MultinomialNB

#include <Skigen/NaiveBayes>

template <typename Scalar = double>
class Skigen::MultinomialNB(alpha=1, force_alpha=true, fit_prior=true, class_prior=VectorType())

Naive Bayes classifier for multinomial models.

The multinomial distribution normally requires integer feature counts (e.g. word counts for text classification). However in practice fractional counts (e.g. tf-idf) may also work.

Mirrors sklearn.naive_bayes.MultinomialNB.

---

---

Attributes:

• class_count : VectorType

• class_log_prior : VectorType

• classes : const Eigen::VectorXi

• feature_count : MatrixType

• feature_log_prob : MatrixType

---

Methods

SKIGEN_PARAMS()

---

predict(X)

---

predict_proba(X)

---

predict_log_proba(X)

---

partial_fit(X, y, classes)

---