist: mistune!=3.1.0 ; extra == "jupyter"
 Requires-Dist: omop ; extra == "omop"
-Requires-Dist: wetlab ; extra == "wetlab"
+Requires-Dist: wetlab>=1.3a1 ; extra == "wetlab"
 Requires-Dist: numcodecs<0.16.0 ; extra == "zarr"
 Requires-Dist: zarr>=2.16.0,<3.0.0a0 ; extra == "zarr"
 Project-URL: Home, https://github.com/laminlabs/lamindb
 Provides-Extra: bionty
-Provides-Extra: cellregistry
 Provides-Extra: clinicore
 Provides-Extra: dev
-Provides-Extra: erdiagram
 Provides-Extra: fcs
 Provides-Extra: gcp
 Provides-Extra: jupyter

{lamindb-1.5.3 → lamindb-1.6a2}/docs/curate.ipynb

@@ -830,14 +830,29 @@
    "metadata": {},
    "source": [
     "```{eval-rst}\n",
-    ".. literalinclude:: scripts/curate-mudata.py\n",
+    ".. literalinclude:: scripts/curate_mudata.py\n",
     "   :language: python\n",
+    "   :caption: curate_mudata.py\n",
     "```"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,
    "id": "72",
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "!python scripts/curate_mudata.py"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73",
    "metadata": {},
    "source": [
     "## SpatialData"
@@ -845,7 +860,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "73",
+   "id": "74",
    "metadata": {},
    "source": [
     "```{eval-rst}\n",
@@ -858,7 +873,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "74",
+   "id": "75",
    "metadata": {
     "tags": [
      "hide-output"
@@ -871,7 +886,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "75",
+   "id": "76",
    "metadata": {},
    "source": [
     "```{eval-rst}\n",
@@ -884,7 +899,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "76",
+   "id": "77",
    "metadata": {
     "tags": [
      "hide-output"
@@ -897,7 +912,41 @@
   },
   {
    "cell_type": "markdown",
-   "id": "77",
+   "id": "78",
+   "metadata": {},
+   "source": [
+    "## TiledbsomaExperiment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79",
+   "metadata": {},
+   "source": [
+    "```{eval-rst}\n",
+    ".. literalinclude:: scripts/curate_soma_experiment.py\n",
+    "   :language: python\n",
+    "   :caption: curate_soma_experiment.py\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "80",
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "!python scripts/curate_soma_experiment.py"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81",
    "metadata": {},
    "source": [
     "## Other data structures"
@@ -905,7 +954,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "78",
+   "id": "82",
    "metadata": {},
    "source": [
     "If you have other data structures, read: {doc}`/faq/curate-any`."
@@ -914,7 +963,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "79",
+   "id": "83",
    "metadata": {
     "tags": [
      "hide-cell"
@@ -923,13 +972,13 @@
    "outputs": [],
    "source": [
     "!rm -rf ./test-curate\n",
+    "!rm -rf ./small_dataset.tiledbsoma\n",
     "!lamin delete --force test-curate"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "py312",
    "language": "python",
    "name": "python3"
   },
@@ -943,7 +992,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.8"
+   "version": "3.11.11"
   },
   "nbproject": {
    "id": "WOK3vP0bNGLx",

