start experiment 59 (exp/59-signal-quality-gate-walk-forward-test-wi)

book/scripts/precompute_signal_quality_gate.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""Precompute the signal-quality gate series and save to pickle.
+
+Usage:
+    python precompute_signal_quality_gate.py <pred_path> <output_path> [topk] [lookback] [threshold]
+
+Example:
+    python precompute_signal_quality_gate.py \
+        /home/data/lake/mlruns/49/34165f27e4a34378ad54843a079a78c0/artifacts/pred.pkl \
+        /app/experiments/book/data/signal_quality_gate/sq_gate_5d_0.50.pkl \
+        10 5 0.5
+"""
+import sys
+import pickle
+from pathlib import Path
+
+# Add tac-qlib to path
+sys.path.insert(0, "/app/tac-qlib")
+
+from tac_qlib.contrib.strategy.signal_quality_gate import compute_signal_quality_gate
+
+if __name__ == "__main__":
+    if len(sys.argv) < 3:
+        print(__doc__)
+        sys.exit(1)
+
+    pred_path = sys.argv[1]
+    output_path = sys.argv[2]
+    topk = int(sys.argv[3]) if len(sys.argv) > 3 else 10
+    lookback = int(sys.argv[4]) if len(sys.argv) > 4 else 5
+    threshold = float(sys.argv[5]) if len(sys.argv) > 5 else 0.5
+
+    lake_root = "/home/data/lake"
+
+    print(f"Computing signal-quality gate: topk={topk}, lookback={lookback}, threshold={threshold}")
+    gate = compute_signal_quality_gate(
+        pred_path,
+        lake_root=lake_root,
+        topk=topk,
+        lookback=lookback,
+        threshold=threshold,
+    )
+
+    print(f"Gate: {gate.sum()}/{len(gate)} days open ({gate.mean():.1%})")
+
+    with open(output_path, "wb") as f:
+        pickle.dump(gate, f)
+    print(f"Saved to {output_path}")

book/workflows/signal_quality_gate.yaml

@@ -1,16 +1,16 @@
 # -----------------------------------------------------------------------------
-# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d
+# Signal-quality gate: TopkDropout gated by rolling hit-rate of topk picks.
-# 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:
+# 1. Compute the gate: python precompute_signal_quality_gate.py <pred.pkl> <gate.pkl>
-#   rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \
+# 2. Run this workflow: rd_run_workflow config_path=<this yaml> experiment_name=<exp>
-#       experiment_name=tac-rd-rank-ablate
+#
+# The strategy loads the precomputed gate from signal_quality_gate_path.
+# When hit rate >= threshold, trade; otherwise, go to cash.
 # -----------------------------------------------------------------------------
 {%- 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" %}
+{%- set GATE_PATH = "/app/experiments/book/data/signal_quality_gate/sq_gate_5d_0.50.pkl" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
@@ -40,27 +40,22 @@ qlib_init:
         module_path: qlib.workflow.expm
         kwargs:
             uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-rank-ablate"
+            default_exp_name: "tac-rd-sq-gate"
 
 task:
     model:
-        class: RankICLGBModel
+        class: LGBModel
-        module_path: tac_qlib.contrib.model.rank_gbdt
+        module_path: qlib.contrib.model.gbdt
         kwargs:
             loss: mse
-            learning_rate: 0.02
+            learning_rate: 0.05
-            num_leaves: 31
+            num_leaves: 15
-            n_estimators: 3000
+            n_estimators: 200
-            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_alpha: 0.01
-            reg_lambda: 1.0
+            reg_lambda: 0.01
-            seed: 42
 
     dataset:
         class: DatasetH
@@ -110,12 +105,13 @@ task:
           kwargs:
               config:
                   strategy:
-                      class: TopkDropoutStrategy
+                      class: SignalQualityGateStrategy
-                      module_path: qlib.contrib.strategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
                       kwargs:
                           signal: "<PRED>"
+                          signal_quality_gate_path: "{{ GATE_PATH }}"
                           topk: 10
-                          n_drop: 2
+                          n_drop: 1
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:

book/workflows/sq_gate/sq_gate_2021.yaml

@@ -1,68 +1,44 @@
-# -----------------------------------------------------------------------------
+# Signal-quality gate backtest for 2021
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
 {%- 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" %}
+{%- 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" %}
+{# Gate computed on-the-fly from signal + lake close prices #}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
-
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            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-risk-limit"
+            default_exp_name: "tac-rd-sq-gate-2021"
 
 task:
     model:
-        class: RankICEnsembleLGBModel
+        class: LGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
+        module_path: qlib.contrib.model.gbdt
         kwargs:
             loss: mse
-            learning_rate: 0.02
+            learning_rate: 0.05
-            num_leaves: 31
+            num_leaves: 15
-            n_estimators: 3000
+            n_estimators: 200
-            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_alpha: 0.01
-            reg_lambda: 1.0
+            reg_lambda: 0.01
-            seeds: "42,7,2026,99,123"
-            parallel: 1
 
     dataset:
         class: DatasetH
@@ -74,9 +50,9 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    end_time: 2021-12-31
-                    fit_start_time: 2016-01-04
+                    fit_start_time: 2015-01-03
-                    fit_end_time: 2025-09-01
+                    fit_end_time: 2021-01-03
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
@@ -94,9 +70,9 @@ task:
                         - class: Fillna
                           kwargs: {}
             segments:
-                train: [2016-01-04, 2025-09-01]
+                train: [2015-01-03, 2020-09-01]
-                valid: [2025-09-03, 2026-01-03]
+                valid: [2020-09-03, 2021-01-03]
-                test: [2026-01-04, 2026-08-10]
+                test: [2021-01-04, 2021-12-31]
 
