if args.pseudocounts:
sys.stderr.write("This run is using pseudocounts.\n\n\n")
sys.stderr.write("Starting the training and testing separation...\n\n")
m.training_testing_sets_separation(args.infile,3,training_filename,testing_filename)
######## 2 +/- ###########
######## 3 kmer dict #####
if (args.pseudocounts):
sys.stderr.write("Starting the training background and foreground separation...\n\n")
back_dict=m.build_hash_pseudocount([x for x in m.background_separation(training_filename)],k)
sys.stderr.write("The MM for the bg is generated...\n\n")
sign_dict=m.build_hash_pseudocount([x for x in m.signal_separation(training_filename)],k)
sys.stderr.write("The MM for the bg is generated...\n\n")
else:
back_dict=m.build_hash([x for x in m.background_separation(training_filename)],k)
sign_dict=m.build_hash([x for x in m.signal_separation(training_filename)],k)
######### 4 print ########
output_filename=args.outfile+"_k_"+str(k)+"_l_"+str(l)+'.MM'
sys.stderr.write("Printing the model in {}...\n\n".format(output_filename))
m.print_hash(sign_dict,back_dict,output_filename)
######## 5 windows #######
sys.stderr.write("Starting the testing background and foreground separation...\n\n")
output_filename= args.outfile+"_k_"+str(k)+"_l_"+str(l)+'.data'
if args.pseudocounts:
sys.stderr.write("This run is using pseudocounts.\n\n\n")
sys.stderr.write("Starting the training and testing separation...\n\n")
m.training_testing_sets_separation(args.infile,3,training_filename,testing_filename)
######## 2 +/- ###########
######## 3 kmer dict #####
if (args.pseudocounts):
sys.stderr.write("Starting the training background and foreground separation...\n\n")
back_dict=m.build_hash_pseudocount([x for x in m.background_separation(training_filename)],args.order)
sys.stderr.write("The MM for the bg is generated...\n\n")
sign_dict=m.build_hash_pseudocount([x for x in m.signal_separation(training_filename)],args.order)
sys.stderr.write("The MM for the bg is generated...\n\n")
else:
back_dict=m.build_hash([x for x in m.background_separation(training_filename)],args.order)
sign_dict=m.build_hash([x for x in m.signal_separation(training_filename)],args.order)
######### 4 print ########
output_filename=args.outfile+'.MM'
sys.stderr.write("Printing the model in {}...\n\n".format(output_filename))
m.print_hash(sign_dict,back_dict,output_filename)
######## 5 windows #######
sys.stderr.write("Starting the testing background and foreground separation...\n\n")
sys.stderr.write("Starting the computation of the Scores...\n\n")
output_filename_fg=args.outfile+'_fg.th'
if args.pseudocounts:
sys.stderr.write("This run is using pseudocounts.\n\n\n")
sys.stderr.write("Starting the training and testing separation...\n\n")
m.training_testing_sets_separation(args.infile,3,training_filename,testing_filename)
######## 2 +/- ###########
######## 3 kmer dict #####
if (args.pseudocounts):
sys.stderr.write("Starting the training background and foreground separation...\n\n")
back_dict=m.build_hash_pseudocount([x for x in m.background_separation(training_filename)],k)
sys.stderr.write("The MM for the bg is generated...\n\n")
sign_dict=m.build_hash_pseudocount([x for x in m.signal_separation(training_filename)],k)
sys.stderr.write("The MM for the bg is generated...\n\n")
else:
back_dict=m.build_hash([x for x in m.background_separation(training_filename)],k)
sign_dict=m.build_hash([x for x in m.signal_separation(training_filename)],k)
######### 4 print ########
output_filename=args.outfile+"_k_"+str(k)+"_l_"+str(l)+'.MM'
sys.stderr.write("Printing the model in {}...\n\n".format(output_filename))
m.print_hash(sign_dict,back_dict,output_filename)
######## 5 windows #######
sys.stderr.write("Starting the testing background and foreground separation...\n\n")
sys.stderr.write("Starting the computation of the Scores...\n\n")
output_filename_fg=args.outfile+"_k_"+str(k)+"_l_"+str(l)+'_fg.th'
