Why I can't load data to Classification Learner App
6 views (last 30 days)
Show older comments
After selecting the trainData I cannot select response.

trainData is prepared like this

Last column is the label.
3 Comments
Subhajyoti
on 30 Nov 2024
I tried to reproduce the error you are facing using the ' Train Decision Trees Using Classification Learner App' example and the 'Response' select options are active.
fishertable = readtable("fisheriris.csv")
% Convert the cell array to a categorical array
categoryCategorical = categorical(fishertable.Species);
% Convert the categorical array to a double array
categoryDouble = double(categoryCategorical);
fishertable.Species = categoryDouble;
trainData = table2array(fishertable)

Cris LaPierre
on 30 Nov 2024
Edited: Cris LaPierre
on 30 Nov 2024
Just a thought, but I think you have too many unique response values.
- Predictor and response variables can be numeric, categorical, string, or logical vectors, cell arrays of character vectors, or character arrays. The response variable cannot contain more than 500 unique class labels. (ref)
Confirm that you want to perform classification. If so, select a subset of your data (<500 rows) and load that into the Classification Learner App. Let us know if that fixes the problem.
Answers (1)
Drew
on 9 Dec 2024
Since all of the data is of type "double", perhaps you had intended to use Regression Learner app?
If classification is intended, how many unique values (classes) are there for the response variable?
0 Comments
See Also
Categories
Find more on Classification Learner App in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!