Update ruff with annotation (#140)

* adds mask to pca * added mask to scaling * fixes scale * adds test for clip * better support for csc * solves memory issue with masks * updates inplace behavior * adds type checking * add _empty * add release note * return to scanpy Empty * add Empty to ignore * init ruff update * update annotation * add annotation * add annotation * updated notebooks * updated decoupler for ruff * fix autocorr * updated decoupler * added release note
scverse · Mar 19, 2024 · 2945ce6 · 2945ce6
1 parent 1a3a04f
commit 2945ce6
Show file tree

Hide file tree

Showing 51 changed files with 442 additions and 281 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -3,8 +3,15 @@ repos:
     rev: v0.3.3
     hooks:
     -   id: ruff
-        args: [--fix, --exit-non-zero-on-fix]
-    - id: ruff-format
+        types_or: [python, pyi, jupyter]
+        args: ["--fix"]
+    -   id: ruff-format
+        types_or: [python, pyi, jupyter]
+    # The following can be removed once PLR0917 is out of preview
+    -   name: ruff preview rules
+        id: ruff
+        types_or: [python, pyi, jupyter]
+        args: ["--preview", "--select=PLR0917"]
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:

diff --git a/docs/notebooks/autocorr_benchmark.ipynb b/docs/notebooks/autocorr_benchmark.ipynb
@@ -23,7 +23,6 @@
    "outputs": [],
    "source": [
     "import rapids_singlecell as rsc\n",
-    "import scanpy as sc\n",
     "import squidpy as sq\n",
     "import cupy as cp"
    ]
@@ -37,10 +36,11 @@
    "source": [
     "import rmm\n",
     "from rmm.allocators.cupy import rmm_cupy_allocator\n",
+    "\n",
     "rmm.reinitialize(\n",
-    "    managed_memory=False, # Allows oversubscription\n",
-    "    pool_allocator=False, # default is False\n",
-    "    devices=0, # GPU device IDs to register. By default registers only GPU 0.\n",
+    "    managed_memory=False,  # Allows oversubscription\n",
+    "    pool_allocator=False,  # default is False\n",
+    "    devices=0,  # GPU device IDs to register. By default registers only GPU 0.\n",
     ")\n",
     "cp.cuda.set_allocator(rmm_cupy_allocator)"
    ]
@@ -133,11 +133,7 @@
    ],
    "source": [
     "%%timeit\n",
-    "rsc.gr.spatial_autocorr(adata,\n",
-    "    mode=\"moran\",\n",
-    "    genes=genes,\n",
-    "    n_perms=100,\n",
-    "    use_sparse=False)"
+    "rsc.gr.spatial_autocorr(adata, mode=\"moran\", genes=genes, n_perms=100, use_sparse=False)"
    ]
   },
   {
@@ -396,10 +392,7 @@
    ],
    "source": [
     "%%time\n",
-    "sq.gr.spatial_autocorr(adata,\n",
-    "    mode=\"moran\",\n",
-    "    genes=genes,\n",
-    "    n_perms=100,n_jobs=32)"
+    "sq.gr.spatial_autocorr(adata, mode=\"moran\", genes=genes, n_perms=100, n_jobs=32)"
    ]
   },
   {
@@ -655,11 +648,7 @@
    ],
    "source": [
     "%%timeit\n",
-    "rsc.gr.spatial_autocorr(adata,\n",
-    "    mode=\"geary\",\n",
-    "    genes=genes,\n",
-    "    n_perms=100,\n",
-    "    use_sparse=False)"
+    "rsc.gr.spatial_autocorr(adata, mode=\"geary\", genes=genes, n_perms=100, use_sparse=False)"
    ]
   },
   {
@@ -918,10 +907,7 @@
    ],
    "source": [
     "%%time\n",
-    "sq.gr.spatial_autocorr(adata,\n",
-    "    mode=\"geary\",\n",
-    "    genes=genes,\n",
-    "    n_perms=100, n_jobs=32)"
+    "sq.gr.spatial_autocorr(adata, mode=\"geary\", genes=genes, n_perms=100, n_jobs=32)"
    ]
   },
   {

