Examples of Formulas in Data Manager
The following are examples of how formulas can be used in Data Manager.
The examples are all based on the Adult dataset.
In the first example, a new attribute newatt has been defined as the ratio between education-num and age multiplied by 100.
Note that the type of the newatt attribute has been automatically changed from nominal to continuous to fit the formula result.
In this second example, newatt is defined as the string concatenation of workclass and marital-status separated by the constant string “_”.
In both these example a new variable has been created.
However, it is also possible to define an already existing attribute by using a formula, as will be illustrated in the examples below.
In the third example, workclass is re-defined as workclass itself, minus the constant string “S”.
The operation a−b, where a and b are strings removes the first occurrence of b from a.
In the last example, education-num is re-defined as education-num divided by the maximum of the same variable.