Naive Bayes classifier in ML Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main assumption behind the Naive Bayes classifier?

Naive Bayes assumes that all features are independent of each other given the class label. This means it treats each feature as if it does not affect or depend on any other feature.

beginner

How does Naive Bayes use Bayes' theorem for classification?

Naive Bayes calculates the probability of each class given the input features using Bayes' theorem, then predicts the class with the highest probability.

intermediate

What are the common types of Naive Bayes classifiers?

The common types are Gaussian Naive Bayes (for continuous data), Multinomial Naive Bayes (for count data like word counts), and Bernoulli Naive Bayes (for binary features).

beginner

Why is Naive Bayes called 'naive'?

Because it makes a 'naive' assumption that all features are independent, which is often not true in real life, but this simplification makes the model simple and fast.

intermediate

What is Laplace smoothing and why is it used in Naive Bayes?

Laplace smoothing adds a small value to feature counts to avoid zero probabilities, which can happen if a feature never appears in training data for a class.

What does Naive Bayes assume about the features?

A Features are independent given the class

B Features are dependent on each other

C Features have no effect on the class

D Features are always continuous

Which type of Naive Bayes is best for text classification with word counts?

A Multinomial Naive Bayes

B Gaussian Naive Bayes

C Bernoulli Naive Bayes

D K-Nearest Neighbors

What problem does Laplace smoothing solve in Naive Bayes?

A Feature scaling

B Overfitting

C Slow training

D Zero probability for unseen features

Which formula does Naive Bayes use to calculate class probabilities?

A P(class|features) = P(class) * P(features)

B P(class|features) = P(class) + P(features)

C P(class|features) = P(features|class) * P(class) / P(features)

D P(class|features) = P(features) / P(class)

Why is Naive Bayes often fast to train?

A Because it uses deep neural networks

B Because it assumes feature independence simplifying calculations

C Because it uses complex feature interactions

D Because it requires no training data

Explain how Naive Bayes classifier works in simple terms.

Describe the role and importance of Laplace smoothing in Naive Bayes.