Linear Discriminant Analysis (deprecated)

Linear Discriminant Analysis (LDA) is similar to PCA but tries to take class information into account to achieve a dimensionality reduction while keeping the class separation high. The result may be used in a subsequent classification. The method tries to maximize the ratio of between-class and within-class scatter in order to achieve a projection where data points of a class are close to each other and far from data points of other classes. More information can be found on Wikipedia .

Input ports

1. Type: Table
   Input data
   The data to reduce the dimensions of

Output ports

1. Type: Table
   Reduced data
   The original data plus columns for the reduced dimensions
2. Type: PCA
   Model
   The transformation matrix. Can be used with PCA apply.