"Which batch of users to end with (exclusive). Default under 10k dataset is None, default under 46k dataset is 5. Values range from 0-47 for 46k. Only applies to 46k dataset." ) parser.add_argument( "--printEvery", action="store", type=int, default=2000, help= "How often to print out to the console. Defaults to 2000 for 10k and 10,000 for 46k." ) args = parser.parse_args() print(args) mus.createLogFile() loc10k = "10kjails" loc46k = "46kjailzips" location = loc10k if args.kind == 10 else loc46k start = args.start if args.kind == 10 else ( 0 if args.start == None else args.start) stop = args.end if args.kind == 10 else ( 5 if args.end == None else args.end) strKind = "10k" if args.kind == 10 else "46k" startStop = "" if args.kind == 10 else "_{}_{}".format(start, stop) printEvery = args.printEvery jails = enumerateLoops(location, start=start, stop=stop, printEvery=printEvery)
for f in files: func(big, little, f, jailHolder) else: mu.logwrite( "findmissing.py::iterateThroughAllJAil: No big directories found! Trying to find zip directories instead." ) files = getFileNames(jailLocation) files = [files[i] for i in range(max(0, start), min(stop, len(files)))] for f in files: zu.withUnzippedFiles(os.path.join(jailLocation, f), iterateThroughArchivedFiles) if __name__ == '__main__': mu.logFileName = "*whatever*" mu.createLogFile() aia10k = "/Users/audrey/Downloads/ai2_10k_random_users_deidentified_aias" jail10k = "/Users/audrey/Personal/School/College/Work/summer2018/jailconversion/10kjails" '''onlyaia = compareDirs(aia10k, jail10k) for d in onlyaia: print d print(len(onlyaia))''' only = compareFiles(aia10k, jail10k) for f in only: mu.logwrite(f) mu.logwrite("main:: # of files missing: " + str(len(only)))