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

for more information, see https://pre-commit.ci
VectorInstitute · Nov 4, 2024 · 084021a · 084021a
1 parent 988f46a
commit 084021a
Showing 1 changed file with 19 additions and 18 deletions.
diff --git a/odyssey/data/DataProcessor.ipynb b/odyssey/data/DataProcessor.ipynb
@@ -25,8 +25,8 @@
     "\n",
     "SEED = 23\n",
     "ROOT = \"/h/afallah/odyssey/odyssey\"\n",
-    "DATA_ROOT = f\"{ROOT}/odyssey/data/meds_data\" # bigbird_data\n",
-    "DATASET = f\"{DATA_ROOT}/patient_sequences/patient_sequences.parquet\" #patient_sequences_2048.parquet\\\n",
+    "DATA_ROOT = f\"{ROOT}/odyssey/data/meds_data\"  # bigbird_data\n",
+    "DATASET = f\"{DATA_ROOT}/patient_sequences/patient_sequences.parquet\"  # patient_sequences_2048.parquet\\\n",
     "DATASET_2048 = f\"{DATA_ROOT}/patient_sequences/patient_sequences_2048.parquet\"\n",
     "MAX_LEN = 2048\n",
     "\n",
@@ -66,19 +66,22 @@
    "source": [
     "dataset = pl.read_parquet(DATASET)\n",
     "dataset = dataset.rename({\"subject_id\": \"patient_id\", \"code\": \"event_tokens\"})\n",
-    "dataset = dataset.filter(pl.col('event_tokens').map_elements(len) > 5)\n",
-    "\n",
-    "dataset = dataset.with_columns([\n",
-    "    pl.col('patient_id').cast(pl.String).alias('patient_id'),\n",
-    "    pl.concat_list([\n",
-    "        pl.col('event_tokens').list.slice(0, 2047),\n",
-    "        pl.lit(['[EOS]'])\n",
-    "    ]).alias('event_tokens'),\n",
-    "])\n",
+    "dataset = dataset.filter(pl.col(\"event_tokens\").map_elements(len) > 5)\n",
+    "\n",
+    "dataset = dataset.with_columns(\n",
+    "    [\n",
+    "        pl.col(\"patient_id\").cast(pl.String).alias(\"patient_id\"),\n",
+    "        pl.concat_list(\n",
+    "            [pl.col(\"event_tokens\").list.slice(0, 2047), pl.lit([\"[EOS]\"])]\n",
+    "        ).alias(\"event_tokens\"),\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "dataset = dataset.with_columns([\n",
-    "    pl.col('event_tokens').map_elements(len).alias('token_length'),\n",
-    "])\n",
+    "dataset = dataset.with_columns(\n",
+    "    [\n",
+    "        pl.col(\"event_tokens\").map_elements(len).alias(\"token_length\"),\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "print(dataset.head())\n",
     "print(dataset.schema)\n",
@@ -175,7 +178,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dataset['event_tokens_2048'].iloc[0]"
+    "dataset[\"event_tokens_2048\"].iloc[0]"
    ]
   },
   {
@@ -229,9 +232,7 @@
    "outputs": [],
    "source": [
     "# Process the dataset for hospital readmission in one month task\n",
-    "dataset_readmission = process_readmission_dataset(\n",
-    "    dataset.copy(), max_len=MAX_LEN\n",
-    ")"
+    "dataset_readmission = process_readmission_dataset(dataset.copy(), max_len=MAX_LEN)"
    ]
   },
   {