Community & Support
Learn
Marketplace
Discussions
Categories
Discussions
General
Platform
Academic
Partner
Regional
User Groups
Documentation
Events
Altair Exchange
Share or Download Projects
Resources
News & Instructions
Programs
YouTube
Employee Resources
This tab can be seen by employees only. Please do not share these resources externally.
Groups
Join a User Group
Support
Altair RISE
A program to recognize and reward our most engaged community members
Nominate Yourself Now!
Home
Discussions
Community Q&A
how to do
JoeJoe
I notice that AUTO CLEANSING has 2 options: PCA and norm
Find more posts tagged with
AI Studio
Accepted answers
varunm1
Hello
@JoeJoe
Yes, you will have two options, it is your choice to perform none of these or any one of these or both. PCA is used for dimensionality reduction, in case you have many attributes (features/columns) and you want to reduce the total features for low complexity or better run times of algorithm then PCA is a useful method. PCA will create new features (Principal components) from existing features, one issue with using PCA is to understand what these features (Principal components) represent in the real world.
The second option normalization is useful in case of features (attributes/columns) with highly varying ranges. For example, you have an age column with 1 to 100 years and income column in 10000 to 100000 then normalization is suggested as the numeric ranges in columns are highly varying and these variations will have an impact on the algorithm.
Hope this helps
All comments
varunm1
Hello
@JoeJoe
Yes, you will have two options, it is your choice to perform none of these or any one of these or both. PCA is used for dimensionality reduction, in case you have many attributes (features/columns) and you want to reduce the total features for low complexity or better run times of algorithm then PCA is a useful method. PCA will create new features (Principal components) from existing features, one issue with using PCA is to understand what these features (Principal components) represent in the real world.
The second option normalization is useful in case of features (attributes/columns) with highly varying ranges. For example, you have an age column with 1 to 100 years and income column in 10000 to 100000 then normalization is suggested as the numeric ranges in columns are highly varying and these variations will have an impact on the algorithm.
Hope this helps
Quick Links
All Categories
Recent Discussions
Activity
Unanswered
日本語 (Japanese)
한국어(Korean)
Groups
