image thumbnail


version 1.0.0 (1.15 KB) by Anan Yaghmour
Refit any data sat that contains categorical features into a complete numerical data set through appropriate mapping


Updated 06 Sep 2019

View License

Suppose you have a data set of this form :

1st column entries: 1,2,3,55,6......
2nd column entries: "good","bad","fair"......

You want to use it to train a mathematical model that needs the data to be in numerical form, to do so follow the following:
1- Import the data as a STRING array.
2- Call FitDataSet and your imported dataset (as a string array) as its argument.

The output array would be as follow:
1st column:won't be changed since it's numerical.
2nd column:( let's say we have four different categories values for this feature) then the output for the 2nd column will be:2,3,4,1,1,2........

Note* No different categorical values under a specific feature will have the same mapping value, for example, let's take the feature "Country" with three different values:{US, UK, GR}, then no one of these values would result in the same numerical mapping.

Cite As

Anan Yaghmour (2022). FitDataSet (, MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2019a
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!