Implementation:Scikit learn Scikit learn GaussianNB

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Classification, Probabilistic Models
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete implementations of Naive Bayes classifiers provided by scikit-learn.

Description

The naive_bayes module provides supervised learning algorithms based on Bayes' theorem with strong (naive) feature independence assumptions. It includes GaussianNB (for continuous features), MultinomialNB (for count data), BernoulliNB (for binary features), ComplementNB (for imbalanced datasets), and CategoricalNB (for categorically distributed features). All support incremental learning via partial_fit.

Usage

Use Naive Bayes classifiers when you need fast, probabilistic classification, particularly for text classification, spam filtering, or as a baseline classifier. They are especially effective with high-dimensional data and small training sets.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/naive_bayes.py

Signature

class _BaseNB(ClassifierMixin, BaseEstimator, metaclass=ABCMeta):
    ...

class GaussianNB(_BaseNB):
    def __init__(self, *, priors=None, var_smoothing=1e-09):
        ...

class MultinomialNB(_BaseNB):
    def __init__(self, *, alpha=1.0, fit_prior=True, class_prior=None, force_alpha="warn"):
        ...

class BernoulliNB(_BaseNB):
    def __init__(self, *, alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None):
        ...

class ComplementNB(_BaseNB):
    def __init__(self, *, alpha=1.0, fit_prior=True, class_prior=None, norm=False):
        ...

class CategoricalNB(_BaseNB):
    def __init__(self, *, alpha=1.0, fit_prior=True, class_prior=None, min_categories=None):
        ...

Import

from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB

I/O Contract

Inputs

Name	Type	Required	Description
X	array-like of shape (n_samples, n_features)	Yes	Training input samples
y	array-like of shape (n_samples,)	Yes	Target class labels
priors	array-like of shape (n_classes,)	No	Prior probabilities of the classes
var_smoothing	float	No	Portion of largest variance added to variances for stability (GaussianNB)
alpha	float	No	Additive (Laplace/Lidstone) smoothing parameter

Outputs

Name	Type	Description
predictions	ndarray of shape (n_samples,)	Predicted class labels
probabilities	ndarray of shape (n_samples, n_classes)	Class probability estimates
class_prior_	ndarray of shape (n_classes,)	Learned class prior probabilities

Usage Examples

Basic Usage

from sklearn.naive_bayes import GaussianNB
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)
clf = GaussianNB()
clf.fit(X, y)
predictions = clf.predict(X)
probabilities = clf.predict_proba(X)
print(f"Accuracy: {(predictions == y).mean():.3f}")

Related Pages

• Principle:Scikit_learn_Scikit_learn_Naive_Bayes_Classification