     record:
         - class: SignalRecord
@@ -104,25 +80,29 @@ task:
           kwargs: {}
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: { ana_long_short: true, ann_scaler: 252 }
-              ana_long_short: true
-              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
               config:
                   strategy:
-                      class: TopkDropoutStrategy
+                      class: SignalQualityGateStrategy
-                      module_path: qlib.contrib.strategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
                       kwargs:
                           signal: "<PRED>"
+                          lake_root: "{{ LAKE }}"
+                          gate_topk: 10
+                          gate_lookback: 5
+                          gate_threshold: 0.5
+                          gate_start: "2015-01-03"
+                          gate_end: "2021-12-31"
                           topk: 10
-                          n_drop: 2
+                          n_drop: 1
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:
-                      start_time: 2026-01-04
+                      start_time: 2021-01-04
-                      end_time: 2026-08-10
+                      end_time: 2021-12-31
                       account: 1000000
                       benchmark: SPY
                       exchange_kwargs:

book/workflows/sq_gate/sq_gate_2023.yaml

@@ -0,0 +1,115 @@
+# Signal-quality gate backtest for 2023
+{%- 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" %}
+{# Gate computed on-the-fly from signal + lake close prices #}
+
+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-sq-gate-2023"
+
+task:
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.05
+            num_leaves: 15
+            n_estimators: 200
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.01
+            reg_lambda: 0.01
+
+    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: 2023-12-29
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2023-01-03
+                    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, 2022-09-01]
+                valid: [2022-09-03, 2023-01-03]
+                test: [2023-01-03, 2023-12-29]
+
+    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: SignalQualityGateStrategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
+                      kwargs:
+                          signal: "<PRED>"
+                          lake_root: "{{ LAKE }}"
+                          gate_topk: 10
+                          gate_lookback: 5
+                          gate_threshold: 0.5
+                          gate_start: "2015-01-03"
+                          gate_end: "2023-12-29"
+                          topk: 10
+                          n_drop: 1
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2023-01-03
+                      end_time: 2023-12-29
+                      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

book/workflows/sq_gate/sq_gate_2024.yaml

@@ -0,0 +1,115 @@
+# Signal-quality gate backtest for 2024
+{%- 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" %}
+{# Gate computed on-the-fly from signal + lake close prices #}
+
+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-sq-gate-2024"
+
+task:
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.05
+            num_leaves: 15
+            n_estimators: 200
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.01
+            reg_lambda: 0.01
+
+    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: 2024-12-31
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2024-01-03
+                    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, 2023-09-01]
+                valid: [2023-09-03, 2024-01-03]
+                test: [2024-01-02, 2024-12-31]
+
+    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: SignalQualityGateStrategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
+                      kwargs:
+                          signal: "<PRED>"
+                          lake_root: "{{ LAKE }}"
+                          gate_topk: 10
+                          gate_lookback: 5
+                          gate_threshold: 0.5
+                          gate_start: "2015-01-03"
+                          gate_end: "2024-12-31"
+                          topk: 10
+                          n_drop: 1
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2024-01-02
+                      end_time: 2024-12-31
+                      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

book/workflows/sq_gate/sq_gate_2025.yaml

@@ -1,68 +1,44 @@
-# -----------------------------------------------------------------------------
+# Signal-quality gate backtest for 2025
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
 {%- 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" %}
+{%- 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" %}
+{# Gate computed on-the-fly from signal + lake close prices #}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
-
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            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-risk-limit"
+            default_exp_name: "tac-rd-sq-gate-2025"
 
 task:
     model:
-        class: RankICEnsembleLGBModel
+        class: LGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
+        module_path: qlib.contrib.model.gbdt
         kwargs:
             loss: mse
-            learning_rate: 0.02
+            learning_rate: 0.05
-            num_leaves: 31
+            num_leaves: 15
-            n_estimators: 3000
+            n_estimators: 200
-            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_alpha: 0.01
-            reg_lambda: 1.0
+            reg_lambda: 0.01
-            seeds: "42,7"
-            parallel: 2
 
     dataset:
         class: DatasetH
@@ -74,9 +50,9 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    end_time: 2025-12-31
-                    fit_start_time: 2016-01-04
+                    fit_start_time: 2015-01-03
-                    fit_end_time: 2025-09-01
+                    fit_end_time: 2026-01-03
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
@@ -94,9 +70,9 @@ task:
                         - class: Fillna
                           kwargs: {}
             segments:
-                train: [2016-01-04, 2025-09-01]
+                train: [2015-01-03, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
+                test: [2025-01-02, 2025-12-31]
 
