NN problem with detector features

Writing features files from flat trees output by DSelector.  Should be easy enough to keep detector information, BUT not every event has meaningful output for each of these.  E.g., for events where the K+ does not enter the BCAL, BCAL values are either 0 or 1000 (the latter a flag value, I assume).  A NN will likely have problems handling this (feature standardization will be screwy), but a BDT should be able to do it easily.