Articles → MACHINE LEARNING → Gini Index In Machine Learning

Gini Index In Machine Learning

This article describes the Gini Index in machine learning.

Purpose

The Gini Index quantifies the heterogeneity (impurity) within a dataset. Heterogeneous data refers to a dataset composed of various data types, structures, and formats.

Example Dataset

ID	Outlook	Temperature	Humidity	Windy	Play Tennis
1	Sunny	Hot	High	False	No
2	Sunny	Hot	High	True	No
3	Overcast	Hot	High	False	Yes
4	Rain	Mild	High	False	Yes
5	Rain	Cool	Normal	False	Yes
6	Rain	Cool	Normal	True	No
7	Overcast	Cool	Normal	True	Yes
8	Sunny	Mild	High	False	No

In the above dataset, Outlook, Temperature, Humidity, and Windy are independent variables. Play Tennis is a dependent variable.

Purpose Of Calculating The Parent Gini Index

The parent Gini serves as a baseline measure of impurity of the complete dataset.

Formula

The formula for calculating the Gini index is: -

Parameter	Description
D	The dataset of the node.
C	The number of distinct values in the dependent variable.
Pi	The number of instances (rows) of a particular class value in the target (dependent) variable.

The formula for calculating Pi is: -

Picture showing the formula of calculating Pi

How To Calculate Parent Gini Index?

In the above dataset, there are 5 No and 3 Yes.

Weighted Gini (Humidity)

The possible values are High and Normal. For High, 3 No, and 2 Yes.

For Normal, 2 Yes, and 1 No.

Weighted Gini for Humidity.

Pure And Impure Nodes

A pure node in a decision tree contains data samples all belonging to the same class. An impure node contains samples from multiple classes.

Posted By -	Karan Gupta

Posted On -	Tuesday, June 17, 2025

Updated On -	Monday, August 18, 2025

Query/Feedback

Your Email Id		**

Subject		*

Query/Feedback	Characters remaining 250	**