finish experiment 57 (exp/57-signal-quality-gate-gate-trades-based-on)

book/data/signal_quality_gate/signal_quality_gate_results.csv

@@ -0,0 +1,46 @@
+window,gate,start,end,trade_dates,gate_open,gate_closed,trip_rate,base_ann,base_sharpe,base_maxDD,gated_ann,gated_sharpe,gated_maxDD
+2026,hitrate_5d_0.50,2026-01-04,2026-08-19,157,92,65,0.414,0.255023,1.4465,-0.080671,0.649911,5.7351,-0.031795
+2026,hitrate_5d_0.60,2026-01-04,2026-08-19,157,49,108,0.6879,0.255023,1.4465,-0.080671,0.489313,6.0111,-0.014864
+2026,hitrate_5d_0.70,2026-01-04,2026-08-19,157,15,142,0.9045,0.255023,1.4465,-0.080671,0.229523,4.3611,-0.002029
+2026,hitrate_10d_0.50,2026-01-04,2026-08-19,157,109,48,0.3057,0.255023,1.4465,-0.080671,0.335822,2.6391,-0.060142
+2026,hitrate_10d_0.60,2026-01-04,2026-08-19,157,36,121,0.7707,0.255023,1.4465,-0.080671,0.251108,3.8579,-0.026842
+2026,hitrate_10d_0.70,2026-01-04,2026-08-19,157,9,148,0.9427,0.255023,1.4465,-0.080671,0.039314,1.3415,-0.012061
+2026,hitrate_20d_0.40,2026-01-04,2026-08-19,157,157,0,0.0,0.255023,1.4465,-0.080671,0.255023,1.4465,-0.080671
+2026,hitrate_20d_0.50,2026-01-04,2026-08-19,157,118,39,0.2484,0.255023,1.4465,-0.080671,0.343819,2.5185,-0.06259
+2026,hitrate_20d_0.60,2026-01-04,2026-08-19,157,28,129,0.8217,0.255023,1.4465,-0.080671,0.020214,0.3601,-0.028489
+2025,hitrate_5d_0.50,2025-01-02,2025-12-31,250,153,97,0.388,0.177515,0.8573,-0.217417,0.72055,6.9599,-0.048495
+2025,hitrate_5d_0.60,2025-01-02,2025-12-31,250,90,160,0.64,0.177515,0.8573,-0.217417,0.48564,5.3623,-0.046673
+2025,hitrate_5d_0.70,2025-01-02,2025-12-31,250,39,211,0.844,0.177515,0.8573,-0.217417,0.249221,4.9448,-0.009619
+2025,hitrate_10d_0.50,2025-01-02,2025-12-31,250,170,80,0.32,0.177515,0.8573,-0.217417,0.435847,3.5614,-0.055776
+2025,hitrate_10d_0.60,2025-01-02,2025-12-31,250,66,184,0.736,0.177515,0.8573,-0.217417,0.324574,5.2279,-0.016028
+2025,hitrate_10d_0.70,2025-01-02,2025-12-31,250,14,236,0.944,0.177515,0.8573,-0.217417,0.043002,1.4635,-0.010154
+2025,hitrate_20d_0.40,2025-01-02,2025-12-31,250,247,3,0.012,0.177515,0.8573,-0.217417,0.202949,0.9896,-0.217417
+2025,hitrate_20d_0.50,2025-01-02,2025-12-31,250,177,73,0.292,0.177515,0.8573,-0.217417,0.340772,2.8303,-0.071731
+2025,hitrate_20d_0.60,2025-01-02,2025-12-31,250,48,202,0.808,0.177515,0.8573,-0.217417,0.266028,4.1749,-0.021527
+2024,hitrate_5d_0.50,2024-01-02,2024-12-31,253,139,114,0.4506,0.08229,0.5594,-0.10685,0.30351,2.4275,-0.088219
+2024,hitrate_5d_0.60,2024-01-02,2024-12-31,253,71,182,0.7194,0.08229,0.5594,-0.10685,0.265365,2.4908,-0.078304
+2024,hitrate_5d_0.70,2024-01-02,2024-12-31,253,19,234,0.9249,0.08229,0.5594,-0.10685,0.143125,3.377,-0.003364
+2024,hitrate_10d_0.50,2024-01-02,2024-12-31,253,157,96,0.3794,0.08229,0.5594,-0.10685,0.277421,2.5767,-0.043146
+2024,hitrate_10d_0.60,2024-01-02,2024-12-31,253,37,216,0.8538,0.08229,0.5594,-0.10685,0.207161,3.6083,-0.011122
+2024,hitrate_10d_0.70,2024-01-02,2024-12-31,253,7,246,0.9723,0.08229,0.5594,-0.10685,0.031785,1.7408,-0.002083
+2024,hitrate_20d_0.40,2024-01-02,2024-12-31,253,247,6,0.0237,0.08229,0.5594,-0.10685,0.078007,0.5342,-0.10685
+2024,hitrate_20d_0.50,2024-01-02,2024-12-31,253,177,76,0.3004,0.08229,0.5594,-0.10685,0.210672,1.8469,-0.056207
+2024,hitrate_20d_0.60,2024-01-02,2024-12-31,253,13,240,0.9486,0.08229,0.5594,-0.10685,0.005953,0.3039,-0.014443
+2023,hitrate_5d_0.50,2023-01-03,2023-12-29,250,139,111,0.444,-0.047644,-0.2738,-0.197856,0.546654,4.2124,-0.035676
+2023,hitrate_5d_0.60,2023-01-03,2023-12-29,250,79,171,0.684,-0.047644,-0.2738,-0.197856,0.556291,5.1026,-0.025449
+2023,hitrate_5d_0.70,2023-01-03,2023-12-29,250,34,216,0.864,-0.047644,-0.2738,-0.197856,0.404269,4.4477,-0.013842
+2023,hitrate_10d_0.50,2023-01-03,2023-12-29,250,148,102,0.408,-0.047644,-0.2738,-0.197856,0.459869,3.5211,-0.046921
+2023,hitrate_10d_0.60,2023-01-03,2023-12-29,250,62,188,0.752,-0.047644,-0.2738,-0.197856,0.368232,4.0148,-0.022983
+2023,hitrate_10d_0.70,2023-01-03,2023-12-29,250,13,237,0.948,-0.047644,-0.2738,-0.197856,0.091481,2.1324,-0.010866
+2023,hitrate_20d_0.40,2023-01-03,2023-12-29,250,237,13,0.052,-0.047644,-0.2738,-0.197856,0.06639,0.3895,-0.146704
+2023,hitrate_20d_0.50,2023-01-03,2023-12-29,250,149,101,0.404,-0.047644,-0.2738,-0.197856,0.366016,2.5969,-0.063998
+2023,hitrate_20d_0.60,2023-01-03,2023-12-29,250,40,210,0.84,-0.047644,-0.2738,-0.197856,0.149844,2.2645,-0.032267
+2021,hitrate_5d_0.50,2021-01-04,2021-12-31,252,145,107,0.4246,0.18367,1.0979,-0.102651,0.556615,5.9167,-0.028062
+2021,hitrate_5d_0.60,2021-01-04,2021-12-31,252,68,184,0.7302,0.18367,1.0979,-0.102651,0.351867,5.8468,-0.011638
+2021,hitrate_5d_0.70,2021-01-04,2021-12-31,252,26,226,0.8968,0.18367,1.0979,-0.102651,0.148417,3.9593,-0.0041
+2021,hitrate_10d_0.50,2021-01-04,2021-12-31,252,163,89,0.3532,0.18367,1.0979,-0.102651,0.465023,4.2342,-0.040569
+2021,hitrate_10d_0.60,2021-01-04,2021-12-31,252,51,201,0.7976,0.18367,1.0979,-0.102651,0.21802,4.7978,-0.011134
+2021,hitrate_10d_0.70,2021-01-04,2021-12-31,252,13,239,0.9484,0.18367,1.0979,-0.102651,0.06108,2.7055,-0.000262
+2021,hitrate_20d_0.40,2021-01-04,2021-12-31,252,252,0,0.0,0.18367,1.0979,-0.102651,0.18367,1.0979,-0.102651
+2021,hitrate_20d_0.50,2021-01-04,2021-12-31,252,166,86,0.3413,0.18367,1.0979,-0.102651,0.289756,2.5787,-0.049244
+2021,hitrate_20d_0.60,2021-01-04,2021-12-31,252,38,214,0.8492,0.18367,1.0979,-0.102651,0.104685,2.394,-0.015084

