The HPSVM Procedure
The PARTITION statement specifies how observations in the input data set are logically partitioned into disjoint subsets for model training, validation, and testing. Either you can designate a variable in the input data set and a set of formatted values of that variable to determine the role of each observation, or you can specify proportions to use for random assignment of observations for each role.
You can specify the following mutually exclusive partition-options:
-
FRACTION(<VALIDATE=fraction> <TEST=fraction> <SEED=number>)
-
requests that specified proportions of the observations in the input data set be randomly assigned to training, validation, and testing roles.
You can specify the following suboptions:
-
VALIDATE=fraction
specifies the proportion for validation. The value of fraction must be nonnegative and less than 1.
-
TEST=fraction
specifies the proportion for testing. The value of fraction must be nonnegative and less than 1. If you specify both the VALIDATE= and TEST= options, then the sum of the specified fractions must be less than 1, and the remaining fraction of the observations are assigned to the training role.
-
SEED=number
specifies an integer that is used to start the pseudorandom number generator for random partitioning of data for training, validation and testing.
-
ROLEVAR=variable ( <TRAIN='value'> <VALIDATE='value'> <TEST='value'> )
-
names the variable in the input data set whose values are used to assign roles to each observation.
You can specify following suboptions:
-
TRAIN=value
requests that an observation be assigned to training if it matches value.
-
VALIDATE=value
requests that an observation be assigned to validation if it matches value.
-
TEST=value
requests that an observation be assigned to testing if it matches value.
If you do not specify the TRAIN= suboption, then any observation whose role is not determined by the VALIDATE= suboption and the TEST= suboption is assigned to the training role.
Last updated: May 25, 2022