✨ Format all notebooks (#155)

Signed-off-by: zethson <[email protected]>
laminlabs · Sep 25, 2024 · b7a7cf3 · b7a7cf3
1 parent 772696b
commit b7a7cf3
Show file tree

Hide file tree

Showing 20 changed files with 105 additions and 76 deletions.
diff --git a/docs/analysis-flow.ipynb b/docs/analysis-flow.ipynb
@@ -233,14 +233,14 @@
    "outputs": [],
    "source": [
     "curate = ln.Curator.from_anndata(\n",
-    "    adata_subset.to_memory(), \n",
-    "    var_index=bt.Gene.ensembl_gene_id, \n",
+    "    adata_subset.to_memory(),\n",
+    "    var_index=bt.Gene.ensembl_gene_id,\n",
     "    categoricals={\n",
-    "        \"cell_type\": bt.CellType.name, \n",
-    "        \"disease\": bt.Disease.name, \n",
+    "        \"cell_type\": bt.CellType.name,\n",
+    "        \"disease\": bt.Disease.name,\n",
     "        \"tissue\": bt.Tissue.name,\n",
     "    },\n",
-    "    organism=\"human\"\n",
+    "    organism=\"human\",\n",
     ")\n",
     "\n",
     "curate.validate()"

diff --git a/docs/analysis-registries.ipynb b/docs/analysis-registries.ipynb
@@ -319,7 +319,7 @@
    "source": [
     "artifact.features._add_set_from_anndata(\n",
     "    var_field=bt.Gene.symbol,\n",
-    "    organism=\"human\", # optionally, globally set organism via bt.settings.organism = \"human\"\n",
+    "    organism=\"human\",  # optionally, globally set organism via bt.settings.organism = \"human\"\n",
     ")"
    ]
   },

diff --git a/docs/bulkrna.ipynb b/docs/bulkrna.ipynb
@@ -93,7 +93,9 @@
    "outputs": [],
    "source": [
     "# pretend we're running a bulk RNA-seq pipeline\n",
-    "ln.track(transform=ln.Transform(name=\"nf-core RNA-seq\", reference=\"https://nf-co.re/rnaseq\"))\n",
+    "ln.track(\n",
+    "    transform=ln.Transform(name=\"nf-core RNA-seq\", reference=\"https://nf-co.re/rnaseq\")\n",
+    ")\n",
     "# create a directory for its output\n",
     "Path(\"./test-bulkrna/output_dir\").mkdir(exist_ok=True)\n",
     "# get the count matrix\n",
@@ -364,10 +366,7 @@
    },
    "outputs": [],
    "source": [
-    "curated_file = ln.Artifact.from_anndata(\n",
-    "    adata,\n",
-    "    description=\"Curated bulk RNA counts\"\n",
-    ")"
+    "curated_file = ln.Artifact.from_anndata(adata, description=\"Curated bulk RNA counts\")"
    ]
   },
   {
@@ -407,7 +406,9 @@
    },
    "outputs": [],
    "source": [
-    "curated_file.features._add_set_from_anndata(var_field=bt.Gene.stable_id, organism=\"saccharomyces cerevisiae\")"
+    "curated_file.features._add_set_from_anndata(\n",
+    "    var_field=bt.Gene.stable_id, organism=\"saccharomyces cerevisiae\"\n",
+    ")"
    ]
   },
   {

diff --git a/docs/cell_marker.ipynb b/docs/cell_marker.ipynb
@@ -391,9 +391,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "source = bt.Source.get(\n",
-    "    name=\"cellmarker\", version=\"2.0\", organism=\"human\"\n",
-    ")\n",
+    "source = bt.Source.get(name=\"cellmarker\", version=\"2.0\", organism=\"human\")\n",
     "public = bt.CellMarker.public(source=source)\n",
     "public"
    ]

diff --git a/docs/celltypist.ipynb b/docs/celltypist.ipynb
@@ -92,6 +92,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
+    "\n",
     "description = \"CellTypist Pan Immune Atlas v2: basic cell type information\"\n",
     "celltypist_source_v2_url = \"https://github.com/Teichlab/celltypist_wiki/raw/main/atlases/Pan_Immune_CellTypist/v2/tables/Basic_celltype_information.xlsx\"\n",
     "\n",

diff --git a/docs/facs2.ipynb b/docs/facs2.ipynb
@@ -436,7 +436,9 @@
    "outputs": [],
    "source": [
     "collection_v2 = ln.Collection(\n",
-    "    [artifact, collection_v1.ordered_artifacts[0]], is_new_version_of=collection_v1, version=\"2\"\n",
+    "    [artifact, collection_v1.ordered_artifacts[0]],\n",
+    "    is_new_version_of=collection_v1,\n",
+    "    version=\"2\",\n",
     ")\n",
     "collection_v2.describe()"
    ]