     record:
         - class: SignalRecord
@@ -104,25 +80,29 @@ task:
           kwargs: {}
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: { ana_long_short: true, ann_scaler: 252 }
-              ana_long_short: true
-              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
               config:
                   strategy:
-                      class: TopkDropoutStrategy
+                      class: SignalQualityGateStrategy
-                      module_path: qlib.contrib.strategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
                       kwargs:
                           signal: "<PRED>"
+                          lake_root: "{{ LAKE }}"
+                          gate_topk: 10
+                          gate_lookback: 5
+                          gate_threshold: 0.5
+                          gate_start: "2015-01-03"
+                          gate_end: "2025-12-31"
                           topk: 10
-                          n_drop: 2
+                          n_drop: 1
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:
-                      start_time: 2026-01-04
+                      start_time: 2025-01-02
-                      end_time: 2026-08-10
+                      end_time: 2025-12-31
                       account: 1000000
                       benchmark: SPY
                       exchange_kwargs:

book/workflows/sq_gate/sq_gate_2026.yaml

@@ -1,67 +1,44 @@
-# -----------------------------------------------------------------------------
+# Signal-quality gate backtest for 2026
-# 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" %}
+{%- 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" %}
+{# Gate computed on-the-fly from signal + lake close prices #}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
-
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            lake_root: "{{ LAKE }}"
-            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
-            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"
+            default_exp_name: "tac-rd-sq-gate-2026"
 
 task:
     model:
-        class: RankICLGBModel
+        class: LGBModel
-        module_path: tac_qlib.contrib.model.rank_gbdt
+        module_path: qlib.contrib.model.gbdt
         kwargs:
             loss: mse
-            learning_rate: 0.02
+            learning_rate: 0.05
-            num_leaves: 31
+            num_leaves: 15
-            n_estimators: 3000
+            n_estimators: 200
-            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_alpha: 0.01
-            reg_lambda: 1.0
+            reg_lambda: 0.01
-            seed: 42
 
     dataset:
         class: DatasetH
@@ -75,7 +52,7 @@ task:
                     start_time: 2015-01-03
                     end_time: 2026-08-10
                     fit_start_time: 2015-01-03
-                    fit_end_time: 2025-09-01
+                    fit_end_time: 2026-01-03
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
@@ -103,20 +80,24 @@ task:
           kwargs: {}
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: { ana_long_short: true, ann_scaler: 252 }
-              ana_long_short: true
-              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
               config:
                   strategy:
-                      class: TopkDropoutStrategy
+                      class: SignalQualityGateStrategy
-                      module_path: qlib.contrib.strategy
+                      module_path: tac_qlib.contrib.strategy.signal_quality_gate
                       kwargs:
                           signal: "<PRED>"
+                          lake_root: "{{ LAKE }}"
+                          gate_topk: 10
+                          gate_lookback: 5
+                          gate_threshold: 0.5
+                          gate_start: "2015-01-03"
+                          gate_end: "2026-08-19"
                           topk: 10
-                          n_drop: 2
+                          n_drop: 1
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:

code/MANIFEST.txt

@@ -1,29 +1,35 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 125be7b96fb5975e798a0b4301eeb5809a8a181c
+# parent repo HEAD : e952feed0a66a20439f4f24ad5524233429cd0c3
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b8112569f9b2537c45b6535e1a505a207878d322  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  861592c63edd6a0853a9cb174b5970435b135fc8  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  8d5333ebd2b44165c50cba639ca2d4ac3fc7cfec  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  5c547a2ef92e075e550fe6d01508a2f1d3f536bc  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  18cb37c0354184c49fa2e598396d7df0634cce0f  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  4f656130d167e79dcaaeb7783a121f0b36852374  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  871ff1e163c29261f140c3f53d42a41e6504c779  tac-qlib/tac_qlib/contrib/data/handler.py
+  0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  ab958203f33a99d12c7d923b6efb435189231666  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  b1489f2fc0dee85f0a4f90b2e6ad545ed9c8967b  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  7478f6b0f6de419615c02d4d92b54529f689ef04  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  121ef237da1df1b8e21a561c3ad0db200b901339  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  9f9014ddd9bce37490061312d51e8e6fe540fec4  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  74d0da348cbcc3700c96b6f4fe4391488e61efc5  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
-  ce77dea53f6a87c5379782709293bf8ff55b2c75  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
+  d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
-  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
-  4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
+  2c2f167b693f4366a769998e3c9d4804f29e31e0  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  74e5ecbbbb20bb71fd5cd083383de4ce88476712  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  f9cd9ab729e3248542ccc490af7adc2e51c71914  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  afaf562aeaa12cebc8529cd916153252e7e3c38a  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  cd3133cfbd2556b25c106e39ae97fb128df0e326  tac-qlib/tac_qlib/contrib/strategy/__pycache__/ic_gate.cpython-312.pyc
-  96a0a25201f0a1bb2fc2190e26228c5c0e711a79  tac-qlib/tac_qlib/contrib/strategy/hmm_risk.py
+  6dd1c568a2961842793674390d5abffd1a0e71b8  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
-  816de5d58ae23d996635d42331cf9fc8963d5dbe  tac-qlib/tac_qlib/contrib/strategy/momentum_gate.py
+  03b5e4d80da00800f1b108bee0735d3d18d856d1  tac-qlib/tac_qlib/contrib/strategy/__pycache__/regime_gate.cpython-312.pyc
+  a6a1c21ab71b62080830df45c4784b73c1531036  tac-qlib/tac_qlib/contrib/strategy/__pycache__/signal_quality_gate.cpython-312.pyc
+  755e3b139496a5e22b0328db45c8199c33029fbc  tac-qlib/tac_qlib/contrib/strategy/__pycache__/weekly_rebalance.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
+  16ab80b731aab6d8bb818525615d77c2d1fcb0c8  tac-qlib/tac_qlib/contrib/strategy/signal_quality_gate.py
+  fe60bacdfedd48617863be31f24b7c7daebfac5a  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  0ed1ead6c1314a3f25784d453e54a15a8a04baaa  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  316bf4aa160cc8d15929ea648be03f4b4999667d  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  9609782800944c45b78bb58eaa7b51ba1b7f8f43  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  554a3f29d181b64effbf49a8161b32e7f93d8d3e  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  a85628d71d12cfe5b18b1c884c5d829c89594579  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  8b47f6d78ac046b6b7b2fb07bd7f3382773ffb73  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
-  686d36f6d101c547491ca866aa143aa542e17518  tac-qlib/tac_qlib/data/config.py
+  53c9007a928841fd3c3b08450f9a6520ce1ac091  tac-qlib/tac_qlib/data/config.py
-  d9f839be30026f337754a3f015425a8efdbe8e2a  tac-qlib/tac_qlib/data/providers.py
+  8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py

