Dataiku DSS icon

Dataiku DSS

Use the Dataiku DSS API

Actions364

Overview

This node integrates with the Dataiku DSS API, enabling users to interact programmatically with various Dataiku DSS resources and operations. Specifically, for the Machine Learning - Lab resource and the Compute Partial Dependencies of Trained Model operation, the node launches the computation of partial dependencies for a trained machine learning model within a specified project and analysis context.

Partial dependence plots are useful in interpreting complex models by showing the marginal effect of one or two features on the predicted outcome. This node is beneficial when you want to analyze how individual features influence the predictions of your trained model in Dataiku DSS.

Practical example:
You have a trained model in a Dataiku DSS project and want to understand the impact of certain features on the model's predictions. Using this node, you can trigger the computation of partial dependencies for that model, which can then be visualized or further analyzed.

Properties

Name Meaning
Project Key The key identifier of the Dataiku DSS project containing the model.
Analysis ID The identifier of the specific analysis within the project related to the ML task.
ML Task ID The identifier of the machine learning task associated with the trained model.
Model Full ID The full identifier of the trained model for which partial dependencies will be computed.
Request Body JSON object representing additional parameters or payload required by the API call.

Output

The output is the JSON response from the Dataiku DSS API after requesting the computation of partial dependencies. It typically contains information about the status or result of the computation request.

  • If the operation returns binary data (not typical for this operation), it would be provided as binary content.
  • For this operation, the output is expected to be JSON indicating success, job status, or details about the launched computation.

Example output structure (simplified):

{
  "status": "started",
  "jobId": "12345",
  "message": "Partial dependencies computation has been launched."
}

Dependencies

  • Requires an active connection to a Dataiku DSS instance.
  • Needs valid API credentials (an API key) for authentication with the Dataiku DSS API.
  • The node expects the Dataiku DSS server URL and user API key to be configured in the credentials.
  • No other external dependencies are required.

Troubleshooting

  • Missing Credentials Error:
    If the node throws an error about missing credentials, ensure that the Dataiku DSS API credentials are properly set up in n8n.

  • Required Parameter Missing:
    The node validates required parameters such as Project Key, Analysis ID, ML Task ID, and Model Full ID. If any are missing, the node will throw an error specifying which parameter is required. Make sure all required fields are filled.

  • API Request Failures:
    Network issues, incorrect server URLs, or invalid API keys can cause request failures. Verify connectivity and credential correctness.

  • Unexpected Response Format:
    If the API returns unexpected data or errors, check the Dataiku DSS server logs and ensure the model and analysis IDs are correct and accessible.

Links and References

Discussion