diff --git a/docs/facs4.ipynb b/docs/facs4.ipynb
@@ -52,9 +52,7 @@
    },
    "outputs": [],
    "source": [
-    "collection = ln.Collection.get(\n",
-    "    name=\"My versioned cytometry collection\", version=\"2\"\n",
-    ")"
+    "collection = ln.Collection.get(name=\"My versioned cytometry collection\", version=\"2\")"
    ]
   },
   {

diff --git a/docs/gene.ipynb b/docs/gene.ipynb
@@ -483,9 +483,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "source = bt.Source.get(\n",
-    "    name=\"ensembl\", version=\"release-112\", organism=\"human\"\n",
-    ")\n",
+    "source = bt.Source.get(name=\"ensembl\", version=\"release-112\", organism=\"human\")\n",
     "public = bt.Gene.public(source=source)\n",
     "public"
    ]

diff --git a/docs/multimodal.ipynb b/docs/multimodal.ipynb
@@ -87,15 +87,15 @@
     "curate = ln.Curator.from_mudata(\n",
     "    mdata,\n",
     "    var_index={\n",
-    "        \"rna\": bt.Gene.symbol, # gene expression\n",
-    "        \"adt\": bt.CellMarker.name, # antibody derived tags reflecting surface proteins\n",
-    "        \"hto\": ln.Feature.name, # cell hashing\n",
-    "        \"gdo\": ln.Feature.name, # guide RNAs\n",
+    "        \"rna\": bt.Gene.symbol,  # gene expression\n",
+    "        \"adt\": bt.CellMarker.name,  # antibody derived tags reflecting surface proteins\n",
+    "        \"hto\": ln.Feature.name,  # cell hashing\n",
+    "        \"gdo\": ln.Feature.name,  # guide RNAs\n",
     "    },\n",
     "    categoricals={\n",
     "        \"perturbation\": ln.ULabel.name,  # shared categorical\n",
-    "        \"replicate\": ln.ULabel.name, # shared categorical\n",
-    "        \"hto:technique\": bt.ExperimentalFactor.name # note this is a modality specific categorical\n",
+    "        \"replicate\": ln.ULabel.name,  # shared categorical\n",
+    "        \"hto:technique\": bt.ExperimentalFactor.name,  # note this is a modality specific categorical\n",
     "    },\n",
     "    organism=\"human\",\n",
     ")"

diff --git a/docs/perturbation.ipynb b/docs/perturbation.ipynb
@@ -340,7 +340,11 @@
     "genetic_treatments = []\n",
     "for name, symbol, target_name in treatments:\n",
     "    treatment = wl.GeneticTreatment(system=\"CRISPR KO\", name=name).save()\n",
-    "    gene = bt.Gene.from_source(symbol=symbol, organism=organism).save() if symbol != \"lacz\" else bt.Gene(symbol=symbol, organism=organism).save()\n",
+    "    gene = (\n",
+    "        bt.Gene.from_source(symbol=symbol, organism=organism).save()\n",
+    "        if symbol != \"lacz\"\n",
+    "        else bt.Gene(symbol=symbol, organism=organism).save()\n",
+    "    )\n",
     "    target = wl.TreatmentTarget(name=target_name).save()\n",
     "    target.genes.add(gene)\n",
     "    treatment.targets.add(target)\n",
@@ -457,8 +461,8 @@
     "# We found a synonym for jq1. Let's use the correct name for the metadata\n",
     "drug_metadata = adata.obs[adata.obs[\"perturbation_type\"] == \"drug\"].copy()\n",
     "drug_metadata[\"perturbation\"] = drug_metadata[\"perturbation\"].cat.rename_categories(\n",
-    "        {\"jq1\": wl.Compound.search(\"jq1\").one().name}\n",
-    "    )"
+    "    {\"jq1\": wl.Compound.search(\"jq1\").one().name}\n",
+    ")"
    ]
   },
   {

diff --git a/docs/project-flow-scripts/hit-identification.ipynb b/docs/project-flow-scripts/hit-identification.ipynb
@@ -90,7 +90,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#ln.context.finish()"
+    "# ln.context.finish()"
    ]
   }
  ],

diff --git a/docs/project-flow-scripts/integrated-analysis.ipynb b/docs/project-flow-scripts/integrated-analysis.ipynb
@@ -107,7 +107,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#ln.context.finish()"
+    "# ln.context.finish()"
    ]
   }
  ],

