Skip to content

Updates to Goodness of Fit #1248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
DennRoy wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Updates to Goodness of Fit #1248

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
1a8a4df
Make nicer GoF plots
DennRoy Apr 22, 2026
4305ee0
Bugfixes for GoF
DennRoy Apr 22, 2026
6bec4b1
linting
DennRoy Apr 22, 2026
3c83a1f
Fixes in plotting text
DennRoy Apr 22, 2026
c5565e2
Small formatting changes
DennRoy Apr 29, 2026
cda4221
Fix for warning messages
DennRoy Apr 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
176 changes: 85 additions & 91 deletions scripts/plotGof.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,69 @@ def DrawAxisHists(pads, axis_hists, def_pad=None):
def_pad.cd()


def DrawText(stat, ntoys, pval, arrowrange, underflow, overflow, obs):
output = []

textlabel = ROOT.TPaveText(0.78, 0.88, 0.90, 0.92, "NDC")
textlabel.SetBorderSize(0)
textlabel.SetFillStyle(0)
textlabel.SetTextAlign(32)
textlabel.SetTextSize(0.04)
textlabel.SetTextColor(1)
textlabel.SetTextFont(62)
textlabel.AddText(stat + ", %s Toys" % ntoys)
output.append(textlabel)

pvalue = ROOT.TPaveText(0.78, 0.83, 0.90, 0.87, "NDC")
pvalue.SetBorderSize(0)
pvalue.SetFillStyle(0)
pvalue.SetTextAlign(32)
pvalue.SetTextSize(0.04)
pvalue.SetTextColor(1)
pvalue.SetTextFont(62)
pvalue.AddText("p-value = %0.3f" % pval)
output.append(pvalue)

warningtext1 = ROOT.TPaveText(0.48, 0.77, 0.60, 0.81, "NDC")
warningtext1.SetBorderSize(0)
warningtext1.SetFillStyle(0)
warningtext1.SetTextAlign(22)
warningtext1.SetTextSize(0.04)
warningtext1.SetTextColor(2)
warningtext1.SetTextFont(62)

if arrowrange and ((underflow != 0) or (overflow != 0)):
warningstrings = []
if underflow != 0:
warningstrings.append("%d underflow" % underflow)
if overflow != 0:
warningstrings.append("%d overflow" % overflow)
warningtext1.AddText(", ".join(warningstrings))
output.append(warningtext1)

warningtext2 = ROOT.TPaveText(0.48, 0.72, 0.60, 0.76, "NDC")
warningtext2.SetBorderSize(0)
warningtext2.SetFillStyle(0)
warningtext2.SetTextAlign(22)
warningtext2.SetTextSize(0.04)
warningtext2.SetTextColor(2)
warningtext2.SetTextFont(62)
warningtext2.AddText(f"observed value not in range, at {obs:.2f}")
output.append(warningtext2)
else:
if (underflow != 0) or (overflow != 0):
warningstrings = []
if underflow != 0:
warningstrings.append("%d underflow" % underflow)
if overflow != 0:
warningstrings.append("%d overflow" % overflow)
warningtext1.AddText(", ".join(warningstrings))
elif arrowrange:
warningtext1.AddText(f"observed value not in range, at {obs:.2f}")
output.append(warningtext1)
return output


## Boilerplate
ROOT.PyConfig.IgnoreCommandLineOptions = True
ROOT.gROOT.SetBatch(ROOT.kTRUE)
Expand Down Expand Up @@ -125,23 +188,24 @@ def DrawAxisHists(pads, axis_hists, def_pad=None):
for i in range(toy_graph.GetN()):
toy_hist.Fill(toy_graph.GetX()[i])
pValue = js[args.mass][key]["p"]
underflow_count = toy_hist.GetBinContent(0)
overflow_count = toy_hist.GetBinContent(args.bins + 1)
obs = plot.ToyTGraphFromJSON(js, [args.mass, key, "obs"])
arr = ROOT.TArrow(obs.GetX()[0], 0.001, obs.GetX()[0], toy_hist.GetMaximum() / 8, 0.02, "<|")
arr = ROOT.TArrow(obs.GetX()[0], 0.001, obs.GetX()[0], toy_hist.GetMaximum() / 6, 0.03, "<|")
arr.SetLineColor(ROOT.kBlue)
arr.SetFillColor(ROOT.kBlue)
arr.SetFillStyle(1001)
arr.SetLineWidth(6)
arr.SetLineWidth(4)
arr.SetLineStyle(1)
arr.SetAngle(60)
toy_hist.Draw()
arr.Draw("<|same")
pads[0].RedrawAxis()
pads[0].RedrawAxis("g")
pads[0].GetFrame().Draw()

