{ "cells": [ { "cell_type": "markdown", "id": "4c5f0736", "metadata": {}, "source": [ "# rf102_dataimport\n", "'BASIC FUNCTIONALITY' RooFit tutorial macro #102\n", "Importing data from ROOT TTrees and THx histograms\n", "\n", "\n", "\n", "\n", "**Author:** Clemens Lange, Wouter Verkerke (C version) \n", "This notebook tutorial was automatically generated with ROOTBOOK-izer from the macro found in the ROOT repository on Tuesday, May 19, 2026 at 08:28 PM." ] }, { "cell_type": "code", "execution_count": 1, "id": "8ee4bfdb", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:27.252506Z", "iopub.status.busy": "2026-05-19T20:28:27.252391Z", "iopub.status.idle": "2026-05-19T20:28:28.241995Z", "shell.execute_reply": "2026-05-19T20:28:28.241422Z" } }, "outputs": [], "source": [ "import ROOT\n", "from array import array\n", "import numpy as np\n", "\n", "\n", "def makeTH1(trnd):\n", "\n", " # Create ROOT ROOT.TH1 filled with a Gaussian distribution\n", "\n", " hh = ROOT.TH1D(\"hh\", \"hh\", 25, -10, 10)\n", " hh.Fill(np.array([trnd.Gaus(0, 3) for _ in range(100)]))\n", " return hh\n", "\n", "\n", "def makeTTree(trnd):\n", " # Create ROOT ROOT.TTree filled with a Gaussian distribution in x and a\n", " # uniform distribution in y\n", "\n", " tree = ROOT.TTree(\"tree\", \"tree\")\n", " px = array(\"d\", [0])\n", " py = array(\"d\", [0])\n", " tree.Branch(\"x\", px, \"x/D\")\n", " tree.Branch(\"y\", py, \"y/D\")\n", " for i in range(100):\n", " px[0] = trnd.Gaus(0, 3)\n", " py[0] = trnd.Uniform() * 30 - 15\n", " tree.Fill()\n", " return tree\n", "\n", "trnd = ROOT.TRandom3()" ] }, { "cell_type": "markdown", "id": "e9389280", "metadata": {}, "source": [ "##########################\n", "Importing ROOT histograms\n", "##########################\n", "Import ROOT TH1 into a RooDataHist\n", "---------------------------------------------------------\n", "Create a ROOT TH1 histogram" ] }, { "cell_type": "code", "execution_count": 2, "id": "8f78651a", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:28.243773Z", "iopub.status.busy": "2026-05-19T20:28:28.243547Z", "iopub.status.idle": "2026-05-19T20:28:28.378348Z", "shell.execute_reply": "2026-05-19T20:28:28.377818Z" } }, "outputs": [], "source": [ "hh = makeTH1(trnd)" ] }, { "cell_type": "markdown", "id": "33076d06", "metadata": {}, "source": [ "Declare observable x" ] }, { "cell_type": "code", "execution_count": 3, "id": "47709660", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:28.379988Z", "iopub.status.busy": "2026-05-19T20:28:28.379862Z", "iopub.status.idle": "2026-05-19T20:28:28.530961Z", "shell.execute_reply": "2026-05-19T20:28:28.530394Z" } }, "outputs": [], "source": [ "x = ROOT.RooRealVar(\"x\", \"x\", -10, 10)" ] }, { "cell_type": "markdown", "id": "7b8f9d5d", "metadata": {}, "source": [ "Create a binned dataset that imports contents of ROOT.TH1 and associates\n", "its contents to observable 'x'" ] }, { "cell_type": "code", "execution_count": 4, "id": "a0214f2b", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:28.532549Z", "iopub.status.busy": "2026-05-19T20:28:28.532422Z", "iopub.status.idle": "2026-05-19T20:28:28.791425Z", "shell.execute_reply": "2026-05-19T20:28:28.790894Z" } }, "outputs": [], "source": [ "dh = ROOT.RooDataHist(\"dh\", \"dh\", [x], Import=hh)" ] }, { "cell_type": "markdown", "id": "04642fe2", "metadata": {}, "source": [ "Plot and fit a RooDataHist\n", "---------------------------------------------------\n", "Make plot of binned dataset showing Poisson error bars (RooFit default)" ] }, { "cell_type": "code", "execution_count": 5, "id": "2348f258", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:28.793016Z", "iopub.status.busy": "2026-05-19T20:28:28.792891Z", "iopub.status.idle": "2026-05-19T20:28:28.940654Z", "shell.execute_reply": "2026-05-19T20:28:28.940154Z" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "frame = x.frame(Title=\"Imported ROOT.TH1 with Poisson error bars\")\n", "dh.plotOn(frame)" ] }, { "cell_type": "markdown", "id": "3b75c0c8", "metadata": {}, "source": [ "Fit a Gaussian p.d.f to the data" ] }, { "cell_type": "code", "execution_count": 6, "id": "812bd93d", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:28.942592Z", "iopub.status.busy": "2026-05-19T20:28:28.942461Z", "iopub.status.idle": "2026-05-19T20:28:29.182991Z", "shell.execute_reply": "2026-05-19T20:28:29.182396Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[#1] INFO:Fitting -- RooAbsPdf::fitTo(gauss_over_gauss_Int[x]) fixing normalization set for coefficient determination to observables in data\n", "[#1] INFO:Fitting -- using generic CPU library compiled with no vectorizations\n", "[#1] INFO:Fitting -- Creation of NLL object took 7.02287 ms\n", "[#1] INFO:Fitting -- RooAddition::defaultErrorLevel(nll_gauss_over_gauss_Int[x]_dh) Summation contains a RooNLLVar, using its error level\n", "[#1] INFO:Minimization -- [fitFCN] No discrete parameters, performing continuous minimization only\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mean = ROOT.RooRealVar(\"mean\", \"mean\", 0, -10, 10)\n", "sigma = ROOT.RooRealVar(\"sigma\", \"sigma\", 3, 0.1, 10)\n", "gauss = ROOT.RooGaussian(\"gauss\", \"gauss\", x, mean, sigma)\n", "gauss.fitTo(dh, PrintLevel=-1)\n", "gauss.plotOn(frame)" ] }, { "cell_type": "markdown", "id": "0b1d1750", "metadata": {}, "source": [ "Plot and fit a RooDataHist with internal errors\n", "---------------------------------------------------------------------------------------------" ] }, { "cell_type": "markdown", "id": "7df070a7", "metadata": {}, "source": [ "If histogram has custom error (i.e. its contents is does not originate from a Poisson process\n", "but e.g. is a sum of weighted events) you can data with symmetric 'sum-of-weights' error instead\n", "(same error bars as shown by ROOT)" ] }, { "cell_type": "code", "execution_count": 7, "id": "1357223d", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.184769Z", "iopub.status.busy": "2026-05-19T20:28:29.184637Z", "iopub.status.idle": "2026-05-19T20:28:29.293911Z", "shell.execute_reply": "2026-05-19T20:28:29.293307Z" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "frame2 = x.frame(Title=\"Imported ROOT.TH1 with internal errors\")\n", "dh.plotOn(frame2, DataError=\"SumW2\")\n", "gauss.plotOn(frame2)" ] }, { "cell_type": "markdown", "id": "6351282f", "metadata": {}, "source": [ "Please note that error bars shown (Poisson or SumW2) are for visualization only, the are NOT used\n", "in a maximum likelihood fit\n", "\n", "A (binned) ML fit will ALWAYS assume the Poisson error interpretation of data (the mathematical definition\n", "of likelihood does not take any external definition of errors). Data with non-unit weights can only be correctly\n", "fitted with a chi^2 fit (see rf602_chi2fit.py)\n", "\n", "Importing ROOT TTrees\n", "-----------------------------------------------------------\n", "Import ROOT TTree into a RooDataSet" ] }, { "cell_type": "code", "execution_count": 8, "id": "34d2646c", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.296022Z", "iopub.status.busy": "2026-05-19T20:28:29.295893Z", "iopub.status.idle": "2026-05-19T20:28:29.424959Z", "shell.execute_reply": "2026-05-19T20:28:29.424209Z" } }, "outputs": [], "source": [ "tree = makeTTree(trnd)" ] }, { "cell_type": "markdown", "id": "2aaa3027", "metadata": {}, "source": [ "Define 2nd observable y" ] }, { "cell_type": "code", "execution_count": 9, "id": "1688314f", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.427084Z", "iopub.status.busy": "2026-05-19T20:28:29.426955Z", "iopub.status.idle": "2026-05-19T20:28:29.530595Z", "shell.execute_reply": "2026-05-19T20:28:29.529825Z" } }, "outputs": [], "source": [ "y = ROOT.RooRealVar(\"y\", \"y\", -10, 10)" ] }, { "cell_type": "markdown", "id": "a3a9e080", "metadata": {}, "source": [ "Construct unbinned dataset importing tree branches x and y matching between branches and ROOT.RooRealVars\n", "is done by name of the branch/RRV\n", "\n", "Note that ONLY entries for which x,y have values within their