Probabilistic Model Reference Data
The reference data values in a probabilistic model represent the types of input data that a Labeler transformation or Parser transformation might read in a mapping.
You can add, edit, and delete reference data rows in the Developer tool. You can paste reference data from the clipboard. You can also use mapping source data as a source for the reference data values in a probabilistic model.
After you add the data values, create the label columns and assign a label to each data value in each row of the model.
Note: The label values in the model indicate the possible structure of the input rows that the transformation reads. Verify that the probabilistic model contains the label structure that you expect the transformation to find in the source data.
Adding a Reference Data String to a Probabilistic Model
You can use the keyboard to add a reference data string to a row in a probabilistic model.
1. Open the content set that contains the model.
Select the model name and click Edit.
2. Select the Data view.
3. Click New to add an empty row to the model.
4. Enter a data string in the empty row.
5. Assign a label to each value in the string.
6. Save the probabilistic model.
After you save the model, optionally compile the model.