global_config.yaml

name: global

# config for all algorithms
all:
  prediction_tasks: ["dep_weekly"] # list of model prediction tasks, should only contains major targets
                                   # other examples: ["UCLA_10items_POST", "PSS_10items_POST"]
  
  # ds_keys: ["INS-W_1", "INS-W_2", "INS-W_3", "INS-W_4"] # list of datasets to analyze
  ds_keys: ["INS-W-sample_1", "INS-W-sample_2", "INS-W-sample_3", "INS-W-sample_4"] # list of datasets to analyze

  # Default False. Only True when the dataset in ds_keys all support an extended list of feature types.
  # Currently only support INS-W
  flag_more_feat_types: True

# config for traditional algorithms
ml:
  training_params:
    # whether to save and re-use features repetitively
    #     True only when re-running the exact same algorithm
    save_and_reload: False

# config for deep learning based algorithms
dl:
  training_params:
    best_epoch_strategy: "direct" # which strategy to pick the best training epoch
    # whether to skip training
    #     True only when the model training is finished
    skip_training: False