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

@@ -64,9 +64,13 @@ def check_transform_proc(proc_l, fit_start_time, fit_end_time):
 
 
 def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> List[str]:
-    """Discover ta-lib columns present in *every* features parquet file of the lake.
+    """Discover feature columns present in *every* feature file of the lake.
 
-    Returns sorted field names (without the ``$`` prefix). Empty if no features are persisted.
+    Walks the `family=ta|sp` partition layout (plus any legacy flat files).
+    TA and SP columns are disjoint by construction, so the common set is
+    computed per family (columns shared by all symbol files of that family),
+    then the per-family results are unioned. Returns sorted field names
+    (without the ``$`` prefix). Empty if no features are persisted.
     """
     cfg = LakeConfig(lake_root, market)
     feat_dir = cfg.features_dir(timeframe)
@@ -74,8 +78,9 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
         return []
     import pyarrow.parquet as pq
 
+    def _family_common(fam_dir: Path) -> set:
         common = None
-    for p in sorted(feat_dir.glob("symbol=*.parquet")):
+        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
@@ -83,7 +88,20 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
             common = cols if common is None else (common & cols)
             if not common:
                 break
-    return sorted(common) if common else []
+        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):

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

@@ -56,7 +56,6 @@ import os
 from concurrent.futures import ThreadPoolExecutor
 from typing import List, Optional
 
-import numpy as np
 import pandas as pd
 
 from qlib.data.dataset import DatasetH
@@ -80,15 +79,11 @@ class RankICEnsembleLGBModel(RankICLGBModel):
         forwarded.
     """
 
-    def __init__(self, seeds: str = "42", parallel: int = 0, weight_mode: str = "equal", **kwargs):
+    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)
-        if weight_mode not in ("equal", "rolling_ic"):
-            raise ValueError(f"weight_mode must be 'equal' or 'rolling_ic', got {weight_mode!r}")
-        self.weight_mode = weight_mode
-        self.rolling_ic_window = int(kwargs.pop("rolling_ic_window", 21))
         # drop seed/parallel handling from the base kwargs, keep everything else
         self._model_kwargs = dict(kwargs)
         super().__init__(**self._model_kwargs)
@@ -184,44 +179,11 @@ class RankICEnsembleLGBModel(RankICLGBModel):
 
     # -------------------------------------------------------------- predict
     def predict(self, dataset: DatasetH, segment="test") -> pd.Series:
-        """Combine per-seed predictions.
+        """Average the per-seed predictions over the given segment."""
-
-        ``weight_mode='equal'`` (default): simple average, as before.
-        ``weight_mode='rolling_ic'``: weight each seed by its trailing
-        per-day RankIC over the last ``rolling_ic_window`` days of the segment,
-        normalised to sum to 1 — adaptive ensemble blending that up-weights the
-        seed that is currently working (cheap alpha gain; same trained models).
-        """
         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)
-        frame.columns = [f"seed{m.params.get('seed', i)}" for i, m in enumerate(self._models)]
-        if self.weight_mode == "equal":
         return frame.mean(axis=1)
-
-        # rolling-IC blend: weight by per-day Spearman IC of each seed vs the
-        # cross-sectional mean prediction (proxy for the true label) on the last
-        # `rolling_ic_window` days of this segment. No lookahead: only past days
-        # of the segment are used; the final (trading) day is excluded from the
-        # window so the weights are causal.
-        mean_pred = frame.mean(axis=1)
-        dates = sorted(frame.index.get_level_values(0).unique())
-        win = [d for d in dates if d < dates[-1]][-self.rolling_ic_window :]
-        ics = {}
-        for col in frame.columns:
-            if not win:
-                ics[col] = 1.0
-                continue
-            sub = pd.DataFrame({"p": frame[col], "m": mean_pred})
-            vals = []
-            for d in win:
-                s = sub[sub.index.get_level_values(0) == d]
-                if len(s) >= 3 and s["p"].nunique() > 1 and s["m"].nunique() > 1:
-                    vals.append(s["p"].rank().corr(s["m"].rank()))
-            ics[col] = float(np.mean(vals)) if vals else 1.0
-        wsum = sum(ics.values()) or len(ics)
-        weights = {c: v / wsum for c, v in ics.items()}
-        return sum(frame[c] * weights[c] for c in frame.columns)