# axis[0].GetYaxis().SetTitle(args.y_title)
# axis[0].GetXaxis().SetTitle(args.x_title)
# axis[0].GetXaxis().SetLabelOffset(axis[0].GetXaxis().GetLabelOffset()*2)
toy_hist.GetYaxis().SetTitle(args.y_title)
toy_hist.GetXaxis().SetTitle(args.x_title)
toy_hist.GetXaxis().SetLabelOffset(toy_hist.GetXaxis().GetLabelOffset() * 2)

y_min, y_max = (plot.GetPadYMin(pads[0]), plot.GetPadYMax(pads[0]))
plot.FixBothRanges(pads[0], 0, 0, y_max, 0.25)
Expand All @@ -159,29 +223,14 @@ def DrawAxisHists(pads, axis_hists, def_pad=None):

legend.Draw()

plot.DrawCMSLogo(pads[0], "CMS", args.cms_sub, 11, 0.045, 0.035, 1.2, "", 0.8)
plot.DrawCMSLogo(pads[0], "CMS", args.cms_sub, 11, 0.095, 0.035, 1.2, "", 0.8)
plot.DrawTitle(pads[0], args.title_right, 3)
plot.DrawTitle(pads[0], title, 1)

textlabel = ROOT.TPaveText(0.68, 0.88, 0.80, 0.92, "NDC")
textlabel.SetBorderSize(0)
textlabel.SetFillStyle(0)
textlabel.SetTextAlign(32)
textlabel.SetTextSize(0.04)
textlabel.SetTextColor(1)
textlabel.SetTextFont(62)
textlabel.AddText(args.statistic + ", %s Toys" % (toy_graph.GetN()))
textlabel.Draw()

pvalue = ROOT.TPaveText(0.68, 0.83, 0.80, 0.87, "NDC")
pvalue.SetBorderSize(0)
pvalue.SetFillStyle(0)
pvalue.SetTextAlign(32)
pvalue.SetTextSize(0.04)
pvalue.SetTextColor(1)
pvalue.SetTextFont(62)
pvalue.AddText("p-value = %0.3f" % pValue)
pvalue.Draw()
arrow_not_in_range = (obs.GetX()[0] > toy_hist.GetBinLowEdge(args.bins + 1)) or (obs.GetX()[0] < toy_hist.GetBinLowEdge(1))
texts = DrawText(args.statistic, toy_graph.GetN(), pValue, arrow_not_in_range, underflow_count, overflow_count, obs.GetX()[0])
for text in texts:
text.Draw()

canv.Print(key + args.output + ".pdf")
canv.Print(key + args.output + ".png")
Expand All @@ -208,24 +257,24 @@ def DrawAxisHists(pads, axis_hists, def_pad=None):
underflow_count = toy_hist.GetBinContent(0)
overflow_count = toy_hist.GetBinContent(args.bins + 1)
obs = plot.ToyTGraphFromJSON(js, [args.mass, "obs"])
arr = ROOT.TArrow(obs.GetX()[0], 0.001, obs.GetX()[0], toy_hist.GetMaximum() / 8, 0.02, "<|")
arr = ROOT.TArrow(obs.GetX()[0], 0.001, obs.GetX()[0], toy_hist.GetMaximum() / 6, 0.03, "<|")
# if axis is None:
# axis = plot.CreateAxisHists(1, graph_sets[-1].values()[0], True)
# DrawAxisHists(pads, axis, pads[0])
arr.SetLineColor(ROOT.kBlue)
arr.SetFillColor(ROOT.kBlue)
arr.SetFillStyle(1001)
arr.SetLineWidth(6)
arr.SetLineWidth(4)
arr.SetLineStyle(1)
arr.SetAngle(60)
toy_hist.Draw()
arr.Draw("<|same")
pads[0].RedrawAxis()
pads[0].RedrawAxis("g")
pads[0].GetFrame().Draw()
# axis[0].GetYaxis().SetTitle(args.y_title)
# axis[0].GetXaxis().SetTitle(args.x_title)
# axis[0].GetXaxis().SetLabelOffset(axis[0].GetXaxis().GetLabelOffset()*2)
toy_hist.GetYaxis().SetTitle(args.y_title)
toy_hist.GetXaxis().SetTitle(args.x_title)
toy_hist.GetXaxis().SetLabelOffset(toy_hist.GetXaxis().GetLabelOffset() * 2)

y_min, y_max = (plot.GetPadYMin(pads[0]), plot.GetPadYMax(pads[0]))
plot.FixBothRanges(pads[0], 0, 0, y_max, 0.25)
Expand All @@ -243,69 +292,14 @@ def DrawAxisHists(pads, axis_hists, def_pad=None):

legend.Draw()

plot.DrawCMSLogo(pads[0], "CMS", args.cms_sub, 11, 0.045, 0.035, 1.2, "", 0.8)
plot.DrawCMSLogo(pads[0], "CMS", args.cms_sub, 11, 0.095, 0.035, 1.2, "", 0.8)
plot.DrawTitle(pads[0], args.title_right, 3)
plot.DrawTitle(pads[0], args.title_left, 1)

textlabel = ROOT.TPaveText(0.68, 0.88, 0.80, 0.92, "NDC")
textlabel.SetBorderSize(0)
textlabel.SetFillStyle(0)
textlabel.SetTextAlign(32)
textlabel.SetTextSize(0.04)
textlabel.SetTextColor(1)
textlabel.SetTextFont(62)
textlabel.AddText(args.statistic + ", %s Toys" % (toy_graph.GetN()))
textlabel.Draw()

