How to generate SIGNALS file with more than 20 input params?

I'm currently experimenting with the R bridge and Keras/Tensorflow.
Was wondering how I can generate something like a signals file (adviseLong(SIGNALS)) using more than 20 input variables.
The manual is pretty clear on how to call TRAIN/LEARN.

"For using more than 20 signals, collect them in a global array and send them to the machine learning algorithm with NEURAL_LEARN or NEURAL_TRAIN."

But what about generating a SIGNALS file, and using the next trade as target?
What I am trying to do is really somehing like this (I know this isn't valid code)


enterLong();

What can I do to generate a file that has the same format as the SIGNALS file, using more than 20 inputs and using the result of the next trade as target?

I am doing something similar using sprintf and file_append to write a csv file with the nbar movement as the target.

I can't easily see how write a custom csv file using the result of the next trade as the target.

Too many features leads to a risk of overfitting, but you do need to select which signals to use. I would suggest writing several scripts to export different sets of 20 signals. Then you can run feature selection on those in order to choose the best 20 signals for the final version.

The next trade can currently not be used as a target with more than 20 signals. But an arbitrary number of signals will be implemented in one of the next Zorro versions, in a similar way as suggested by Dalla.