book/data/signal_quality_gate/signal_quality_gate_results.json

@@ -0,0 +1,722 @@
+[
+  {
+    "window": "2026",
+    "gate": "hitrate_5d_0.50",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 92,
+    "gate_closed": 65,
+    "trip_rate": 0.414,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.649911,
+    "gated_sharpe": 5.7351,
+    "gated_maxDD": -0.031795
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_5d_0.60",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 49,
+    "gate_closed": 108,
+    "trip_rate": 0.6879,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.489313,
+    "gated_sharpe": 6.0111,
+    "gated_maxDD": -0.014864
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_5d_0.70",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 15,
+    "gate_closed": 142,
+    "trip_rate": 0.9045,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.229523,
+    "gated_sharpe": 4.3611,
+    "gated_maxDD": -0.002029
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_10d_0.50",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 109,
+    "gate_closed": 48,
+    "trip_rate": 0.3057,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.335822,
+    "gated_sharpe": 2.6391,
+    "gated_maxDD": -0.060142
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_10d_0.60",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 36,
+    "gate_closed": 121,
+    "trip_rate": 0.7707,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.251108,
+    "gated_sharpe": 3.8579,
+    "gated_maxDD": -0.026842
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_10d_0.70",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 9,
+    "gate_closed": 148,
+    "trip_rate": 0.9427,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.039314,
+    "gated_sharpe": 1.3415,
+    "gated_maxDD": -0.012061
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_20d_0.40",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 157,
+    "gate_closed": 0,
+    "trip_rate": 0.0,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.255023,
+    "gated_sharpe": 1.4465,
+    "gated_maxDD": -0.080671
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_20d_0.50",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 118,
+    "gate_closed": 39,
+    "trip_rate": 0.2484,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.343819,
+    "gated_sharpe": 2.5185,
+    "gated_maxDD": -0.06259
+  },
+  {
+    "window": "2026",
+    "gate": "hitrate_20d_0.60",
+    "start": "2026-01-04",
+    "end": "2026-08-19",
+    "trade_dates": 157,
+    "gate_open": 28,
+    "gate_closed": 129,
+    "trip_rate": 0.8217,
+    "base_ann": 0.255023,
+    "base_sharpe": 1.4465,
+    "base_maxDD": -0.080671,
+    "gated_ann": 0.020214,
+    "gated_sharpe": 0.3601,
+    "gated_maxDD": -0.028489
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_5d_0.50",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 153,
+    "gate_closed": 97,
+    "trip_rate": 0.388,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.72055,
+    "gated_sharpe": 6.9599,
+    "gated_maxDD": -0.048495
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_5d_0.60",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 90,
+    "gate_closed": 160,
+    "trip_rate": 0.64,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.48564,
+    "gated_sharpe": 5.3623,
+    "gated_maxDD": -0.046673
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_5d_0.70",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 39,
+    "gate_closed": 211,
+    "trip_rate": 0.844,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.249221,
+    "gated_sharpe": 4.9448,
+    "gated_maxDD": -0.009619
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_10d_0.50",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 170,
+    "gate_closed": 80,
+    "trip_rate": 0.32,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.435847,
+    "gated_sharpe": 3.5614,
+    "gated_maxDD": -0.055776
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_10d_0.60",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 66,
+    "gate_closed": 184,
+    "trip_rate": 0.736,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.324574,
+    "gated_sharpe": 5.2279,
+    "gated_maxDD": -0.016028
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_10d_0.70",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 14,
+    "gate_closed": 236,
+    "trip_rate": 0.944,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.043002,
+    "gated_sharpe": 1.4635,
+    "gated_maxDD": -0.010154
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_20d_0.40",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 247,
+    "gate_closed": 3,
+    "trip_rate": 0.012,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.202949,
+    "gated_sharpe": 0.9896,
+    "gated_maxDD": -0.217417
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_20d_0.50",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 177,
+    "gate_closed": 73,
+    "trip_rate": 0.292,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.340772,
+    "gated_sharpe": 2.8303,
+    "gated_maxDD": -0.071731
+  },
+  {
+    "window": "2025",
+    "gate": "hitrate_20d_0.60",
+    "start": "2025-01-02",
+    "end": "2025-12-31",
+    "trade_dates": 250,
+    "gate_open": 48,
+    "gate_closed": 202,
+    "trip_rate": 0.808,
+    "base_ann": 0.177515,
+    "base_sharpe": 0.8573,
+    "base_maxDD": -0.217417,
+    "gated_ann": 0.266028,
+    "gated_sharpe": 4.1749,
+    "gated_maxDD": -0.021527
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_5d_0.50",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 139,
+    "gate_closed": 114,
+    "trip_rate": 0.4506,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.30351,
+    "gated_sharpe": 2.4275,
+    "gated_maxDD": -0.088219
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_5d_0.60",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 71,
+    "gate_closed": 182,
+    "trip_rate": 0.7194,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.265365,
+    "gated_sharpe": 2.4908,
+    "gated_maxDD": -0.078304
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_5d_0.70",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 19,
+    "gate_closed": 234,
+    "trip_rate": 0.9249,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.143125,
+    "gated_sharpe": 3.377,
+    "gated_maxDD": -0.003364
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_10d_0.50",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 157,
+    "gate_closed": 96,
+    "trip_rate": 0.3794,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.277421,
+    "gated_sharpe": 2.5767,
+    "gated_maxDD": -0.043146
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_10d_0.60",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 37,
+    "gate_closed": 216,
+    "trip_rate": 0.8538,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.207161,
+    "gated_sharpe": 3.6083,
+    "gated_maxDD": -0.011122
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_10d_0.70",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 7,
+    "gate_closed": 246,
+    "trip_rate": 0.9723,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.031785,
+    "gated_sharpe": 1.7408,
+    "gated_maxDD": -0.002083
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_20d_0.40",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 247,
+    "gate_closed": 6,
+    "trip_rate": 0.0237,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.078007,
+    "gated_sharpe": 0.5342,
+    "gated_maxDD": -0.10685
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_20d_0.50",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 177,
+    "gate_closed": 76,
+    "trip_rate": 0.3004,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.210672,
+    "gated_sharpe": 1.8469,
+    "gated_maxDD": -0.056207
+  },
+  {
+    "window": "2024",
+    "gate": "hitrate_20d_0.60",
+    "start": "2024-01-02",
+    "end": "2024-12-31",
+    "trade_dates": 253,
+    "gate_open": 13,
+    "gate_closed": 240,
+    "trip_rate": 0.9486,
+    "base_ann": 0.08229,
+    "base_sharpe": 0.5594,
+    "base_maxDD": -0.10685,
+    "gated_ann": 0.005953,
+    "gated_sharpe": 0.3039,
+    "gated_maxDD": -0.014443
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_5d_0.50",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 139,
+    "gate_closed": 111,
+    "trip_rate": 0.444,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.546654,
+    "gated_sharpe": 4.2124,
+    "gated_maxDD": -0.035676
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_5d_0.60",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 79,
+    "gate_closed": 171,
+    "trip_rate": 0.684,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.556291,
+    "gated_sharpe": 5.1026,
+    "gated_maxDD": -0.025449
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_5d_0.70",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 34,
+    "gate_closed": 216,
+    "trip_rate": 0.864,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.404269,
+    "gated_sharpe": 4.4477,
+    "gated_maxDD": -0.013842
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_10d_0.50",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 148,
+    "gate_closed": 102,
+    "trip_rate": 0.408,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.459869,
+    "gated_sharpe": 3.5211,
+    "gated_maxDD": -0.046921
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_10d_0.60",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 62,
+    "gate_closed": 188,
+    "trip_rate": 0.752,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.368232,
+    "gated_sharpe": 4.0148,
+    "gated_maxDD": -0.022983
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_10d_0.70",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 13,
+    "gate_closed": 237,
+    "trip_rate": 0.948,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.091481,
+    "gated_sharpe": 2.1324,
+    "gated_maxDD": -0.010866
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_20d_0.40",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 237,
+    "gate_closed": 13,
+    "trip_rate": 0.052,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.06639,
+    "gated_sharpe": 0.3895,
+    "gated_maxDD": -0.146704
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_20d_0.50",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 149,
+    "gate_closed": 101,
+    "trip_rate": 0.404,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.366016,
+    "gated_sharpe": 2.5969,
+    "gated_maxDD": -0.063998
+  },
+  {
+    "window": "2023",
+    "gate": "hitrate_20d_0.60",
+    "start": "2023-01-03",
+    "end": "2023-12-29",
+    "trade_dates": 250,
+    "gate_open": 40,
+    "gate_closed": 210,
+    "trip_rate": 0.84,
+    "base_ann": -0.047644,
+    "base_sharpe": -0.2738,
+    "base_maxDD": -0.197856,
+    "gated_ann": 0.149844,
+    "gated_sharpe": 2.2645,
+    "gated_maxDD": -0.032267
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_5d_0.50",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 145,
+    "gate_closed": 107,
+    "trip_rate": 0.4246,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.556615,
+    "gated_sharpe": 5.9167,
+    "gated_maxDD": -0.028062
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_5d_0.60",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 68,
+    "gate_closed": 184,
+    "trip_rate": 0.7302,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.351867,
+    "gated_sharpe": 5.8468,
+    "gated_maxDD": -0.011638
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_5d_0.70",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 26,
+    "gate_closed": 226,
+    "trip_rate": 0.8968,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.148417,
+    "gated_sharpe": 3.9593,
+    "gated_maxDD": -0.0041
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_10d_0.50",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 163,
+    "gate_closed": 89,
+    "trip_rate": 0.3532,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.465023,
+    "gated_sharpe": 4.2342,
+    "gated_maxDD": -0.040569
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_10d_0.60",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 51,
+    "gate_closed": 201,
+    "trip_rate": 0.7976,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.21802,
+    "gated_sharpe": 4.7978,
+    "gated_maxDD": -0.011134
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_10d_0.70",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 13,
+    "gate_closed": 239,
+    "trip_rate": 0.9484,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.06108,
+    "gated_sharpe": 2.7055,
+    "gated_maxDD": -0.000262
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_20d_0.40",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 252,
+    "gate_closed": 0,
+    "trip_rate": 0.0,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.18367,
+    "gated_sharpe": 1.0979,
+    "gated_maxDD": -0.102651
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_20d_0.50",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 166,
+    "gate_closed": 86,
+    "trip_rate": 0.3413,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.289756,
+    "gated_sharpe": 2.5787,
+    "gated_maxDD": -0.049244
+  },
+  {
+    "window": "2021",
+    "gate": "hitrate_20d_0.60",
+    "start": "2021-01-04",
+    "end": "2021-12-31",
+    "trade_dates": 252,
+    "gate_open": 38,
+    "gate_closed": 214,
+    "trip_rate": 0.8492,
+    "base_ann": 0.18367,
+    "base_sharpe": 1.0979,
+    "base_maxDD": -0.102651,
+    "gated_ann": 0.104685,
+    "gated_sharpe": 2.394,
+    "gated_maxDD": -0.015084
+  }
+]

book/scripts/signal_quality_gate_bt.py

@@ -0,0 +1,293 @@
+"""Signal-quality gate walk-forward backtest.
+
+Gates trades based on whether the model's recent topk predictions were correct
+(hit rate). This is a retrospective gate — it measures prediction accuracy,
+not market state.
+
+Usage:
+    cd /app && .venv/bin/python book/scripts/signal_quality_gate_bt.py
+"""
+
+from __future__ import annotations
+
+import json
+import pathlib
+import sys
+import time
+
+import numpy as np
+import pandas as pd
+
+LAKE_ROOT = "/home/data/lake"
+MARKET = "US"
+OUT_DIR = pathlib.Path("/app/experiments/book/data/signal_quality_gate")
+
+WINDOWS = [
+    {"label": "2026", "start": "2026-01-04", "end": "2026-08-19",
+     "pred": f"{LAKE_ROOT}/mlruns/52/9f98ea5c550a409f87b56a6cd8fee343/artifacts/pred.pkl"},
+    {"label": "2025", "start": "2025-01-02", "end": "2025-12-31",
+     "pred": f"{LAKE_ROOT}/mlruns/52/fe96741654df4780957a3a949999ae6a/artifacts/pred.pkl"},
+    {"label": "2024", "start": "2024-01-02", "end": "2024-12-31",
+     "pred": f"{LAKE_ROOT}/mlruns/52/71ed5bfa9984490f8bba8b222f7acc39/artifacts/pred.pkl"},
+    {"label": "2023", "start": "2023-01-03", "end": "2023-12-29",
+     "pred": f"{LAKE_ROOT}/mlruns/56/8ca46e554311444c9a42637a788226e8/artifacts/pred.pkl"},
+    {"label": "2021", "start": "2021-01-04", "end": "2021-12-31",
+     "pred": f"{LAKE_ROOT}/mlruns/56/4e0700ddab2a4e108b46efece7346ee3/artifacts/pred.pkl"},
+]
+
+# Signal-quality gate configs: (lookback_days, threshold, name)
+SIGNAL_GATE_CONFIGS = [
+    (5, 0.50, "hitrate_5d_0.50"),
+    (5, 0.60, "hitrate_5d_0.60"),
+    (5, 0.70, "hitrate_5d_0.70"),
+    (10, 0.50, "hitrate_10d_0.50"),
+    (10, 0.60, "hitrate_10d_0.60"),
+    (10, 0.70, "hitrate_10d_0.70"),
+    (20, 0.40, "hitrate_20d_0.40"),
+    (20, 0.50, "hitrate_20d_0.50"),
+    (20, 0.60, "hitrate_20d_0.60"),
+]
+
+
+def load_pred(path: str) -> pd.Series:
+    df = pd.read_pickle(path)
+    if isinstance(df, pd.DataFrame):
+        if "score" in df.columns:
+            s = df["score"]
+        else:
+            s = df.iloc[:, 0]
+    else:
+        s = df
+    idx = s.index
+    new_dt = pd.to_datetime(idx.get_level_values(0)).normalize()
+    s.index = pd.MultiIndex.from_arrays([new_dt, idx.get_level_values(1)], names=idx.names)
+    return s
+
+
+def load_bars_for_window(start: str, end: str) -> pd.DataFrame:
+    from tac_qlib.data.config import LakeConfig, resolve_lake_root
+    cfg = LakeConfig(resolve_lake_root(LAKE_ROOT), MARKET)
+    sp = cfg.lake_root / "symbols.parquet"
+    if sp.exists():
+        syms = pd.read_parquet(sp)
+        col = "symbol" if "symbol" in syms.columns else syms.columns[0]
+        symbols = sorted(syms[col].astype(str).str.upper().tolist())
+    else:
+        return pd.DataFrame()
+    closes = {}
+    for sym in symbols:
+        p = cfg.bar_path("1d", sym)
+        if not p.exists():
+            continue
+        try:
+            df = pd.read_parquet(p)
+        except Exception:
+            continue
+        if not len(df):
+            continue
+        tcol = df["t"] if "t" in df.columns else df["date"]
+        ts = pd.to_datetime(tcol)
+        df = df.assign(_t=ts).set_index("_t").sort_index()
+        warmup_start = pd.Timestamp(start) - pd.Timedelta(days=60)
+        df = df.loc[warmup_start:end]
+        if len(df) >= 22:
+            closes[sym] = df["c"]
+    return pd.DataFrame(closes)
+
+
+def compute_hit_rate_series(
+    pred: pd.Series, ret_df: pd.DataFrame, topk: int = 10, lookback: int = 10,
+) -> pd.Series:
+    dt_idx = pred.index.get_level_values(0)
+    trade_dates = sorted(dt_idx.unique())
+    hit_rates = {}
+    for i in range(1, len(trade_dates)):
+        prev_date = trade_dates[i - 1]
+        curr_date = trade_dates[i]
+        try:
+            prev_scores = pred.loc[prev_date]
+        except KeyError:
+            continue
+        if isinstance(prev_scores, pd.DataFrame):
+            prev_scores = prev_scores.iloc[:, 0]
+        prev_scores = prev_scores.dropna().sort_values(ascending=False)
+        topk_syms = list(prev_scores.index[:topk])
+        if curr_date not in ret_df.index:
+            continue
+        today_ret = ret_df.loc[curr_date]
+        topk_rets = today_ret.reindex(topk_syms).dropna()
+        if len(topk_rets) > 0:
+            hit_rate = (topk_rets > 0).mean()
+            hit_rates[curr_date] = hit_rate
+    hit_series = pd.Series(hit_rates)
+    if len(hit_series) == 0:
+        return hit_series
+    rolling_hr = hit_series.rolling(lookback, min_periods=max(1, lookback // 2)).mean()
+    return rolling_hr
+
+
+def run_backtest(pred, hit_rate, close_df, start, end, topk=10, threshold=0.5):
+    if not isinstance(pred.index, pd.MultiIndex):
+        return {"error": "pred must have MultiIndex"}
+    ret_df = close_df.pct_change()
+    ret_df.index = pd.to_datetime(ret_df.index).normalize()
+    dt_idx = pred.index.get_level_values(0)
+    window_mask = (dt_idx >= pd.Timestamp(start)) & (dt_idx <= pd.Timestamp(end))
+    window_pred = pred.loc[window_mask]
+    if len(window_pred) == 0:
+        return {"error": "no pred data in window"}
+    trade_dates = sorted(dt_idx[window_mask].unique())
+    gate_open = {}
+    for d in trade_dates:
+        known = hit_rate[hit_rate.index <= d]
+        if len(known) > 0 and not pd.isna(known.iloc[-1]):
+            gate_open[d] = bool(known.iloc[-1] >= threshold)
+        else:
+            gate_open[d] = True
+    n_total = len(trade_dates)
+    n_open = sum(1 for v in gate_open.values() if v)
+    n_closed = n_total - n_open
+    holdings_base = []
+    holdings_gated = []
+    equity_gated = 1_000_000.0
+    equity_base = 1_000_000.0
+    prev_week = None
+    prev_scores = None
+    daily_gated = []
+    daily_base = []
+    ret_by_date = {rd: ret_df.loc[rd] for rd in ret_df.index}
+    for d in trade_dates:
+        try:
+            day_scores = window_pred.loc[d]
+        except KeyError:
+            daily_gated.append(equity_gated)
+            daily_base.append(equity_base)
+            prev_scores = None
+            continue
+        if isinstance(day_scores, pd.DataFrame):
+            day_scores = day_scores.iloc[:, 0]
+        day_scores = day_scores.dropna().sort_values(ascending=False)
+        if len(day_scores) == 0:
+            daily_gated.append(equity_gated)
+            daily_base.append(equity_base)
+            prev_scores = None
+            continue
+        ret_row = ret_by_date.get(d)
+        if ret_row is None:
+            daily_gated.append(equity_gated)
+            daily_base.append(equity_base)
+            prev_scores = day_scores
+            continue
+        cur_week = (d.isocalendar()[0], d.isocalendar()[1]) if hasattr(d, 'isocalendar') else None
+        gate_val = gate_open.get(d, True)
+        if cur_week != prev_week or not holdings_base:
+            if prev_scores is not None:
+                holdings_base = list(prev_scores.index[:topk])
+        if holdings_base:
+            base_rets = ret_row.reindex(holdings_base).dropna()
+            if len(base_rets) > 0:
+                equity_base *= (1 + base_rets.mean())
+        if gate_val:
+            if cur_week != prev_week or not holdings_gated:
+                if prev_scores is not None:
+                    holdings_gated = list(prev_scores.index[:topk])
+            if holdings_gated:
+                hold_rets = ret_row.reindex(holdings_gated).dropna()
+                if len(hold_rets) > 0:
+                    equity_gated *= (1 + hold_rets.mean())
+        else:
+            holdings_gated = []
+        prev_week = cur_week
+        prev_scores = day_scores
+        daily_gated.append(equity_gated)
+        daily_base.append(equity_base)
+    g_series = pd.Series(daily_gated, index=trade_dates)
+    b_series = pd.Series(daily_base, index=trade_dates)
+    def _metrics(eq):
+        if len(eq) < 2:
+            return {"ann_return": 0, "sharpe": 0, "maxDD": 0}
+        rets = eq.pct_change().dropna()
+        ann_ret = float((eq.iloc[-1] / eq.iloc[0]) ** (252 / max(len(eq), 1)) - 1)
+        vol = float(rets.std() * (252 ** 0.5)) if len(rets) > 1 else 0
+        sharpe = ann_ret / vol if vol > 0 else 0
+        peak = eq.cummax()
+        dd = (eq - peak) / peak
+        maxDD = float(dd.min())
+        return {"ann_return": round(ann_ret, 6), "sharpe": round(sharpe, 4), "maxDD": round(maxDD, 6)}
+    base_m = _metrics(b_series)
+    gated_m = _metrics(g_series)
+    return {
+        "trade_dates": n_total,
+        "gate_open_days": n_open,
+        "gate_closed_days": n_closed,
+        "trip_rate": round(n_closed / n_total, 4) if n_total else 0,
+        "base": base_m,
+        "gated": gated_m,
+    }
+
+
+def main():
+    OUT_DIR.mkdir(parents=True, exist_ok=True)
+    full_start = "2015-01-03"
+    full_end = "2026-08-19"
+    print("Loading lake bars...")
+    close_df = load_bars_for_window(full_start, full_end)
+    print(f"  {close_df.shape[1]} symbols, {close_df.shape[0]} days")
+    ret_df = close_df.pct_change()
+    ret_df.index = pd.to_datetime(ret_df.index).normalize()
+    results = []
+    for window in WINDOWS:
+        wl, ws, we = window["label"], window["start"], window["end"]
+        pred_path = window["pred"]
+        print(f"\n=== Window {wl} ({ws} to {we}) ===")
+        pred = load_pred(pred_path)
+        print(f"  pred shape: {pred.shape}")
+        hit_rates = {}
+        for lookback, _, name in SIGNAL_GATE_CONFIGS:
+            if lookback not in hit_rates:
+                hr = compute_hit_rate_series(pred, ret_df, topk=10, lookback=lookback)
+                hit_rates[lookback] = hr
+                print(f"  lookback={lookback}: {len(hr)} days with hit rates")
+        for lookback, threshold, name in SIGNAL_GATE_CONFIGS:
+            hr = hit_rates[lookback]
+            bt = run_backtest(pred, hr, close_df, ws, we, topk=10, threshold=threshold)
+            if "error" in bt:
+                print(f"  {name}: {bt['error']}")
+                continue
+            row = {
+                "window": wl,
+                "gate": name,
+                "start": ws,
+                "end": we,
+                "trade_dates": bt["trade_dates"],
+                "gate_open": bt["gate_open_days"],
+                "gate_closed": bt["gate_closed_days"],
+                "trip_rate": bt["trip_rate"],
+                "base_ann": bt["base"]["ann_return"],
+                "base_sharpe": bt["base"]["sharpe"],
+                "base_maxDD": bt["base"]["maxDD"],
+                "gated_ann": bt["gated"]["ann_return"],
+                "gated_sharpe": bt["gated"]["sharpe"],
+                "gated_maxDD": bt["gated"]["maxDD"],
+            }
+            results.append(row)
+            print(f"  {name}: trip={bt['trip_rate']:.1%}, "
+                  f"base={bt['base']['ann_return']:+.1%} (Sharpe {bt['base']['sharpe']:.2f}), "
+                  f"gated={bt['gated']['ann_return']:+.1%} (Sharpe {bt['gated']['sharpe']:.2f})")
+    df = pd.DataFrame(results)
+    out_path = OUT_DIR / "signal_quality_gate_results.csv"
+    df.to_csv(out_path, index=False)
+    with open(OUT_DIR / "signal_quality_gate_results.json", "w") as f:
+        json.dump(df.to_dict(orient="records"), f, indent=2, default=str)
+    print(f"\nSaved to {out_path}")
+    print("\n=== Summary: Gated Return by Window ===")
+    for gate_name in df["gate"].unique():
+        gdf = df[df["gate"] == gate_name]
+        print(f"\n{gate_name}:")
+        for _, r in gdf.iterrows():
+            print(f"  {r['window']}: base={r['base_ann']:+.1%}, gated={r['gated_ann']:+.1%}, "
+                  f"trip={r['trip_rate']:.0%}, diff={r['gated_ann']-r['base_ann']:+.1%}pp")
+
+
+if __name__ == "__main__":
+    main()

