# QUEUE-18 — OptimalStopControl clean re-test vs TopkDropout (exp 13/14 claim).
# CLAIMS.md HYPOTHESIS: "TopkDropout beats stochastic-control OptimalStopControl on
# the ensemble signal" — exp 13/14 were pre-clean-lake; never re-tested post-reset.
# Same compact signal as the exp-26 reference; ONLY the strategy changes to
# OptimalStopControl with exp-13 params (entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
# PREREQUISITE: tac_qlib/contrib/strategy/optimal_stop.py must be synced to the venv
# site-packages snapshot before running (see /app/AGENTS.md).
# Acceptance: TopkDropout net_IR >= stop-control net_IR; document cost drag of both.
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q18_optstop.yaml \
#        experiment_name=tac-rd-q18-optstop
{%- 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 FEATURES = "$open,$high,$low,$close,$vwap,$volume,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-q18-optstop" }

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: 2026-08-10
                    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: "{{ FEATURES }}"
                    infer_processors:
                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
                        - { class: ProcessInf, kwargs: {} }
                        - { class: CSRankNorm, kwargs: {} }
                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
                        - { 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: OptimalStopControl
                      module_path: tac_qlib.contrib.strategy.optimal_stop
                      kwargs: { signal: "<PRED>", topk: 10, entry_pct: 0.85, exit_pct: 0.7, max_hold_days: 10, min_hold_days: 2, sl: -0.08 }
                  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