[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

@@ -85,20 +85,17 @@
    ],
    "source": [
     "import warnings\n",
-    "from typing import Any\n",
     "\n",
     "import cellxgene_census\n",
     "import numpy as np\n",
-    "import pandas as pd\n",
     "import scanpy as sc\n",
     "import scvi\n",
     "import tiledbsoma as soma\n",
-    "import tiledbsoma_ml\n",
-    "import torch\n",
     "from cellxgene_census.experimental.pp import highly_variable_genes\n",
-    "#from lightning import LightningDataModule\n",
-    "#from sklearn.preprocessing import LabelEncoder\n",
-    "#from torch.utils.data import DataLoader\n",
+    "\n",
+    "# from lightning import LightningDataModule\n",
+    "# from sklearn.preprocessing import LabelEncoder\n",
+    "# from torch.utils.data import DataLoader\n",
     "from scvi.dataloaders import TileDBDataModule\n",
     "\n",
     "warnings.filterwarnings(\"ignore\")"
@@ -142,11 +139,11 @@
    "outputs": [],
    "source": [
     "experiment_name = \"mus_musculus\"\n",
-    "#obs_val_filt = 'is_primary_data == True and tissue_general in [\"spleen\", \"kidney\"] and nnz >= 500'\n",
+    "# obs_val_filt = 'is_primary_data == True and tissue_general in [\"spleen\", \"kidney\"] and nnz >= 500'\n",
     "obs_val_filt = 'is_primary_data == True and tissue_general in [\"liver\"] and nnz >= 500'\n",
-    "#obs_val_filt = 'is_primary_data == True and tissue_general in [\"liver\", \"heart\"] and nnz >= 500'\n",
+    "# obs_val_filt = 'is_primary_data == True and tissue_general in [\"liver\", \"heart\"] and nnz >= 500'\n",
     "top_n_hvg = 500\n",
-    "hvg_batch = [\"dataset_id\",\"donor_id\"]"
+    "hvg_batch = [\"dataset_id\", \"donor_id\"]"
    ]
   },
   {
@@ -171,7 +168,7 @@
     ")\n",
     "hv = hvgs_df.highly_variable\n",
     "hv_idx = hv[hv].index\n",
-    "#hv_idx = np.arange(10)"
+    "# hv_idx = np.arange(10)"
    ]
   },
   {
@@ -207,7 +204,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "batch_keys = [\"dataset_id\",\"donor_id\"]"
+    "batch_keys = [\"dataset_id\", \"donor_id\"]"
    ]
   },
   {
@@ -242,11 +239,11 @@
     "    batch_size=1024,\n",
     "    shuffle=True,\n",
     "    seed=42,\n",
-    "    batch_column_names = batch_keys,\n",
+    "    batch_column_names=batch_keys,\n",
     "    dataloader_kwargs={\"num_workers\": 64, \"persistent_workers\": False},\n",
     "    accelerator=\"gpu\",\n",
     "    device=2,\n",
-    "    return_sparse_X=False\n",
+    "    return_sparse_X=False,\n",
     ")\n",
     "print(datamodule.n_obs, datamodule.n_vars, datamodule.n_batch)"
    ]
@@ -281,7 +278,12 @@
     "n_latent = 10\n",
     "datamodule.setup()\n",
     "model = scvi.model.SCVI(\n",
-    "    adata=None, registry=datamodule.registry ,n_layers=n_layers, n_latent=n_latent, gene_likelihood=\"nb\", encode_covariates=False\n",
+    "    adata=None,\n",
+    "    registry=datamodule.registry,\n",
+    "    n_layers=n_layers,\n",
+    "    n_latent=n_latent,\n",
+    "    gene_likelihood=\"nb\",\n",
+    "    encode_covariates=False,\n",
     ")"
    ]
   },
@@ -301,8 +303,7 @@
    "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",
     ")"
    ]
   },
@@ -361,15 +362,16 @@
    ],
    "source": [