pvalue = ROOT.TPaveText(0.68, 0.83, 0.80, 0.87, "NDC")
pvalue.SetBorderSize(0)
pvalue.SetFillStyle(0)
pvalue.SetTextAlign(32)
pvalue.SetTextSize(0.04)
pvalue.SetTextColor(1)
pvalue.SetTextFont(62)
pvalue.AddText("p-value = %0.3f" % pValue)
pvalue.Draw()

arrow_not_in_range = (obs.GetX()[0] > toy_hist.GetBinLowEdge(args.bins + 1)) or (obs.GetX()[0] < toy_hist.GetBinLowEdge(0))

warningtext1 = ROOT.TPaveText(0.68, 0.78, 0.80, 0.82, "NDC")
warningtext1.SetBorderSize(0)
warningtext1.SetFillStyle(0)
warningtext1.SetTextAlign(32)
warningtext1.SetTextSize(0.04)
warningtext1.SetTextColor(2)
warningtext1.SetTextFont(62)

if arrow_not_in_range and ((underflow_count != 0) or (overflow_count != 0)):
warningstrings = []
if underflow_count != 0:
warningstrings.append("%d underflow" % underflow_count)
if overflow_count != 0:
warningstrings.append("%d overflow" % overflow_count)
warningtext1.AddText(", ".join(warningstrings))
warningtext1.Draw()

warningtext2 = ROOT.TPaveText(0.68, 0.73, 0.80, 0.77, "NDC")
warningtext2.SetBorderSize(0)
warningtext2.SetFillStyle(0)
warningtext2.SetTextAlign(32)
warningtext2.SetTextSize(0.04)
warningtext2.SetTextColor(2)
warningtext2.SetTextFont(62)
warningtext2.AddText("observed value not in range")
warningtext2.Draw()
else:
if (underflow_count != 0) or (overflow_count != 0):
warningstrings = []
if underflow_count != 0:
warningstrings.append("%d underflow" % underflow_count)
if overflow_count != 0:
warningstrings.append("%d overflow" % overflow_count)
warningtext1.AddText(", ".join(warningstrings))
elif arrow_not_in_range:
warningtext1.AddText("observed value not in range")
warningtext1.Draw()
arrow_not_in_range = (obs.GetX()[0] > toy_hist.GetBinLowEdge(args.bins + 1)) or (obs.GetX()[0] < toy_hist.GetBinLowEdge(1))
texts = DrawText(args.statistic, toy_graph.GetN(), pValue, arrow_not_in_range, underflow_count, overflow_count, obs.GetX()[0])
for text in texts:
text.Draw()

canv.Print(".pdf")
canv.Print(".png")
9 changes: 6 additions & 3 deletions src/GoodnessOfFit.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,6 +283,7 @@
for (int i = 0; i < datasetsList->GetSize(); ++i) {
datasets.emplace_back(dynamic_cast<RooAbsData*>(datasetsList->At(i)));
}
datasetsList.reset();

Check warning on line 286 in src/GoodnessOfFit.cc

View check run for this annotation

Codecov / codecov/patch

src/GoodnessOfFit.cc#L286 

Added line #L286 was not covered by tests
#endif

// Number of categories should always equal the number of datasets
Expand All @@ -293,7 +294,7 @@

for (unsigned i = 0; i < binNames_.size(); i++) {
RooAbsData *cat_data = datasets[i].get();
RooAbsPdf *cat_pdf = sim->getPdf(binNames_[i].c_str());
RooAbsPdf *cat_pdf = sim->getPdf(cat_data->GetName());

Check warning on line 297 in src/GoodnessOfFit.cc

View check run for this annotation

Codecov / codecov/patch

src/GoodnessOfFit.cc#L297 

Added line #L297 was not covered by tests
std::unique_ptr<RooArgSet> observables(cat_pdf->getObservables(cat_data));
if (observables->getSize() > 1) {
std::cout << "Warning, KS and AD statistics are not well defined for "
Expand Down Expand Up @@ -402,9 +403,11 @@
}
}else{
bin_prob = current_cdf_val-last_cdf_val;
distance = s_data*pow((empirical_df-current_cdf_val), 2)/current_cdf_val/(1.-current_cdf_val)*bin_prob;
if (current_cdf_val >= 1.0) {
if (current_cdf_val >= 1.0 || current_cdf_val <= 0.0) {
distance = 0.;
} else {
distance = s_data * pow((empirical_df - current_cdf_val), 2) / current_cdf_val / (1. - current_cdf_val) *

Check warning on line 409 in src/GoodnessOfFit.cc

View check run for this annotation

Codecov / codecov/patch

src/GoodnessOfFit.cc#L409 

Added line #L409 was not covered by tests
bin_prob;
}
Comment thread
coderabbitai[bot] marked this conversation as resolved.
if (verbose >= 3) {
std::cout << "Observable: " << observableval << "\tdata: " << d->second << "\tedf: " << empirical_df << "\tcdf: " << current_cdf_val << "\tdistance: " << distance << "\n";
Expand Down
Loading