- InputTable
- Specifies the name of the table that contains the prediction-actual pairs for a binary classifier.
- ModelIdColumn
- [Optional] Specifies the name of the input table column that contains the model or partition identifiers for the ROC curves.
- ProbabilityColumn
- Specifies the name of the input table column that contains the predictions.
- ObsColumn
- Specifies the name of the input table column that contains the actual classes.
- OutputTable
- Specifies the name for the output table that the function creates. The output_table must not already exist.
- PositiveClass
- Specifies the label of the positive class.
- NumThreshold
- [Optional] Specifies the number of thresholds for the function to use. The num_threshold must be a NUMERIC value in the range [1, 10000]. Default: 50. The function uniformly distributes the thresholds between 0 and 1.
- ROC
- [Optional] Specifies whether the function displays ROC values (thresholds, false positive rates, and true positive rates). Default: 'true'. See the note after the table.
- AUC
- [Optional] Specifies whether the function displays the AUC calculated from the ROC. Default: 'false'. See the note after the table.
- Gini
- [Optional] Specifies whether the function displays the Gini coefficient calculated from the ROC. Default: 'false'. See the note after the table.
The valid combinations of ROC, AUC, and Gini values are those that specify one of the following:
- ROC only
- AUC only
- Gini only
- AUC and Gini
When specifying AUC only, Gini only, or AUC and Gini only, you do not need to specify ROC ('false'), but you must not specify ROC ('true').
If you specify an invalid combination (such as ROC ('true') and AUC ('true'), or all three 'false'), the function issues an error message.