[2026-05-28] 외부 데이터 학습 파이프라인 복구

scripts/build_external_training_dataset.py

@@ -31,16 +31,29 @@ def _num(value, default=0.0):
         return default
 
 
-def _load_daily_amounts() -> dict[tuple[str, str], dict]:
-    result = {}
+def _load_daily_amounts() -> dict[str, list[dict]]:
+    by_ticker = defaultdict(dict)
     for file in DAILY_ROOT.glob("*/stocks.csv"):
         rows = _read_csv(file)
         for row in rows:
             date = str(row.get("date") or file.parent.name)
             ticker = str(row.get("ticker") or row.get("티커") or "")
             if ticker:
-                result[(date, ticker)] = row
-    return result
+                row["date"] = date
+                by_ticker[ticker][date] = row
+    return {
+        ticker: [rows[date] for date in sorted(rows)]
+        for ticker, rows in by_ticker.items()
+    }
+
+
+def _previous_daily_row(daily: dict[str, list[dict]], date: str, ticker: str) -> dict:
+    previous = {}
+    for row in daily.get(ticker, []):
+        if str(row.get("date", "")) >= date:
+            break
+        previous = row
+    return previous
 
 
 def _future_metrics(rows: list[dict], idx: int, entry_price: float):
@@ -84,7 +97,7 @@ def _rows_for_file(path: Path, daily: dict, k: float, breakout_only: bool):
     for date in sorted(by_date):
         day_rows = by_date[date]
         ticker = day_rows[0]["ticker"]
-        daily_row = daily.get((date, ticker), {})
+        daily_row = _previous_daily_row(daily, date, ticker)
         prev_high = _num(daily_row.get("high"))
         prev_low = _num(daily_row.get("low"))
         prev_amount = _num(daily_row.get("amount"))