I am performing a supervised classification in GEE and want to verify how well my classifier has got trained. For this, I found a method confusionMatrix() and my respective program is

var training = india_image.sampleRegions(ft,['class'],30);
var trained = ee.Classifier.cart().train(training, 'class', new_bands);

var trainAccuracy = trained.confusionMatrix();

var exportAccuracy = ee.Feature(null, {matrix: trainAccuracy.accuracy()});

// Export the FeatureCollection.
  collection: ee.FeatureCollection(exportAccuracy),
  description: 'exportAccuracy',
  fileFormat: 'CSV'

The exported csv is here

Can you please explain it or give some suggestion about how to find presision, recall and accuracy

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.