Categories &

Functions List

Class Definition: CompactClassificationGAM

statistics: CompactClassificationGAM

A CompactClassificationGAM object is a compact version of a Generalized Additive Model, ClassificationGAM.

The CompactClassificationGAM does not include the training data resulting to a smaller classifier size, which can be used for making predictions from new data, but not for tasks such as cross validation. It can only be created from a ClassificationGAM model by using the compact object method.

The available methods for a CompactClassificationGAM object are:

  • predict
  • savemodel

See also: fitcgam, compact, ClassificationGAM

Source Code: CompactClassificationGAM

Properties

CompactClassificationGAM.NumPredictors is not documented.
CompactClassificationGAM.PredictorNames is not documented.
CompactClassificationGAM.ResponseName is not documented.
CompactClassificationGAM.ClassNames is not documented.
CompactClassificationGAM.Prior is not documented.
CompactClassificationGAM.Cost is not documented.
CompactClassificationGAM.ScoreTransform is not documented.
CompactClassificationGAM.Formula is not documented.
CompactClassificationGAM.Interactions is not documented.
CompactClassificationGAM.Knots is not documented.
CompactClassificationGAM.Order is not documented.
CompactClassificationGAM.DoF is not documented.
CompactClassificationGAM.LearningRate is not documented.
CompactClassificationGAM.NumIterations is not documented.
CompactClassificationGAM.BaseModel is not documented.
CompactClassificationGAM.ModelwInt is not documented.
CompactClassificationGAM.IntMatrix is not documented.

Methods

CompactClassificationGAM: label = predict (obj, XC)
CompactClassificationGAM: label = predict (…, 'IncludeInteractions', includeInteractions)
CompactClassificationGAM: [label, score] = predict (…)

label = predict (obj, XC) returns the predicted labels for the data in XC based on the model stored in the CompactClassificationGAM object, obj.

label = predict (obj, XC, 'IncludeInteractions', includeInteractions) allows you to specify whether interaction terms should be included when making predictions.

[label, score] = predict (…) also returns score, which contains the predicted class scores or posterior probabilities for each observation.

  • obj must be a CompactClassificationGAM class object.
  • XC must be an M×P numeric matrix where each row is an observation and each column corresponds to a predictor variable.
  • includeInteractions is a ’true’ or ’false’ indicating whether to include interaction terms in the predictions.

See also: CompactClassificationGAM, fitcgam

ClassificationGAM: savemodel (obj, filename)

savemodel (obj, filename) saves each property of a CompactClassificationGAM object into an Octave binary file, the name of which is specified in filename, along with an extra variable, which defines the type classification object these variables constitute. Use loadmodel in order to load a classification object into Octave’s workspace.

See also: loadmodel, fitcgam, ClassificationGAM, cvpartition, ClassificationPartitionedModel

Examples

  
 # and compare their size

 load fisheriris
 X = meas;
 Y = species;

 Mdl = fitcdiscr (X, Y, 'ClassNames', unique (species))
 CMdl = crossval (Mdl)
  
Mdl =

  ClassificationDiscriminant

             ResponseName: 'Y'
               ClassNames: {'setosa' 'versicolor' 'virginica'}
           ScoreTransform: 'none'
          NumObservations: 150
            NumPredictors: 4
              DiscrimType: 'linear'
                       Mu: [3x4 double]
                   Coeffs: [4x4 struct]

CMdl =

  ClassificationPartitionedModel object with properties:

                   BinEdges: []
      CategoricalPredictors: []
                          X: [5.1000, 3.5000, 1.4000, 0.2000; 4.9000, 3, 1.4000, 0.2000; 4.7000, 3.2000, ...]
                          Y: [150x1 cell]
                 ClassNames: [3x1 cell]
                       Cost: [0, 1, 1; 1, 0, 1; 1, 1, 0]
        CrossValidatedModel: 'ClassificationDiscriminant'
                      KFold: 10
            ModelParameters: [1x1 struct]
            NumObservations: 150
                  Partition: [1x1 cvpartition]
             PredictorNames: [1x4 cell]
                      Prior: [0.3333; 0.3333; 0.3333]
               ResponseName: 'Y'
             ScoreTransform: 'none'
                Standardize: []
                    Trained: [10x1 cell]