Naive Bayes

Back to Index

---

Objective

Learn Naive Bayes

Essentials Reading

Understanding Classifications

Read the basics of classifications

Basics of Naive Bayes

• Naive Bayes explained - video
• Another Naive Bayes explanation - video
• Naive Bayes intro

Implementing Naive Bayes in Scikit-Learn

• Naive Bayes Classification using Scikit-learn
• Naive Bayes algorithm in Scikit

Extra Reading

Checklist

Check your knowledge:

• What data NB works best with?
• What are the 3 types of NB?

• Calculate the probability of Queen card, given I got a face card from a 52 deck of cards - P (queen

  face)

  • First calculate the probability of getting a face card
  • calculate the probability of getting a queen card

  • Now calculate the P(queen

    face)

Exercises

Difficulty Level

★☆☆ - Easy
★★☆ - Medium
★★★ - Challenging
★★★★ - Bonus

EX-1: Practice with synthetic data

Use Scikit’s make_blobs or make_classification to generate some sample data.

Try to separate them using NB

EX-2: SPAM detection

• Here is SMS Spam dataset
• Start with this notebook
• Use NB to predict spam / ham
• Create a confusion matrix
• What is the accuracy of the model

EX-3 - BONUS Lab

• Choose another text or categorical data from data section
• And solve it with naive bayes

More Exercises

---

Index