# Create a model based on the distribution of data for classification purposes

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)

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?