[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

use_cases/custom_dl/tiledb.ipynb

@@ -140,14 +140,18 @@
    "source": [
     "min_nnz\n",
     "experiment_name = \"mus_musculus\"\n",
-    "#obs_val_filt = ('is_primary_data == True and tissue_general in [\"spleen\", \"kidney\"] '\n",
+    "# obs_val_filt = ('is_primary_data == True and tissue_general in [\"spleen\", \"kidney\"] '\n",
     "#            'and nnz >= 500')\n",
-    "obs_val_filt = ('is_primary_data == True and tissue_general in [\"kidney\"] '\n",
-    "            'and nnz >= 500 and donor_id not in [\"pooled\"]')\n",
-    "#obs_val_filt = ('is_primary_data == True and tissue_general in [\"liver\", \"heart\"] '\n",
+    "obs_val_filt = (\n",
+    "    'is_primary_data == True and tissue_general in [\"kidney\"] '\n",
+    "    'and nnz >= 500 and donor_id not in [\"pooled\"]'\n",
+    ")\n",
+    "# obs_val_filt = ('is_primary_data == True and tissue_general in [\"liver\", \"heart\"] '\n",
     "#            'and nnz >= 500')\n",
-    "obs_val_filt = ('is_primary_data == True and cell_type in [\"B cell\",\"T cell\", \"macrophage\",\"fibroblast\",\"endothelial\",\"myeloid\",\"lymphocyte\",\"natural killer cell\",\"CD4-positive, alpha-beta T cell\",\"CD8-positive, alpha-beta T cell\"] '\n",
-    "            'and donor_id not in [\"pooled\"] and dataset_id in [\"98e5ea9f-16d6-47ec-a529-686e76515e39\",\"58b01044-c5e5-4b0f-8a2d-6ebf951e01ff\",\"48b37086-25f7-4ecd-be66-f5bb378e3aea\"] and tissue_general not in [\"vasculature\"] and nnz >= 300')"
+    "obs_val_filt = (\n",
+    "    'is_primary_data == True and cell_type in [\"B cell\",\"T cell\", \"macrophage\",\"fibroblast\",\"endothelial\",\"myeloid\",\"lymphocyte\",\"natural killer cell\",\"CD4-positive, alpha-beta T cell\",\"CD8-positive, alpha-beta T cell\"] '\n",
+    "    'and donor_id not in [\"pooled\"] and dataset_id in [\"98e5ea9f-16d6-47ec-a529-686e76515e39\",\"58b01044-c5e5-4b0f-8a2d-6ebf951e01ff\",\"48b37086-25f7-4ecd-be66-f5bb378e3aea\"] and tissue_general not in [\"vasculature\"] and nnz >= 300'\n",
+    ")"
    ]
   },
   {
@@ -163,7 +167,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "batch_keys = [\"dataset_id\",\"donor_id\",\"assay\",\"tissue_general\"]"
+    "batch_keys = [\"dataset_id\", \"donor_id\", \"assay\", \"tissue_general\"]"
    ]
   },
   {
@@ -248,7 +252,7 @@
     "    dataloader_kwargs={\"num_workers\": 64, \"persistent_workers\": False},\n",
     "    accelerator=\"gpu\",\n",
     "    device=1,\n",
-    "    return_sparse_X=False\n",
+    "    return_sparse_X=False,\n",
     ")\n",
     "print(datamodule.n_obs, datamodule.n_vars, datamodule.n_batch)"
    ]
@@ -300,8 +304,7 @@
    "source": [
     "# creating the dataloader for trainset\n",
     "training_dataloader = (\n",
-    "    datamodule.on_before_batch_transfer(batch, None)\n",
-    "    for batch in datamodule.train_dataloader()\n",
+    "    datamodule.on_before_batch_transfer(batch, None) for batch in datamodule.train_dataloader()\n",
     ")"
    ]
   },
@@ -358,10 +361,11 @@
    ],
    "source": [
     "import time\n",
+    "\n",
     "start = time.time()\n",
     "model.train(\n",
     "    datamodule=training_dataloader,\n",
-    "    #datamodule=datamodule,\n",
+    "    # datamodule=datamodule,\n",
     "    max_epochs=100,\n",
     "    batch_size=1024,\n",
     "    # accelerator=\"gpu\",\n",
@@ -572,8 +576,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#adata = adata[~adata.obs[\"cell_type\"].str.contains(\"kidney\", na=False)]\n",
-    "#adata.obs.loc[adata.obs.cell_type.isin([\"CD8-positive, alpha-beta T cell\",\"CD4-positive, alpha-beta T cell\"],\"cell_type\"] = \"T cell\""
