> ## Documentation Index
> Fetch the complete documentation index at: https://docs.autocleaneeg.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction to Task Files

> Learn how Task files define your preprocessing pipeline in AutoCleanEEG Pipeline

Task files are the **blueprints** of AutoCleanEEG pipeline.

They combine two parts:

1. **Configuration (`config`)** – a dictionary that specifies which steps to enable and how to parameterize them.
2. **Task class (`Task`)** – a Python class that orchestrates the execution of steps in order.

## High-Level Overview

```mermaid theme={null}
flowchart TD

    A[Task File] --> B[Task Config]
    A --> C[Task Class]

    %% Styles
    style A fill:#f9f,stroke:#333,stroke-width:2px,color:#000
    style B fill:#bbf,stroke:#333,stroke-width:2px,color:#000
    style C fill:#bfb,stroke:#333,stroke-width:2px,color:#000
```

## Why Task Files?

* **Reproducibility**: The same task file always runs with the same parameters.
* **Transparency**: Every step and setting is explicitly defined.
* **Flexibility**: You can create different task files for different study designs or datasets (e.g., resting state vs. oddball tasks).
* **Automation**: Tasks integrate with the pipeline CLI to run end-to-end preprocessing.

<Info>
  Task files are designed to be **human-readable and editable**.\
  While you can generate them automatically, customizing them allows you to tailor preprocessing to your study’s specific needs.
</Info>

## Example Snippet

```python theme={null}
config = {
    "resample_step": {"enabled": True, "value": 250},
    "filtering": {"enabled": True, "value": {"l_freq": 1, "h_freq": 100}},
    "ICA": {"enabled": True, "value": {"method": "infomax"}},
    "epoch_settings": {"enabled": True, "value": {"tmin": -1, "tmax": 1}},
}

class RestingState_Basic(Task):
    def run(self) -> None:
        self.import_raw()
        self.resample_data()
        self.filter_data()
        self.run_ica()
        self.create_regular_epochs(export=True)
        self.generate_reports()
```