naive

Documentation

Index

• Variables
• type Classifier
  • func New(opts ...Option) *Classifier
  • func (c *Classifier) Classify(r io.Reader) (string, error)
  • func (c *Classifier) ClassifyString(doc string) (string, error)
  • func (c *Classifier) Probabilities(str string) (map[string]float64, string)
  • func (c *Classifier) Train(r io.Reader, category string) error
  • func (c *Classifier) TrainString(doc string, category string) error
• type Option
  • func Tokenizer(t classifier.Tokenizer) Option

Variables

var ErrNotClassified = errors.New("unable to classify document")

ErrNotClassified indicates that a document could not be classified

Types

type Classifier

type Classifier struct {
	// contains filtered or unexported fields
}

Classifier implements a naive bayes classifier

func New

func New(opts ...Option) *Classifier

New initializes a new naive Classifier using the standard tokenizer

func (*Classifier) Classify

func (c *Classifier) Classify(r io.Reader) (string, error)

Classify attempts to classify a document. If the document cannot be classified (eg. because the classifier has not been trained), an error is returned.

func (*Classifier) ClassifyString

func (c *Classifier) ClassifyString(doc string) (string, error)

ClassifyString provides convenience classification for strings

func (*Classifier) Probabilities

func (c *Classifier) Probabilities(str string) (map[string]float64, string)

Probabilities runs the provided string through the model and returns the potential probability for each classification

func (*Classifier) Train

func (c *Classifier) Train(r io.Reader, category string) error

Train provides supervisory training to the classifier

func (*Classifier) TrainString

func (c *Classifier) TrainString(doc string, category string) error

TrainString provides supervisory training to the classifier

type Option

type Option func(c *Classifier) error

Option provides a functional setting for the Classifier

func Tokenizer

func Tokenizer(t classifier.Tokenizer) Option

Tokenizer overrides the classifier's default Tokenizer