Set Cutpoints
This section of the Make Validation Column report enables you to specify how cutpoints are determined. It appears only when a cutpoint column is specified in the launch window. The cutpoints are determined by one of the following four methods:
Proportions
Determines the cutpoints based on the proportions of rows specified for each set. In the boxes next to Training Set, Validation Set, and Test Set, enter values that represent the proportions that you would like to include in each of these sets. Depending on the number of rows and the proportions, the actual sizes of the resulting sets might vary slightly from the sizes that you specified.
Numbers of Rows
Determines the cutpoints based on the number of rows specified for each set. In the boxes next to Training Set, Validation Set, and Test Set, enter values that represent the number of rows that you would like to include in each of these sets. This option enables you to specify the sets exactly.
Assign Extra Rows
When the levels of the Cutpoint Batch ID variable contain unequal numbers of rows, the boxes to specify the number of rows in each set are based on the level of the Cutpoint Batch ID variable that contains the minimum number of rows. Therefore, after specifying the number of rows for each set, some levels of the Cutpoint Batch ID variable will have extra rows not allocated to a specific set. This option specifies if these extra rows should be assigned to the training, validation, or test set.
Fixed Time or Date
(Not available if a Cutpoint Batch ID is specified in the launch window.) Determines the cutpoints based on fixed data points in the specified cutpoint column. If you select this option, the minimum and maximum values for the cutpoint column are shown for reference. In the boxes next to Training Set, Validation Set, and Test Set, enter the value that represents the minimum value that you would like to include in each of these sets.
Elapsed Time
Determines the cutpoints based on the amount of time that has elapsed since the first timestamp in the cutpoint column. If you select this option, the total elapsed time from the first value to the last value is shown for reference. In the boxes next to Training Set, Validation Set, and Test Set, enter the values that represent the amounts of elapsed time that you would like to include in each of these sets.