From e657c587587f6fc056ead9fa79aa0b38ff435f5c Mon Sep 17 00:00:00 2001 From: zhaoli Date: Thu, 13 Aug 2026 04:32:30 +0000 Subject: [PATCH] start exp 9 (sp5d-feature-family-ablation): baseline all-24 + generic-only 19 workflow YAMLs --- workflows/ablate_baseline_all_sp_fields.yaml | 133 ++++++++++++++++++ workflows/ablate_generic_only_sp_fields.yaml | 134 +++++++++++++++++++ 2 files changed, 267 insertions(+) create mode 100644 workflows/ablate_baseline_all_sp_fields.yaml create mode 100644 workflows/ablate_generic_only_sp_fields.yaml diff --git a/workflows/ablate_baseline_all_sp_fields.yaml b/workflows/ablate_baseline_all_sp_fields.yaml new file mode 100644 index 0000000..5ff3ed3 --- /dev/null +++ b/workflows/ablate_baseline_all_sp_fields.yaml @@ -0,0 +1,133 @@ +# ----------------------------------------------------------------------------- +# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d +# panel, using ALL 24 sp_* feature columns (ou,hmm,jump,har,trend,hurst, +# signature). Copy of the canonical workflow_lgb_sp5d_rankic.yaml with a +# distinct experiment name so the ablation runs are isolated. +# +# Run: +# rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \ +# experiment_name=tac-rd-rank-ablate +# ----------------------------------------------------------------------------- +{%- set LAKE = TAC_LAKE_DIR %} +{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %} +{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %} + +qlib_init: + provider_uri: "{{ LAKE }}" + region: us + expression_cache: null + dataset_cache: null + + calendar_provider: + class: tac_qlib.data.providers.LakeCalendarProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + instrument_provider: + class: tac_qlib.data.providers.LakeInstrumentProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + markets: {} + feature_provider: + class: tac_qlib.data.providers.LakeFeatureProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + + exp_manager: + class: MLflowExpManager + module_path: qlib.workflow.expm + kwargs: + uri: "sqlite:///{{ LAKE }}/mlruns.db" + default_exp_name: "tac-rd-rank-ablate" + +task: + model: + class: RankICLGBModel + module_path: tac_qlib.contrib.model.rank_gbdt + kwargs: + loss: mse + learning_rate: 0.02 + num_leaves: 31 + n_estimators: 3000 + num_boost_round: 3000 + early_stopping_rounds: 200 + min_data_in_leaf: 20 + lambda_l2: 0.5 + colsample_bytree: 0.8 + subsample: 0.8 + subsample_freq: 1 + reg_alpha: 0.1 + reg_lambda: 1.0 + seed: 42 + + dataset: + class: DatasetH + module_path: qlib.data.dataset + kwargs: + handler: + class: TACHandler + module_path: tac_qlib.contrib.data.handler + kwargs: + instruments: "{{ UNIVERSE }}" + start_time: 2015-01-03 + end_time: 2026-08-10 + fit_start_time: 2015-01-03 + fit_end_time: 2025-09-01 + freq: day + lake_root: "{{ LAKE }}" + market: US + label: "Ref($close,-6)/Ref($close,-1)-1" + feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}" + infer_processors: + - class: DropAllNaN + kwargs: {} + - class: ProcessInf + kwargs: {} + - class: CSRankNorm + kwargs: {} + - class: ZScoreNorm + kwargs: {} + - class: Fillna + kwargs: {} + segments: + train: [2015-01-03, 2025-09-01] + valid: [2025-09-03, 2026-01-03] + test: [2026-01-04, 2026-08-10] + + record: + - class: SignalRecord + module_path: qlib.workflow.record_temp + kwargs: {} + - class: SigAnaRecord + module_path: qlib.workflow.record_temp + kwargs: + ana_long_short: true + ann_scaler: 252 + - class: PortAnaRecord + module_path: qlib.workflow.record_temp + kwargs: + config: + strategy: + class: TopkDropoutStrategy + module_path: qlib.contrib.strategy + kwargs: + signal: "" + 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 diff --git a/workflows/ablate_generic_only_sp_fields.yaml b/workflows/ablate_generic_only_sp_fields.yaml new file mode 100644 index 0000000..fa24a87 --- /dev/null +++ b/workflows/ablate_generic_only_sp_fields.yaml @@ -0,0 +1,134 @@ +# ----------------------------------------------------------------------------- +# ABLATION B (generic-only): same panel/model as the baseline, but feature +# fields restricted to the model-free / generic stochastic-process families +# (jump,har,trend,hurst,signature). Drops the model-specific ou (OU/AR-1 +# half-life) and hmm (2-state regime) families to test whether the generic +# families alone dominate the rank dimension. +# +# Run: +# rd_run_workflow config_path=tac-qlib/workflows/ablate_generic_only_sp_fields.yaml \ +# experiment_name=tac-rd-rank-ablate +# ----------------------------------------------------------------------------- +{%- set LAKE = TAC_LAKE_DIR %} +{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %} +{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %} + +qlib_init: + provider_uri: "{{ LAKE }}" + region: us + expression_cache: null + dataset_cache: null + + calendar_provider: + class: tac_qlib.data.providers.LakeCalendarProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + instrument_provider: + class: tac_qlib.data.providers.LakeInstrumentProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + markets: {} + feature_provider: + class: tac_qlib.data.providers.LakeFeatureProvider + kwargs: + lake_root: "{{ LAKE }}" + market: US + + exp_manager: + class: MLflowExpManager + module_path: qlib.workflow.expm + kwargs: + uri: "sqlite:///{{ LAKE }}/mlruns.db" + default_exp_name: "tac-rd-rank-ablate" + +task: + model: + class: RankICLGBModel + module_path: tac_qlib.contrib.model.rank_gbdt + kwargs: + loss: mse + learning_rate: 0.02 + num_leaves: 31 + n_estimators: 3000 + num_boost_round: 3000 + early_stopping_rounds: 200 + min_data_in_leaf: 20 + lambda_l2: 0.5 + colsample_bytree: 0.8 + subsample: 0.8 + subsample_freq: 1 + reg_alpha: 0.1 + reg_lambda: 1.0 + seed: 42 + + dataset: + class: DatasetH + module_path: qlib.data.dataset + kwargs: + handler: + class: TACHandler + module_path: tac_qlib.contrib.data.handler + kwargs: + instruments: "{{ UNIVERSE }}" + start_time: 2015-01-03 + end_time: 2026-08-10 + fit_start_time: 2015-01-03 + fit_end_time: 2025-09-01 + freq: day + lake_root: "{{ LAKE }}" + market: US + label: "Ref($close,-6)/Ref($close,-1)-1" + feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}" + infer_processors: + - class: DropAllNaN + kwargs: {} + - class: ProcessInf + kwargs: {} + - class: CSRankNorm + kwargs: {} + - class: ZScoreNorm + kwargs: {} + - class: Fillna + kwargs: {} + segments: + train: [2015-01-03, 2025-09-01] + valid: [2025-09-03, 2026-01-03] + test: [2026-01-04, 2026-08-10] + + record: + - class: SignalRecord + module_path: qlib.workflow.record_temp + kwargs: {} + - class: SigAnaRecord + module_path: qlib.workflow.record_temp + kwargs: + ana_long_short: true + ann_scaler: 252 + - class: PortAnaRecord + module_path: qlib.workflow.record_temp + kwargs: + config: + strategy: + class: TopkDropoutStrategy + module_path: qlib.contrib.strategy + kwargs: + signal: "" + 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