Upload engine/predict_yearly.py with huggingface_hub

engine/predict_yearly.py

@@ -237,6 +237,51 @@ def fetch_all_data_yearly(ticker, years=10, no_cache=False):
     """Fetch all data for yearly prediction. 10yr price history + 2Y Treasury."""
     data = {}
 
+    # ── Concurrent cache pre-warm ──────────────────────────────────────────────
+    # The 20+ Alpha Vantage endpoints below are independent; fetched one-by-one they
+    # serialize network latency (~30s cold). Warm them concurrently first (bounded
+    # pool + the locked throttle keeps us under AV's 5/s burst & 75/min caps); the
+    # sequential blocks then read straight from the just-written cache. Skipped when
+    # no_cache — that path bypasses the cache, so a prewarm would double every call.
+    # Specs MUST mirror the (params, cache_key, cache_hours) used by the blocks below.
+    if not no_cache:
+        _prewarm = [
+            ({"function": "OVERVIEW", "symbol": ticker}, f"{ticker}_overview", 168),
+            ({"function": "INCOME_STATEMENT", "symbol": ticker}, f"{ticker}_income", 168),
+            ({"function": "BALANCE_SHEET", "symbol": ticker}, f"{ticker}_balance", 168),
+            ({"function": "CASH_FLOW", "symbol": ticker}, f"{ticker}_cashflow", 168),
+            ({"function": "EARNINGS", "symbol": ticker}, f"{ticker}_earnings", 168),
+            ({"function": "EARNINGS_ESTIMATES", "symbol": ticker}, f"{ticker}_earnings_estimates", 24),
+            ({"function": "GLOBAL_QUOTE", "symbol": ticker}, f"{ticker}_gq", 1),
+            ({"function": "INSIDER_TRANSACTIONS", "symbol": ticker}, f"{ticker}_insider", 168),
+            ({"function": "REALTIME_OPTIONS", "symbol": ticker}, f"{ticker}_options", 4),
+            ({"function": "NEWS_SENTIMENT", "tickers": ticker, "limit": "50", "sort": "LATEST"}, f"{ticker}_sentiment", 2),
+            ({"function": "ANALYTICS_FIXED_WINDOW", "SYMBOLS": ticker, "RANGE": "1year",
+              "INTERVAL": "DAILY", "OHLCV": "close",
+              "CALCULATIONS": "MEAN,STDDEV,CUMULATIVE_RETURN"}, f"{ticker}_analytics_1y", 4),
+            ({"function": "TREASURY_YIELD", "interval": "daily", "maturity": "10year"}, "treasury_10y", 12),
+            ({"function": "FEDERAL_FUNDS_RATE", "interval": "daily"}, "fed_funds", 12),
+            ({"function": "CPI", "interval": "monthly"}, "cpi", 24),
+            ({"function": "UNEMPLOYMENT"}, "unemployment", 24),
+            ({"function": "TREASURY_YIELD", "interval": "daily", "maturity": "2year"}, "treasury_2y", 12),
+            ({"function": "REAL_GDP", "interval": "quarterly"}, "real_gdp", 168),
+            ({"function": "NONFARM_PAYROLL"}, "nonfarm_payroll", 48),
+            ({"function": "WTI", "interval": "monthly"}, "wti_monthly", 168),
+            ({"function": "NATURAL_GAS", "interval": "monthly"}, "natural_gas_monthly", 168),
+            ({"function": "COPPER", "interval": "monthly"}, "copper_monthly", 168),
+        ]
+        from concurrent.futures import ThreadPoolExecutor as _TPE
+
+        def _warm(spec):
+            try:
+                api_call(spec[0], spec[1], spec[2], no_cache=False)
+            except Exception:
+                pass
+
+        print(f"    {DIM}Pre-warming {len(_prewarm)} data endpoints (concurrent)…{RESET}", flush=True)
+        with _TPE(max_workers=6) as _ex:
+            list(_ex.map(_warm, _prewarm))
+
     # 1. Daily price history (10+ years)
     print(f"    [1/17] Daily price history (10yr)...", end=" ", flush=True)
     cache_file = CACHE_DIR / f"{ticker}_daily.csv"