allowed ranges as defined in\n", "ROOT.RooRealVar x and y are imported. Since the y values in the import tree are in the range [-15,15]\n", "and RRV y defines a range [-10,10] this means that the ROOT.RooDataSet\n", "below will have less entries than the ROOT.TTree 'tree'" ] }, { "cell_type": "code", "execution_count": 10, "id": "fc028426", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.532292Z", "iopub.status.busy": "2026-05-19T20:28:29.532165Z", "iopub.status.idle": "2026-05-19T20:28:29.701433Z", "shell.execute_reply": "2026-05-19T20:28:29.700835Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[#1] INFO:DataHandling -- RooTreeDataStore::loadValues(ds) Skipping event #0 because y cannot accommodate the value 14.424\n", "[#1] INFO:DataHandling -- RooTreeDataStore::loadValues(ds) Skipping event #3 because y cannot accommodate the value -12.0022\n", "[#1] INFO:DataHandling -- RooTreeDataStore::loadValues(ds) Skipping event #5 because y cannot accommodate the value 13.8261\n", "[#1] INFO:DataHandling -- RooTreeDataStore::loadValues(ds) Skipping event #6 because y cannot accommodate the value -14.9925\n", "[#1] INFO:DataHandling -- RooTreeDataStore::loadValues(ds) Skipping ...\n", "[#0] WARNING:DataHandling -- RooTreeDataStore::loadValues(ds) Ignored 36 out-of-range events\n" ] } ], "source": [ "ds = ROOT.RooDataSet(\"ds\", \"ds\", {x, y}, Import=tree)" ] }, { "cell_type": "markdown", "id": "559f3322", "metadata": {}, "source": [ "Use ascii import/export for datasets\n", "------------------------------------------------------------------------------------" ] }, { "cell_type": "code", "execution_count": 11, "id": "ed675d2f", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.703567Z", "iopub.status.busy": "2026-05-19T20:28:29.703439Z", "iopub.status.idle": "2026-05-19T20:28:29.842233Z", "shell.execute_reply": "2026-05-19T20:28:29.841519Z" } }, "outputs": [], "source": [ "def write_dataset(ds, filename):\n", " # Write data to output stream\n", " outstream = ROOT.std.ofstream(filename)\n", " # Optionally, adjust the stream here (e.g. std::setprecision)\n", " ds.write(outstream)\n", " outstream.close()\n", "\n", "\n", "write_dataset(ds, \"rf102_testData.txt\")" ] }, { "cell_type": "markdown", "id": "20e07e14", "metadata": {}, "source": [ "Read data from input stream. The variables of the dataset need to be supplied\n", "to the RooDataSet::read() function." ] }, { "cell_type": "code", "execution_count": 12, "id": "7348d002", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.844262Z", "iopub.status.busy": "2026-05-19T20:28:29.844136Z", "iopub.status.idle": "2026-05-19T20:28:29.961202Z", "shell.execute_reply": "2026-05-19T20:28:29.960347Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "-----------------------\n", "Reading data from ASCII\n", "[#1] INFO:DataHandling -- RooDataSet::read: reading file rf102_testData.txt\n", "[#1] INFO:DataHandling -- RooDataSet::read: read 64 events (ignored 0 out of range events)\n", "DataStore dataset (rf102_testData.txt)\n", " Contains 64 entries\n", " Observables: \n", " 1) x = 9.46654 L(-10 - 10) \"x\"\n", " 2) y = 0.0174204 L(-10 - 10) \"y\"\n", " 3) blindState = Normal(idx = 0)\n", " \"Blinding State\"\n", "\n", "Original data, line 20:\n", "\n", "Read-back data, line 20:\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " 1) RooRealVar:: y = 0.0106407\n", " 2) RooRealVar:: x = -0.79919\n", " 1) RooRealVar:: x = 0.0106407\n", " 2) RooRealVar:: y = -0.79919\n", " 3) RooCategory:: blindState = Normal(idx = 0)\n", "\n" ] } ], "source": [ "print(\"\\n-----------------------\\nReading data from ASCII\")\n", "dataReadBack = ROOT.RooDataSet.read(\n", " \"rf102_testData.txt\",\n", " [x, y], # variables to be read. If the file has more fields, these are ignored.\n", " \"D\", # Prints if a RooFit message stream listens for debug messages. Use Q for quiet.