feat: add OHLCV market data updater

data_manager.py

@@ -103,6 +103,66 @@ def _clean(data: pd.DataFrame) -> pd.DataFrame:
     return data
 
 
+def _clean_market_data(data: pd.DataFrame, field: str) -> pd.DataFrame:
+    """Clean market data while preserving volume gaps."""
+    good = data.columns[data.notna().mean() > 0.5]
+    dropped = set(data.columns) - set(good)
+    if dropped:
+        print(f"--- Dropped {len(dropped)} tickers with >50% missing data ---")
+    data = data[good]
+    if field == "volume":
+        return data
+    return data.ffill().dropna(how="all")
+
+
+def _merge_market_panel(existing: pd.DataFrame | None, new_data: pd.DataFrame) -> pd.DataFrame:
+    """Merge new data into an existing cached panel, preserving old columns and dates."""
+    if existing is None or existing.empty:
+        merged = new_data.copy()
+    elif new_data.empty:
+        merged = existing.copy()
+    else:
+        merged = existing.combine_first(new_data)
+        merged.loc[new_data.index, new_data.columns] = new_data
+    merged = merged.sort_index()
+    merged = merged[~merged.index.duplicated(keep="last")]
+    return merged
+
+
+def update_market_data(market: str, tickers: list[str], fields: list[str]) -> dict[str, pd.DataFrame]:
+    """Download, clean, persist, and return market data panels for requested Yahoo fields."""
+    field_aliases = {
+        "close": "Close",
+        "open": "Open",
+        "high": "High",
+        "low": "Low",
+        "volume": "Volume",
+    }
+    normalized_fields = []
+    yahoo_fields = []
+    for field in fields:
+        normalized = field.lower()
+        if normalized not in field_aliases:
+            raise ValueError(f"Unsupported market data field: {field}")
+        normalized_fields.append(normalized)
+        yahoo_fields.append(field_aliases[normalized])
+
+    os.makedirs(DATA_DIR, exist_ok=True)
+    start = (datetime.now() - timedelta(days=365 * 10)).strftime("%Y-%m-%d")
+    downloaded = _download(tickers, start=start, fields=yahoo_fields)
+
+    cleaned = {}
+    for normalized, yahoo_field in zip(normalized_fields, yahoo_fields):
+        data = _clean_market_data(downloaded.get(yahoo_field, pd.DataFrame()), normalized)
+        existing = load(market, normalized)
+        data = _merge_market_panel(existing, data)
+        path = _data_path(market, normalized)
+        data.to_csv(path)
+        print(f"--- Saved {data.shape[0]} days x {data.shape[1]} tickers to {path} ---")
+        cleaned[normalized] = data
+    return cleaned
+
+
 def update(market: str, tickers: list[str],
            with_open: bool = False) -> pd.DataFrame | tuple[pd.DataFrame, pd.DataFrame]:
     """