I have data set which is stored as a matrix where each row is an observation (number of observations listed is 4000 ) and each column the feature extracted from that observation (number of features extracted from each observation is 324).

Beside the matrix i have a vector that determines the class of each observation.

I want to create a distribution describing how the data is distributed for each class, such that i can use it as a model, predict the class of future test samples. The problem is though i am not sure how to do it.

I tried using NaiveBayes to plot the model i retrieved from the {klaR} library Which gave me this plot (one for each feature)

enter image description here

It make sense to create a distribution of each feature across the different classes, but isn't there a more optimal way to model rather than having 9 x 324 distributions?..

Could the distributions somehow be fed to a Naive bayes method and input data?


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.