code/MANIFEST.txt

@@ -0,0 +1,30 @@
+# TradeAC custom-qlib-code snapshot (auto-generated)
+# parent repo HEAD : ceb1e196e24761a87d1afe1bde00079b79e02693
+#   tac-qlib/tac_qlib/contrib
+#   tac-qlib/tac_qlib/data
+# per-file hashes (git hash-object):
+  1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
+  861592c63edd6a0853a9cb174b5970435b135fc8  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
+  5c547a2ef92e075e550fe6d01508a2f1d3f536bc  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  4f656130d167e79dcaaeb7783a121f0b36852374  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
+  b1489f2fc0dee85f0a4f90b2e6ad545ed9c8967b  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  121ef237da1df1b8e21a561c3ad0db200b901339  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  74d0da348cbcc3700c96b6f4fe4391488e61efc5  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
+  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  2c2f167b693f4366a769998e3c9d4804f29e31e0  tac-qlib/tac_qlib/contrib/strategy/__init__.py
+  c29e45e562256bf786c36f91a971b097467276e9  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  6dd1c568a2961842793674390d5abffd1a0e71b8  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  519a1f4c05dbe0ac018ab8b779eb33d53b4dd545  tac-qlib/tac_qlib/contrib/strategy/ic_gate.py
+  79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
+  7bcee5f0b09cfa721440f1354f16f2dd9a112b12  tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
+  fe60bacdfedd48617863be31f24b7c7daebfac5a  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
+  92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
+  316bf4aa160cc8d15929ea648be03f4b4999667d  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  554a3f29d181b64effbf49a8161b32e7f93d8d3e  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  8b47f6d78ac046b6b7b2fb07bd7f3382773ffb73  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/__init__.py

@@ -0,0 +1,11 @@
+from . import data  # noqa: F401  (registers tac_qlib.contrib.data)
+from . import model, strategy  # noqa: F401
+from .data import TACHandler  # noqa: F401
+from .model import RankICLGBModel  # noqa: F401
+from .strategy import OptimalStopControl  # noqa: F401
+
+__all__ = [
+    "TACHandler",
+    "RankICLGBModel",
+    "OptimalStopControl",
+]

code/tac-qlib/tac_qlib/contrib/data/__init__.py

@@ -0,0 +1,3 @@
+from .handler import TACHandler
+
+__all__ = ["TACHandler"]

code/tac-qlib/tac_qlib/contrib/data/handler.py

@@ -0,0 +1,254 @@
+"""TACHandler: a qlib DataHandlerLP that builds datasets from the TradeAC lake.
+
+This is the "custom DataHandler" entry point (Option B): the handler is referenced from the
+workflow yaml's ``dataset.handler`` and reads OHLCV + pre-computed ta-lib features straight
+from the lake parquet files through ``QLibDataLoader`` + the tac_qlib feature provider.
+
+The standard qlib processor pipeline (``infer_processors`` / ``learn_processors``) still runs
+on top, so existing recipes such as ``DropnaLabel``, ``CSZScoreNorm`` or ``RobustZScoreNorm``
+keep working unchanged.
+"""
+
+from __future__ import annotations
+
+import os
+from inspect import getfullargspec
+from typing import List, Optional, Tuple, Union
+
+from qlib.data.dataset import processor as processor_module
+from qlib.data.dataset.handler import DataHandlerLP
+from qlib.utils import get_callable_kwargs
+
+from ...data.config import (
+    LakeConfig,
+    timeframe_for_freq,
+    NON_FEATURE_COLUMNS,
+)
+
+DEFAULT_INFER_PROCESSORS = [
+    {"class": "DropAllNaN", "kwargs": {}},
+    {"class": "ProcessInf", "kwargs": {}},
+    {"class": "ZScoreNorm", "kwargs": {}},
+    {"class": "Fillna", "kwargs": {}},
+]
+DEFAULT_LEARN_PROCESSORS = [
+    {"class": "DropnaLabel"},
+    {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
+]
+
+#: always include raw OHLCV; ta-lib columns are discovered from the lake and appended.
+RAW_FEATURE_FIELDS = ("$open", "$high", "$low", "$close", "$vwap", "$volume")
+
+DEFAULT_LABEL = "Ref($close,-2)/Ref($close,-1)-1"
+
+
+def check_transform_proc(proc_l, fit_start_time, fit_end_time):
+    """Port of ``qlib.contrib.data.handler.check_transform_proc`` (inject fit window into procs)."""
+    new_l = []
+    for p in proc_l:
+        if not isinstance(p, processor_module.Processor):
+            klass, pkwargs = get_callable_kwargs(p, processor_module)
+            args = getfullargspec(klass).args
+            if "fit_start_time" in args and "fit_end_time" in args:
+                assert fit_start_time is not None and fit_end_time is not None, (
+                    "Make sure `fit_start_time` and `fit_end_time` are not None."
+                )
+                pkwargs.update({"fit_start_time": fit_start_time, "fit_end_time": fit_end_time})
+            proc_config = {"class": klass.__name__, "kwargs": pkwargs}
+            if isinstance(p, dict) and "module_path" in p:
+                proc_config["module_path"] = p["module_path"]
+            new_l.append(proc_config)
+        else:
+            new_l.append(p)
+    return new_l
+
+
+def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> List[str]:
+    """Discover feature columns present in *every* feature file of the lake.
+
+    Walks the `family=ta|sp` partition layout (plus any legacy flat files).
+    TA and SP columns are disjoint by construction, so the common set is
+    computed per family (columns shared by all symbol files of that family),
+    then the per-family results are unioned. Returns sorted field names
+    (without the ``$`` prefix). Empty if no features are persisted.
+    """
+    cfg = LakeConfig(lake_root, market)
+    feat_dir = cfg.features_dir(timeframe)
+    if not feat_dir.exists():
+        return []
+    import pyarrow.parquet as pq
+
+    def _family_common(fam_dir: Path) -> set:
+        common = None
+        for p in sorted(fam_dir.glob("symbol=*.parquet")):
+            try:
+                cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
+            except Exception:  # pragma: no cover - skip unreadable files
+                continue
+            common = cols if common is None else (common & cols)
+            if not common:
+                break
+        return common or set()
+
+    common: set = set()
+    # family tier: features/market=*/timeframe=*/family=*/symbol=*.parquet
+    for fam in ("ta", "sp"):
+        fam_dir = feat_dir / f"family={fam}"
+        if fam_dir.is_dir():
+            common |= _family_common(fam_dir)
+    # legacy flat: features/market=*/timeframe=*/symbol=*.parquet
+    if (feat_dir / "family=ta").exists() or (feat_dir / "family=sp").exists():
+        pass  # family layout already covered
+    else:
+        common |= _family_common(feat_dir)
+    return sorted(common)
+
+
+class DropAllNaN(processor_module.Processor):
+    """Drop feature columns that are all-NaN over the fit window.
+
+    The lake can hold fully-empty indicator columns (e.g. a ta-lib output that was NaN
+    from the start). Such columns carry no learnable signal and make ``ZScoreNorm.fit``
+    warn on empty slices, so we drop them before any other processor runs. The drop set
+    is fixed on the fit window once (during ``fit``), then applied consistently to every
+    segment so train/valid/test keep identical feature columns.
+    """
+
+    def __init__(self, fit_start_time=None, fit_end_time=None):
+        self.fit_start_time = fit_start_time
+        self.fit_end_time = fit_end_time
+        self.cols_to_drop = []
+
+    def fit(self, df=None):
+        if df is None or len(df) == 0:
+            return self
+        window = df
+        if self.fit_start_time is not None and self.fit_end_time is not None:
+            try:
+                from qlib.data.dataset.utils import fetch_df_by_index
+
+                window = fetch_df_by_index(
+                    df, slice(self.fit_start_time, self.fit_end_time), level="datetime"
+                )
+            except Exception:  # pragma: no cover - defensive
+                window = df
+        if len(window) == 0:
+            return self
+        self.cols_to_drop = [c for c in window.columns if window[c].isna().all()]
+        return self
+
+    def __call__(self, df):
+        if self.cols_to_drop:
+            return df.drop(columns=self.cols_to_drop, errors="ignore")
+        return df
+
+
+class TACHandler(DataHandlerLP):
+    """DataHandlerLP backed by the TradeAC parquet lake.
+
+    Parameters mirror ``Alpha158``: ``instruments``/``start_time``/``end_time``/``freq`` define
+    the queried window; ``feature_fields`` selects the features (default: raw OHLCV + all common
+    ta-lib columns found in the lake); ``label`` is a qlib expression for the target.
+    """
+
+    def __init__(
+        self,
+        instruments="all",
+        start_time=None,
+        end_time=None,
+        freq="day",
+        infer_processors=DEFAULT_INFER_PROCESSORS,
+        learn_processors=DEFAULT_LEARN_PROCESSORS,
+        fit_start_time=None,
+        fit_end_time=None,
+        process_type=DataHandlerLP.PTYPE_A,
+        filter_pipe=None,
+        feature_fields=None,
+        label=DEFAULT_LABEL,
+        lake_root=None,
+        market="US",
+        **kwargs,
+    ):
+        # default the processor fit window to the queried window (like Alpha158 without a split)
+        if fit_start_time is None:
+            fit_start_time = start_time
+        if fit_end_time is None:
+            fit_end_time = end_time
+
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
+
+        feature_fields = self._normalize_feature_fields(feature_fields, freq, lake_root, market)
+        if not feature_fields:
+            raise ValueError(
+                "no feature fields available for the lake; set `feature_fields` explicitly "
+                "(e.g. ['$close', '$rsi_14', '$sma_20'])"
+            )
+
+        label_expr, label_names = self._normalize_label(label)
+
+        data_loader = {
+            "class": "QlibDataLoader",
+            "kwargs": {
+                "config": {
+                    "feature": (feature_fields, feature_fields),
+                    "label": (label_expr, label_names),
+                },
+                "filter_pipe": filter_pipe,
+                "freq": freq,
+            },
+        }
+        super().__init__(
+            instruments=instruments,
+            start_time=start_time,
+            end_time=end_time,
+            data_loader=data_loader,
+            infer_processors=infer_processors,
+            learn_processors=learn_processors,
+            process_type=process_type,
+            **kwargs,
+        )
+
+    # ------------------------------------------------------------------ config
+    @staticmethod
+    def _normalize_feature_fields(feature_fields, freq, lake_root, market) -> List[str]:
+        if feature_fields is None:
+            common = get_common_feature_fields(lake_root, market, timeframe_for_freq(freq))
+            feature_fields = list(RAW_FEATURE_FIELDS) + ["$" + f for f in common if "$" + f not in RAW_FEATURE_FIELDS]
+        elif isinstance(feature_fields, str):
+            feature_fields = [f.strip() for f in feature_fields.split(",") if f.strip()]
+        fields = [f if f.startswith("$") else "$" + f for f in feature_fields]
+        # de-dup while preserving order
+        seen, out = set(), []
+        for f in fields:
+            if f not in seen:
+                seen.add(f)
+                out.append(f)
+        return out
+
+    @staticmethod
+    def _normalize_label(label) -> Tuple[List[str], List[str]]:
+        if isinstance(label, str):
+            return [label], ["LABEL0"]
+        if isinstance(label, (list, tuple)):
+            if len(label) == 2 and isinstance(label[0], str):
+                return [label[0]], list(label[1]) if isinstance(label[1], (list, tuple)) else [label[1]]
+            return list(label), ["LABEL%d" % i for i in range(len(label))]
+        raise TypeError(f"unsupported label config: {label!r}")
+
+    # ------------------------------------------------------------------ utils
+    def get_label_config(self):
+        return DEFAULT_LABEL
+
+    @staticmethod
+    def discover_feature_fields(lake_root=None, market="US", freq="day") -> List[str]:
+        return get_common_feature_fields(lake_root, market, timeframe_for_freq(freq))
+
+
+__all__ = ["TACHandler", "DropAllNaN", "get_common_feature_fields"]
+
+
+# Make `DropAllNaN` resolvable by bare name from processor configs (e.g. the default
+# ``infer_processors`` and workflow yamls that reference it without a ``module_path``),
+# mirroring how qlib registers its own processors in ``qlib.data.dataset.processor``.
+processor_module.DropAllNaN = DropAllNaN

