build(deps-dev): bump ruff from 0.5.1 to 0.6.1 (opentargets#732)

* build(deps-dev): bump ruff from 0.5.1 to 0.6.1 Bumps [ruff](https://github.com/astral-sh/ruff) from 0.5.1 to 0.6.1. - [Release notes](https://github.com/astral-sh/ruff/releases) - [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md) - [Commits](astral-sh/ruff@0.5.1...0.6.1) --- updated-dependencies: - dependency-name: ruff dependency-type: direct:development update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> * fix: linting issues associated with ruff 0.6 * chore: fixing imports for notebooks * chore: removing old notebook --------- Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: David Ochoa <[email protected]> Co-authored-by: Daniel Considine <[email protected]>
thehyve · Aug 22, 2024 · f49a5c5 · f49a5c5
1 parent e45f295
commit f49a5c5
Show file tree

Hide file tree

Showing 13 changed files with 2,393 additions and 4,637 deletions.
diff --git a/notebooks/FineMappingSimmuations.ipynb b/notebooks/FineMappingSimmuations.ipynb
@@ -82,7 +82,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ld_matrix = np.load('/Users/yt4/Projects/ot_data/tmp/ld_matrix.npy')\n",
+    "ld_matrix = np.load(\"/Users/yt4/Projects/ot_data/tmp/ld_matrix.npy\")\n",
     "ld_index=session.spark.read.parquet(\"/Users/yt4/Projects/ot_data/tmp/ld_index\")\n",
     "ld_matrix_for_sim=ld_matrix[0:500,:][:,0:500]\n",
     "ld_index_for_sim=ld_index.limit(500)"
@@ -129,11 +129,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {
@@ -177,11 +174,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {
@@ -227,11 +221,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {
@@ -277,11 +268,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {
@@ -335,11 +323,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {
@@ -386,11 +371,8 @@
     }
    ],
    "source": [
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x1,n_causal=n_causal))\n",
     "x2=x1[(x1[\"pValueExponent\"]<=-6) | (x1[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x2,n_causal=n_causal))\n",
-    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]\n",
-    "print(FineMappingSimulations.ProvideSummary(cred_sets=x3,n_causal=n_causal))"
+    "x3=x2[(x2[\"purityMinR2\"]>=0.25) | (x2[\"credibleSetIndex\"]==1)]"
    ]
   },
   {

diff --git a/notebooks/FineMapping_AlzheimierDisease.ipynb b/notebooks/FineMapping_AlzheimierDisease.ipynb
@@ -121,19 +121,20 @@
    ],
    "source": [
     "import os\n",
+    "\n",
     "import hail as hl\n",
-    "import pyspark.sql.functions as f\n",
     "import pandas as pd\n",
-    "pd.set_option('display.max_colwidth', None)\n",
-    "pd.set_option('display.expand_frame_repr', False)\n",
+    "import pyspark.sql.functions as f\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_index import StudyIndex\n",
     "from gentropy.method.window_based_clumping import WindowBasedClumping\n",
     "from gentropy.susie_finemapper import SusieFineMapperStep\n",
     "\n",
+    "pd.set_option(\"display.max_colwidth\", None)\n",
+    "pd.set_option(\"display.expand_frame_repr\", False)\n",
+    "\n",
     "hail_dir = os.path.dirname(hl.__file__)\n",
     "session = Session(hail_home=hail_dir, start_hail=True, extended_spark_conf={\"spark.driver.memory\": \"12g\",\n",
     "    \"spark.kryoserializer.buffer.max\": \"500m\",\"spark.driver.maxResultSize\":\"3g\"})"
@@ -195,10 +196,7 @@
     "study_index = StudyIndex.from_parquet(session, path_si)\n",
     "\n",
     "slt=WindowBasedClumping.clump(gwas1,gwas_significance=5e-8,distance=1e6)\n",
-    "slt_df=slt._df\n",
-    "\n",
-    "print(\"Number of SNPs in GWAS: \",gwas1._df.count())\n",
-    "print(\"Number of clumps: \",slt_df.count())"
+    "slt_df=slt._df\n"
    ]
   },
   {
@@ -254,9 +252,7 @@
      ]
     }
    ],
-   "source": [
-    "print(slt_df.show())"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -1071,7 +1067,7 @@
    "source": [
     "df = slt_df.withColumn(\"row_index\", f.monotonically_increasing_id())\n",
     "\n",
-    "columns = ['N_gwas', 'N_ld', 'N_overlap', 'N_outliers', 'N_imputed', 'N_final_to_fm', 'eleapsed_time']\n",
+    "columns = [\"N_gwas\", \"N_ld\", \"N_overlap\", \"N_outliers\", \"N_imputed\", \"N_final_to_fm\", \"eleapsed_time\"]\n",
     "logs = pd.DataFrame(columns=columns)\n",
     "\n",
     "for i in range(0,df.count()):\n",
@@ -1095,7 +1091,6 @@
     "\n",
     "        sl=res[\"study_locus\"]\n",
     "        #print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "        print(\"Region: \",sl._df.collect()[0]['region'], \"; number of CSs: \",sl._df.count(), \"; log:\")\n",
     "        #print(res[\"log\"])\n",
     "        logs=pd.concat([logs,res[\"log\"]])"
    ]
@@ -1146,8 +1141,7 @@
     }
    ],
    "source": [
-    "pd.set_option('display.max_rows', None)\n",
-    "print(logs)"
+    "pd.set_option(\"display.max_rows\", None)"
    ]
   },
   {
@@ -1164,8 +1158,7 @@
     }
    ],
    "source": [
-    "summary = logs['N_overlap'].mean()\n",
-    "print(summary)"
+    "summary = logs[\"N_overlap\"].mean()"
    ]
   },
   {
@@ -1318,9 +1311,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   },
   {
@@ -1382,9 +1373,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   },
   {
@@ -1482,9 +1471,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   },
   {
@@ -1546,9 +1533,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   },
   {
@@ -1610,9 +1595,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   },
   {
@@ -1703,9 +1686,7 @@
     "    imputed_r2_threshold=0.8,\n",
     "    ld_score_threshold=4\n",
     ")\n",
-    "sl=res[\"study_locus\"]\n",
-    "print(sl._df.withColumn(\"size\", f.size(sl._df[\"locus\"])).show())\n",
-    "print(res[\"log\"])"
+    "sl=res[\"study_locus\"]"
    ]
   }
  ],