Running Datasets Against Saved Models

How to:

After you train and save a predictive model, you can load it and run other datasets against it, in order to learn more about your data.

The following model that was previously trained and saved, predicts Heating Load, as shown in the following image.

In the procedure below, a similar dataset that does not include a Heating Load column will be run against this predictive model, so the new target model will predict Heating Load.

For more information about training and saving models, see Running Predictive Analytics On Your Data.

Procedure: How to Run Datasets Against Saved Models

  1. From the WebFOCUS Hub, click the plus menu, and then click Create Data Flow.

    The TIBCO WebFOCUS Reporting Server browser interface opens.

  2. Choose a dataset from an application and drag it onto the canvas, as shown in the following image.

    You can double-click the dataset to display sample data.

    Note: The data sample does not include a Heating Load column.

  3. From the left panel, click Run Models.

    The Run Models directory opens and shows only models that are applicable to your data set.

  4. Double-click a model that you want to run your dataset against.

    A new function is defined based on this model, and a function icon is added to the end of the canvas workflow, as shown in the following image.

    To view and edit the function, click the function icon and select Edit. The function name, properties, and parameters display, as shown in the following image.

  5. To run your dataset, click Target from the left panel and then select New Target.

    A new target model is added to the data flow, as shown in the following image.

    You can double-click the target model to display sample data.

    Note: The sample data includes a Heating Load Predicted column.

  6. From the WebFOCUS toolbar menu, select Save As to save your target model.