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/curate-any.ipynb

@@ -25,7 +25,7 @@
     "LaminDB makes it easy to validate categorical variables based on registries that inherit from {class}`~lamindb.models.CanCurate`.\n",
     "\n",
     "{class}`~lamindb.models.CanCurate` methods validate against the registries in your LaminDB instance.\n",
-    "In {doc}`/bio-registries`, you'll see how to extend standard validation to validation against _public references_ using a `ReferenceTable` ontology object: `public = Record.public()`.\n",
+    "In {doc}`/bio-registries`, you'll see how to extend standard validation to validation against _public references_ using a `PubliOntology` object, e.g., via `public_genes = bt.Gene.public()`.\n",
     "By default, {meth}`~lamindb.models.CanCurate.from_values` considers a match in a public reference a validated value for any {mod}`bionty` entity.\n",
     "\n",
     ":::"
@@ -63,13 +63,18 @@
     "import zarr\n",
     "import numpy as np\n",
     "\n",
-    "data = zarr.create(\n",
-    "    (3,),\n",
-    "    dtype=[(\"temperature\", \"f8\"), (\"knockout_gene\", \"U15\"), (\"disease\", \"U16\")],\n",
-    "    store=\"data.zarr\",\n",
+    "data = zarr.open_group(store=\"data.zarr\", mode=\"a\")\n",
+    "\n",
+    "data.create_dataset(name=\"temperature\", shape=(3,), dtype=\"float32\")\n",
+    "data.create_dataset(name=\"knockout_gene\", shape=(3,), dtype=str)\n",
+    "data.create_dataset(name=\"disease\", shape=(3,), dtype=str)\n",
+    "\n",
+    "data[\"knockout_gene\"][:] = np.array(\n",
+    "    [\"ENSG00000139618\", \"ENSG00000141510\", \"ENSG00000133703\"]\n",
     ")\n",
-    "data[\"knockout_gene\"] = [\"ENSG00000139618\", \"ENSG00000141510\", \"ENSG00000133703\"]\n",
-    "data[\"disease\"] = np.random.default_rng().choice([\"MONDO:0004975\", \"MONDO:0004980\"], 3)"
+    "data[\"disease\"][:] = np.random.default_rng().choice(\n",
+    "    [\"MONDO:0004975\", \"MONDO:0004980\"], 3\n",
+    ")"
    ]
   },
   {
@@ -79,6 +84,22 @@
     "## Validate and standardize vectors"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Read the `disease` array from the zarr group into memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease = data[\"disease\"][:]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -97,7 +118,7 @@
    },
    "outputs": [],
    "source": [
-    "bt.Disease.validate(data[\"disease\"], field=bt.Disease.ontology_id)"
+    "bt.Disease.validate(disease, field=bt.Disease.ontology_id)"
    ]
   },
   {
@@ -121,7 +142,7 @@
    },
    "outputs": [],
    "source": [
-    "bt.Disease.inspect(data[\"disease\"], field=bt.Disease.ontology_id)"
+    "bt.Disease.inspect(disease, field=bt.Disease.ontology_id)"
    ]
   },
   {
@@ -141,7 +162,7 @@
    },
    "outputs": [],
    "source": [
-    "diseases = bt.Disease.from_values(data[\"disease\"], field=bt.Disease.ontology_id).save()"
+    "diseases = bt.Disease.from_values(disease, field=bt.Disease.ontology_id).save()"
    ]
   },
   {
@@ -166,7 +187,9 @@
     "    field=ln.ULabel.name,\n",
     "    create=True,  # create non-validated labels\n",
     ").save()\n",
-    "genes = bt.Gene.from_values(data[\"knockout_gene\"], field=bt.Gene.ensembl_gene_id).save()"
+    "genes = bt.Gene.from_values(\n",
+    "    data[\"knockout_gene\"][:], field=bt.Gene.ensembl_gene_id\n",
+    ").save()"
    ]
   },
   {
@@ -241,7 +264,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "py312",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -255,7 +278,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.8"
+   "version": "3.10.16"
   }
  },
  "nbformat": 4,

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/delete.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# How to delete records?\n",
     "\n",
-    "Records can be deleted with `record.delete()`, which will **permanently remove** them from your database.\n",
+    "SQLRecords can be deleted with `record.delete()`, which will **permanently remove** them from your database.\n",
     "\n",
     "When it comes to **records of `Artifact` and `Collection`**, they are **\"moved into trash\"** when you first call `record.delete()`.\n",
     "\n",

