IBM Data WH Decision Tree Nugget - Settings Tab

The Settings tab enables you to set some options for scoring the model.

Include input fields. If selected, this option passes all the original input fields downstream, appending the extra modeling field or fields to each row of data. If you clear this check box, only the Record ID field and the extra modeling fields are passed on, and so the stream runs more quickly.

Compute probabilities of assigned classes for scoring records. (Decision Tree and Naive Bayes only) If selected, this option means that the extra modeling fields include a confidence (that is, a probability) field as well as the prediction field. If you clear this check box, only the prediction field is produced.

Use deterministic input data. If selected, this option ensures that any Netezza algorithm that runs multiple passes of the same view will use the same set of data for each pass. If you clear this check box to show that non-deterministic data is being used a temporary table is created to hold the data output for processing, such as that produced by a partition node; this table is deleted after the model is created.