dotesting = 0
docrossvalidation = 0
doRoCLearning = 0
doBoundary = 0
doBinarySearch = 0
ncores = -1
doRoCLearningGradBoostClass = 1 # mfaggin
##########################################################################################
# var_pt="pt_cand_ML"
# var_signal="signal_ML"
# path = "./plots/%.1f_%.1f_GeV"%(ptmin,ptmax)
# checkdir(path)
classifiers, names = getclassifiers()
mylistvariables = getvariablestraining(optionClassification)
mylistvariablesothers = getvariablesothers(optionClassification)
myvariablesy = getvariableissignal(optionClassification)
mylistvariablesx, mylistvariablesy = getvariablecorrelation(
optionClassification)
mylistvariablesall = getvariablesall(optionClassification)
train_set = pd.read_pickle("../buildsample/trainsample%s.pkl" % (suffix))
test_set = pd.read_pickle("../buildsample/testsample%s.pkl" % (suffix))
X_train = train_set[mylistvariables]
y_train = train_set[myvariablesy]
X_test = test_set[mylistvariables]
y_test = test_set[myvariablesy]
plotdir)
scatterplot(train_set_ptsel_sig, train_set_ptsel_bkg, mylistvariablesx,
mylistvariablesy, plotdir)
correlationmatrix(train_set_ptsel_sig, plotdir, "signal")
correlationmatrix(train_set_ptsel_bkg, plotdir, "background")
if (doStandard == 1):
X_train = GetDataFrameStandardised(X_train)
if (doPCA == 1):
n_pca = 5
X_train, pca = GetPCADataFrameAndPC(X_train, n_pca)
plotvariancePCA(pca, plotdir)
if (activateScikitModels == 1):
classifiersScikit, namesScikit = getclassifiers()
classifiers = classifiers + classifiersScikit
names = names + namesScikit
if (activateKerasModels == 1):
classifiersDNN, namesDNN = getclassifiersDNN(len(X_train.columns))
classifiers = classifiers + classifiersDNN
names = names + namesDNN
if (dotraining == 1):
trainedmodels = fit(names, classifiers, X_train, y_train)
savemodels(names, trainedmodels, output, suffix)
if (dotesting == 1):
filenametest_set_ML = output + "/testsample%sMLdecision.pkl" % (suffix)
filenametest_set_ML_root = output + "/testsample%sMLdecision.root" % (