PE.table_CRR(train_features, train_classes, test_features, test_classes)
PE.performance_evaluation(train_features, train_classes, test_features,
test_classes)
#thresholds_2=[0.74,0.76,0.78]
# this part is for bootsrap
starttime = datetime.datetime.now()
thresholds_3 = np.arange(0.6, 0.9, 0.02)
times = 100 #running 100 times takes about 1 to 2 hours
total_fmrs, total_fnmrs, crr_mean, crr_u, crr_l = IM.IrisMatchingBootstrap(
train_features, train_classes, test_features, test_classes, times,
thresholds_3)
fmrs_mean, fmrs_l, fmrs_u, fnmrs_mean, fnmrs_l, fnmrs_u = IM.calcROCBootstrap(
total_fmrs, total_fnmrs)
endtime = datetime.datetime.now()
print('Bootsrap takes' + str((endtime - starttime).seconds) + 'seconds')
fmrs_mean *= 100 #use for percent(%)
fmrs_l *= 100
fmrs_u *= 100
fnmrs_mean *= 100
fnmrs_l *= 100
fnmrs_u *= 100
PE.FM_FNM_table(fmrs_mean, fmrs_l, fmrs_u, fnmrs_mean, fnmrs_l, fnmrs_u,
thresholds_3)
PE.FMR_conf(fmrs_mean, fmrs_l, fmrs_u, fnmrs_mean, fnmrs_l, fnmrs_u)
PE.FNMR_conf(fmrs_mean, fmrs_l, fmrs_u, fnmrs_mean, fnmrs_l, fnmrs_u)