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

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

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

@@ -1,3 +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__ = ["OptimalStopControl"]
+__all__ = [
+    "ICGateTopkDropoutStrategy",
+    "OptimalStopControl",
+    "RegimeGateTopkDropoutStrategy",
+    "WeeklyRebalanceDropoutStrategy",
+]

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

@@ -1,138 +0,0 @@
-"""TopkDropout with HMM high-volatility + drawdown-pause risk gates.
-
-Gates NEW entries on two risk conditions (held names are never force-sold):
-
-1. **HMM high-vol pause**: when the cross-sectional mean of ``sp_hmm_p_regime1``
-   (HMM high-vol regime probability) on the signal date is >= ``hmm_pause_pct``,
-   new buys are paused. The time-series study showed HMM high-vol probability
-   pulses BEFORE sharp moves (regime-change cut) — pausing new exposure at the
-   boundary reduces drawdown from price over-reaction.
-2. **Drawdown pause**: when the account equity drawdown from its running peak
-   exceeds ``drawdown_pause_pct``, new buys are paused. This is the
-   ``drawdown_pause_pct`` risk-limit expressed inside the backtest (the pure
-   executor-side gate is documented as not expressible in a one-shot backtest).
-3. **Liquidity floor**: names whose 20-day average daily dollar volume is below
-   ``liquidity_floor_adv`` are dropped from BUY candidates (the proven mitigant
-   from exp-18: $5M floor cut drawdown 7.9%->5.4% at higher IR).
-
-Implementation: pre-filter the signal score before the base TopkDropout
-decision — non-held names get score 0 when any gate fires.
-
-Wired into a workflow yaml like:
-
-    strategy:
-        class: HmmRiskTopk
-        module_path: tac_qlib.contrib.strategy.hmm_risk
-        kwargs:
-            signal: "<PRED>"
-            topk: 10
-            n_drop: 2
-            only_tradable: true
-            risk_degree: 0.95
-            hmm_pause_pct: 0.70
-            drawdown_pause_pct: 8.0
-            liquidity_floor_adv: 5000000
-"""
-
-from __future__ import annotations
-
-import copy
-from typing import Dict
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest.decision import TradeDecisionWO
-from qlib.backtest.position import Position
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["HmmRiskTopk"]
-
-
-class HmmRiskTopk(TopkDropoutStrategy):
-    """TopkDropoutStrategy with HMM high-vol pause + drawdown pause + liquidity floor."""
-
-    def __init__(
-        self,
-        *,
-        hmm_pause_pct: float = 0.70,
-        drawdown_pause_pct: float = 8.0,
-        liquidity_floor_adv: float = 0.0,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.hmm_pause_pct = float(hmm_pause_pct)
-        self.drawdown_pause_pct = float(drawdown_pause_pct)
-        self.liquidity_floor_adv = float(liquidity_floor_adv)
-        self._peak_equity = 0.0
-
-    # ------------------------------------------------------------- gates
-    def _hmm_high_vol(self, pred_date) -> bool:
-        """Cross-sectional mean HMM high-vol regime probability >= threshold."""
-        try:
-            from qlib.data import D
-
-            feat = D.features(D.instruments("all"), ["$sp_hmm_p_regime1"],
-                              start_time=pred_date, end_time=pred_date)
-            if feat is None or len(feat) == 0:
-                return False
-            p = feat["$sp_hmm_p_regime1"].dropna()
-            if len(p) == 0:
-                return False
-            return float(p.mean()) >= self.hmm_pause_pct
-        except Exception:
-            return False
-
-    def _drawdown_active(self, equity: float) -> bool:
-        if self.drawdown_pause_pct <= 0:
-            return False
-        self._peak_equity = max(self._peak_equity, equity)
-        if self._peak_equity <= 0:
-            return False
-        dd = (self._peak_equity - equity) / self._peak_equity * 100.0
-        return dd >= self.drawdown_pause_pct
-
-    def _illiquid(self, codes, asof) -> Dict[str, bool]:
-        if self.liquidity_floor_adv <= 0 or not codes:
-            return {}
-        from tac_qlib.risk_limits import dollar_adv
-
-        adv = dollar_adv(codes, market="US", asof=asof, lookback=20)
-        return {c: adv.get(str(c).upper(), 0.0) < self.liquidity_floor_adv for c in codes}
-
-    # ------------------------------------------------------------- decision
-    def generate_trade_decision(self, execute_result=None):
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-        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 pred_score is None:
-            return TradeDecisionWO([], self)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-
-        current_temp = copy.deepcopy(self.trade_position)
-        assert isinstance(current_temp, Position)
-        held = {c for c in current_temp.get_stock_list() if abs(current_temp.get_stock_amount(c)) > 1e-6}
-
-        equity = current_temp.get_cash()
-        for code in held:
-            mark = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=1
-            )
-            if mark is not None and np.isfinite(mark):
-                equity += abs(current_temp.get_stock_amount(code)) * mark
-
-        hmm_pause = self._hmm_high_vol(str(pd.Timestamp(pred_start_time).date()))
-        dd_pause = self._drawdown_active(equity)
-        buys_paused = hmm_pause or dd_pause
-
-        pred_score = pred_score.copy()
-        if buys_paused or self.liquidity_floor_adv > 0:
-            new_codes = [c for c in pred_score.index if c not in held]
-            illiquid = self._illiquid(new_codes, str(pd.Timestamp(pred_start_time).date()))
-            for code in new_codes:
-                if buys_paused or illiquid.get(code, False):
-                    pred_score[code] = -1e9  # cannot enter today
-
-        return super().generate_trade_decision(execute_result)