diff --git a/docs/notebooks/demo_gpu-PR.ipynb b/docs/notebooks/demo_gpu-PR.ipynb
@@ -27,13 +27,13 @@
    "outputs": [],
    "source": [
     "import scanpy as sc\n",
-    "import anndata\n",
     "import cupy as cp\n",
     "\n",
     "import time\n",
     "import rapids_singlecell as rsc\n",
     "\n",
     "import warnings\n",
+    "\n",
     "warnings.filterwarnings(\"ignore\")"
    ]
   },
@@ -46,12 +46,13 @@
    "source": [
     "import rmm\n",
     "from rmm.allocators.cupy import rmm_cupy_allocator\n",
+    "\n",
     "rmm.reinitialize(\n",
-    "    managed_memory=False, # Allows oversubscription\n",
-    "    pool_allocator=False, # default is False\n",
-    "    devices=0, # GPU device IDs to register. By default registers only GPU 0.\n",
+    "    managed_memory=False,  # Allows oversubscription\n",
+    "    pool_allocator=False,  # default is False\n",
+    "    devices=0,  # GPU device IDs to register. By default registers only GPU 0.\n",
     ")\n",
-    "cp.cuda.set_allocator(rmm_cupy_allocator)\n"
+    "cp.cuda.set_allocator(rmm_cupy_allocator)"
    ]
   },
   {
@@ -176,7 +177,7 @@
    ],
    "source": [
     "data_load_time = time.time()\n",
-    "print(\"Total data load and format time: %s\" % (data_load_time-data_load_start))"
+    "print(\"Total data load and format time: %s\" % (data_load_time - data_load_start))"
    ]
   },
   {
@@ -230,7 +231,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.flag_gene_family(adata,gene_family_name=\"MT\", gene_family_prefix=\"mt-\")"
+    "rsc.pp.flag_gene_family(adata, gene_family_name=\"MT\", gene_family_prefix=\"mt-\")"
    ]
   },
   {
@@ -250,7 +251,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.calculate_qc_metrics(adata,qc_vars=[\"MT\"])"
+    "rsc.pp.calculate_qc_metrics(adata, qc_vars=[\"MT\"])"
    ]
   },
   {
@@ -281,8 +282,8 @@
     }
    ],
    "source": [
-    "sc.pl.scatter(adata,\"total_counts\",\"pct_counts_MT\")\n",
-    "sc.pl.scatter(adata,\"total_counts\",\"n_genes_by_counts\")"
+    "sc.pl.scatter(adata, \"total_counts\", \"pct_counts_MT\")\n",
+    "sc.pl.scatter(adata, \"total_counts\", \"n_genes_by_counts\")"
    ]
   },
   {
@@ -323,9 +324,9 @@
     }
    ],
    "source": [
-    "sc.pl.violin(adata,keys=\"n_genes_by_counts\")\n",
-    "sc.pl.violin(adata,keys=\"total_counts\")\n",
-    "sc.pl.violin(adata,keys=\"pct_counts_MT\")"
+    "sc.pl.violin(adata, keys=\"n_genes_by_counts\")\n",
+    "sc.pl.violin(adata, keys=\"total_counts\")\n",
+    "sc.pl.violin(adata, keys=\"pct_counts_MT\")"
    ]
   },
   {
@@ -395,8 +396,8 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.filter_cells(adata,qc_var=\"n_genes_by_counts\", min_count=500,max_count= 4000)\n",
-    "rsc.pp.filter_cells(adata,qc_var=\"total_counts\", max_count= 20000)\n",
+    "rsc.pp.filter_cells(adata, qc_var=\"n_genes_by_counts\", min_count=500, max_count=4000)\n",
+    "rsc.pp.filter_cells(adata, qc_var=\"total_counts\", max_count=20000)\n",
