wandb_sweep.yaml

# sweep.yaml
program: train.py
method: grid  # Using 'grid' to exhaustively search all values of push_all_lags_by
metric:
  name: validation_1-mae.min  # Ensure this matches the metric logged in your training script
  goal: minimize
parameters:
  # Fixed Parameters from config.yaml
  model:
    value: "xgboost"
  
  lags:
    value: [1, 2, 3, 6, 12, 13, 14, 24, 25, 26, 48, 49, 72, 168]
  
  rolling_avgs:
    value: [1, 3, 9, 24, 48, 72, 86, 168]
  
  delta_reference_points:
    value:
      - [1, 2]
      - [1, 3]
      - [1, 6]
      - [1, 24]
      - [24, 25]
      - [48, 49]
      - [169, 1]
      - [168, 169]
  
  std_windows:
    value: [3, 6, 12, 24, 48, 72, 86, 168]
  
  num_zeros_windows:
    value: [6, 12, 24]
  
  hour_shifts:
    value: [0, 6, 12, 18]
  
  weekday_shifts:
    value: [0, 3, 6]
  
  target_forward_shift:  
    values: [
      0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 
             21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 
             38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 
             55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 
             72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 
             89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 
             105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 
             119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 
             133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 
             147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 
             161, 162, 163, 164, 165, 166, 167]

  use_station_id_feat:
    value: true
  
  use_cell_id_feat:
    value: true
  
  use_beam_id_feat:
    value: true
  
  # train_percentage:
  #   value: 0.8
  
  # val_percentage:
  #   value: 0.2
  
  run_shap:
    value: false
  
  target_df_names:
    value: ['thp_vol', 'mr_number']
  
  feat_base_df_names:
    value: ['thp_vol', 'mr_number']
  
  enable_categorical:
    value: true
  
  # Fixed XGBoost Hyperparameters from config.yaml
  eta:
    value: 0.03
  
  subsample:
    value: 0.7

  col_subsample:
    value: 0.9
  
  n_estimators:
    value: 125
  
  max_depth:
    value: 8
  
  min_child_weight:
    value: 1  # Fixed value as per config.yaml
  
  colsample_bytree:
    value: 1.0  # Fixed value as per config.yaml
  
  objective:
    value: 'reg:squarederror'
  
  eval_metric:
    value: 'mae'
  
  # early_stopping_rounds:
  #   value: 200