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/momentum_gate.py

@@ -1,91 +0,0 @@
-"""TopkDropout with a 1-day momentum entry-confirmation gate.
-
-Gates NEW entries on short-term momentum: a name that is not currently held
-may only be bought when its trailing 1-day return is above ``min_momentum``
-(Lag-1 autocorr ~ +0.45 in the time-series study => short-term momentum
-continuation). Held names are never force-sold by this gate — exits stay the
-pure TopkDropout rule.
-
-Implementation: override ``generate_trade_decision`` and zero out the signal
-score of any non-held name that fails the momentum check BEFORE calling the
-base TopkDropout decision, so it can never be selected as a buy candidate.
-This is a clean pre-filter: the rest of the strategy (top-k, n_drop, sizing,
-costs) is untouched.
-
-Wired into a workflow yaml like:
-
-    strategy:
-        class: MomentumGateTopk
-        module_path: tac_qlib.contrib.strategy.momentum_gate
-        kwargs:
-            signal: "<PRED>"
-            topk: 10
-            n_drop: 2
-            only_tradable: true
-            risk_degree: 0.95
-            min_momentum: 0.0
-"""
-
-from __future__ import annotations
-
-import copy
-
-import pandas as pd
-
-from qlib.backtest.decision import TradeDecisionWO
-from qlib.backtest.position import Position
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["MomentumGateTopk"]
-
-
-class MomentumGateTopk(TopkDropoutStrategy):
-    """TopkDropoutStrategy gated on 1-day momentum for new entries."""
-
-    def __init__(self, *, min_momentum: float = 0.0, **kwargs):
-        super().__init__(**kwargs)
-        self.min_momentum = float(min_momentum)
-
-    def _momentum_ok(self, code, trade_start, trade_end) -> bool:
-        """True when the trailing 1-day return is above the momentum floor."""
-        try:
-            cur = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start, end_time=trade_end, direction=1
-            )
-        except Exception:
-            return False
-        if cur is None or cur != cur or cur <= 0:
-            return False
-        prev_start = trade_start - pd.Timedelta(days=5)
-        prev_end = trade_start - pd.Timedelta(seconds=1)
-        prev = self.trade_exchange.get_deal_price(
-            stock_id=code, start_time=prev_start, end_time=prev_end, direction=0
-        )
-        if prev is None or prev != prev or prev <= 0:
-            return False
-        return (cur / prev - 1.0) >= self.min_momentum
-
-    def generate_trade_decision(self, execute_result=None):
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-        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 pred_score is None:
-            return TradeDecisionWO([], self)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-
-        current_temp = copy.deepcopy(self.trade_position)
-        assert isinstance(current_temp, Position)
-        held = set(current_temp.get_stock_list())
-        held = {c for c in held if abs(current_temp.get_stock_amount(c)) > 1e-6}
-
-        # pre-filter: zero the score of non-held names that fail momentum
-        pred_score = pred_score.copy()
-        for code in pred_score.index:
-            if code in held:
-                continue  # never gate exits / re-balancing of held names
-            if not self._momentum_ok(code, trade_start_time, trade_end_time):
-                pred_score[code] = -1e9  # cannot enter today
-
-        return super().generate_trade_decision(execute_result)

