The implementations for SVM classification offered by scikit-learn are shown here:
|
Class |
Purpose |
Hyperparameters |
|
sklearn.svm.SVC |
The LIBSVM implementation for binary and multiclass linear and kernel classification |
C, kernel, degree, and gamma |
|
sklearn.svm.NuSVC |
Same as for the .SVC version |
nu, kernel, degree, and gamma |
|
sklearn.svm.OneClassSVM |
Unsupervised detection of outliers |
nu, kernel, degree, and gamma |
|
sklearn.svm.LinearSVC |
Based on LIBLINEAR; it is a binary and multiclass linear classifier |
Penalty, loss, and C |
As an example for classification using SVM, we will use SVC with both a linear and an RBF kernel (RBF stands for Radial Basis Function, which is an effective nonlinear ...
