Update data_us.py

data_us.py

@@ -4,7 +4,7 @@ data_us.py — US market data layer (yfinance), replacing baostock/pytdx.
 Levels & history limits (Yahoo Finance API constraints):
     daily   : 10 years          (weekly / monthly are resampled from daily
                                  by chan_multilevel.resample_weekly/_monthly)
-    60m     : last 730 days
+    60m     : last 730 days  (fetched as "1h" interval with explicit start/end dates)
     30m/15m : last 60 days
     5m      : last 60 days
     1m      : last 7 days only → too short for Chan decomposition, NOT used.
@@ -20,6 +20,7 @@ and refreshed when stale (daily: >12h old, intraday: >2h old) or on force=True.
 from __future__ import annotations
 
 import os
+import threading
 import time
 import traceback
 
@@ -27,12 +28,22 @@ import pandas as pd
 
 import paths
 
+# yfinance uses a shared SQLite cache (peewee) for timezone lookups.
+# When multiple threads call yf.Ticker().history() simultaneously the DB
+# gets locked and raises peewee.OperationalError, stalling prefetch and
+# freezing the "Run analysis" button. Serialise the yfinance connect/lookup
+# phase with a process-wide lock — Yahoo's own rate-limit is the real
+# bottleneck anyway, so the extra serialisation costs almost nothing.
+_YF_LOCK = threading.Lock()
+
 CACHE_DIR = os.environ.get("CHAN_CACHE_DIR", paths.CACHE_DIR)
 
 LEVELS = {
-    # level: (yfinance interval, period) — Yahoo's max history per interval
+    # level: (yfinance interval, period_or_days)
+    # For "60m" Yahoo requires explicit start/end dates (not a period string)
+    # when fetching more than ~60 days back; we pass days as an int sentinel.
     "d":   ("1d",  "10y"),
-    "60m": ("1h", "730d"),
+    "60m": ("1h",  "730d"),    # use explicit start/end — "period='730d'" is rejected by Yahoo for 1h
     "30m": ("30m", "60d"),
     "15m": ("15m", "60d"),
     "5m":  ("5m",  "60d"),
@@ -91,9 +102,22 @@ def load_level(ticker: str, level: str, force: bool = False) -> pd.DataFrame:
                 pass
     try:
         import yfinance as yf
+        from datetime import datetime, timedelta
         interval, period = LEVELS[level]
-        raw = yf.Ticker(ticker).history(period=period, interval=interval,
-                                        auto_adjust=True, actions=False)
+        # Acquire lock before any yfinance call — the shared peewee/SQLite
+        # timezone cache raises "database is locked" under concurrent access.
+        with _YF_LOCK:
+            if isinstance(period, int):
+                # Yahoo rejects period strings for hourly data older than ~60 days.
+                # Use explicit start/end timestamps instead.
+                end_dt = datetime.utcnow()
+                start_dt = end_dt - timedelta(days=period)
+                raw = yf.Ticker(ticker).history(start=start_dt, end=end_dt,
+                                                interval=interval,
+                                                auto_adjust=True, actions=False)
+            else:
+                raw = yf.Ticker(ticker).history(period=period, interval=interval,
+                                                auto_adjust=True, actions=False)
         df = _normalize(raw)
         if len(df):
             df.to_parquet(path, index=False)
@@ -144,4 +168,4 @@ def prefetch(tickers, levels=FAST_LEVELS, force: bool = False, workers: int = 5,
 
 def last_daily_date(ticker: str):
     df = load_level(ticker, "d")
-    return None if df.empty else pd.Timestamp(df["date"].iloc[-1])
+    return None if df.empty else pd.Timestamp(df["date"].iloc[-1])