Thanks for that. I’ve missed something here. I thought that the one hot coding would convert each individual letter, A, T, C, G into individual four-digit codes such as 1 0 0 0, 0 1 0 0, 0 0 1 0, and 0 0 0 1.
There may be much better ways in Julia, but I was looking for something equivalent to the keras.tensorflow function that is supposed to work like:
preprocessing.text.one_hot(
input_text = input_object, # dataframe?
n = 4, # number of individual objects to code for, A, T, C, G
filters = 'N', # filter out the N values
lower = False,
split = ' ')
BTW, I’ve tried this and not got it to work either, but I can see the logic. I’m happy to be told there are more precise and/or elegant ways to get the final result?