MATLAB Answers

Failed to show the accuracy of testing data (Classification Learner's Testing Function)

3 views (last 30 days)
Hussein Hasan Mohsen
Hussein Hasan Mohsen on 13 Jul 2020
Answered: Jalaj Gambhir on 29 Jul 2020
Currantly i am able to test my data after converting the model from classification learner app
Right now i'm not able to show the accuracy of my testing data (classification was correct but the accuracy not show??)
can some one provided me with any code???
code that using to test the new data is here:
trainedClassifier ---> model that export from classification
featureVector ---> data that used for testing
yfit = trainedClassifier.predictFcn(featureVector)

  0 Comments

Sign in to comment.

Answers (1)

Jalaj Gambhir
Jalaj Gambhir on 29 Jul 2020
Hi,
The Classification learner App splits the data that you have provided into Training Data and Validation Data It will show the detailed evaluation on the validation data when you click on 'Confusion Chart' in your App. To test your model on the testing data, you will need to compute the evaluation metrics, like accuracy, yourself after getting the predictions on the testing data using 'predictFcn'. For this workflow, look at the answer here.
Hope this helps.

  0 Comments

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!