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

@@ -0,0 +1,4 @@
+from .rank_ensemble import RankICEnsembleLGBModel  # noqa: F401
+from .rank_gbdt import RankICLGBModel, rankic_feval  # noqa: F401
+
+__all__ = ["RankICLGBModel", "rankic_feval", "RankICEnsembleLGBModel"]

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

@@ -0,0 +1,189 @@
+"""Seed-ensembled LightGBM that early-stops on cross-sectional RankIC.
+
+``RankICEnsembleLGBModel`` wraps ``RankICLGBModel`` (per-day RankIC feval +
+``metric='None'`` + ``first_metric_only`` early stopping) over a seed ensemble:
+one sub-model is trained per seed with identical hyper-parameters, and
+predictions are averaged across seeds. This is the model class the
+``tac-rd-rank-ensemble-isolated`` reference run wires into its workflow
+(``module_path: tac_qlib.contrib.model.rank_ensemble``).
+
+The ensemble inherits the RankIC early-stopping behaviour of the single-seed
+model (valid RankIC drives the stopping iteration) while the seed averaging
+stabilizes the prediction against any single seed's early-stopping path.
+
+Training is parallelized: the seed sub-models train in a thread pool —
+``lgb.train`` is C++ and releases the GIL, so concurrent seeds do not block on
+the GIL (5 seeds ~40min/5 on this box). Measured on a 6-physical-core / 12 SMT
+host: the seeds scale ~2x, not linearly — the runs are memory-bandwidth bound
+and each Booster caps its threads at ``cores // workers`` so 5 concurrent
+boosters don't oversubscribe; larger-core hosts scale better. The qlib data
+pipeline is warmed once on the calling thread (fills the handler cache), and
+each worker then prepares its **own** ``lgb.Dataset`` (independent handle, so
+no concurrent ``construct()`` on a shared handle — LightGBM's ``Dataset`` is
+not thread-safe to build). qlib's ``R`` recorder is also not thread-safe, so
+the per-seed evaluation curves are logged on the calling thread after the pool
+finishes.
+
+Wired into a workflow yaml like:
+
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+Any ``**kwargs`` other than ``seeds``/``parallel`` are forwarded unchanged to
+every ``RankICLGBModel`` sub-model (same params, different ``seed``).
+"""
+
+from __future__ import annotations
+
+import os
+from concurrent.futures import ThreadPoolExecutor
+from typing import List, Optional
+
+import pandas as pd
+
+from qlib.data.dataset import DatasetH
+from qlib.data.dataset.handler import DataHandlerLP
+
+from tac_qlib.contrib.model.rank_gbdt import RankICLGBModel
+
+__all__ = ["RankICEnsembleLGBModel"]
+
+
+class RankICEnsembleLGBModel(RankICLGBModel):
+    """Seed ensemble of RankIC-early-stopping LightGBM models.
+
+    Parameters
+    ----------
+    seeds : comma-separated integers, one sub-model per seed.
+    parallel : number of seeds to train concurrently. ``0`` (default) = auto
+        (all seeds, bounded by the available cores); ``1`` = sequential.
+    **kwargs : forwarded to every ``RankICLGBModel`` sub-model (model
+        hyper-parameters). ``seeds``/``parallel`` are consumed here and not
+        forwarded.
+    """
+
+    def __init__(self, seeds: str = "42", parallel: int = 0, **kwargs):
+        self.seeds = [int(s.strip()) for s in str(seeds).split(",") if s.strip()]
+        if not self.seeds:
+            raise ValueError("seeds must contain at least one integer")
+        self.parallel = int(parallel)
+        # drop seed/parallel handling from the base kwargs, keep everything else
+        self._model_kwargs = dict(kwargs)
+        super().__init__(**self._model_kwargs)
+        self._models: List[RankICLGBModel] = []
+
+    # --------------------------------------------------------------- helpers
+    @staticmethod
+    def _cores() -> int:
+        try:
+            return max(1, len(os.sched_getaffinity(0)))
+        except AttributeError:
+            return max(1, os.cpu_count() or 1)
+
+    def _worker_count(self) -> int:
+        if self.parallel > 0:
+            return min(len(self.seeds), self.parallel)
+        return min(len(self.seeds), self._cores())
+
+    # ------------------------------------------------------------------ fit
+    def fit(
+        self,
+        dataset: DatasetH,
+        num_boost_round: Optional[int] = None,
+        early_stopping_rounds: Optional[int] = None,
+        verbose_eval: int = 20,
+        evals_result=None,
+        reweighter=None,
+        **kwargs,
+    ):
+        """Train one RankICLGBModel per seed and keep them for prediction.
+
+        The qlib data pipeline is warmed once on this thread (handler cache),
+        then each seed sub-model trains in a parallel worker thread on its own
+        ``lgb.Dataset`` (LightGBM releases the GIL in ``lgb.train``). Evals
+        are logged on this thread after the pool (qlib's ``R`` is not
+        thread-safe).
+        """
+        n_round = num_boost_round or self.num_boost_round
+        n_es = early_stopping_rounds or self.early_stopping_rounds
+
+        if len(self.seeds) == 1:
+            m = RankICLGBModel(seed=self.seeds[0], **self._model_kwargs)
+            m.fit(
+                dataset,
+                num_boost_round=n_round,
+                early_stopping_rounds=n_es,
+                verbose_eval=verbose_eval,
+                evals_result=evals_result,
+                reweighter=reweighter,
+                **kwargs,
+            )
+            self._models = [m]
+            return
+
+        # Warm the qlib handler cache once on this thread so the workers'
+        # concurrent prepare() calls only hit cached frames (no first-write race).
+        proto = RankICLGBModel(seed=self.seeds[0], **self._model_kwargs)
+        proto._prepare_data(dataset, reweighter)
+
+        workers = self._worker_count()
+        # Cap per-Booster threads so concurrent seeds don't oversubscribe
+        # (LightGBM's num_threads=0 uses ALL cores per Booster).
+        per_booster = max(1, self._cores() // workers)
+
+        def fit_seed(seed):
+            m = RankICLGBModel(seed=seed, **self._model_kwargs)
+            if workers > 1 and "num_threads" not in m.params:
+                m.params["num_threads"] = per_booster
+            ds_l = m._prepare_data(dataset, reweighter)
+            booster, evals, names = m._train_from_datasets(
+                ds_l,
+                num_boost_round=n_round,
+                early_stopping_rounds=n_es,
+                verbose_eval=verbose_eval,
+                **kwargs,
+            )
+            m.model = booster
+            return m, evals, names
+
+        with ThreadPoolExecutor(max_workers=workers) as ex:
+            results = list(ex.map(fit_seed, self.seeds))
+
+        self._models = [m for m, _, _ in results]
+
+        # Merge + log evals on the main thread (qlib's R is not thread-safe).
+        if evals_result is not None:
+            for m, evals, names in results:
+                for k in names:
+                    for key, val in evals.get(k, {}).items():
+                        evals_result.setdefault(f"{k}.seed{m.params['seed']}", {})[key] = val
+        for m, evals, names in results:
+            self._log_evals(evals, names, prefix=f"seed{m.params['seed']}.")
+
+    # -------------------------------------------------------------- predict
+    def predict(self, dataset: DatasetH, segment="test") -> pd.Series:
+        """Average the per-seed predictions over the given segment."""
+        if not self._models:
+            raise ValueError("model is not fitted yet!")
+        preds = [m.predict(dataset, segment=segment) for m in self._models]
+        if len(preds) == 1:
+            return preds[0]
+        frame = pd.concat(preds, axis=1)
+        return frame.mean(axis=1)

