Create a Custom Algorithm

When you create a data analytics job, you can either use a predefined algorithm or a custom algorithm, depending on your use case.

To create a custom algorithm

1. Click +Algorithm and provide the following information:

   

   1. Algorithm - Select Custom Algorithm to be used for the data analytics job.

   2. Algorithm Name - Provide a unique name for the algorithm.

   3. Column Name (Optional) - Select the column on which to apply the selected algorithm. This field is optional when adding a custom algorithm.

   4. Source (Optional) - Select the source file or table containing the column on which the algorithm will be applied. This field is optional when adding a custom algorithm.

   5. Target (Optional) - Select the file or table where the output of the algorithm will be stored. You can either choose an existing file or table or create a new one. This field is optional when adding a custom algorithm.

   

   Note:

   Ensure that the selected column contains binary data only.

   6. Click Add.

   7. After you click Add, the Creation Status displays the following types of statuses depending on whether the data analytics job for the selected algorithm is created or not:

      1. In Progress - when the job is being created.

      2. Success - when the job is created successfully.

      3. Failed - when the job creation fails.

   8. To add code to the custom algorithm, click the algorithm name. You are navigated to JupyterLab Notebook.

      

   9. In the JupyterLab Notebook, add the custom code in the specified section.

      

To visualize the data from a custom algorithm

1. Uncomment the section of the code starting with the import pickle statement.

   

2. Ensure that you use the exact path specified in the following line of code for the pickle file.

Recommended Topics

What's next? Data Analytics using Python with JupyterLab