How do I link my data with the training and validation set indices I have created using 'dividerand' function?
8 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
I have a dataset of 200 values. I want to randomly split the data into training (70%) and validation (30%) sets. I used the 'dividerand' function to create random indices for both sets. But now I am unsure as to how to link my data with the indices in order to proceed further with my analysis.
0 Kommentare
Antworten (1)
Manan Mishra
am 10 Okt. 2017
Bearbeitet: Manan Mishra
am 10 Okt. 2017
You can pass the vectors created by "dividerand" as index to extract training and validation sets from your dataset.
For example, if "ds" is your dataset of 200 values and you use the following command to create random indices:
[trainInd,valInd,~] = dividerand(3000,0.7,0.3,0);
Then you can extract the training and validation sets as follows:
trainSet = ds(trainInd);
valSet = ds(valInd);
1 Kommentar
LE-LE YANG
am 31 Mär. 2018
trainSet = ds(trainInd); valSet = ds(valInd);
But how to use these datasets for train and validate? I know the train is like: net=train(net,x,t) But how to validate the net?
Siehe auch
Kategorien
Mehr zu Statistics and Machine Learning Toolbox finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!