# -----------------------------------------------------------------------------
# Tune run 6 (NEXT run): wider 10-name universe A/B vs run f744455056 (exp 1).
#
# Baseline (exp 1 / run f744455056 — this run):
#   Input : universe AAPL,MSFT,QQQ,IVV,SMH,TLT (6 names, 5 of them the same
#           tech beta); 21 features (OHLCV + TA); label 1-day next return;
#           LGB lr 0.05 / 15 leaves / 200 trees / reg 0.01,0.01;
#           train 03-01..05-31 / valid 06-01..06-30 / test 07-01..08-06.
#   Output: IC 0.048, ICIR 0.09, Rank IC 0.065, Rank ICIR 0.13  ->  noise-level
#           (per-day n=6, IC swings -0.89..+0.74 with many null days).
#           Backtest had NO benchmark (benchmark null) -> the "+180% ann, IR 6.4"
#           headline is raw strategy return, not excess. Strategy +16.5% over 27
#           days, but ~half the P&L came from ONE day (2026-07-30 MSFT +14% sell,
#           +$72k realized). 30 trades/27 days, $15.3k cost (1.5% of $1M),
#           ending book 46.6% SMH + 50.8% TLT (2-name lottery).
#
# PRIMARY LEVER (change one thing, everything else held at baseline):
#   universe: 6 -> 10 names (AAPL,MSFT,TSLA,QQQ,IVV,SMH,TLT,IBIT,MCHI,AIQ).
#   Rationale: with 6 near-collinear names there is nothing to rank — ICIR 0.09
#   is cross-sectional noise and the topk book just re-buys tech momentum on
#   correlated bets. Widening to ~10 independent-ish betas (mega tech, semis,
#   S&P, Nasdaq, bonds, BTC, EM, robotics) gives the cross-section real breadth,
#   stabilizes IC, and makes a diversified topk book possible.
#
# SUPPORTING (kept minimal, flagged for attribution):
#   - topk 2 -> 4, n_drop 1 -> 2: kill the 2-name lottery, cut per-name churn.
#   - benchmark: unset -> QQQ: the baseline "excess return" was raw strategy
#     return because no benchmark was wired; QQQ is the index the tech-heavy
#     universe tracks.
#   - model: explicit num_boost_round 1000 + early_stopping_rounds 50 so round
#     count is controlled (baseline's n_estimators: 200 was swallowed into lgb
#     params and valid l2 rose monotonically -> overfit). Hyperparameters
#     otherwise identical to baseline for a clean universe A/B.
#   - label: KEPT at 1-day next return so this run isolates the universe lever;
#     a 5-day horizon is the natural NEXT experiment (see tune_run3).
#
# Trigger into a NEW experiment (do not pollute exp 1); evolved_from = f744455056:
#   rd_run_workflow config_path=tac-qlib/workflows/tune_run6_wider_universe_ab.yaml \
#       experiment_name=tac-rd-tune
# -----------------------------------------------------------------------------
{%- set LAKE = TAC_LAKE_DIR %}

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-tune"

task:
    model:
        class: LGBModel
        module_path: qlib.contrib.model.gbdt
        kwargs:
            loss: mse
            learning_rate: 0.05
            num_leaves: 15
            num_boost_round: 1000
            early_stopping_rounds: 50
            colsample_bytree: 0.8
            subsample: 0.8
            subsample_freq: 1
            reg_alpha: 0.01
            reg_lambda: 0.01
            seed: 2026

    dataset:
        class: DatasetH
        module_path: qlib.data.dataset
        kwargs:
            handler:
                class: TACHandler
                module_path: tac_qlib.contrib.data.handler
                kwargs:
                    instruments: AAPL,MSFT,TSLA,QQQ,IVV,SMH,TLT,IBIT,MCHI,AIQ
                    start_time: 2000-01-03
                    end_time: 2026-08-06
                    fit_start_time: 2026-03-01
                    fit_end_time: 2026-05-31
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-2)/Ref($close,-1)-1"
            segments:
                train: [2026-03-01, 2026-05-31]
                valid: [2026-06-01, 2026-06-30]
                test: [2026-07-01, 2026-08-06]

    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: 4
                          n_drop: 2
                          only_tradable: true
                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-07-01
                      end_time: 2026-08-06
                      account: 1000000
                      benchmark: QQQ
                      exchange_kwargs:
                          codes: AAPL,MSFT,TSLA,QQQ,IVV,SMH,TLT,IBIT,MCHI,AIQ
                          deal_price: $close
                          freq: day
                          open_cost: 0.0005
                          close_cost: 0.0015
                          min_cost: 5.0
              risk_analysis_freq: 1d