Articles → MACHINE LEARNING → One-Hot Encoding And Label Encoding In Machine Learning

One-Hot Encoding And Label Encoding In Machine Learning

This article describes one-hot encoding and label encoding in Machine Learning.

One-Hot Encoding

The one-hot encoding is a technique in machine learning used to convert categorical (non-numeric) data into a numerical format that algorithms can process.

Example

Consider a categorical feature Color with three categories.

Red
Green
Blue

After hot-encoding, it becomes: -

Color	Red	Green	Blue
Red	1	0	0
Green	0	1	0
Blue	0	0	1

Label Encoding

Like one-hot encoding, the label encoding also converts categorical data to a numerical format. But there are some differences.

Difference

One-Hot Encoding	Label Encoding
Creates a binary column for each category.	Sequential numbers are assigned to each category.
As each category is assigned either 0 or 1. So, the unique number is not assigned.	A unique number is assigned to each category.
The encoding is used when categories are independent of each other, like Red, Green, Blue, etc.	Creates a false sense of order among the categories like Low < Medium < High.

Posted By -	Karan Gupta

Posted On -	Tuesday, October 28, 2025

Query/Feedback

Your Email Id		**

Subject		*

Query/Feedback	Characters remaining 250	**