     "adata = adata[adata.obs[\"pct_counts_MT\"] < 20]"
    ]
   },
@@ -453,7 +454,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.normalize_total(adata,target_sum=1e4)"
+    "rsc.pp.normalize_total(adata, target_sum=1e4)"
    ]
   },
   {
@@ -555,7 +556,9 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.highly_variable_genes(adata,n_top_genes=5000,flavor=\"pearson_residuals\",layer = \"counts\")"
+    "rsc.pp.highly_variable_genes(\n",
+    "    adata, n_top_genes=5000, flavor=\"pearson_residuals\", layer=\"counts\"\n",
+    ")"
    ]
   },
   {
@@ -642,7 +645,9 @@
    ],
    "source": [
     "%%time\n",
-    "adata.layers[\"pearson_residuals\"] = rsc.pp.normalize_pearson_residuals(adata,layer= \"counts\",inplace = False)"
+    "adata.layers[\"pearson_residuals\"] = rsc.pp.normalize_pearson_residuals(\n",
+    "    adata, layer=\"counts\", inplace=False\n",
+    ")"
    ]
   },
   {
@@ -686,7 +691,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.pp.pca(adata, n_comps = 150, layer = \"pearson_residuals\")"
+    "rsc.pp.pca(adata, n_comps=150, layer=\"pearson_residuals\")"
    ]
   },
   {
@@ -707,7 +712,7 @@
     }
    ],
    "source": [
-    "sc.pl.pca_variance_ratio(adata, log=True,n_pcs=150)"
+    "sc.pl.pca_variance_ratio(adata, log=True, n_pcs=150)"
    ]
   },
   {
@@ -754,7 +759,7 @@
    ],
    "source": [
     "preprocess_time = time.time()\n",
-    "print(\"Total Preprocessing time: %s\" % (preprocess_time-preprocess_start))"
+    "print(\"Total Preprocessing time: %s\" % (preprocess_time - preprocess_start))"
    ]
   },
   {
@@ -876,7 +881,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.tl.louvain(adata,resolution=1.0)"
+    "rsc.tl.louvain(adata, resolution=1.0)"
    ]
   },
   {
@@ -896,7 +901,7 @@
    ],
    "source": [
     "%%time\n",
-    "rsc.tl.leiden(adata,resolution=1.0)"
+    "rsc.tl.leiden(adata, resolution=1.0)"
    ]
   },
   {
@@ -926,7 +931,7 @@
    ],
    "source": [
     "%%time\n",
-    "sc.pl.umap(adata, color=[\"louvain\",\"leiden\"],legend_loc = 'on data')"
+    "sc.pl.umap(adata, color=[\"louvain\", \"leiden\"], legend_loc=\"on data\")"
    ]
   },
   {
@@ -956,7 +961,7 @@
    ],
    "source": [
     "%%time\n",
-    "sc.pl.umap(adata, color=[\"Stmn2\",\"Hes1\"],legend_loc = 'on data', cmap=\"Reds\")"
+    "sc.pl.umap(adata, color=[\"Stmn2\", \"Hes1\"], legend_loc=\"on data\", cmap=\"Reds\")"
    ]
   },
   {
@@ -997,7 +1002,7 @@
     }
    ],
    "source": [
-    "adata.obsm[\"X_diffmap_\"] = adata.obsm[\"X_diffmap\"][:, 1:] \n",
+    "adata.obsm[\"X_diffmap_\"] = adata.obsm[\"X_diffmap\"][:, 1:]\n",
     "sc.pl.embedding(adata, \"diffmap_\", color=\"louvain\")"
    ]
   },
@@ -1072,7 +1077,7 @@
     }
    ],
    "source": [
-    "print(\"Total Processing time: %s\" % (time.time()-preprocess_start))"
+    "print(\"Total Processing time: %s\" % (time.time() - preprocess_start))"
    ]
   }
  ],