Pipeline Configuration

In this section, we will have a look at the pipeline configuration that we’ll be using for our target strength processing. The configuration is presented in YAML format, which is a structured and human-readable way to define settings for data processing.

Here’s the configuration we’ll be using:

active_recipe: target_strength 
use_local_dask: true
n_workers: 5
pipeline:
- recipe_name: target_strength
  stages:
  - name: echodataflow_open_raw
    module: echodataflow.stages.subflows.open_raw
    options:
      save_raw_file: true
      use_raw_offline: true
      use_offline: true
  - name: echodataflow_compute_TS
    module: echodataflow.stages.subflows.compute_TS
    options:
      use_offline: true

Note: For a more comprehensive understanding of each option and its functionality, you can refer to the Pipeline documentation.

Keep in mind that in this example, we’ll be setting up a local Dask Cluster with 5 workers for parallel processing. This configuration will enable us to efficiently process our data for target strength analysis. To turn it off, toggle use_local_dask to false.

Feel free to explore and modify the configuration to understand better.