Probabilistic Models > Creating a Probabilistic Model from a Data Object
  

Creating a Probabilistic Model from a Data Object

You can use a data object as a source for probabilistic model data. For example, use the source data object from the mapping that will read the probabilistic model. You can also profile an object in the mapping and create a data object from the profile results.
A probabilistic model performs optimally when you use the input data from the Labeler or Parser transformation as the source for the model reference data. For example, you can run a profile on the transformation object in the mapping. Create a data object from the profile results.
    1. In Object Explorer, open or create a content set.
    2. Select the Content view.
    3. Select Probabilistic Models, and click Add.
    The Probabilistic Model wizard opens.
    4. Select the Probabilistic Model from Data Objectsoption.
    Click Next.
    5. Enter a name for the probabilistic model.
    Optionally, enter a text description of the model.
    6. Browse the Model repository and select the data object that contains the reference data.
    Click Next.
    7. Review the data columns on the data object, and select a column to add as reference data values or label values for the model.
    Click Next.
    8. Select the number of rows to copy from the data source.
    Select all rows, or enter the number of rows to copy. If you enter a number, the model counts the rows from the start of the data set.
    9. Set the delimiters to use for the reference data values. Specify a delimiter to identify multiple values that represent a single piece of information.
    The default delimiter is a character space.
    10. Enter a name for the overflow column.
    The overflow column contain a any token that the labeling or parsing operation cannot recognize.
    The default name is O.
    11. Click Finish and save the model.
    The probabilistic model opens in the Developer tool.
After you create the probabilistic model, compile the model.