# CTA 1D Configuration for Parquet Loading
# Use this instead of config.yaml when using CTA1DLoaderParquet

data:
  dt_range: ['2020-01-01', '2023-12-31']

  # Parquet paths (populated by data_ops_research)
  feature_path: /data/parquet/dataset/cta_alpha158_1d
  hffactor_path: /data/parquet/dataset/cta_hffactor_1d
  dom_path: /data/parquet/dataset/cta_dom_1d
  label_path: /data/parquet/dataset/cta_labels_1d

  feature_sets:
    - alpha158
    - hffactor
  normalization: dual
  blend_weights: equal

segments:
  train: ['2020-01-01', '2022-06-30']
  valid: ['2022-07-01', '2022-12-31']
  test: ['2023-01-01', '2023-12-31']

model:
  type: xgb
  params:
    objective: reg:squarederror
    eval_metric: rmse
    eta: 0.05
    max_depth: 6
    subsample: 0.8
    colsample_bytree: 0.8
    seed: 42
  num_boost_round: 500
  early_stopping_rounds: 50

training:
  return_type: o2c_twap1min
  weight_factors:
    positive: 1.0
    negative: 2.0