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/signal_quality_gate.py

@@ -0,0 +1,301 @@
+"""Signal-quality gate TopkDropout strategy.
+
+Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
+holds the book (issues NO orders) when the model's recent prediction accuracy
+is below a threshold.  When the gate is open it behaves exactly like the
+reference TopkDropoutStrategy.
+
+Unlike the regime gate (which asks "is the market calm?"), the signal-quality
+gate asks "are my predictions accurate?" — and works across ALL years.
+
+The gate is provided as a precomputed ``pd.Series`` of booleans indexed by
+datetime (True = trade allowed).  The companion ``compute_signal_quality_gate``
+function builds this series from a pred.pkl and lake bars; call it once before
+backtesting and pass the result as the ``signal_quality_gate`` parameter.
+"""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["SignalQualityGateStrategy", "compute_signal_quality_gate"]
+
+
+class SignalQualityGateStrategy(TopkDropoutStrategy):
+    """TopkDropout with signal-quality gate overlay.
+
+    When ``lake_root`` is provided the gate is computed on-the-fly from the
+    signal (``<PRED>``) and close prices — no precomputed gate file needed.
+    This ensures the gate matches the model that is actually generating the
+    predictions (critical when the model is retrained each year).
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    signal_quality_gate : pd.Series — precomputed per-date gate (bool).
+    signal_quality_gate_path : str — path to pickled gate Series.
+    lake_root : str — lake root for on-the-fly gate computation (preferred).
+    gate_topk, gate_lookback, gate_threshold : int/float — gate params.
+    gate_start, gate_end : str — date window for loading close prices.
+    """
+
+    def __init__(self, *, signal_quality_gate=None, signal_quality_gate_path=None,
+                 lake_root=None, gate_topk=10, gate_lookback=5, gate_threshold=0.5,
+                 gate_start="2015-01-03", gate_end="2026-08-19", **kwargs):
+        super().__init__(**kwargs)
+        self._sq_gate_computed = False
+        if signal_quality_gate is not None:
+            self._sq_gate = signal_quality_gate
+            self._sq_gate_computed = True
+        elif signal_quality_gate_path is not None:
+            import pickle
+            with open(signal_quality_gate_path, "rb") as f:
+                self._sq_gate = pickle.load(f)
+            self._sq_gate_computed = True
+        elif lake_root is not None:
+            self._sq_gate = None
+            self._lake_root = lake_root
+            self._gate_topk = gate_topk
+            self._gate_lookback = gate_lookback
+            self._gate_threshold = gate_threshold
+            self._gate_start = gate_start
+            self._gate_end = gate_end
+        else:
+            self._sq_gate = None
+
+    def _compute_gate_on_fly(self):
+        """Compute gate from the signal (pred.pkl) and lake close prices."""
+        import pickle
+        from pathlib import Path
+
+        signal_path = self._signal
+        if not Path(signal_path).exists():
+            return
+
+        with open(signal_path, "rb") as f:
+            pred = pickle.load(f)
+
+        # Handle MultiIndex DataFrame -> unstack to wide
+        if isinstance(pred, pd.DataFrame) and isinstance(pred.index, pd.MultiIndex):
+            pred = pred.iloc[:, 0]
+            pred.index = pd.MultiIndex.from_arrays([
+                pd.to_datetime(pred.index.get_level_values(0)).normalize(),
+                pred.index.get_level_values(1)
+            ])
+            pred = pred.unstack(level=1)
+        elif isinstance(pred, pd.DataFrame):
+            pred = pred.iloc[:, 0] if pred.shape[1] >= 1 else pred.squeeze()
+            pred.index = pd.to_datetime(pred.index).normalize()
+
+        # Load close prices from lake
+        close_df = _load_close_prices(self._lake_root, "US", self._gate_start, self._gate_end)
+        if close_df.empty:
+            return
+
+        ret_df = close_df.pct_change()
+        ret_df.index = pd.to_datetime(ret_df.index).normalize()
+
+        pred_dates = sorted(pred.index.unique())
+        if len(pred_dates) < 2:
+            self._sq_gate = pd.Series(True, index=pd.DatetimeIndex(pred_dates))
+            self._sq_gate_computed = True
+            return
+
+        hit_rates = {}
+        for i in range(1, len(pred_dates)):
+            day = pred_dates[i]
+            prev_day = pred_dates[i - 1]
+            try:
+                prev_scores = pred.loc[prev_day]
+            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[:self._gate_topk])
+
+            if day not in ret_df.index:
+                continue
+            today_ret = ret_df.loc[day]
+            topk_rets = today_ret.reindex(topk_syms).dropna()
+            if len(topk_rets) == 0:
+                continue
+
+            hit_rates[day] = (topk_rets > 0).sum() / len(topk_rets)
+
+        if not hit_rates:
+            self._sq_gate_computed = True
+            return
+
+        hr_series = pd.Series(hit_rates).sort_index()
+        rolling_hr = hr_series.rolling(self._gate_lookback, min_periods=1).mean()
+        gate = rolling_hr >= self._gate_threshold
+        gate.iloc[:self._gate_lookback] = True
+
+        self._sq_gate = gate
+        self._sq_gate_computed = True
+
+    def _gate_open(self, trade_start_time) -> bool:
+        if self._sq_gate is None:
+            return True
+        ts = pd.Timestamp(trade_start_time)
+        known = self._sq_gate[self._sq_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):
+        if not self._sq_gate_computed:
+            self._compute_gate_on_fly()
+        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_signal_quality_gate(
+    pred_path: str,
+    *,
+    lake_root: str = "",
+    market: str = "US",
+    topk: int = 10,
+    lookback: int = 5,
+    threshold: float = 0.5,
+    start: str = "2015-01-03",
+    end: str = "2026-08-19",
+) -> pd.Series:
+    """Build a per-date signal-quality gate series from a pred.pkl and lake bars.
+
+    For each day, checks whether the model's topk picks from the previous day
+    had positive returns.  Computes a rolling hit rate over ``lookback`` days
+    and opens the gate when hit rate >= ``threshold``.
+
+    Parameters
+    ----------
+    pred_path : str — path to pred.pkl (from rd_train / rd_predict).
+    lake_root, market : str — lake location (for loading close prices).
+    topk : int — number of top picks to track for hit rate.
+    lookback : int — rolling window for hit rate computation.
+    threshold : float — hit rate threshold to keep trading.
+    start, end : str — date window for loading prices.
+
+    Returns
+    -------
+    pd.Series — bool, indexed by datetime.  True = trade allowed.
+    """
+    from pathlib import Path
+    import pickle
+
+    # Load pred.pkl
+    with open(pred_path, "rb") as f:
+        pred = pickle.load(f)
+
+    # Handle MultiIndex DataFrame (datetime, instrument) -> unstack to wide
+    if isinstance(pred, pd.DataFrame) and isinstance(pred.index, pd.MultiIndex):
+        pred = pred.iloc[:, 0]  # take score column as Series
+        pred.index = pd.MultiIndex.from_arrays([
+            pd.to_datetime(pred.index.get_level_values(0)).normalize(),
+            pred.index.get_level_values(1)
+        ])
+        # Unstack to wide: dates x instruments
+        pred = pred.unstack(level=1)
+    elif isinstance(pred, pd.DataFrame):
+        pred = pred.iloc[:, 0] if pred.shape[1] >= 1 else pred.squeeze()
+        pred.index = pd.to_datetime(pred.index).normalize()
+
+    # Load close prices from lake
+    close_df = _load_close_prices(lake_root, market, start, end)
+    if close_df.empty:
+        return pd.Series(dtype=bool)
+
+    ret_df = close_df.pct_change()
+    ret_df.index = pd.to_datetime(ret_df.index).normalize()
+
+    # Get sorted unique prediction dates
+    pred_dates = sorted(pred.index.unique())
+    if len(pred_dates) < 2:
+        return pd.Series(True, index=pd.DatetimeIndex(pred_dates))
+
+    # Compute hit rates
+    hit_rates = {}
+    for i in range(1, len(pred_dates)):
+        day = pred_dates[i]
+        # Get yesterday's topk
+        prev_day = pred_dates[i - 1]
+        try:
+            prev_scores = pred.loc[prev_day]
+        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])
+
+        # Get today's returns
+        if day not in ret_df.index:
+            continue
+        today_ret = ret_df.loc[day]
+        topk_rets = today_ret.reindex(topk_syms).dropna()
+        if len(topk_rets) == 0:
+            continue
+
+        hit_rates[day] = (topk_rets > 0).sum() / len(topk_rets)
+
+    if not hit_rates:
+        return pd.Series(dtype=bool)
+
+    hr_series = pd.Series(hit_rates).sort_index()
+
+    # Rolling hit rate
+    rolling_hr = hr_series.rolling(lookback, min_periods=1).mean()
+
+    # Gate is open when rolling hit rate >= threshold
+    gate = rolling_hr >= threshold
+    gate.iloc[:lookback] = True  # warmup: allow trading
+
+    return gate
+
+
+def _load_close_prices(lake_root, market, start, end):
+    """Load daily close prices for all symbols into a wide DataFrame."""
+    from pathlib import Path
+
+    lake = Path(lake_root)
+    symbols_parquet = lake / "symbols.parquet"
+    if not symbols_parquet.exists():
+        return pd.DataFrame()
+
+    df = pd.read_parquet(symbols_parquet)
+    col = "symbol" if "symbol" in df.columns else df.columns[0]
+    symbols = sorted(df[col].astype(str).str.upper().tolist())
+
+    closes = {}
+    for sym in symbols:
+        p = lake / "market=US" / "timeframe=1d" / f"symbol={sym}.parquet"
+        if not p.exists():
+            continue
+        try:
+            bar = pd.read_parquet(p)
+        except Exception:
+            continue
+        if not len(bar):
+            continue
+        tcol = "t" if "t" in bar.columns else "date"
+        ts = pd.to_datetime(bar[tcol])
+        bar = bar.assign(_t=ts).set_index("_t").sort_index()
+        bar = bar.loc[start:end]
+        if len(bar) < 10:
+            continue
+        closes[sym] = bar["c"] if "c" in bar.columns else bar["close"]
+
+    return pd.DataFrame(closes)

