| DataLab is a compact statistics package aiming at exploratory data analysis. Please visit the DataLab Web site for more information.... |
Home  Programming DataLab DLabPascal Multivariate Methods Memory Based Learner TMemBasedLearner |
||||||
See also: Create a kNN Model
 |
||||||
  |
||||||
TMemBasedLearnerThe class TMemBasedLearner encapsulates the well-known kNN (k-nearest neighbor) classification strategy, also known as "memory based learner". In order to establish a classifier you first have to load the data and specify the variable types. Further, you have to specify the scaling mode, the distance metrics, the local model and the number of nearest neighbors. In order to apply a classifier you call the method ApplyModel. Performance measures of the classifier can be obtained by the methods CalcContingencyTable and CalcNNOfModelData. The classifier can be stored and loaded by the methods StoreModelBin, StoreModelXML, LoadModelBin and LoadModelXML. The classifier can be controlled and applied by using the following properties and methods:
|
||||||