XXX-HIST:  Build a histogram for a quantity using data from log files.

There is a version of this program for each application (eg, net-hist). 
Each version allows histograms to be created for the set of quantities
defined for that application.  The histogram is written to standard
output, in a form suitable for plotting.

Usage:
  
    xxx-hist quantities low high bins { log-file [ range ] } 
           [ / { app-args } ]

Here 'xxx' is a prefix identifying the particular incarnation of this
program.  The 'quantities' specification says what to make a histogram
of; 'low' and 'high' give the range, which is divided into 'bins'
bins.  There follow specifications of where the data comes from; and
perhaps further arguments, depending on the application (for which,
see the documentation specific to that application - eg, net-hist.doc).

For the format of the quantity specifications, see the documentation
on generic quantities, quantities for Monte Carlo runs, quantities for
neural networks, etc.  Many quantities may be given; all their values
are merged in one histogram.

Data comes from records with indexes in the specified ranges within
the log files mentioned.  The ranges have the form "[low][:[high]]][%mod]".  
The low bound defaults to one.  If no high bound is given, the range
extends to the highest index in the log file.  If the "%mod" option is
present, only iterations within the range whose index is a multiple of
"mod" are used (e.g. "5:12%3" is equivalent to 6 9 12).  If no range
is given, the default is "1:".

The output consists as many lines as bins, with each line giving the
value at the centre of the bin and either the count of values falling
within the bin or the fraction of values falling within the bin.  The
latter option is selected by preceding the number of bins with a minus
sign.  Values falling outside the range are discarded, except that
they affect the normalization of counts to give fractions.

            Copyright (c) 1995-2004 by Radford M. Neal