# -----------------------------------------------------------------------------
# CANONICAL: SP-5d LightGBM with the stochastic-control OptimalStopControl
# strategy (entry-gated by signal percentile, optimal-stopping exits by
# percentile / time stop / stop-loss, equal-weight control sizing).
#
# This is the stochastic-optimal-stopping strategy ported from the experiments:
#   - entry:   a symbol opens only when its cross-sectional signal percentile
#              >= entry_pct and fewer than `topk` positions are open
#   - exit:    percentile < exit_pct (continuation value too low), or
#              max_hold_days (finite-horizon time stop), or P&L <= sl
#              (loss control) after min_hold_days
#   - sizing:  equal-weight control (risk_degree fraction of total value split
#              across targets)
#
# Strategy class: tac_qlib.contrib.strategy.optimal_stop.OptimalStopControl
# Calibrate entry_pct / exit_pct / max_hold_days on the VALID window only
# (the experiments showed valid-window calibration overfits; prefer robust
# defaults: entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
#
# Run:
#   rd_run_workflow config_path=tac-qlib/workflows/workflow_lgb_sp5d_optstop.yaml \
#       experiment_name=tac-rd-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 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-optstop"

task:
    model:
        class: LGBModel
        module_path: qlib.contrib.model.gbdt
        kwargs:
            loss: mse
            learning_rate: 0.03
            num_leaves: 31
            n_estimators: 500
            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: 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
                          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