# Example configuration file for a data processing pipeline

general:
  logging: "console"  # Options: "console", "file", "both"
  log_level: "INFO"  # Options: "DEBUG", "INFO", "WARN", "ERROR", "CRITICAL"
  log_file: "logs/pipeline.log"  # Path to the log file if logging to file

stages:
  - name: "Load_datasets"
    output_stream: "input_dataset"
    module_path: "EEG_preprocessing_modules/data_loader.py"
    module_params:
      datasets:
        - path: "data/dataset1.csv"
          name: "dataset1"
        - path: "data/dataset2.csv"
          name: "dataset2"
      action: "merge"
  
  - name: "Process_data"
    input_stream: "input_dataset"
    output_stream: "processed_dataset"
    module_path: "EEG_preprocessing_modules/preprocessing.py"
    module_params:
      select_channels:
        - "channel1"
        - "channel2"
      filter_frequency: 0.5
      resample_rate: 1000

  - name: "Train_augment_model"
    type: "train"
    input_stream: "processed_dataset"
    module_path: "models_augment/GAN/main.py"
    module_params: # Model specific parameters, they're passed to the module script as dictionary
      noise_level: 0.01
      save_path: "models_augment/GAN/model.pth"


  - name: "Augment_data"
    type: "inference" # Inference is default, but can be specified explicitly
    input_stream: "processed_dataset"
    output_stream: "augmented_dataset"
    module_path: "models_augment/GAN/main.py"
    module_params: # Model specific parameters, they're passed to the model script as dict
      noise_level: 0.01
      model_weights: "models_augment/GAN/model.pth"

  - name: "Save_dataset"
    input_stream: "augmented_dataset"
    module_params:
      output_path: "data/augmented_dataset.mne"