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

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

Author: pre-commit-ci[bot]

hub/Tahoe100.ipynb

@@ -1433,7 +1433,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#because we have so many drugs, we wont plot the umap here\n",
+    "# because we have so many drugs, we wont plot the umap here\n",
     "# sc.pl.umap(\n",
     "#    subset_adata,\n",
     "#    color=[\"drug\"],\n",
@@ -1536,11 +1536,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#sc.pl.umap(\n",
+    "# sc.pl.umap(\n",
     "#    subset_adata2,\n",
     "#    color=[\"plate\", \"Cell_ID_Cellosaur\"],\n",
     "#    frameon=False,\n",
-    "#)"
+    "# )"
    ]
   },
   {
@@ -1785,7 +1785,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#tahoe_scanvi.train(max_epochs=5,batch_size=64) #this fails in the workstation"
+    "# tahoe_scanvi.train(max_epochs=5,batch_size=64) #this fails in the workstation"
    ]
   },
   {
@@ -1805,7 +1805,7 @@
    "source": [
     "predictions = tahoe_scanvi.predict(subset_adata)\n",
     "subset_adata.obs[\"predictions_scanvi\"] = predictions\n",
-    "#predictions"
+    "# predictions"
    ]
   },
   {
@@ -1851,7 +1851,7 @@
     }
    ],
    "source": [
-    "print(f\"The overall Accuracy is:\",np.round(np.trace(norm_df),2))"
+    "print(\"The overall Accuracy is:\", np.round(np.trace(norm_df), 2))"
    ]
   },
   {
@@ -1870,8 +1870,8 @@
    "outputs": [],
    "source": [
     "SCANVI_LATENT_KEY = \"X_scanVI\"\n",
-    "#latent_scanvi = tahoe_scanvi.get_latent_representation(subset_adata2)\n",
-    "#subset_adata2.obsm[SCANVI_LATENT_KEY] = latent_scanvi"
+    "# latent_scanvi = tahoe_scanvi.get_latent_representation(subset_adata2)\n",
+    "# subset_adata2.obsm[SCANVI_LATENT_KEY] = latent_scanvi"
    ]
   },
   {
@@ -1882,8 +1882,8 @@
    "outputs": [],
    "source": [
     "# use scVI latent space for UMAP generation\n",
-    "#sc.pp.neighbors(subset_adata2, use_rep=SCANVI_LATENT_KEY)\n",
-    "#sc.tl.umap(subset_adata2, min_dist=0.3)"
+    "# sc.pp.neighbors(subset_adata2, use_rep=SCANVI_LATENT_KEY)\n",
+    "# sc.tl.umap(subset_adata2, min_dist=0.3)"
    ]
   },
   {
@@ -1893,12 +1893,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#sc.pl.umap(\n",
+    "# sc.pl.umap(\n",
     "#    subset_adata2,\n",
     "#    color=[\"plate\", \"Cell_ID_Cellosaur\"],\n",
     "#    ncols=2,\n",
     "#    frameon=False,\n",
-    "#)"
+    "# )"
    ]
   },
   {
@@ -2016,7 +2016,7 @@
     "    subset_adata2,\n",
     "    batch_key=\"plate\",\n",
     "    label_key=\"Cell_ID_Cellosaur\",\n",
-    "    embedding_obsm_keys=[\"X_pca\",\"X_scVI\"],\n",
+    "    embedding_obsm_keys=[\"X_pca\", \"X_scVI\"],\n",
     "    n_jobs=-1,\n",
     ")\n",
     "bm.benchmark()"
@@ -2614,6 +2614,7 @@
    ],
    "source": [
     "import plotnine as p9\n",
+    "\n",
     "(\n",
     "    p9.ggplot(de_change, p9.aes(\"lfc_mean\", \"-log10_pscore\", color=\"Biotype\"))\n",
     "    + p9.geom_point(\n",
@@ -2746,9 +2747,9 @@
    "outputs": [],
    "source": [
     "# get the generated expression from the minified model (will take very long time)\n",
-    "#tahoe.adata[:, upregulated_genes.index] = tahoe.get_normalized_expression(\n",
+    "# tahoe.adata[:, upregulated_genes.index] = tahoe.get_normalized_expression(\n",
     "#    gene_list=list(upregulated_genes.index), n_samples=10\n",
-    "#)"
+    "# )"
    ]
   },
   {