Debugging kpi extraction...

api/services/dataset_service.py

@@ -25,21 +25,46 @@ DATA_PATH = Path(__file__).resolve().parent.parent.parent / "data"
 DATASET_PATH = DATA_PATH / "medical_dataset_3M.csv"
 KPIS_PATH = DATA_PATH / "kpis_export.json"
 MOCK_KPIS_PATH = DATA_PATH / "kpis_export_mock.json"
+LOG_PATH = DATA_PATH / "trace.log"
 
 WORKING_DIR = DATA_PATH
 
+# In[3]:
 
-def extract_kpis():
 
-    # with open(MOCK_KPIS_PATH, "r", encoding="utf-8") as f:
-    #     data = json.load(f)
+# Fonctions et variables utiles
+start_time = 0
+
+def start():
+    global start_time
+    start_time = perf_counter()
+
+
+def time_lapse(display=True):
+
+    time_elapsed = perf_counter() - start_time
+
+    hours, rem = divmod(time_elapsed, 3600)
+    minutes, seconds = divmod(rem, 60)
+
+    if display:
+        return f"{int(hours)}h {int(minutes)}m {seconds:.2f}s"
+
+    return int(hours), int(minutes), seconds
+
+def log(message):
+    with open(LOG_PATH, "a", encoding="utf-8") as logger:
+        logger.write(f"[{time_lapse()}] :\t{message}\n")
 
-    # with open(KPIS_PATH, "w", encoding="utf-8") as f:
-    #     json.dump(data, f, ensure_ascii=False, indent=2)
+def extract_kpis():
 
-    # return 0
+    start()
+    
+    log("KPIs Extraction started...")
 
     # Configuration globale des graphes matplotlib
+    log("Configuration globale des graphes matplotlib...")
+
     matplotlib.rcParams.update({
         "figure.dpi": 120,
         "figure.facecolor": "white",
@@ -58,39 +83,23 @@ def extract_kpis():
     PALETTE_SEQUENTIELLE = "YlOrRd"
 
     print("Imports effectues avec succes.")
+    log("Imports effectues avec succes.")
     print(f"Pandas version : {pd.__version__}")
     print(f"NumPy version  : {np.__version__}")
 
 
-    # In[3]:
-
-
-    # Fonctions et variables utiles
-    start_time = 0
-    def start():
-        start_time = perf_counter()
-
-    def time_lapse(start_time = start_time, end_time = perf_counter(), display = True):
-        time_elapsed = end_time - start_time
-        hours, rem = divmod(time_elapsed, 3600)
-        minutes, seconds = divmod(rem, 60)
-        if display:
-            return f"{int(hours)}h {int(minutes)}m {seconds:.2f}s"
-        return int(hours), int(minutes), seconds
-
-
     # In[4]:
 
 
     # Chargement et Aperçu de la Dataset
     print(f"Chemin de la dataset : {DATASET_PATH}")
     print("Chargement du fichier...")
-    start()
+    log("Chargement de la dataset...")
 
     df = pd.read_csv(DATASET_PATH, low_memory=False)
 
-    print("Temps écroulé : ", time_lapse())
     print(f"\nDataset charge avec succes.")
+    log("Dataset chargée avec succes.")
     print(f"Dimensions : {df.shape[0]:,} lignes x {df.shape[1]} colonnes")
 
     # Apercu des premieres lignes
@@ -110,6 +119,7 @@ def extract_kpis():
     print(f"Exemples : {symptom_cols[:5]}")
 
     # Résumé
+    log("Affichage du résumé...")
     symptom_cols = df.columns[4:].tolist()
     meta = {
         "shape": df.shape,
@@ -130,6 +140,7 @@ def extract_kpis():
     with open(f"{WORKING_DIR}/dataset_summary.json", "w", encoding="utf-8") as f:
         json.dump(meta, f, indent=2, ensure_ascii=False)
 
+    log("Résumé exporté avec succès.")
 
     # In[ ]: