Fix ruff and mypy

Author: LTan-101104

notebooks/Efficiency Analysis.ipynb

@@ -112,7 +112,7 @@
             "outputs": [],
             "source": [
                 "# Load the jobs DataFrame from DuckDB\n",
-                "preprocessed_jobs_df = ea.load_preprocessed_jobs_dataframe_from_duckdb(\n",
+                "preprocessed_jobs_df = load_and_preprocess_jobs(\n",
                 "    db_path=\"../data/slurm_data.db\",\n",
                 "    table_name=\"Jobs\",\n",
                 ")\n",
@@ -608,7 +608,11 @@
             ]
         }
     ],
-    "metadata": {},
+    "metadata": {
+        "language_info": {
+            "name": "python"
+        }
+    },
     "nbformat": 4,
     "nbformat_minor": 5
-}
+}

src/analysis/efficiency_analysis.py

@@ -4,18 +4,13 @@
 The aim is to identify potential inefficiencies in GPU usage and notify users or PIs about these issues.
 """
 
-from pathlib import Path
 from typing import cast
 
 import numpy as np
 import pandas as pd
-import numpy as np
 from src.config.constants import DEFAULT_MIN_ELAPSED_SECONDS
 from src.config.enum_constants import FilterTypeEnum, MetricsDataFrameNameEnum
 
-from src.database import DatabaseConnection
-from src.preprocess.preprocess import preprocess_data
-
 
 class EfficiencyAnalysis:
     """

tests/test_preprocess.py

@@ -359,9 +359,9 @@ def test_preprocess_timedelta_conversion(mock_data_path: str, mock_data_frame: p
     time_limit = data["TimeLimit"]
     assert time_limit.dtype == "timedelta64[ns]"  # assert correct type
 
-    time_limit = time_limit.tolist()
+    time_limit_list = time_limit.tolist()
     ground_truth_time_limit = ground_truth["TimeLimit"].tolist()
-    for i, timedelta in enumerate(time_limit):
+    for i, timedelta in enumerate(time_limit_list):
         assert timedelta.total_seconds() / 60 == ground_truth_time_limit[i]