fix

train_autogluon.py

@@ -7,35 +7,35 @@ def train_bolt_small(
     start="2015-01-01",
     interval="1d",
     prediction_length=30,
-    time_limit=900,              # seconds (15 min). Adjust if needed.
+    time_limit=900,              # Sekunden (15 Min). Bei Bedarf anpassen.
 ):
     """
-    Trains Chronos-Bolt-Small on CPU via AutoGluon with strict CPU-friendly limits.
-    Uses business-day ('B') frequency to handle weekends/holidays.
+    Trainiert Chronos-Bolt-Small auf CPU via AutoGluon mit CPU-freundlichen Limits.
+    Explizite Business-Day-Frequenz ('B') verhindert Frequency-Fehler.
     """
     print(f"[AutoFT] Lade {ticker} ...")
     close = fetch_close_series(ticker, start=start, interval=interval)
     rv = realized_vol(close)
 
-    # Make a tidy dataframe
-    df = rv_to_autogluon_df(rv)  # columns: item_id, timestamp, target
+    # tidy DataFrame: columns = item_id, timestamp, target
+    df = rv_to_autogluon_df(rv)
 
-    # Create a TimeSeriesDataFrame with explicit frequency
+    # TimeSeriesDataFrame mit expliziter Frequenz erzeugen
     tsdf = TimeSeriesDataFrame.from_data_frame(
         df,
         id_column="item_id",
         timestamp_column="timestamp",
-        target_column="target",
-        freq="B",                           # <- set business-day freq
+        # KEIN target_column-Argument in AG 1.4.0 – 'target' wird implizit erkannt
+        freq="B",
     )
-    # Ensure regular frequency (fills gaps with NaNs)
+    # auf reguläres Business-Day-Gitter bringen (Lücken = NaN)
     tsdf = tsdf.convert_frequency("B")
 
     predictor = TimeSeriesPredictor(
         path="/mnt/data/AutogluonChronosBoltSmall",
         prediction_length=prediction_length,
         eval_metric="WQL",
-        freq="B",                           # <- set freq on predictor too
+        freq="B",
         verbosity=2,
     )
 
@@ -47,13 +47,13 @@ def train_bolt_small(
             "Chronos": {
                 "model_path": "autogluon/chronos-bolt-small",
                 "fine_tune": True,
-                "fine_tune_steps": 200,     # keep small for CPU
+                "fine_tune_steps": 200,     # klein halten für CPU
                 "fine_tune_lr": 1e-4,
-                "context_length": 128,      # keep small for CPU
+                "context_length": 128,      # klein halten für CPU
                 "quantile_levels": [0.1, 0.5, 0.9],
             }
         },
-        time_limit=time_limit,               # hard cap so HF Space won’t time out
+        time_limit=time_limit,               # harter Cap, damit HF nicht timeoutet
     )
 
     print("✅ Training abgeschlossen. Modellpfad:", predictor.path)