diff --git a/docs/project-flow.ipynb b/docs/project-flow.ipynb
@@ -137,6 +137,7 @@
     "    )\n",
     "    output_file.save()\n",
     "\n",
+    "\n",
     "mock_upload_crispra_result_app()"
    ]
   },
@@ -170,7 +171,9 @@
     "from pathlib import Path\n",
     "\n",
     "cwd = Path.cwd()\n",
-    "nbproject_test.execute_notebooks(cwd / \"project-flow-scripts/hit-identification.ipynb\", write=True)"
+    "nbproject_test.execute_notebooks(\n",
+    "    cwd / \"project-flow-scripts/hit-identification.ipynb\", write=True\n",
+    ")"
    ]
   },
   {
@@ -316,7 +319,9 @@
    "source": [
     "# the following mimics the integrated analysis notebook\n",
     "# In reality, you would execute inside the notebook\n",
-    "nbproject_test.execute_notebooks(cwd / \"project-flow-scripts/integrated-analysis.ipynb\", write=True)"
+    "nbproject_test.execute_notebooks(\n",
+    "    cwd / \"project-flow-scripts/integrated-analysis.ipynb\", write=True\n",
+    ")"
    ]
   },
   {

diff --git a/docs/rdf-sparql.ipynb b/docs/rdf-sparql.ipynb
@@ -26,6 +26,7 @@
    "outputs": [],
    "source": [
     "import warnings\n",
+    "\n",
     "warnings.filterwarnings(\"ignore\")"
    ]
   },
@@ -102,10 +103,12 @@
     "namespace = URIRef(\"http://sparql-example.org/\")\n",
     "\n",
     "for _, row in diseases.iterrows():\n",
-    "    subject = URIRef(namespace + str(row['ontology_id']))\n",
+    "    subject = URIRef(namespace + str(row[\"ontology_id\"]))\n",
     "    rdf_graph.add((subject, RDF.type, URIRef(namespace + \"Disease\")))\n",
-    "    rdf_graph.add((subject, URIRef(namespace + \"name\"), Literal(row['name'])))\n",
-    "    rdf_graph.add((subject, URIRef(namespace + \"description\"), Literal(row['description'])))\n",
+    "    rdf_graph.add((subject, URIRef(namespace + \"name\"), Literal(row[\"name\"])))\n",
+    "    rdf_graph.add(\n",
+    "        (subject, URIRef(namespace + \"description\"), Literal(row[\"description\"]))\n",
+    "    )\n",
     "\n",
     "rdf_graph"
    ]

diff --git a/docs/scrna-tiledbsoma.ipynb b/docs/scrna-tiledbsoma.ipynb
@@ -62,9 +62,7 @@
    },
    "outputs": [],
    "source": [
-    "collection = ln.Collection.get(\n",
-    "    name=\"My versioned scRNA-seq collection\", version=\"2\"\n",
-    ")\n",
+    "collection = ln.Collection.get(name=\"My versioned scRNA-seq collection\", version=\"2\")\n",
     "collection.describe()"
    ]
   },
@@ -96,9 +94,15 @@
     "adatas = [artifact.load() for artifact in collection.ordered_artifacts]\n",
     "\n",
     "# compute the intersection of columns for these objects\n",
-    "var_columns = reduce(pd.Index.intersection, [adata.var.columns for adata in adatas])  # this only affects metadata columns of features (say, gene annotations)\n",
-    "var_raw_columns = reduce(pd.Index.intersection, [adata.raw.var.columns for adata in adatas])\n",
-    "obs_columns = reduce(pd.Index.intersection, [adata.obs.columns for adata in adatas])  # this actually subsets features (dataset dimensions)"
+    "var_columns = reduce(\n",
+    "    pd.Index.intersection, [adata.var.columns for adata in adatas]\n",
+    ")  # this only affects metadata columns of features (say, gene annotations)\n",
+    "var_raw_columns = reduce(\n",
+    "    pd.Index.intersection, [adata.raw.var.columns for adata in adatas]\n",
+    ")\n",
+    "obs_columns = reduce(\n",
+    "    pd.Index.intersection, [adata.obs.columns for adata in adatas]\n",
+    ")  # this actually subsets features (dataset dimensions)"
    ]
   },
   {
@@ -120,17 +124,19 @@
    "source": [
     "for i, adata in enumerate(adatas):\n",
     "    del adata.obsp  # not supported by tiledbsoma\n",
-    "    del adata.uns   # not supported by tiledbsoma\n",
-    "    \n",
+    "    del adata.uns  # not supported by tiledbsoma\n",
+    "\n",
     "    adata.obs = adata.obs.filter(obs_columns)  # filter columns to intersection\n",
-    "    adata.obs[\"obs_id\"] = adata.obs.index  # prepare a column for tiledbsoma to use as an index\n",
+    "    adata.obs[\"obs_id\"] = (\n",
+    "        adata.obs.index\n",
+    "    )  # prepare a column for tiledbsoma to use as an index\n",
     "    adata.obs[\"dataset\"] = i\n",
     "    adata.obs.index.name = None\n",
-    "    \n",
+    "\n",
     "    adata.var = adata.var.filter(var_columns)  # filter columns to intersection\n",
     "    adata.var[\"var_id\"] = adata.var.index\n",
     "    adata.var.index.name = None\n",
-    "    \n",
+    "\n",
     "    drop_raw_var_columns = adata.raw.var.columns.difference(var_raw_columns)\n",
     "    adata.raw.var.drop(columns=drop_raw_var_columns, inplace=True)\n",
     "    adata.raw.var[\"var_id\"] = adata.raw.var.index\n",
@@ -167,7 +173,7 @@
     "    measurement_name=\"RNA\",\n",
     "    obs_id_name=\"obs_id\",\n",
     "    var_id_name=\"var_id\",\n",
-    "    append_obsm_varm=True\n",
+    "    append_obsm_varm=True,\n",
     ")"
    ]
   },
@@ -211,12 +217,12 @@
     "with soma_artifact.open() as soma_store:\n",
     "    obs = soma_store[\"obs\"]\n",
     "    var = soma_store[\"ms\"][\"RNA\"][\"var\"]\n",
-    "    \n",
+    "\n",
     "    obs_columns_store = obs.schema.names\n",
     "    var_columns_store = var.schema.names\n",
-    "    \n",
+    "\n",
     "    obs_store_df = obs.read().concat().to_pandas()\n",
-    "    \n",
+    "\n",
     "    display(obs_store_df)"
    ]
   },
@@ -280,10 +286,14 @@
     "\n",
     "adata.obs[\"dataset\"] = obs_store_df[\"dataset\"].max()\n",
     "\n",
-    "obs_columns_same = [obs_col for obs_col in adata.obs.columns if obs_col in obs_columns_store]\n",
+    "obs_columns_same = [\n",
+    "    obs_col for obs_col in adata.obs.columns if obs_col in obs_columns_store\n",
+    "]\n",
     "adata.obs = adata.obs[obs_columns_same]\n",
     "\n",
-    "var_columns_same = [var_col for var_col in adata.var.columns if var_col in var_columns_store]\n",
+    "var_columns_same = [\n",
+    "    var_col for var_col in adata.var.columns if var_col in var_columns_store\n",
+    "]\n",
     "adata.var = adata.var[var_columns_same]\n",
     "\n",
     "adata.write_h5ad(\"adata_to_append.h5ad\")"
@@ -311,7 +321,7 @@
     "    revises=soma_artifact,\n",
     "    measurement_name=\"RNA\",\n",
     "    obs_id_name=\"obs_id\",\n",
-    "    var_id_name=\"var_id\"\n",
+    "    var_id_name=\"var_id\",\n",
     ")"
    ]
   },
@@ -373,7 +383,7 @@
     "        measurement_name=\"RNA\",\n",
     "        collection_name=\"obsm\",\n",
     "        matrix_name=\"pca\",\n",
-    "        matrix_data=pca_array\n",
+    "        matrix_data=pca_array,\n",
     "    )"
    ]
   },

diff --git a/docs/scrna.ipynb b/docs/scrna.ipynb
@@ -57,7 +57,7 @@
    },
    "outputs": [],
    "source": [
-    "# !pip install 'lamindb[jupyter,aws,bionty]' \n",
+    "# !pip install 'lamindb[jupyter,aws,bionty]'\n",
     "!lamin init --storage ./test-scrna --schema bionty"
    ]
   },
@@ -124,14 +124,14 @@
    "outputs": [],
    "source": [
     "curate = ln.Curator.from_anndata(\n",
-    "    adata, \n",
-    "    var_index=bt.Gene.ensembl_gene_id, \n",
+    "    adata,\n",
+    "    var_index=bt.Gene.ensembl_gene_id,\n",
     "    categoricals={\n",
-    "        adata.obs.donor.name: ln.ULabel.name, \n",
-    "        adata.obs.tissue.name: bt.Tissue.name, \n",
-    "        adata.obs.cell_type.name: bt.CellType.name, \n",
-    "        adata.obs.assay.name: bt.ExperimentalFactor.name\n",
-    "    }, \n",
+    "        adata.obs.donor.name: ln.ULabel.name,\n",
+    "        adata.obs.tissue.name: bt.Tissue.name,\n",
+    "        adata.obs.cell_type.name: bt.CellType.name,\n",
+    "        adata.obs.assay.name: bt.ExperimentalFactor.name,\n",
+    "    },\n",
     "    organism=\"human\",\n",
     ")"
    ]