     "import time\n",
+    "\n",
     "start = time.time()\n",
     "model.train(\n",
     "    datamodule=training_dataloader,\n",
-    "    #datamodule=datamodule,\n",
+    "    # datamodule=datamodule,\n",
     "    max_epochs=10,\n",
     "    batch_size=1024,\n",
-    "    #accelerator=\"gpu\",\n",
-    "    #devices=-1,\n",
-    "    #strategy=\"ddp_notebook_find_unused_parameters_true\",\n",
+    "    # accelerator=\"gpu\",\n",
+    "    # devices=-1,\n",
+    "    # strategy=\"ddp_notebook_find_unused_parameters_true\",\n",
     ")\n",
     "end = time.time()\n",
     "print(f\"Elapsed time: {end - start:.2f} seconds\")"
@@ -610,7 +612,7 @@
    "source": [
     "sc.pp.neighbors(adata, use_rep=\"scvi\", key_added=\"scvi\")\n",
     "sc.tl.umap(adata, neighbors_key=\"scvi\")\n",
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], title=\"SCVI\")"
+    "sc.pl.umap(adata, color=[\"dataset_id\", \"donor_id\"], title=\"SCVI\")"
    ]
   },
   {
@@ -641,7 +643,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#sc.pl.umap(adata, color=\"tissue_general\", title=\"SCVI\")"
+    "# sc.pl.umap(adata, color=\"tissue_general\", title=\"SCVI\")"
    ]
   },
   {
@@ -666,8 +668,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "scvi.model.SCVI.setup_anndata(adata, \n",
-    "                              batch_key=\"batch\")"
+    "scvi.model.SCVI.setup_anndata(adata, batch_key=\"batch\")"
    ]
   },
   {
@@ -676,7 +677,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#model_census3 = scvi.model.SCVI.load(\"census_model\", adata=adata)\n",
+    "# model_census3 = scvi.model.SCVI.load(\"census_model\", adata=adata)\n",
     "model_census3 = scvi.model.SCVI(adata)"
    ]
   },
@@ -769,7 +770,7 @@
    "source": [
     "sc.pp.neighbors(adata, use_rep=\"scvi_non_dataloder\", key_added=\"scvi_non_dataloder\")\n",
     "sc.tl.umap(adata, neighbors_key=\"scvi_non_dataloder\")\n",
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], title=\"SCVI_non_dataloder\")"
+    "sc.pl.umap(adata, color=[\"dataset_id\", \"donor_id\"], title=\"SCVI_non_dataloder\")"
    ]
   },
   {
@@ -798,7 +799,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#sc.pl.umap(adata, color=\"tissue_general\", title=\"SCVI_non_dataloder\")"
+    "# sc.pl.umap(adata, color=\"tissue_general\", title=\"SCVI_non_dataloder\")"
    ]
   },
   {
@@ -945,7 +946,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#model_scanvi.save(\"census_model_scanvi\", save_anndata=False, overwrite=True, datamodule=datamodule_scanvi)"
+    "# model_scanvi.save(\"census_model_scanvi\", save_anndata=False, overwrite=True, datamodule=datamodule_scanvi)"
    ]
   },
   {
@@ -1037,7 +1038,7 @@
    "source": [
     "sc.pp.neighbors(adata, use_rep=\"scanvi\", key_added=\"scanvi\")\n",
     "sc.tl.umap(adata, neighbors_key=\"scanvi\")\n",
-    "sc.pl.umap(adata, color=[\"dataset_id\",\"donor_id\"], title=\"SCANVI\")"
+    "sc.pl.umap(adata, color=[\"dataset_id\", \"donor_id\"], title=\"SCANVI\")"
    ]
   },
   {
@@ -1066,7 +1067,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#sc.pl.umap(adata, color=\"tissue_general\", title=\"SCANVI\")"
+    "# sc.pl.umap(adata, color=\"tissue_general\", title=\"SCANVI\")"
    ]
   },
   {