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

@@ -0,0 +1,238 @@
+"""LGBModel variant that early-stops on cross-sectional RankIC instead of l2.
+
+Standard qlib ``LGBModel`` early-stops on the regression loss (mse). For
+cross-sectional alpha signals the quantity we actually care about is the per-day
+rank correlation (Rank IC), which mse early-stopping does not optimize for.
+Experiments on the 50-ETF lake (SP-5d 55-feature panel) show that early-stopping
+on a custom RankIC feval lifts RankIC 0.047 -> 0.075 vs. the mse-stopped model.
+
+This class reuses ``LGBModel``'s data preparation but:
+
+  - tags each ``lgb.Dataset`` with per-day query ``group`` sizes so a ranking
+    metric can be computed per trading day;
+  - injects a custom ``feval`` (mean per-day Spearman of pred vs label) into
+    ``lgb.train``; early stopping then selects the iteration that maximizes
+    RankIC on the valid set;
+  - forces ``metric='None'`` + ``first_metric_only=True`` so early-stopping
+    tracks RankIC only (not the regression loss).
+
+Wired into a workflow yaml like:
+
+    model:
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.03
+            num_leaves: 31
+            n_estimators: 500
+            ...
+
+The rank feval is used for early-stopping selection only; the objective stays
+the configured loss (default mse). Set ``rank_eval=False`` to fall back to the
+plain LGBModel behaviour (early-stop on the loss).
+
+Generic: works for any cross-sectional panel whose qlib dataset index has a
+``datetime`` level (each level value = one query group). The per-day groups are
+derived automatically, so no universe-specific configuration is needed.
+"""
+
+from __future__ import annotations
+
+from typing import List, Optional, Tuple
+
+import numpy as np
+import pandas as pd
+import lightgbm as lgb
+
+from qlib.data.dataset import DatasetH
+from qlib.data.dataset.handler import DataHandlerLP
+from qlib.contrib.model.gbdt import LGBModel
+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))])
+    gid = np.repeat(np.arange(len(group)), group.astype(int))
+    rp = _group_averaged_rank(preds, gid, offs)
+    rl = _group_averaged_rank(labels, gid, offs)
+    n_g = group.astype(float)
+    s_p = np.bincount(gid, weights=rp)
+    s_l = np.bincount(gid, weights=rl)
+    s_pl = np.bincount(gid, weights=rp * rl)
+    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):
+    """LightGBM feval: mean RankIC (higher is better in lgb convention)."""
+    labels = dataset.get_label()
+    group = dataset.get_group()
+    ric = _per_day_spearman(preds, labels, group)
+    return "rankic", ric, True  # (name, value, higher_is_better)
+
+
+class RankICLGBModel(LGBModel):
+    """LGBModel that early-stops on per-day RankIC via a custom feval."""
+
+    def __init__(self, rank_eval: bool = True, **kwargs):
+        super().__init__(**kwargs)
+        self.rank_eval = rank_eval
+
+    def _prepare_data(self, dataset: DatasetH, reweighter=None) -> List[Tuple[lgb.Dataset, str]]:
+        ds_l = []
+        assert "train" in dataset.segments
+        for key in ["train", "valid"]:
+            if key in dataset.segments:
+                df = dataset.prepare(key, col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
+                if df.empty:
+                    raise ValueError("Empty data from dataset, please check your dataset config.")
+                x, y = df["feature"], df["label"]
+                if y.values.ndim == 2 and y.values.shape[1] == 1:
+                    y = np.squeeze(y.values)
+                else:
+                    raise ValueError("LightGBM doesn't support multi-label training")
+
+                if reweighter is None:
+                    w = None
+                elif hasattr(reweighter, "reweight"):
+                    w = reweighter.reweight(df)
+                else:
+                    raise ValueError("Unsupported reweighter type.")
+
+                # per-day query groups: each trading day is one group
+                if self.rank_eval and isinstance(df.index, pd.MultiIndex) and "datetime" in df.index.names:
+                    group = df.groupby(level="datetime").size().to_numpy(dtype=np.int32)
+                else:
+                    group = None
+
+                d = lgb.Dataset(x.values, label=y, weight=w, group=group, free_raw_data=False)
+                ds_l.append((d, key))
+        return ds_l
+
+    def _train_from_datasets(
+        self,
+        ds_l: List[Tuple[lgb.Dataset, str]],
+        num_boost_round: Optional[int] = None,
+        early_stopping_rounds: Optional[int] = None,
+        verbose_eval: int = 20,
+        evals_result=None,
+        **kwargs,
+    ) -> Tuple[lgb.Booster, dict, List[str]]:
+        """Train a Booster from already-prepared ``lgb.Dataset`` objects.
+
+        Pure training — no ``R.log_metrics`` — so it can be called from worker
+        threads (qlib's ``R`` recorder is not thread-safe; the caller decides
+        when/where to log). Returns ``(booster, evals_result, segment_names)``.
+        """
+        if evals_result is None:
+            evals_result = {}
+        ds, names = list(zip(*ds_l))
+
+        callbacks = [
+            lgb.early_stopping(
+                self.early_stopping_rounds if early_stopping_rounds is None else early_stopping_rounds
+            ),
+            lgb.log_evaluation(period=verbose_eval),
+            lgb.record_evaluation(evals_result),
+        ]
+        if self.rank_eval:
+            # early-stopping must be driven ONLY by the RankIC feval, not l2.
+            # metric='None' suppresses the default l2 metric; first_metric_only
+            # makes early_stopping track the single remaining (rankic) metric.
+            self.params["metric"] = "None"
+            self.params["first_metric_only"] = True
+            feval = rankic_feval
+        else:
+            self.params.pop("metric", None)
+            self.params.pop("first_metric_only", None)
+            feval = None
+
+        booster = lgb.train(
+            self.params,
+            ds[0],
+            num_boost_round=self.num_boost_round if num_boost_round is None else num_boost_round,
+            valid_sets=ds,
+            valid_names=names,
+            feval=feval,
+            callbacks=callbacks,
+            **kwargs,
+        )
+        return booster, evals_result, list(names)
+
+    def _log_evals(self, evals_result, names: List[str], prefix: str = "") -> None:
+        """Log recorded evaluation curves to qlib's active recorder."""
+        for k in names:
+            for key, val in evals_result.get(k, {}).items():
+                name = f"{prefix}{key}.{k}"
+                for epoch, m in enumerate(val):
+                    R.log_metrics(**{name.replace("@", "_"): m}, step=epoch)
+
+    def fit(
+        self,
+        dataset: DatasetH,
+        num_boost_round: Optional[int] = None,
+        early_stopping_rounds: Optional[int] = None,
+        verbose_eval: int = 20,
+        evals_result=None,
+        reweighter=None,
+        **kwargs,
+    ):
+        if evals_result is None:
+            evals_result = {}
+        ds_l = self._prepare_data(dataset, reweighter)
+        self.model, evals_result, names = self._train_from_datasets(
+            ds_l,
+            num_boost_round=num_boost_round,
+            early_stopping_rounds=early_stopping_rounds,
+            verbose_eval=verbose_eval,
+            evals_result=evals_result,
+            **kwargs,
+        )
+        self._log_evals(evals_result, names)

code/tac-qlib/tac_qlib/contrib/strategy/__init__.py

@@ -0,0 +1,11 @@
+from .ic_gate import ICGateTopkDropoutStrategy  # noqa: F401
+from .optimal_stop import OptimalStopControl  # noqa: F401
+from .regime_gate import RegimeGateTopkDropoutStrategy  # noqa: F401
+from .weekly_rebalance import WeeklyRebalanceDropoutStrategy  # noqa: F401
+
+__all__ = [
+    "ICGateTopkDropoutStrategy",
+    "OptimalStopControl",
+    "RegimeGateTopkDropoutStrategy",
+    "WeeklyRebalanceDropoutStrategy",
+]

code/tac-qlib/tac_qlib/contrib/strategy/ic_gate.py

@@ -0,0 +1,117 @@
+"""Realized-IC circuit breaker TopkDropout strategy.
+
+Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
+holds the book (issues NO orders) while the streaming realized RankIC of the
+deployed signal is below threshold — i.e. the model's cross-sectional
+predictions are no longer earning against realized forward returns. When the
+gate is open it behaves exactly like the reference TopkDropoutStrategy.
+
+The gate is evaluated per trade step on the trailing mean realized RankIC of
+the signal over the last ``ic_window`` trading days whose label is fully
+realized as of the decision date (no lookahead — a 5d fwd label ``close[t+6]/
+close[t+1]-1`` is only known at ``t+6``).
+
+Two wiring modes:
+
+* ``ic_gate``: a precomputed ``pd.Series`` indexed by datetime of booleans
+  (True = gate open / trade allowed). Computed once by the caller (e.g.
+  ``rd_backtest``) and looked up per step. Missing dates default to open.
+* realized-IC self-computation: when ``ic_min_rankic`` is given but no
+  ``ic_gate``, the strategy computes the per-date realized RankIC itself from
+  ``self.signal`` (the pred scores) and the lake 1d bars via
+  ``tac_qlib.risk_limits.realized_rankic_series``, then applies the same
+  trailing-window comparison. Works when instantiated from a workflow YAML
+  PortAnaRecord config (``lake_root`` / ``market`` must be provided).
+"""
+
+from __future__ import annotations
+
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+from tac_qlib.risk_limits import ic_circuit_breaker, realized_rankic_series
+
+__all__ = ["ICGateTopkDropoutStrategy"]
+
+
+class ICGateTopkDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout with a streaming realized-IC circuit breaker.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    ic_min_rankic : float — pause new trading while trailing realized RankIC is
+        below this threshold (0 disables the gate).
+    ic_window : int — trailing window for the realized RankIC mean (default 22).
+    ic_label_horizon : int — label horizon in trading days (default 6).
+    ic_min_obs : int — min realized labels before the gate arms (default 10).
+    ic_gate : pd.Series, optional — precomputed per-date gate (bool indexed by
+        datetime). When provided, it overrides self-computation.
+    lake_root, market : str — lake location for self-computed realized IC.
+    """
+
+    def __init__(
+        self,
+        *,
+        topk,
+        n_drop,
+        ic_min_rankic: float = 0.0,
+        ic_window: int = 22,
+        ic_label_horizon: int = 6,
+        ic_min_obs: int = 10,
+        ic_gate=None,
+        lake_root: str = "",
+        market: str = "US",
+        **kwargs,
+    ):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.ic_min_rankic = float(ic_min_rankic or 0.0)
+        self.ic_window = int(ic_window or 22)
+        self.ic_label_horizon = int(ic_label_horizon or 6)
+        self.ic_min_obs = int(ic_min_obs or 10)
+        self._ic_gate = ic_gate
+        self._realized_ic = None
+        self.lake_root = lake_root or ""
+        self.market = market or "US"
+
+    def _load_realized_ic(self):
+        if self._realized_ic is None:
+            pred_start_time, pred_end_time = self.trade_calendar.get_step_time(
+                self.trade_calendar.get_trade_step(), shift=-self.ic_label_horizon
+            )
+            pred = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+            if isinstance(pred, pd.DataFrame):
+                pred = pred.iloc[:, 0]
+            self._realized_ic = realized_rankic_series(
+                pred, self.lake_root, self.market, label_horizon=self.ic_label_horizon
+            )
+        return self._realized_ic
+
+    def _gate_open(self, trade_start_time) -> bool:
+        ts = pd.Timestamp(trade_start_time)
+        if self._ic_gate is not None:
+            # precomputed gate series: look up the latest known decision date <= ts
+            known = self._ic_gate[self._ic_gate.index <= ts]
+            if len(known):
+                return bool(known.iloc[-1])
+            return True
+        if self.ic_min_rankic <= 0:
+            return True
+        realized = self._load_realized_ic()
+        limits = {
+            "ic_min_rankic": self.ic_min_rankic,
+            "ic_window": self.ic_window,
+            "ic_min_obs": self.ic_min_obs,
+        }
+        tripped, _reason, _trail = ic_circuit_breaker(realized, ts, limits)
+        return not tripped
+
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
+        if not self._gate_open(trade_start_time):
+            return TradeDecisionWO([], self)
+        return super().generate_trade_decision(execute_result)

code/tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py

@@ -0,0 +1,217 @@
+"""Optimal-stopping / stochastic-control strategy for cross-sectional signals.
+
+Entry is a control policy: a symbol opens a position only when its cross-sectional
+signal percentile is at or above ``entry_pct`` (i.e. it is one of the top-ranked
+names) and the portfolio has fewer than ``topk`` open positions.
+
+Exit is an optimal-stopping rule: a held position is stopped (closed) when its
+signal percentile falls below ``exit_pct`` (the continuation value of holding is
+no longer worth the risk), OR after ``max_hold_days`` (time stop / finite
+horizon), OR when the position P&L breaches ``sl`` (loss control) and the
+position has been held at least ``min_hold_days``.
+
+Sizing is fixed ``notional`` per position (equal-weight control), unlike the
+TopkDropout cash-allocation heuristic.
+
+Wired into qrun workflows like any ``BaseStrategy`` (see ``PortAnaRecord``
+config). Mirrors the API usage of qlib's ``TopkDropoutStrategy``: ``Order``/
+``OrderDir`` from ``qlib.backtest.decision``, ``trade_calendar`` /
+``trade_exchange`` / ``trade_position`` injected by the backtest executor.
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import BaseSignalStrategy
+
+__all__ = ["OptimalStopControl"]
+
+DEFAULT_NOTIONAL = 20_000.0
+DEFAULT_ENTRY_PCT = 0.80
+DEFAULT_EXIT_PCT = 0.50
+DEFAULT_MAX_HOLD_DAYS = 10
+DEFAULT_MIN_HOLD_DAYS = 2
+DEFAULT_SL = -0.06
+
+
+class OptimalStopControl(BaseSignalStrategy):
+    """Optimal-stopping long-only strategy over a cross-sectional signal.
+
+    Parameters
+    ----------
+    topk : max number of concurrent positions.
+    entry_pct : min cross-sectional score percentile required to OPEN (0..1).
+    exit_pct : held positions are stopped when score percentile < exit_pct.
+    max_hold_days : hard time stop (finite-horizon close).
+    min_hold_days : minimum holding days before stop-loss is evaluated.
+    notional : $ per position (equal-weight control).
+    sl : stop-loss threshold as fraction of entry price (<= 0), disabled if 0.
+    """
+
+    def __init__(
+        self,
+        *,
+        signal=None,
+        topk: int = 10,
+        entry_pct: float = DEFAULT_ENTRY_PCT,
+        exit_pct: float = DEFAULT_EXIT_PCT,
+        max_hold_days: int = DEFAULT_MAX_HOLD_DAYS,
+        min_hold_days: int = DEFAULT_MIN_HOLD_DAYS,
+        notional: float = DEFAULT_NOTIONAL,
+        sl: float = DEFAULT_SL,
+        risk_degree: float = 0.95,
+        trade_exchange=None,
+        level_infra=None,
+        common_infra=None,
+        **kwargs,
+    ):
+        super().__init__(
+            signal=signal,
+            trade_exchange=trade_exchange,
+            level_infra=level_infra,
+            common_infra=common_infra,
+            **kwargs,
+        )
+        self.topk = topk
+        self.entry_pct = entry_pct
+        self.exit_pct = exit_pct
+        self.max_hold_days = max_hold_days
+        self.min_hold_days = min_hold_days
+        self.notional = notional
+        self.sl = sl
+
+    # ------------------------------------------------------------------ utils
+    @staticmethod
+    def _pct_rank(score: pd.Series) -> pd.Series:
+        return score.rank(pct=True)
+
+    def _entry_price(self, pos) -> float:
+        # Position stores avg entry price under key "price" (see Position.position)
+        price = pos.position.get("price")
+        if price is None:
+            price = pos.get_stock_amount("price")
+        return float(price)
+
+    def _pnl_pct(self, pos, mark: float) -> float:
+        entry = self._entry_price(pos)
+        if not entry or entry != entry:
+            return 0.0
+        return mark / entry - 1.0
+
+    def _is_tradable(self, code, start, end, direction) -> bool:
+        try:
+            return self.trade_exchange.is_stock_tradable(
+                stock_id=code, start_time=start, end_time=end, direction=direction
+            )
+        except TypeError:  # some exchanges take no direction kwarg
+            return self.trade_exchange.is_stock_tradable(stock_id=code, start_time=start, end_time=end)
+
+    # ------------------------------------------------------------ decision
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start, trade_end = self.trade_calendar.get_step_time(trade_step)
+        pred_start, pred_end = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start, end_time=pred_end)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None or len(pred_score) == 0:
+            return TradeDecisionWO([], self)
+
+        pct = self._pct_rank(pred_score)
+        time_per_step = self.trade_calendar.get_freq()
+        current_temp = __import__("copy").deepcopy(self.trade_position)
+
+        holdings = {}
+        for code in current_temp.get_stock_list():
+            if abs(current_temp.get_stock_amount(code)) > 1e-6:
+                holdings[code] = current_temp
+
+        # ---- optimal stopping: close held positions -----------------------
+        sell_orders: List[Order] = []
+        closed_today = set()
+        kept = {}
+        for code, pos in holdings.items():
+            held = current_temp.get_stock_count(code, bar=time_per_step)
+            mark = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start, end_time=trade_end, direction=Order.SELL
+            )
+            if mark is None or mark != mark:
+                continue
+            rank = pct.get(code, 0.0)
+            stop_pnl = held >= self.min_hold_days and self.sl < 0 and self._pnl_pct(pos, mark) <= self.sl
+            if held >= self.max_hold_days or rank < self.exit_pct or stop_pnl:
+                amt = abs(current_temp.get_stock_amount(code))
+                o = Order(stock_id=code, amount=amt, start_time=trade_start,
+                          end_time=trade_end, direction=Order.SELL)
+                if self.trade_exchange.check_order(o):
+                    sell_orders.append(o)
+                    self.trade_exchange.deal_order(o, position=current_temp)
+                closed_today.add(code)
+            else:
+                kept[code] = mark
+
+        # ---- equal-weight control: target notional per name -----------------
+        # candidate opens: top-ranked names whose signal pct >= entry_pct
+        rank_desc = pred_score.sort_values(ascending=False)
+        held_codes = set(kept)
+        opens = []
+        for sym in rank_desc.index:
+            if len(opens) >= self.topk:
+                break
+            if sym in held_codes:
+                continue
+            if pct.get(sym, 0.0) < self.entry_pct:
+                continue
+            if not self._is_tradable(sym, trade_start, trade_end, OrderDir.BUY):
+                continue
+            opens.append(sym)
+
+        targets = held_codes | set(opens)
+        if not targets:
+            return TradeDecisionWO(sell_orders, self)
+
+        # total value (cash + marked positions) -> per-target notional
+        total_value = current_temp.get_cash()
+        for code, mark in kept.items():
+            total_value += abs(current_temp.get_stock_amount(code)) * mark
+
+        target_notional = total_value * self.risk_degree / max(1, len(targets))
+
+        # ---- rebalance kept positions toward target weight ------------------
+        buy_orders: List[Order] = []
+        for code, mark in kept.items():
+            cur = abs(current_temp.get_stock_amount(code)) * mark
+            diff_notional = target_notional - cur
+            if abs(diff_notional) / target_notional < 0.02:
+                continue  # skip tiny rebalances
+            amount_delta = diff_notional / mark
+            direction = Order.BUY if amount_delta > 0 else Order.SELL
+            o = Order(stock_id=code, amount=abs(amount_delta), start_time=trade_start,
+                      end_time=trade_end, direction=direction)
+            if self.trade_exchange.check_order(o):
+                (buy_orders if direction == Order.BUY else sell_orders).append(o)
+                self.trade_exchange.deal_order(o, position=current_temp)
+
+        # ---- open new positions at target weight ----------------------------
+        for sym in opens:
+            px = self.trade_exchange.get_deal_price(
+                stock_id=sym, start_time=trade_start, end_time=trade_end, direction=OrderDir.BUY
+            )
+            if px is None or px != px or px <= 0:
+                continue
+            amount = target_notional / px
+            factor = self.trade_exchange.get_factor(
+                stock_id=sym, start_time=trade_start, end_time=trade_end
+            )
+            amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
+            o = Order(stock_id=sym, amount=amount, start_time=trade_start,
+                      end_time=trade_end, direction=Order.BUY)
+            if self.trade_exchange.check_order(o):
+                buy_orders.append(o)
+
+        return TradeDecisionWO(sell_orders + buy_orders, self)