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/config.py

@@ -6,10 +6,11 @@ The lake is a hive-partitioned parquet store (see ``tac-engine/skills/tradeac-la
     ├── market=US/
     │   └── timeframe=1d/
     │       └── symbol=AAPL.parquet        # OHLCV bars: t, date, o, h, l, c, v, n, vw
-    ├── features/                          # ta-lib indicators, wide format
+    ├── features/                          # indicators, wide format, family tier
     │   └── market=US/
     │       └── timeframe=1d/
-    │           └── symbol=AAPL.parquet    # t, sma_5, sma_20, rsi_14, ...
+    │           ├── 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
@@ -107,8 +108,34 @@ class LakeConfig:
         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"
 

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

@@ -173,8 +173,7 @@ class LakeFeatureProvider(FeatureProvider):
     def _load_feature_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
         key = (instrument, timeframe)
         if key not in self._feature_cache:
-            p = self.cfg.features_path(timeframe, instrument)
+            self._feature_cache[key] = self.cfg.load_features(timeframe, instrument)
-            self._feature_cache[key] = pd.read_parquet(p) if p.exists() else pd.DataFrame()
         return self._feature_cache[key]
 
     @staticmethod

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/exp18-risk-limit/a_baseline.yaml

@@ -1,141 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
-#
-# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
-# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
-# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
-# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
-# (same pred, liquidity/size/concentration caps) can be compared 1:1.
-#
-# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
-# (tool-level param, not a YAML key); this run records the unconstrained
-# baseline that the limit A/B is measured against.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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/exp20-risk-limit-improve/r0_5seed_baseline.yaml

@@ -1,135 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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/exp20-risk-limit-improve/r2_momentum.yaml

@@ -1,136 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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: MomentumGateTopk
-                      module_path: tac_qlib.contrib.strategy.momentum_gate
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          min_momentum: 0.0
-                          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/exp20-risk-limit-improve/r3_hmm_risk.yaml

@@ -1,138 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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: HmmRiskTopk
-                      module_path: tac_qlib.contrib.strategy.hmm_risk
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          hmm_pause_pct: 0.70
-                          drawdown_pause_pct: 8.0
-                          liquidity_floor_adv: 5000000
-                          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/exp20-risk-limit-improve/r4_rolling_ic.yaml

@@ -1,137 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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"
-            weight_mode: rolling_ic
-            rolling_ic_window: 21
-            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/exp20-risk-limit-improve/r5_ma3_ewma.yaml

@@ -1,135 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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,sma_3,ema_3" %}
-
-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-risk-limit"
-
-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