Modeling Guide

Apply PA Automated

This graph runs the PA Automated Aanalytics application on streaming string input data, using a model trained on the Census data set as example. It contains a dataGenerator that mocks census input data, an Automated Analytics Execution operator, a JavaScript operator to throttle the stream for demonstration purposes, and a terminal operator to display the prediction results.

Configure and Run the Graph

Follow the steps below to run the example graph:
  1. Click on the Automated Analytics component.
  2. In the configuration panel, set the modelPath to the path to your kxen model data generated by PA Automated Analytics. NOTE: This path is relative to the blobs/ directory in the Vora VFlow repository.
  3. Then set modelName to a model that you want to select.

    You can optionally set a schema description file if the data that is streamed does not match the data representation of the trained model.

  4. In the tool bar, select Save Graph (disk button) and then Run Graph (play button).
  5. The Status panel indicates if the graph is running.
  6. The graph runs and terminates itself on success.