code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py

@@ -0,0 +1,215 @@
+"""Regime-gate TopkDropout strategy.
+
+Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
+holds the book (issues NO orders) while a regime detector says the market is in
+an unfavorable state.  When the gate is open it behaves exactly like the
+reference TopkDropoutStrategy.
+
+Three detector types are supported (all causal — no lookahead):
+
+* ``dispersion``: cross-sectional standard deviation of 22-day rolling returns
+  across the universe.  Gate closes when CS dispersion < threshold (low
+  dispersion means the spread between winners and losers is too narrow for
+  TopkDropout to exploit).
+* ``vol``: cross-sectional mean of 22-day rolling realized volatility.  Gate
+  closes when avg vol is outside a band ``[vol_low, vol_high]`` (strategy
+  needs moderate vol — too calm or too turbulent both hurt).
+* ``hmm``: pre-computed HMM posterior for regime 1 (``sp_hmm_p_regime1``).
+  Gate closes when posterior < threshold (model is not confident the calm
+  regime is active).
+
+The gate is provided as a precomputed ``pd.Series`` of booleans indexed by
+datetime (True = trade allowed).  The companion ``compute_regime_gate``
+function builds this series from lake bars; call it once before backtesting
+and pass the result as the ``regime_gate`` parameter.
+"""
+
+from __future__ import annotations
+
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["RegimeGateTopkDropoutStrategy", "compute_regime_gate"]
+
+
+class RegimeGateTopkDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout with a regime-gate circuit breaker.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    regime_gate : pd.Series — precomputed per-date gate (bool indexed by
+        datetime).  True = trade allowed, False = no orders.  Missing dates
+        default to open (trade allowed).
+    """
+
+    def __init__(self, *, regime_gate=None, **kwargs):
+        super().__init__(**kwargs)
+        self._regime_gate = regime_gate
+
+    def _gate_open(self, trade_start_time) -> bool:
+        if self._regime_gate is None:
+            return True
+        ts = pd.Timestamp(trade_start_time)
+        known = self._regime_gate[self._regime_gate.index <= ts]
+        if len(known):
+            return bool(known.iloc[-1])
+        return True  # default open if no history yet
+
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
+        if not self._gate_open(trade_start_time):
+            return TradeDecisionWO([], self)
+        return super().generate_trade_decision(execute_result)
+
+
+# ---------------------------------------------------------------------------
+# Precomputation helper
+# ---------------------------------------------------------------------------
+
+def compute_regime_gate(
+    detector: str,
+    threshold: float = 0.0,
+    *,
+    lake_root: str = "",
+    market: str = "US",
+    start: str = "2015-01-03",
+    end: str = "2026-08-19",
+    vol_low: float = 0.0,
+    vol_high: float = 999.0,
+    hmm_field: str = "sp_hmm_p_regime1",
+) -> pd.Series:
+    """Build a per-date regime gate series from lake bars.
+
+    Parameters
+    ----------
+    detector : str — ``"dispersion"``, ``"vol"``, or ``"hmm"``.
+    threshold : float — for ``dispersion``: min CS dispersion to allow trading.
+        For ``hmm``: min HMM posterior to allow trading.
+        Ignored for ``vol`` (uses ``vol_low``/``vol_high`` band instead).
+    lake_root, market : str — lake location.
+    start, end : str — date window.
+    vol_low, vol_high : float — annualized vol band for the ``vol`` detector.
+    hmm_field : str — HMM feature column name for the ``hmm`` detector.
+
+    Returns
+    -------
+    pd.Series — bool, indexed by datetime.  True = trade allowed.
+    """
+    from tac_qlib.data.config import LakeConfig, resolve_lake_root
+
+    cfg = LakeConfig(resolve_lake_root(lake_root or None), market)
+    symbols = _universe_symbols(cfg)
+    close_df, vol_df = _load_daily_bars(symbols, cfg, start, end)
+    if close_df.empty:
+        return pd.Series(dtype=bool)
+
+    if detector == "dispersion":
+        return _dispersion_gate(close_df, threshold)
+    elif detector == "vol":
+        return _vol_gate(close_df, vol_low, vol_high)
+    elif detector == "hmm":
+        return _hmm_gate(cfg, symbols, threshold, start, end, hmm_field)
+    else:
+        raise ValueError(f"Unknown detector: {detector!r}")
+
+
+def _universe_symbols(cfg) -> list:
+    """Read symbols from the lake symbols.parquet."""
+    import pathlib
+
+    sp = cfg.lake_root / "symbols.parquet"
+    if sp.exists():
+        df = pd.read_parquet(sp)
+        col = "symbol" if "symbol" in df.columns else df.columns[0]
+        return sorted(df[col].astype(str).str.upper().tolist())
+    return []
+
+
+def _load_daily_bars(symbols, cfg, start, end):
+    """Load daily close prices for all symbols into a wide DataFrame."""
+    closes = {}
+    vols = {}
+    for sym in symbols:
+        p = cfg.bar_path("1d", sym)
+        if not p.exists():
+            continue
+        try:
+            df = pd.read_parquet(p)
+        except Exception:
+            continue
+        if not len(df):
+            continue
+        tcol = df["t"] if "t" in df.columns else df["date"]
+        ts = pd.to_datetime(tcol)
+        df = df.assign(_t=ts).set_index("_t").sort_index()
+        df = df.loc[start:end]
+        if len(df) < 22:
+            continue
+        closes[sym] = df["c"]
+        if "v" in df.columns:
+            vols[sym] = df["v"]
+    close_df = pd.DataFrame(closes)
+    vol_df = pd.DataFrame(vols) if vols else None
+    return close_df, vol_df
+
+
+def _dispersion_gate(close_df, threshold):
+    """Cross-sectional dispersion of 22-day rolling returns."""
+    if close_df.empty or close_df.shape[1] < 2:
+        return pd.Series(dtype=bool)
+    ret = close_df.pct_change(22)
+    cs_disp = ret.std(axis=1)
+    gate = cs_disp >= threshold
+    gate.iloc[:22] = True  # warmup: allow trading
+    return gate
+
+
+def _vol_gate(close_df, vol_low, vol_high):
+    """Cross-sectional mean of 22-day rolling realized vol."""
+    if close_df.empty or close_df.shape[1] < 2:
+        return pd.Series(dtype=bool)
+    import numpy as np
+    log_ret = np.log(close_df / close_df.shift(1))
+    rv22 = log_ret.rolling(22).std() * (252 ** 0.5)
+    cs_mean_vol = rv22.mean(axis=1)
+    gate = (cs_mean_vol >= vol_low) & (cs_mean_vol <= vol_high)
+    gate.iloc[:22] = True  # warmup
+    return gate
+
+
+def _hmm_gate(cfg, symbols, threshold, start, end, hmm_field):
+    """HMM regime posterior gate from persisted SP features."""
+    feat_root = cfg.lake_root / "features"
+    all_posteriors = {}
+    for sym in symbols:
+        # check both ta and sp family paths
+        for family in ("sp", "ta"):
+            p = feat_root / f"market=US" / f"timeframe=1d" / f"family={family}" / f"symbol={sym}.parquet"
+            if not p.exists():
+                continue
+            try:
+                df = pd.read_parquet(p)
+            except Exception:
+                continue
+            if hmm_field not in df.columns:
+                continue
+            tcol = df["t"] if "t" in df.columns else df["date"]
+            ts = pd.to_datetime(tcol)
+            s = pd.Series(df[hmm_field].values, index=ts, name=sym)
+            s = s.loc[start:end].dropna()
+            if len(s) > 0:
+                all_posteriors[sym] = s
+                break
+    if not all_posteriors:
+        # no HMM features found — default open
+        idx = pd.date_range(start, end, freq="B")
+        return pd.Series(True, index=idx)
+    post_df = pd.DataFrame(all_posteriors)
+    cs_mean = post_df.mean(axis=1)
+    gate = cs_mean >= threshold
+    return gate

