Builds Fisher's Linear Discriminant function. The threshold is selected so that the separator is half-way between centroids. The class must be binary and all other attributes must be numeric. Missing values are not permitted. Constant attributes are removed using RemoveUseless. No standardization or normalization of attributes is performed.
This classifier can be found in the discriminantAnalysis package.
The table below describes the options available for FLDA.
The preferred number of instances to process if batch prediction is being performed. More or fewer instances may be provided, but this gives implementations a chance to specify a preferred batch size.
If set to true, classifier may output additional info to the console.
If set, classifier capabilities are not checked before classifier is built (Use with caution to reduce runtime).
The number of decimal places to be used for the output of numbers in the model.
The value of the ridge parameter.
The table below describes the capabilities of FLDA.
Binary class, Missing class values
Min # of instances