The TREESPLIT Procedure

INPUT and TARGET Statement Syntax

In addition to the syntax that is described in the CLASS and MODEL statement sections, PROC TREESPLIT supports INPUT/TARGET syntax that you might be familiar with from other procedures. The INPUT/TARGET syntax cannot be used together with the CLASS/MODEL syntax.

This syntax requires one TARGET statement and one or more INPUT statements. If you use this syntax, then the PROC TREESPLIT statement, the TARGET statement, and the INPUT statement are required. Depending on the options in those statements, specified variables can be interval or nominal. By default, numeric INPUT variables are treated as interval (or continuous) predictors, and character INPUT variables are treated as nominal (or categorical) predictors.

INPUT variables </ option>;
TARGET variable </ option>;

INPUT Statement

INPUT variables </ option>;

The INPUT statement specifies predictor variables for the decision tree or regression tree. The value of variable can be a range such as "var_1–var_1000" or the special "_ALL_" value to include all variables in the data tables. As with CLASS variables, all nominal INPUT variables are padded or truncated to 32 characters.

You cannot use an INPUT statement with a MODEL or CLASS statement.

You can specify the following option:

LEVEL=INTERVAL |NOMINAL

specifies whether the specified predictor variables are interval or nominal. You can specify the following values:

INTERVAL: treats all numeric variables as interval predictors.
NOMINAL: treats all variables as nominal predictors.

By default, numeric variables are treated as interval predictors, and character variables are treated as nominal predictors. Specifying LEVEL=NOMINAL forces all variables in that statement to be treated as nominal. You cannot specify LEVEL=INTERVAL for character variables.

TARGET Statement

TARGET variable </ options>;

The TARGET statement names the variable whose values PROC TREESPLIT predicts. Missing values in the target are ignored except during scoring.

You cannot use a TARGET statement with a MODEL or CLASS statement.

You can specify the following option:

LEVEL=INTERVAL | NOMINAL

specifies whether the specified response variable is interval or nominal. You can specify the following values:

INTERVAL: treats the response as an interval variable and creates a regression tree.
NOMINAL: treats the response as a nominal variable and creates a decision tree.

By default, LEVEL=INTERVAL for numeric variables and LEVEL=NOMINAL for categorical variables.

Last updated: December 21, 2018