code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py

@@ -0,0 +1,202 @@
+"""Weekly-rebalance TopkDropout strategy.
+
+Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
+the topk/n_drop selection and sizing are identical to the reference, but the
+target book is recomputed only on the first trading day of each ISO week; on the
+other days the strategy issues NO orders (holds the book untouched).
+
+The weekly cadence is derived from the qlib trade calendar: a rebalance happens
+when the current trade step's date belongs to a different ISO ``(year, week)``
+than the previous trade step. ``hold_band_pct`` (default 0) optionally skips
+tiny rebalances: when a name's existing position differs from the new target by
+less than this fraction, no order is generated for it.
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["WeeklyRebalanceDropoutStrategy"]
+
+DEFAULT_HOLD_BAND_PCT = 0.0
+
+
+class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout rebalanced once per ISO week; holds otherwise.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    hold_band_pct : skip order for a name whose deviation from target weight is
+        below this fraction of the target (no-trade buffer band).
+    """
+
+    def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.hold_band_pct = hold_band_pct
+
+    @staticmethod
+    def _iso_week(ts) -> tuple:
+        return (ts.year, ts.week)
+
+    def generate_trade_decision(self, execute_result=None):
+        import copy
+
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+
+        cur_week = self._iso_week(trade_start_time)
+        prev_week = getattr(self, "_last_week", None)
+        self._last_week = cur_week
+
+        if prev_week is not None and prev_week == cur_week:
+            # not the first trading day of this ISO week -> hold
+            return TradeDecisionWO([], self)
+
+        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+
+        if self.only_tradable:
+
+            def get_first_n(li, n, reverse=False):
+                cur_n = 0
+                res = []
+                for si in reversed(li) if reverse else li:
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    ):
+                        res.append(si)
+                        cur_n += 1
+                        if cur_n >= n:
+                            break
+                return res[::-1] if reverse else res
+
+            def get_last_n(li, n):
+                return get_first_n(li, n, reverse=True)
+
+            def filter_stock(li):
+                return [
+                    si
+                    for si in li
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    )
+                ]
+
+        else:
+
+            def get_first_n(li, n):
+                return list(li)[:n]
+
+            def get_last_n(li, n):
+                return list(li)[-n:]
+
+            def filter_stock(li):
+                return li
+
+        current_temp: "object" = copy.deepcopy(self.trade_position)
+        sell_order_list: List[Order] = []
+        buy_order_list: List[Order] = []
+        cash = current_temp.get_cash()
+        current_stock_list = current_temp.get_stock_list()
+        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
+
+        if self.method_buy == "top":
+            today = get_first_n(
+                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
+                self.n_drop + self.topk - len(last),
+            )
+        elif self.method_buy == "random":
+            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
+            candi = list(filter(lambda x: x not in last, topk_candi))
+            n = self.n_drop + self.topk - len(last)
+            try:
+                today = np.random.choice(candi, n, replace=False)
+            except ValueError:
+                today = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
+
+        if self.method_sell == "bottom":
+            sell = last[last.isin(get_last_n(comb, self.n_drop))]
+        elif self.method_sell == "random":
+            candi = filter_stock(last)
+            try:
+                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
+            except ValueError:
+                sell = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        buy = today[: len(sell) + self.topk - len(last)]
+        for code in current_stock_list:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
+            ):
+                continue
+            if code in sell:
+                time_per_step = self.trade_calendar.get_freq()
+                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
+                    continue
+                sell_amount = current_temp.get_stock_amount(code=code)
+                sell_order = Order(
+                    stock_id=code,
+                    amount=sell_amount,
+                    start_time=trade_start_time,
+                    end_time=trade_end_time,
+                    direction=Order.SELL,
+                )
+                if self.trade_exchange.check_order(sell_order):
+                    sell_order_list.append(sell_order)
+                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
+                        sell_order, position=current_temp
+                    )
+                    cash += trade_val - trade_cost
+
+        if len(buy) == 0:
+            return TradeDecisionWO(sell_order_list, self)
+
+        value = cash * self.risk_degree / len(buy)
+        for code in buy:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
+            ):
+                continue
+            buy_price = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
+            )
+            buy_amount = value / buy_price
+            factor = self.trade_exchange.get_factor(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+            )
+            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
+            buy_order = Order(
+                stock_id=code,
+                amount=buy_amount,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.BUY,
+            )
+            buy_order_list.append(buy_order)
+
+        return TradeDecisionWO(sell_order_list + buy_order_list, self)

code/tac-qlib/tac_qlib/data/__init__.py

@@ -0,0 +1,25 @@
+from .config import (
+    LakeConfig,
+    BAR_FIELD_MAP,
+    FREQ_TO_TIMEFRAME,
+    UNKNOWN_FIELD_NAMES,
+    timeframe_for_freq,
+    resolve_lake_root,
+)
+from .providers import (
+    LakeCalendarProvider,
+    LakeInstrumentProvider,
+    LakeFeatureProvider,
+)
+
+__all__ = [
+    "LakeConfig",
+    "BAR_FIELD_MAP",
+    "FREQ_TO_TIMEFRAME",
+    "UNKNOWN_FIELD_NAMES",
+    "timeframe_for_freq",
+    "resolve_lake_root",
+    "LakeCalendarProvider",
+    "LakeInstrumentProvider",
+    "LakeFeatureProvider",
+]

code/tac-qlib/tac_qlib/data/config.py

@@ -0,0 +1,202 @@
+"""TradeAC lake configuration helpers.
+
+The lake is a hive-partitioned parquet store (see ``tac-engine/skills/tradeac-lake``):
+
+    $TAC_LAKE_DIR/
+    ├── market=US/
+    │   └── timeframe=1d/
+    │       └── symbol=AAPL.parquet        # OHLCV bars: t, date, o, h, l, c, v, n, vw
+    ├── features/                          # indicators, wide format, family tier
+    │   └── market=US/
+    │       └── timeframe=1d/
+    │           ├── family=ta/symbol=AAPL.parquet  # t, sma_5, sma_20, rsi_14, ...
+    │           └── family=sp/symbol=AAPL.parquet  # t, sp_ou_*, sp_hmm_*, ...
+    ├── calendar.parquet                   # trading days per market
+    ├── coverage.parquet                   # per (market,timeframe,symbol) loaded windows
+    └── symbols.parquet                    # asset master
+"""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+from typing import Dict, List, Optional
+
+import pandas as pd
+
+#: qlib freq string (Freq.__str__) -> lake timeframe partition name
+FREQ_TO_TIMEFRAME: Dict[str, str] = {
+    "day": "1d",
+    "1d": "1d",
+    "min": "1m",
+    "1min": "1m",
+    "5min": "5m",
+    "10min": "10m",
+    "15min": "15m",
+    "30min": "30m",
+    "hour": "1h",
+    "1hour": "1h",
+    "2hour": "2h",
+    "4hour": "4h",
+    "week": "1w",
+    "1week": "1w",
+    "month": "1M",
+    "1month": "1M",
+}
+
+#: bar-field map: qlib field name (without the leading ``$``) -> lake bar column
+BAR_FIELD_MAP: Dict[str, str] = {
+    "open": "o",
+    "high": "h",
+    "low": "l",
+    "close": "c",
+    "volume": "v",
+    "vwap": "vw",
+    "avg_amount": "vw",  # amount / volume
+}
+
+#: fields that qlib core/backtest queries but the lake does not store -> all-NaN
+UNKNOWN_FIELD_NAMES = ("factor", "change", "trade_unit", "suspend_flag")
+
+#: columns in the parquet files that are not features
+NON_FEATURE_COLUMNS = ("t", "date", "market", "timeframe", "symbol")
+
+
+def timeframe_for_freq(freq: str) -> str:
+    """Map a qlib frequency (e.g. ``day``, ``1min``) to a lake timeframe (e.g. ``1d``)."""
+    f = str(freq).lower()
+    if f not in FREQ_TO_TIMEFRAME:
+        raise ValueError(
+            f"unsupported qlib freq {freq!r}; supported freqs: {sorted(set(FREQ_TO_TIMEFRAME))}"
+        )
+    return FREQ_TO_TIMEFRAME[f]
+
+
+def resolve_lake_root(lake_root: Optional[str] = None) -> Path:
+    """Resolve the lake root: explicit arg > ``TAC_LAKE_DIR`` (no fallback).
+
+    ``TAC_LAKE_DIR`` is **mandatory** — there is deliberately no default
+    A missing/empty value raises so a
+    misconfigured environment never silently points at a wrong directory.
+    """
+    if lake_root is None:
+        lake_root = os.environ.get("TAC_LAKE_DIR")
+    if not lake_root:
+        raise RuntimeError(
+            "TAC_LAKE_DIR is not set. Point it at the TradeAC lake root, e.g. "
+            "export TAC_LAKE_DIR=/home/data/lake (docker) or set an absolute "
+            "path in your local .env."
+        )
+    return Path(str(lake_root)).expanduser().resolve()
+
+
+class LakeConfig:
+    """Path helpers + cached readers for a (lake_root, market) combination."""
+
+    def __init__(self, lake_root: Optional[str] = None, market: str = "US"):
+        self.lake_root: Path = resolve_lake_root(lake_root)
+        self.market: str = (market or "US").upper()
+
+    # ---- paths --------------------------------------------------------------
+    def bar_dir(self, timeframe: str) -> Path:
+        return self.lake_root / f"market={self.market}" / f"timeframe={timeframe}"
+
+    def bar_path(self, timeframe: str, symbol: str) -> Path:
+        return self.bar_dir(timeframe) / f"symbol={str(symbol).upper()}.parquet"
+
+    def features_dir(self, timeframe: str) -> Path:
+        return self.lake_root / "features" / f"market={self.market}" / f"timeframe={timeframe}"
+
+    def features_path(self, timeframe: str, symbol: str) -> Path:
+        # Legacy flat path (no family tier). Prefer `load_features` which
+        # resolves the family=ta|sp partition layout.
+        return self.features_dir(timeframe) / f"symbol={str(symbol).upper()}.parquet"
+
+    def load_features(self, timeframe: str, symbol: str) -> pd.DataFrame:
+        """All feature columns for a symbol, merging the `family=ta` and
+        `family=sp` partitions by timestamp. Returns an empty frame when no
+        feature files exist (legacy flat layout falls back transparently)."""
+        sym = str(symbol).upper()
+        frames = []
+        for family in ("ta", "sp"):
+            p = self.features_dir(timeframe) / f"family={family}" / f"symbol={sym}.parquet"
+            if p.exists():
+                frames.append(pd.read_parquet(p))
+        if not frames:
+            flat = self.features_dir(timeframe) / f"symbol={sym}.parquet"
+            if flat.exists():
+                return pd.read_parquet(flat)
+            return pd.DataFrame()
+        if len(frames) == 1:
+            return frames[0]
+        merged = frames[0]
+        for extra in frames[1:]:
+            merged = merged.merge(extra, on="t", how="outer", suffixes=("", "_dup"))
+            for c in [c for c in merged.columns if c.endswith("_dup")]:
+                merged = merged.drop(columns=c)
+        return merged
+
+    def calendar_path(self) -> Path:
+        return self.lake_root / "calendar.parquet"
+
+    def symbols_path(self) -> Path:
+        return self.lake_root / "symbols.parquet"
+
+    def coverage_path(self) -> Path:
+        return self.lake_root / "coverage.parquet"
+
+    # ---- metadata readers ----------------------------------------------------
+    def load_symbols(self) -> List[str]:
+        """All symbols known to the lake (from ``symbols.parquet``)."""
+        p = self.symbols_path()
+        if not p.exists():
+            return []
+        df = pd.read_parquet(p)
+        if "symbol" not in df.columns:
+            return []
+        return sorted(df["symbol"].astype(str).str.upper().tolist())
+
+    def symbol_spans(self, symbol: str, timeframe: str) -> List[tuple]:
+        """Listing span(s) ``[(start_iso, end_iso)]`` for a symbol from coverage.parquet."""
+        p = self.coverage_path()
+        if p.exists():
+            try:
+                df = pd.read_parquet(p)
+            except Exception:  # pragma: no cover - defensive
+                df = pd.DataFrame()
+            if len(df):
+                df = df[
+                    (df.get("market") == self.market)
+                    & (df.get("timeframe") == timeframe)
+                    & (df.get("symbol") == str(symbol).upper())
+                ]
+                if len(df):
+                    row = df.iloc[0]
+                    first = pd.Timestamp(row["first_t"]).date()
+                    last = pd.Timestamp(row["last_t"]).date()
+                    return [(first.isoformat(), last.isoformat())]
+        # fallback: derive from the bar file itself
+        p = self.bar_path(timeframe, symbol)
+        if p.exists():
+            import pyarrow.parquet as pq
+
+            tbl = pq.read_table(p, columns=["t"])
+            first = pd.Timestamp(tbl.column("t")[0].as_py()).date()
+            last = pd.Timestamp(tbl.column("t")[-1].as_py()).date()
+            return [(first.isoformat(), last.isoformat())]
+        return [("1970-01-01", "2099-12-31")]
+
+    def load_calendar_dates(self) -> List[pd.Timestamp]:
+        """Trading days (midnight timestamps) for the market, from ``calendar.parquet``."""
+        p = self.calendar_path()
+        if p.exists():
+            df = pd.read_parquet(p)
+            if "date" in df.columns:
+                if "market" in df.columns:
+                    df = df[df["market"] == self.market]
+                dates = pd.to_datetime(df["date"]).dt.normalize().sort_values().unique()
+                return [pd.Timestamp(x) for x in dates]
+        return []
+
+    def __repr__(self) -> str:  # pragma: no cover
+        return f"LakeConfig(lake_root={self.lake_root}, market={self.market})"

