gemseo.mlearning.classification.algos.svm module#

The Support Vector Machine algorithm for classification.

This module implements the SVMClassifier class. A support vector machine (SVM) passes the data through a kernel in order to increase its dimension and thereby make the classes linearly separable.

Dependence#

The classifier relies on the SVC class of the scikit-learn library.

class SVMClassifier(data, settings_model=None, **settings)[source]#

Bases: BaseClassifier

The Support Vector Machine algorithm for classification.

Parameters:
  • data (Dataset) -- The training dataset.

  • settings_model (BaseMLAlgoSettings | None) -- The machine learning algorithm settings as a Pydantic model. If None, use **settings.

  • **settings (Any) -- The machine learning algorithm settings. These arguments are ignored when settings_model is not None.

Raises:

ValueError -- When both the variable and the group it belongs to have a transformer.

Settings#

alias of SVMClassifier_Settings

LIBRARY: ClassVar[str] = 'scikit-learn'#

The name of the library of the wrapped machine learning algorithm.

SHORT_ALGO_NAME: ClassVar[str] = 'SVM'#

The short name of the machine learning algorithm, often an acronym.

Typically used for composite names, e.g. f"{algo.SHORT_ALGO_NAME}_{dataset.name}" or f"{algo.SHORT_ALGO_NAME}_{discipline.name}".