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/idempotency.ipynb

@@ -17,9 +17,9 @@
    "source": [
     "LaminDB's operations are idempotent in the sense defined here, which allows you to re-run code without duplicating data.\n",
     "\n",
-    ":::{admonition} Records with `name` field\n",
+    ":::{admonition} SQLRecords with `name` field\n",
     "\n",
-    "When you instantiate {class}`~lamindb.models.Record` with a name, in case a name has an _exact match_ in a registry, the constructor returns it instead of creating a new record. In case records with _similar names_ exist, you'll see them in a table: you can then decide whether you want to save the new record or pick an existing record.\n",
+    "When you instantiate {class}`~lamindb.models.SQLRecord` with a name, in case a name has an _exact match_ in a registry, the constructor returns it instead of creating a new record. In case records with _similar names_ exist, you'll see them in a table: you can then decide whether you want to save the new record or pick an existing record.\n",
     "\n",
     "If you set {attr}`~lamindb.core.subsettings.CreationSettings.search_names` to `False`, you bypass these checks.\n",
     "\n",
@@ -69,7 +69,7 @@
    "id": "4",
    "metadata": {},
    "source": [
-    "## Records with name field"
+    "## SQLRecords with name field"
    ]
   },
   {
@@ -390,7 +390,7 @@
    },
    "outputs": [],
    "source": [
-    "ln.context.track(new_run=True)\n",
+    "ln.track(new_run=True)\n",
     "artifact3 = ln.Artifact(filepath, key=\"my_fcs_file.fcs\")\n",
     "assert artifact3.id == artifact2.id\n",
     "assert artifact3.run == artifact2.run != ln.context.run  # run is not updated\n",

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/search.ipynb

@@ -30,7 +30,7 @@
    "id": "2",
    "metadata": {},
    "source": [
-    "Here we show how to perform text search on `Record` and evaluate some search queries for the {class}`bionty.CellType` ontology."
+    "Here we show how to perform text search on `SQLRecord` and evaluate some search queries for the {class}`bionty.CellType` ontology."
    ]
   },
   {

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/track-run-inputs.ipynb

@@ -53,7 +53,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.context.track(transform=ln.Transform(key=\"Dummpy pipeline\"))\n",
+    "ln.track(transform=ln.Transform(key=\"Dummpy pipeline\"))\n",
     "ln.Artifact(ln.core.datasets.file_jpg_paradisi05(), description=\"My image\").save()\n",
     "ln.Artifact(ln.core.datasets.file_mini_csv(), description=\"My csv\").save()"
    ]

{lamindb-1.5.3 → lamindb-1.6a2}/docs/faq/visibility.ipynb

@@ -11,7 +11,7 @@
     "- 0: \"archive\", excluded from query & search by default\n",
     "- -1: \"trash\", excluded from the query results, set with `.delete()`\n",
     "\n",
-    "These values are represented in the database via a private integer field `_branch_code` that also models the branches involved in merge requests.\n",
+    "These values are represented in the database via a private integer field `branch_id` that also models the branches involved in merge requests.\n",
     "\n",
     "However, `.filter()` also accepts the `visibility` keyword, see below."
    ]
@@ -23,7 +23,7 @@
    "outputs": [],
    "source": [
     "# !pip install lamindb\n",
-    "!lamin init --storage test-_branch_code"
+    "!lamin init --storage test-branch_id"
    ]
   },
   {
@@ -52,7 +52,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "A new artifact has default visibility 1 via `_branch_code`:"
+    "A new artifact has default visibility 1 via `branch_id`:"
    ]
   },
   {
@@ -61,14 +61,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "assert artifact._branch_code == 1"
+    "assert artifact.branch_id == 1"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "When you delete an artifact, its `_branch_code` is set to -1 (\"trash\"):"
+    "When you delete an artifact, its `branch_id` is set to -1 (\"trash\"):"
    ]
   },
   {
@@ -86,7 +86,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "assert artifact._branch_code == -1"
+    "assert artifact.branch_id == -1"
    ]
   },
   {
@@ -143,7 +143,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "assert artifact._branch_code == 1"
+    "assert artifact.branch_id == 1"
    ]
   },
   {
@@ -177,7 +177,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!lamin delete --force test-_branch_code"
+    "!lamin delete --force test-branch_id"
    ]
   }
  ],