code/tac-qlib/tac_qlib/data/providers.py

@@ -0,0 +1,230 @@
+"""qlib data providers backed by the TradeAC parquet lake.
+
+These providers plug into the standard qlib mechanism: ``qlib.init(calendar_provider=...,
+instrument_provider=..., feature_provider=...)`` instantiates them and binds them to the
+``Cal`` / ``Inst`` / ``FeatureD`` wrappers (see ``qlib.data.data.register_all_wrappers``).
+The rest of qlib (``LocalDatasetProvider`` expression engine, backtest ``Exchange``) keeps
+working unchanged because the interface contract is identical to the file-based providers:
+
+- ``feature()`` returns a ``pd.Series`` indexed by the **calendar position** range
+  ``[start_index, end_index]`` (matching ``FileFeatureStorage.__getitem__`` semantics).
+- ``list_instruments()`` returns ``{symbol: [(start, end), ...]}``.
+- ``load_calendar()`` returns a list of ``pd.Timestamp`` trading days.
+"""
+
+from __future__ import annotations
+
+import bisect
+from typing import Dict, List, Optional, Union
+
+import numpy as np
+import pandas as pd
+
+from qlib.data.data import CalendarProvider, FeatureProvider, InstrumentProvider
+from qlib.log import get_module_logger
+
+from .config import (
+    BAR_FIELD_MAP,
+    LakeConfig,
+    UNKNOWN_FIELD_NAMES,
+    timeframe_for_freq,
+)
+
+logger = get_module_logger("tac_qlib.data.providers")
+
+
+def _day_freq(freq: str) -> bool:
+    return str(freq).lower() in ("day", "1d")
+
+
+def _calendar_keys(cal: List[pd.Timestamp], freq: str) -> pd.Index:
+    """Convert calendar timestamps into the same key space as the lake parquet."""
+    if _day_freq(freq):
+        return pd.Index([pd.Timestamp(x).date() for x in cal])
+    return pd.Index([pd.Timestamp(x) for x in cal])
+
+
+class LakeCalendarProvider(CalendarProvider):
+    """Trading calendar read from ``<lake>/calendar.parquet`` (fallback: derived from bars)."""
+
+    def __init__(self, lake_root: Optional[str] = None, market: str = "US"):
+        super().__init__()
+        self.cfg = LakeConfig(lake_root, market)
+
+    def load_calendar(self, freq, future):
+        timeframe = timeframe_for_freq(freq)
+        if not _day_freq(freq):
+            raise NotImplementedError(
+                f"freq={freq!r} (timeframe={timeframe}) is not supported yet: the lake calendar "
+                f"only covers daily sessions; add a minute-level calendar to `calendar.parquet`"
+            )
+
+        dates = self.cfg.load_calendar_dates()
+        if not dates:
+            # Fallback: derive the trading-day set from the persisted bar files.
+            bar_dir = self.cfg.bar_dir(timeframe)
+            if bar_dir.exists():
+                import pyarrow.parquet as pq
+
+                cal: Dict[pd.Timestamp, None] = {}
+                for p in sorted(bar_dir.glob("symbol=*.parquet")):
+                    tbl = pq.read_table(p, columns=["t"])
+                    for v in tbl.column("t"):
+                        cal[pd.Timestamp(v.as_py()).normalize()] = None
+                dates = sorted(cal.keys())
+            if not dates:
+                return []
+
+        if future:
+            # append the next calendar day so that "today" is a valid trade date
+            last = dates[-1]
+            dates = dates + [pd.Timestamp(last) + pd.Timedelta(days=1)]
+        return dates
+
+
+class LakeInstrumentProvider(InstrumentProvider):
+    """Instruments from ``<lake>/symbols.parquet`` with listing spans from ``coverage.parquet``."""
+
+    def __init__(
+        self,
+        lake_root: Optional[str] = None,
+        market: str = "US",
+        markets: Optional[Dict[str, list]] = None,
+    ):
+        super().__init__()
+        self.cfg = LakeConfig(lake_root, market)
+        #: optional named pools, e.g. ``{"sp500": ["AAPL", "MSFT"], "etf": ["SPY"]}``.
+        #: ``all`` / any unregistered name resolves to every symbol in the lake.
+        self.markets: Dict[str, list] = markets or {}
+
+    def _resolve_symbols(self, market: Union[str, list]) -> List[str]:
+        if isinstance(market, (list, tuple, pd.Index, np.ndarray)):
+            return [str(s).upper() for s in market]
+        if isinstance(market, str) and "," in market:
+            return [s.strip().upper() for s in market.split(",") if s.strip()]
+        if market in self.markets:
+            return [str(s).upper() for s in self.markets[market]]
+        return self.cfg.load_symbols()
+
+    def list_instruments(self, instruments, start_time=None, end_time=None, freq="day", as_list=False):
+        market = instruments["market"]
+        timeframe = timeframe_for_freq(freq)
+
+        symbols = self._resolve_symbols(market)
+        if not symbols:
+            if as_list:
+                return []
+            return {}
+
+        # clip listing spans to the queried window (mirror of LocalInstrumentProvider)
+        from qlib.data.data import Cal  # pylint: disable=C0415
+
+        cal = Cal.calendar(freq=freq)
+        start_time = pd.Timestamp(start_time or cal[0])
+        end_time = pd.Timestamp(end_time or cal[-1])
+
+        out: Dict[str, list] = {}
+        for symbol in symbols:
+            spans = []
+            for begin, end in self.cfg.symbol_spans(symbol, timeframe):
+                lo = max(start_time, pd.Timestamp(begin))
+                hi = min(end_time, pd.Timestamp(end))
+                if lo <= hi:
+                    spans.append((lo, hi))
+            if spans:
+                out[symbol] = spans
+
+        filter_pipe = instruments.get("filter_pipe") or []
+        for filter_config in filter_pipe:
+            from qlib.data import filter as F  # pylint: disable=C0415
+
+            filter_t = getattr(F, filter_config["filter_type"]).from_config(filter_config)
+            out = filter_t(out, start_time, end_time, freq)
+
+        if as_list:
+            return list(out)
+        return out
+
+
+class LakeFeatureProvider(FeatureProvider):
+    """Feature data from the lake parquet (OHLCV bars + pre-computed ta-lib features).
+
+    Field routing:
+        - ``$open/$high/$low/$close/$volume/$vwap``      -> bar parquet columns
+        - ``$amount`` (= v*vw), ``$avg_amount`` (= vw)  -> derived from bar parquet
+        - ``$factor/$change/...``                        -> all-NaN (not stored)
+        - anything else                                  -> a ta-lib column in the features parquet
+    """
+
+    def __init__(self, lake_root: Optional[str] = None, market: str = "US"):
+        super().__init__()
+        self.cfg = LakeConfig(lake_root, market)
+        self._bar_cache: Dict[tuple, pd.DataFrame] = {}
+        self._feature_cache: Dict[tuple, pd.DataFrame] = {}
+
+    # ------------------------------------------------------------------ caches
+    def _load_bar_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
+        key = (instrument, timeframe)
+        if key not in self._bar_cache:
+            p = self.cfg.bar_path(timeframe, instrument)
+            self._bar_cache[key] = pd.read_parquet(p) if p.exists() else pd.DataFrame()
+        return self._bar_cache[key]
+
+    def _load_feature_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
+        key = (instrument, timeframe)
+        if key not in self._feature_cache:
+            self._feature_cache[key] = self.cfg.load_features(timeframe, instrument)
+        return self._feature_cache[key]
+
+    @staticmethod
+    def _keys(df: pd.DataFrame, freq: str) -> pd.Index:
+        ts = pd.to_datetime(df["t"])
+        return ts.dt.date if _day_freq(freq) else ts
+
+    # ------------------------------------------------------------------ fields
+    def _extract(self, instrument: str, field: str, timeframe: str, freq: str) -> Optional[pd.Series]:
+        """Return the field as a Series keyed by date/timestamp (None if not present in the lake)."""
+        bar = self._load_bar_df(instrument, timeframe)
+
+        if field in BAR_FIELD_MAP:
+            col = BAR_FIELD_MAP[field]
+            if col in bar.columns:
+                return bar[col].astype(float).set_axis(self._keys(bar, freq))
+            return None
+        if field == "amount":
+            if "v" in bar.columns and "vw" in bar.columns:
+                return (bar["v"] * bar["vw"]).astype(float).set_axis(self._keys(bar, freq))
+            return None
+        if field in UNKNOWN_FIELD_NAMES:
+            return None
+
+        feat = self._load_feature_df(instrument, timeframe)
+        if field in feat.columns:
+            return feat[field].astype(float).set_axis(self._keys(feat, freq))
+        return None
+
+    # ------------------------------------------------------------------ api
+    def _get_calendar(self, freq: str) -> List[pd.Timestamp]:
+        from qlib.data.data import Cal  # pylint: disable=C0415
+
+        cal = Cal.calendar(freq=freq)
+        return list(cal)
+
+    def feature(self, instrument, field, start_index, end_index, freq):
+        field = str(field)[1:]
+        timeframe = timeframe_for_freq(freq)
+
+        cal = self._get_calendar(freq)
+        n = len(cal)
+        lo = max(0, int(start_index))
+        hi = min(n - 1, int(end_index))
+        if lo > hi:
+            return pd.Series(dtype=np.float32)
+
+        keys = _calendar_keys(cal[lo : hi + 1], freq)
+        ser = self._extract(str(instrument).upper(), field, timeframe, freq)
+        if ser is None:
+            vals = np.full(len(keys), np.nan, dtype=np.float64)
+        else:
+            vals = ser.reindex(keys).to_numpy(dtype=np.float64)
+        return pd.Series(vals, index=pd.RangeIndex(lo, hi + 1))

workflows/ablate_baseline_all_sp_fields.yaml

@@ -1,133 +0,0 @@
-# -----------------------------------------------------------------------------
-# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d
-# panel, using ALL 24 sp_* feature columns (ou,hmm,jump,har,trend,hurst,
-# signature). Copy of the canonical workflow_lgb_sp5d_rankic.yaml with a
-# distinct experiment name so the ablation runs are isolated.
-#
-# Run:
-#   rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \
-#       experiment_name=tac-rd-rank-ablate
-# -----------------------------------------------------------------------------
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs:
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-rank-ablate"
-
-task:
-    model:
-        class: RankICLGBModel
-        module_path: tac_qlib.contrib.model.rank_gbdt
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seed: 42
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2015-01-03
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
-                    infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
-            segments:
-                train: [2015-01-03, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - class: SignalRecord
-          module_path: qlib.workflow.record_temp
-          kwargs: {}
-        - class: SigAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              ana_long_short: true
-              ann_scaler: 252
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

workflows/ablate_generic_only_sp_fields.yaml

@@ -1,134 +0,0 @@
-# -----------------------------------------------------------------------------
-# ABLATION B (generic-only): same panel/model as the baseline, but feature
-# fields restricted to the model-free / generic stochastic-process families
-# (jump,har,trend,hurst,signature). Drops the model-specific ou (OU/AR-1
-# half-life) and hmm (2-state regime) families to test whether the generic
-# families alone dominate the rank dimension.
-#
-# Run:
-#   rd_run_workflow config_path=tac-qlib/workflows/ablate_generic_only_sp_fields.yaml \
-#       experiment_name=tac-rd-rank-ablate
-# -----------------------------------------------------------------------------
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs:
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-rank-ablate"
-
-task:
-    model:
-        class: RankICLGBModel
-        module_path: tac_qlib.contrib.model.rank_gbdt
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seed: 42
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2015-01-03
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
-                    infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
-            segments:
-                train: [2015-01-03, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - class: SignalRecord
-          module_path: qlib.workflow.record_temp
-          kwargs: {}
-        - class: SigAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              ana_long_short: true
-              ann_scaler: 252
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

workflows/exp12_isolation_ensemble.yaml

@@ -1,141 +0,0 @@
-# -----------------------------------------------------------------------------
-# ISOLATION: multi-seed RankIC ensemble, ablate-B generic-only feature set.
-#
-# Isolates the ensemble effect on the SP-5d rank signal. Same panel, segments,
-# history (full backfilled 2016+) and feature set as the exp-9 ablate-B winner
-# (generic-only sp_* families: jump,har,trend,hurst,signature), but replaces the
-# single RankICLGBModel with a 5-seed RankICEnsembleLGBModel (42,7,2026,99,123)
-# that averages per-day predictions.
-#
-# Differs from exp-15 (tac-rd-rank-ensemble, mlflow exp 15) ONLY by dropping the
-# TA subset (rsi_14,roc_10,macd_hist,willr_14,atr_14) and the inter-asset xr_*
-# features, so any change vs exp-15 is attributable to the feature set alone,
-# and any change vs exp-9 is attributable to the ensemble + full history alone.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp12_isolation_ensemble.yaml \
-#       experiment_name=tac-rd-rank-ensemble-isolated
-# -----------------------------------------------------------------------------
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs:
-            uri: "sqlite:///mlruns.db"
-            default_exp_name: "tac-rd-rank-ensemble-isolated"
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-14
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
-                    infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - class: SignalRecord
-          module_path: qlib.workflow.record_temp
-          kwargs: {}
-        - class: SigAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              ana_long_short: true
-              ann_scaler: 252
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

workflows/exp15-kelly-size/a_topk_baseline.yaml

@@ -1,136 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 15 - Strategy A (baseline): parallel reference model + TopkDropout.
-#
-# Model = RankICEnsembleLGBModel with PARALLEL=5 (thread-pool seed training,
-# rank_ensemble.py) - the speedup means the 5-seed 3000-round ensemble trains in
-# ~1/5th the wall time of the serial reference. Strategy = TopkDropout topk=10
-# n_drop=2 risk_degree=0.95 (the reference's recorded strategy).
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp15-kelly-size/a_topk_baseline.yaml \
-#       experiment_name=tac-rd-kelly-size
-# -----------------------------------------------------------------------------
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs:
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-kelly-size"
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-            parallel: 5
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-14
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
-                    infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - class: SignalRecord
-          module_path: qlib.workflow.record_temp
-          kwargs: {}
-        - class: SigAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              ana_long_short: true
-              ann_scaler: 252
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

workflows/exp15-kelly-size/b_kelly_weight.yaml

@@ -1,144 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 15 - Strategy B: parallel reference model + KellyWeightStrategy.
-#
-# Model = RankICEnsembleLGBModel PARALLEL=5 (same as A). Strategy =
-# KellyWeightStrategy (tac_qlib.contrib.strategy.kelly_weight): applies the
-# Kelly criterion to position SIZING -
-#     f* = kelly_fraction * mu_i / var_i   (Gaussian Kelly, mu_i > 0)
-# with per-name mu/var estimated from the rolling signal history (no
-# lookahead), floored/capped and normalized to the risk_degree leverage budget.
-# This is the piece the reference's equal-weight TopkDropout never tunes: it
-# weights names by edge/risk instead of equal-weight top-k.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp15-kelly-size/b_kelly_weight.yaml \
-#       experiment_name=tac-rd-kelly-size
-# -----------------------------------------------------------------------------
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs:
-            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-kelly-size"
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-            parallel: 5
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-14
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
-                    infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - class: SignalRecord
-          module_path: qlib.workflow.record_temp
-          kwargs: {}
-        - class: SigAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              ana_long_short: true
-              ann_scaler: 252
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: KellyWeightStrategy
-                      module_path: tac_qlib.contrib.strategy.kelly_weight
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          lookback: 20
-                          min_obs: 10
-                          kelly_fraction: 0.5
-                          max_weight: 0.15
-                          min_weight: 0.0
-                          risk_degree: 0.95
-                          max_turnover: 0.30
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d