\n", ")\n", "\n", "dataReadBack.Print(\"V\")\n", "\n", "print(\"\\nOriginal data, line 20:\")\n", "ds.get(20).Print(\"V\")\n", "\n", "print(\"\\nRead-back data, line 20:\")\n", "dataReadBack.get(20).Print(\"V\")" ] }, { "cell_type": "markdown", "id": "14ecb6ff", "metadata": {}, "source": [ "Plot data set with multiple binning choices\n", "------------------------------------------------------------------------------------\n", "Print number of events in dataset" ] }, { "cell_type": "code", "execution_count": 13, "id": "7eaef6b9", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:29.963071Z", "iopub.status.busy": "2026-05-19T20:28:29.962903Z", "iopub.status.idle": "2026-05-19T20:28:30.067114Z", "shell.execute_reply": "2026-05-19T20:28:30.066420Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "RooDataSet::ds[y,x] = 64 entries\n" ] } ], "source": [ "ds.Print()" ] }, { "cell_type": "markdown", "id": "0f2a3bef", "metadata": {}, "source": [ "Print unbinned dataset with default frame binning (100 bins)" ] }, { "cell_type": "code", "execution_count": 14, "id": "29addcf8", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:30.072773Z", "iopub.status.busy": "2026-05-19T20:28:30.072640Z", "iopub.status.idle": "2026-05-19T20:28:30.177429Z", "shell.execute_reply": "2026-05-19T20:28:30.176656Z" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "frame3 = y.frame(Title=\"Unbinned data shown in default frame binning\")\n", "ds.plotOn(frame3)" ] }, { "cell_type": "markdown", "id": "12e212af", "metadata": {}, "source": [ "Print unbinned dataset with custom binning choice (20 bins)" ] }, { "cell_type": "code", "execution_count": 15, "id": "cf4c35b6", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:30.179161Z", "iopub.status.busy": "2026-05-19T20:28:30.179023Z", "iopub.status.idle": "2026-05-19T20:28:30.302409Z", "shell.execute_reply": "2026-05-19T20:28:30.301702Z" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "frame4 = y.frame(Title=\"Unbinned data shown with custom binning\")\n", "ds.plotOn(frame4, Binning=20)\n", "\n", "frame5 = y.frame(Title=\"Unbinned data read back from ASCII file\")\n", "ds.plotOn(frame5, Binning=20)\n", "dataReadBack.plotOn(frame5, Binning=20, MarkerColor=\"r\", MarkerStyle=5)" ] }, { "cell_type": "markdown", "id": "e3bf4497", "metadata": {}, "source": [ "Draw all frames on a canvas" ] }, { "cell_type": "code", "execution_count": 16, "id": "44820598", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:30.304178Z", "iopub.status.busy": "2026-05-19T20:28:30.304041Z", "iopub.status.idle": "2026-05-19T20:28:30.572494Z", "shell.execute_reply": "2026-05-19T20:28:30.571802Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Info in : png file rf102_dataimport.png has been created\n" ] } ], "source": [ "c = ROOT.TCanvas(\"rf102_dataimport\", \"rf102_dataimport\", 800, 800)\n", "c.Divide(3, 2)\n", "c.cd(1)\n", "ROOT.gPad.SetLeftMargin(0.15)\n", "frame.GetYaxis().SetTitleOffset(1.4)\n", "frame.Draw()\n", "c.cd(2)\n", "ROOT.gPad.SetLeftMargin(0.15)\n", "frame2.GetYaxis().SetTitleOffset(1.4)\n", "frame2.Draw()\n", "c.cd(4)\n", "ROOT.gPad.SetLeftMargin(0.15)\n", "frame3.GetYaxis().SetTitleOffset(1.4)\n", "frame3.Draw()\n", "c.cd(5)\n", "ROOT.gPad.SetLeftMargin(0.15)\n", "frame4.GetYaxis().SetTitleOffset(1.4)\n", "frame4.Draw()\n", "c.cd(6)\n", "ROOT.gPad.SetLeftMargin(0.15)\n", "frame4.GetYaxis().SetTitleOffset(1.4)\n", "frame5.Draw()\n", "\n", "c.SaveAs(\"rf102_dataimport.png\")" ] }, { "cell_type": "markdown", "id": "3a89cb32", "metadata": {}, "source": [ "Draw all canvases " ] }, { "cell_type": "code", "execution_count": 17, "id": "17c0cc34", "metadata": { "collapsed": false, "execution": { "iopub.execute_input": "2026-05-19T20:28:30.574704Z", "iopub.status.busy": "2026-05-19T20:28:30.574553Z", "iopub.status.idle": "2026-05-19T20:28:30.763215Z", "shell.execute_reply": "2026-05-19T20:28:30.762463Z" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "
\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from ROOT import gROOT \n", "gROOT.GetListOfCanvases().Draw()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.12" } }, "nbformat": 4, "nbformat_minor": 5 }