Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type BaggedModel ¶
type BaggedModel struct {
base.BaseClassifier
Models []base.Classifier
RandomFeatures int
// contains filtered or unexported fields
}
BaggedModel trains base.Classifiers on subsets of the original Instances and combine the results through voting
func (*BaggedModel) AddModel ¶
func (b *BaggedModel) AddModel(m base.Classifier)
AddModel adds a base.Classifier to the current model
func (*BaggedModel) Fit ¶
func (b *BaggedModel) Fit(from base.FixedDataGrid)
Fit generates and trains each model on a randomised subset of Instances.
func (*BaggedModel) Predict ¶
func (b *BaggedModel) Predict(from base.FixedDataGrid) base.FixedDataGrid
Predict gathers predictions from all the classifiers and outputs the most common (majority) class
IMPORTANT: in the event of a tie, the first class which achieved the tie value is output.
func (*BaggedModel) String ¶
func (b *BaggedModel) String() string
String returns a human-readable representation of the BaggedModel and everything it contains
type OneVsAllModel ¶
type OneVsAllModel struct {
NewClassifierFunction func(string) base.Classifier
// contains filtered or unexported fields
}
OneVsAllModel replaces class Attributes with numeric versions and trains n wrapped classifiers. The actual class is chosen by whichever is most confident. Only one CategoricalAttribute class variable is supported.
func NewOneVsAllModel ¶
func NewOneVsAllModel(f func(string) base.Classifier) *OneVsAllModel
NewOneVsAllModel creates a new OneVsAllModel. The argument must be a function which returns a base.Classifier ready for training.
func (*OneVsAllModel) Fit ¶
func (m *OneVsAllModel) Fit(using base.FixedDataGrid)
Fit creates n filtered datasets (where n is the number of values a CategoricalAttribute can take) and uses them to train the underlying classifiers.
func (*OneVsAllModel) Predict ¶
func (m *OneVsAllModel) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error)
Predict issues predictions. Each class-specific classifier is expected to output a value between 0 (indicating that a given instance is not a given class) and 1 (indicating that the given instance is definitely that class). For each instance, the class with the highest value is chosen. The result is undefined if several underlying models output the same value.
Source Files