From 6a9601f46adb053882ab86b681826f1f5c8fd46f Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 18 Nov 2024 12:22:48 +0000
Subject: [PATCH] chore: pre-commit auto fixes [...]

---
 .../20241114_out_of_sample_validation.ipynb    | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/notebooks/20241114_out_of_sample_validation.ipynb b/notebooks/20241114_out_of_sample_validation.ipynb
index 85ef1bc72..217eb04ea 100644
--- a/notebooks/20241114_out_of_sample_validation.ipynb
+++ b/notebooks/20241114_out_of_sample_validation.ipynb
@@ -122,21 +122,15 @@
     "import os\n",
     "\n",
     "import hail as hl\n",
-    "import numpy as np\n",
     "import pyspark.sql.functions as f\n",
-    "from pyspark.sql import DataFrame\n",
     "\n",
     "from gentropy.common.session import Session\n",
-    "from gentropy.dataset.study_index import StudyIndex\n",
-    "from gentropy.dataset.summary_statistics import SummaryStatistics\n",
-    "from gentropy.dataset.study_locus import StudyLocus\n",
-    "from gentropy.susie_finemapper import SusieFineMapperStep\n",
     "\n",
     "hail_dir = os.path.dirname(hl.__file__)\n",
     "session = Session(hail_home=hail_dir, start_hail=True, extended_spark_conf={\n",
     "    \"spark.driver.memory\": \"12g\",\"spark.kryoserializer.buffer.max\": \"500m\",\"spark.driver.maxResultSize\":\"2g\",\n",
-    "    'spark.hadoop.fs.gs.requester.pays.buckets': 'requester-pays-bucket1,requester-pays-bucket2',\n",
-    "    'spark.hadoop.fs.gs.requester.pays.project.id': 'open-targets-genetics-dev',\n",
+    "    \"spark.hadoop.fs.gs.requester.pays.buckets\": \"requester-pays-bucket1,requester-pays-bucket2\",\n",
+    "    \"spark.hadoop.fs.gs.requester.pays.project.id\": \"open-targets-genetics-dev\",\n",
     "    \"spark.hadoop.fs.gs.requester.pays.mode\":\"AUTO\"})"
    ]
   },
@@ -173,7 +167,7 @@
     "        .cache())\n",
     "\n",
     "    counts_df = df.groupBy(\"gsp_status\", \"score_to_use\").agg(f.count(\"*\").alias(\"count\"))\n",
-    "    counts = { (row.gsp_status, row.score_to_use): row['count'] for row in counts_df.collect() }\n",
+    "    counts = { (row.gsp_status, row.score_to_use): row[\"count\"] for row in counts_df.collect() }\n",
     "    count_1_1 = counts.get((1, 1), 0)\n",
     "    count_1_0 = counts.get((1, 0), 0)\n",
     "    count_0_1 = counts.get((0, 1), 0)\n",
@@ -273,7 +267,7 @@
     "        valid_set_to_remove.select(\"studyLocusId\", \"geneId\"),\n",
     "        on=[\"studyLocusId\", \"geneId\"],\n",
     "        how=\"left_anti\"\n",
-    "    )   \n",
+    "    )\n",
     "    validate_pred(\n",
     "        valid_set=filtered_valid_set,\n",
     "        prediction_set=filtered_l2g,\n",
@@ -318,7 +312,7 @@
     "        gsp_colum=\"goldStandardSet\",\n",
     "        positive=\"positive\",\n",
     "        score_thr=thr,\n",
-    "    )   \n",
+    "    )\n",
     "\n",
     "    print(\"\")\n",
     "    print(\"\")\n",
@@ -333,7 +327,7 @@
     "        gsp_colum=\"Goldstandard_positive\",\n",
     "        positive=1,\n",
     "        score_thr=thr,\n",
-    "    )   \n"
+    "    )\n"
    ]
   },
   {