SMO_C KEEL Classification Algorithm

Description

SMO_C Classification Algorithm from KEEL.

Usage

1
2
3
4
5
6
7
8
SMO_C(train, test, C, toleranceParameter, epsilon,
   RBFKernel_gamma, normalized_PolyKernel_exponent,
   normalized_PolyKernel_useLowerOrder, PukKernel_omega,
   PukKernel_sigma, StringKernel_lambda,
   StringKernel_subsequenceLength,
   StringKernel_maxSubsequenceLength, StringKernel_normalize,
   StringKernel_pruning, KernelType, FitLogisticModels,
   ConvertNominalAttributesToBinary, PreprocessType, seed)

Arguments

train

Train dataset as a data.frame object

test

Test dataset as a data.frame object

C

C. Default value = 1.0

toleranceParameter

toleranceParameter. Default value = 0.001

epsilon

epsilon. Default value = 1.0e-12

RBFKernel_gamma

RBFKernel_gamma. Default value = 0.01

normalized_PolyKernel_exponent

normalized_PolyKernel_exponent. Default value = 1

normalized_PolyKernel_useLowerOrder

normalized_PolyKernel_useLowerOrder. Default value = FALSE

PukKernel_omega

PukKernel_omega. Default value = 1.0

PukKernel_sigma

PukKernel_sigma. Default value = 1.0

StringKernel_lambda

StringKernel_lambda. Default value = 0.5

StringKernel_subsequenceLength

StringKernel_subsequenceLength. Default value = 3

StringKernel_maxSubsequenceLength

StringKernel_maxSubsequenceLength. Default value = 9

StringKernel_normalize

StringKernel_normalize. Default value = FALSE

StringKernel_pruning

StringKernel_pruning. Default value = "None"

KernelType

KernelType. Default value = "PolyKernel"

FitLogisticModels

FitLogisticModels. Default value = FALSE

ConvertNominalAttributesToBinary

ConvertNominalAttributesToBinary. Default value = TRUE

PreprocessType

PreprocessType. Default value = "Normalize"

seed

Seed for random numbers. If it is not assigned a value, the seed will be a random number

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::SMO_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.