start experiment 33 (exp/33-q01-m2-reproduction-add-spsharpe22-to-th)

code/MANIFEST.txt

@@ -1,27 +1,27 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : e660b4f2dd7c521615c54a142eec9266837f2e64
+# parent repo HEAD : 483a86e47f777e22f8f4be0326c05133b7dbb5a5
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b5e28b7c0a10ab553eaa6303013a880731742378  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  b419ee55ed455a1c45423d1c9025ca5cc0a98576  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  715ab312125a446af751b928fe41cf41b99ffcd0  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  a82a6a236db93097d48748e541c2cf9caa4e48b5  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  fdd5923a70a399e8680913593ff111641947898e  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
   0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  483221cf1d5bad779d3cf9505269b7fb0b3f165d  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  1286dec07a861f25691b24f71ecc22d8eb3537df  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  6fb61946ea9a83dfb560de3717f5fbf482c4c00e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  5185764bd55dbc63d16582bfcb6adc11b7e6d342  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  3e80f2e08b661ddd2f58ffe5a6196063fa41ae51  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
   d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
-  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
   4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  13a8e4a41ce9afde97a55756d666d3ff5cbbec0e  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  0bb5804a79611c66bc25988226ca0f1cdbe1a7eb  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  8d684b3216b040071d9ee4fa920a0e0c7486d278  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  3cbc0686e6f863d306d93c589a607a5bdb7201f2  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  7c4e6c345fad1978efe8860c0d977d0c02d6f8d9  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  46bcdbcc173ff3a6281fed33d10c1bcac96876b0  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  99e602392d51663cb06d5c425000b1ed1e5a916b  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  6df4f88af22ab4c026c14ef1835f2e630cdf850c  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  020dcdcf288e4832c8cf2386351f78d5ceb4fe13  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
   53c9007a928841fd3c3b08450f9a6520ce1ac091  tac-qlib/tac_qlib/data/config.py
   8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py

code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py

@@ -53,23 +53,61 @@ from qlib.workflow import R
 __all__ = ["RankICLGBModel", "rankic_feval"]
 
 
+def _group_averaged_rank(values: np.ndarray, gid: np.ndarray, offs: np.ndarray) -> np.ndarray:
+    """Averaged (tie-corrected) rank of ``values`` within each group, vectorized.
+
+    ``gid`` maps each row to its group id; ``offs`` holds the cumulative row
+    offsets so that group ``i`` occupies rows ``[offs[i], offs[i+1])``. Returns
+    the same result as ``pandas.Series.rank(method='average')`` applied per
+    group, but in one pass (``np.lexsort`` is the only non-linear step).
+    """
+    n = len(values)
+    order = np.lexsort((values, gid))
+    ord_rank = np.empty(n, dtype=np.float64)
+    ord_rank[order] = np.arange(n, dtype=np.float64) - offs[gid[order]] + 1.0
+    sg = gid[order]
+    sv = values[order]
+    newblock = np.empty(n, dtype=bool)
+    newblock[0] = True
+    newblock[1:] = (sg[1:] != sg[:-1]) | (sv[1:] != sv[:-1])
+    blockid = np.cumsum(newblock) - 1
+    block_mean = np.bincount(blockid, weights=ord_rank[order]) / np.bincount(blockid)
+    out = np.empty(n)
+    out[order] = block_mean[blockid]
+    return out
+
+
 def _per_day_spearman(preds: np.ndarray, labels: np.ndarray, group: np.ndarray) -> float:
     """Mean per-day Spearman rank correlation of preds vs labels.
 
     ``group`` holds the number of rows of each trading day (query group), in
     order. Days with <3 valid rows or a constant pred/label are skipped.
+
+    Vectorized: per-day Spearman == Pearson of the per-day rank transforms,
+    and the Pearson moments (``sum``, ``sum`` of products/squares) aggregate
+    over each day with ``np.bincount``. Runs ~10x faster than the per-day
+    ``pd.Series.rank()`` loop that preceded it — this feval is invoked on the
+    train and valid panels every boosting round, per seed.
     """
     if group is None or len(group) == 0:
         return 0.0
     offs = np.concatenate([[0], np.cumsum(group.astype(int))])
-    vals = []
+    gid = np.repeat(np.arange(len(group)), group.astype(int))
-    for i in range(len(group)):
+    rp = _group_averaged_rank(preds, gid, offs)
-        s = slice(offs[i], offs[i + 1])
+    rl = _group_averaged_rank(labels, gid, offs)
-        p, l = preds[s], labels[s]
+    n_g = group.astype(float)
-        if len(p) < 3 or np.std(p) == 0 or np.std(l) == 0:
+    s_p = np.bincount(gid, weights=rp)
-            continue
+    s_l = np.bincount(gid, weights=rl)
-        vals.append(np.corrcoef(pd.Series(p).rank(), pd.Series(l).rank())[0, 1])
+    s_pl = np.bincount(gid, weights=rp * rl)
-    return float(np.mean(vals)) if vals else 0.0
+    s_pp = np.bincount(gid, weights=rp * rp)
+    s_ll = np.bincount(gid, weights=rl * rl)
+    cov = n_g * s_pl - s_p * s_l
+    var_p = n_g * s_pp - s_p ** 2
+    var_l = n_g * s_ll - s_l ** 2
+    denom = np.sqrt(var_p * var_l)
+    valid = (n_g >= 3) & (denom > 0)
+    corr = np.where(valid, cov / np.where(denom == 0, 1, denom), 0.0)
+    return float(corr[valid].mean()) if valid.any() else 0.0
 
 
 def rankic_feval(preds, dataset):