# region declaration
schema_version: '1.0'
metadata:
  name: book_compiled_factorized
  mode: development
sfd:
  manifest:
    type: ml
    data_source:
      method: limen.data.HistoricalData.get_any_file
      params:
        file_path_or_url: inputs/spot_1h_20240101_20241231.parquet
    split_dates:
      train_start: '2024-01-01'
      train_end: '2024-01-15'
      val_start: '2024-01-15'
      val_end: '2024-01-18'
      test_start: '2024-01-18'
      test_end: '2024-01-22'
    indicators:
    - func: limen.indicators.window_return
      params:
        period: 1
    target:
      name: quantile_flag
      class: limen.targets.QuantileBinaryTarget
      fit_params:
        source_column: ret_1
        quantile: 0.5
      transform_params:
        shift: -1
    backtest:
      fee_bps: '{fee}'
      slip_bps: 3.0
      notional_rate: 0.5
    scaler:
      class: limen.scalers.RobustScaler
    reference_architecture: limen.sfd.reference_architecture.lightgbm_binary
  params:
    fee:
    - 7.0
    - 9.0
    n_estimators:
    - 4
    - 8
    n_jobs:
    - 1
    random_state:
    - 42
    deterministic:
    - true
    force_row_wise:
    - true
    early_stopping_rounds:
    - 0
    subsample_freq:
    - 0
    subsample:
    - 1.0
    colsample_bytree:
    - 1.0
uel:
  output_path: compiled-factorized
  factorize: true
  n_permutations: 4
  search_strategy:
    type: grid
    shuffle: true
    seed: 13
  output_format: csv
  checkpoint_interval: 1
# endregion declaration