Epsilon Support Vector Regression

Support vector machine based regressor (SVR)

Documentation

Attributes

coef_

Weights assigned to the features (coefficients in the primal problem). This is only available in the case of a linear kernel.

coef_ is readonly property derived from dual_coef_ and support_vectors_.

dual_coef_

Coefficients of the support vector in the decision function.

intercept_

Constants in decision function.

support_

Number of support vectors for each class.

support_vectors_

Support vectors.

Definition

Output ports

model model

Model

Configuration

Penalty (C)

Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. The penalty is a squared l2 penalty.

Independent term in kernel function (coef0)

Independent term in kernel function. It is only significant in ‘poly’ and ‘sigmoid’.

Polynomial Degree (degree)

Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels.

Epsilon (epsilon)

Epsilon in the epsilon-SVR model. It specifies the epsilon-tube within which no penalty is associated in the training loss function with points predicted within a distance epsilon from the actual value.

Gamma (gamma)

Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.

• if gamma='scale' (default) is passed then it uses 1 / (n_features * X.var()) as value of gamma,

• if ‘auto’, uses 1 / n_features.

Changed in version 0.22: The default value of gamma changed from ‘auto’ to ‘scale’.

Kernel (kernel)

Specifies the kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used. If a callable is given it is used to precompute the kernel matrix.

Maximum iterations (max_iter)

Hard limit on iterations within solver, or -1 for no limit.

Shrinking (shrinking)

Whether to use the shrinking heuristic. See the User Guide <shrinking_svm>.

Tolerance (tol)

Tolerance for stopping criterion.

Implementation

class node_regression.SupportVectorRegression