feat(surfer): Phase 0 GPU floor + validation harness — first real (weak) OOS trend edge

PyTorch-GPU diversified-trend floor (TSMOM 1/3/12mo + inverse-vol + 10% vol-target) + CPCV/Deflated-Sharpe validation, over 22 CME futures x 19.7y (Databento GLBX ohlcv-1d via budget-capped fetcher, ~$32 credits). Verdict: Sharpe +0.32, CPCV median +0.30, IS +0.36/OOS +0.08 (sign-consistent), Deflated Sharpe ~0.92 at honest n_trials. Real but weak edge; fails deploy-grade gates (correct), passes edge-exists. Includes roll-neutralization fix (max-vol outright + zero roll-day returns) that eliminated 988%/day continuous-contract artifacts (RB vol 550%->31%). Plus install_torch_gpu.sh. Data gitignored. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 01:31:37 +02:00
parent e07c409950
commit 8df1c7eea2
4 changed files with 300 additions and 0 deletions
--- a/scripts/surfer/fetch_daily.py
+++ b/scripts/surfer/fetch_daily.py
@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""Download daily OHLCV for the surfer universe — continuous front-month, BUDGET-CAPPED.
+
+Re-confirms get_cost (free, no download) and ABORTS if over the cap before spending.
+Saves raw DBN to data/surfer/ (gitignored). Reads DATABENTO_API_KEY from env (never printed).
+"""
+import os
+import sys
+
+import databento as db
+
+CAP_USD = 40.00          # hard ceiling on cumulative get_cost; covered by $125 free credits ($0 cash)
+PER_ROOT_CAP = 10.00     # per-root sanity cap
+DS = "GLBX.MDP3"
+SCHEMA = "ohlcv-1d"
+START = "2010-06-06"
+END = "2026-06-05"
+ROOTS = ["ES", "NQ", "YM", "RTY", "ZN", "ZB", "ZF", "ZT", "6E", "6J", "6B", "6A",
+         "6C", "GC", "SI", "HG", "CL", "NG", "RB", "ZC", "ZS", "ZW"]
+# parent symbology = all outright expiries per root (fast; continuous chain resolution 504s).
+# We build the continuous series ourselves (volume-roll + ratio-adjust) from these.
+STYPE = "parent"
+OUT_DIR = "data/surfer"
+
+
+def main():
+    key = os.environ.get("DATABENTO_API_KEY")
+    if not key:
+        print("DATABENTO_API_KEY not set"); return 2
+    client = db.Historical(key)
+
+    os.makedirs(OUT_DIR, exist_ok=True)
+    print(f"fetching {SCHEMA} per-root ({len(ROOTS)} roots, {STYPE}) {START}..{END}; "
+          f"per-root get_cost gate (≤${PER_ROOT_CAP}), cumulative cap ${CAP_USD}")
+    import time
+    total_recs = 0
+    spent = 0.0
+    failed = []
+    for r in ROOTS:
+        sym = r + ".FUT"
+        out_r = f"{OUT_DIR}/{r}.dbn"
+        # per-root cost gate (free, no download)
+        try:
+            c_r = client.metadata.get_cost(dataset=DS, symbols=[sym], schema=SCHEMA,
+                                           start=START, end=END, stype_in=STYPE)
+        except Exception as e:
+            print(f"  {r}: get_cost failed ({type(e).__name__}); skipping"); failed.append(r); continue
+        if c_r > PER_ROOT_CAP or spent + c_r > CAP_USD:
+            print(f"  {r}: cost ${c_r:.4f} would breach cap (spent ${spent:.2f}) — SKIP"); failed.append(r); continue
+        ok = False
+        for attempt in range(1, 4):
+            try:
+                data = client.timeseries.get_range(dataset=DS, symbols=[sym], schema=SCHEMA,
+                                                   start=START, end=END, stype_in=STYPE)
+                data.to_file(out_r)
+                n = sum(1 for _ in data)
+                total_recs += n; spent += c_r
+                print(f"  {r}: ${c_r:.4f} {n:,} recs -> {out_r}  (cum ${spent:.2f})")
+                ok = True
+                break
+            except Exception as e:
+                print(f"  {r}: attempt {attempt} {type(e).__name__}; retry in 3s")
+                time.sleep(3)
+        if not ok:
+            failed.append(r)
+    print(f"DONE: {total_recs:,} records, get_cost-cum ${spent:.2f}, "
+          f"{len(ROOTS)-len(failed)}/{len(ROOTS)} roots ok"
+          + (f"; FAILED/SKIPPED: {failed}" if failed else ""))
+    return 1 if failed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())