# -----------------------------------------------------------------------------
# LightGBM on the TradeAC lake -- qrun workflow (train -> signal -> backtest).
#
# Run it like a stock qlib project:
#
#     cd tac-qlib
#     qrun workflows/workflow_lgb_taclake.yaml \
#          --experiment_name tac-lake-lgb --uri_folder mlruns
#
# Or with a custom lake root:
#
#     TAC_LAKE_DIR=/path/to/lake qrun workflows/workflow_lgb_taclake.yaml \
#          --experiment_name tac-lake-lgb
#
# The lake providers (calendar/instrument/feature) are wired in `qlib_init`; the
# expression engine and backtest Exchange stay upstream qlib. The TACHandler reads
# OHLCV + ta-lib features straight from the parquet lake.
#
# Segment split (the lake holds 1d bars since 2026-02-09):
#     train 2026-03-01..2026-05-31 / valid 2026-06-01..2026-06-30 / test 2026-07-01..2026-08-06
# -----------------------------------------------------------------------------
{%- set LAKE = TAC_LAKE_DIR %}

qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null

    # --- lake-backed providers (see tac_qlib.data.providers) -----------------
    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

    # sqlite backend avoids mlflow's filesystem-backend maintenance-mode opt-out
    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
        kwargs:
            uri: "sqlite:///mlruns.db"
            default_exp_name: "tac-lake-demo"

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: all
                    start_time: 2026-03-01
                    end_time: 2026-08-06
                    fit_start_time: 2026-03-01
                    fit_end_time: 2026-05-31
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
            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: 2
                          n_drop: 1
                          only_tradable: true
                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-07-01
                      end_time: 2026-08-06
                      account: 1000000
                      # any symbol the lake holds works; the lake has no index quotes yet
                      benchmark: AAPL
                      exchange_kwargs:
                          codes: all
                          deal_price: $close
                          freq: day
                          open_cost: 0.0005
                          close_cost: 0.0015
                          min_cost: 5.0
              risk_analysis_freq: 1d