+    "# adata = adata[~adata.obs[\"cell_type\"].str.contains(\"kidney\", na=False)]\n",
+    "# adata.obs.loc[adata.obs.cell_type.isin([\"CD8-positive, alpha-beta T cell\",\"CD4-positive, alpha-beta T cell\"],\"cell_type\"] = \"T cell\""
    ]
   },
   {
@@ -603,8 +607,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], \n",
-    "           title=[\"SCVI_\"+x for x in [\"dataset_id\",\"donor_id\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"dataset_id\", \"donor_id\"],\n",
+    "    title=[\"SCVI_\" + x for x in [\"dataset_id\", \"donor_id\"]],\n",
+    ")"
    ]
   },
   {
@@ -624,8 +631,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"assay\",\"tissue_general\"], \n",
-    "           title=[\"SCVI_\"+x for x in [\"assay\",\"tissue_general\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"assay\", \"tissue_general\"],\n",
+    "    title=[\"SCVI_\" + x for x in [\"assay\", \"tissue_general\"]],\n",
+    ")"
    ]
   },
   {
@@ -754,9 +764,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "scvi.model.SCVI.setup_anndata(adata, \n",
-    "                              layer=\"counts\",\n",
-    "                              categorical_covariate_keys=batch_keys)"
+    "scvi.model.SCVI.setup_anndata(adata, layer=\"counts\", categorical_covariate_keys=batch_keys)"
    ]
   },
   {
@@ -858,8 +866,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], \n",
-    "           title=[\"SCVI_adata_\"+x for x in [\"dataset_id\",\"donor_id\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"dataset_id\", \"donor_id\"],\n",
+    "    title=[\"SCVI_adata_\" + x for x in [\"dataset_id\", \"donor_id\"]],\n",
+    ")"
    ]
   },
   {
@@ -879,8 +890,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"assay\",\"tissue_general\"], \n",
-    "           title=[\"SCVI_adata_\"+x for x in [\"assay\",\"tissue_general\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"assay\", \"tissue_general\"],\n",
+    "    title=[\"SCVI_adata_\" + x for x in [\"assay\", \"tissue_general\"]],\n",
+    ")"
    ]
   },
   {
@@ -1039,9 +1053,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#model_scanvi.save(\n",
+    "# model_scanvi.save(\n",
     "#    \"census_model_scanvi\", save_anndata=False, overwrite=True, datamodule=datamodule_scanvi\n",
-    "#)"
+    "# )"
    ]
   },
   {
@@ -1126,8 +1140,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], \n",
-    "           title=[\"SCANVI_\"+x for x in [\"dataset_id\",\"donor_id\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"dataset_id\", \"donor_id\"],\n",
+    "    title=[\"SCANVI_\" + x for x in [\"dataset_id\", \"donor_id\"]],\n",
+    ")"
    ]
   },
   {
@@ -1147,8 +1164,11 @@
     }
    ],
    "source": [
-    "sc.pl.umap(adata, color=[\"assay\",\"tissue_general\"], \n",
-    "           title=[\"SCANVI_\"+x for x in [\"assay\",\"tissue_general\"]])"
+    "sc.pl.umap(\n",
+    "    adata,\n",
+    "    color=[\"assay\", \"tissue_general\"],\n",
+    "    title=[\"SCANVI_\" + x for x in [\"assay\", \"tissue_general\"]],\n",
+    ")"
    ]
   },
   {
@@ -1247,6 +1267,7 @@
     "df = adata.obs.groupby([\"cell_type\", \"predictions_scanvi\"]).size().unstack(fill_value=0)\n",
     "norm_df = df / df.sum(axis=0)\n",
     "import matplotlib.pyplot as plt\n",
+    "\n",
     "plt.figure(figsize=(8, 8))\n",
     "_ = plt.pcolor(norm_df)\n",
     "_ = plt.xticks(np.arange(0.5, len(df.columns), 1), df.columns, rotation=90)\n",
@@ -1349,6 +1370,7 @@
    ],
    "source": [
     "from scib_metrics.benchmark import Benchmarker\n",
+    "\n",
     "bm = Benchmarker(\n",
     "    adata,\n",
     "    batch_key=\"batch\",\n",