{
"cells": [
{
"cell_type": "markdown",
"id": "d9300f5f",
"metadata": {},
"source": [
"# distrdf003_live_visualization\n",
"Configure a Dask connection and visualize the filling of a 1D and 2D\n",
"histograms distributedly.\n",
"\n",
"This tutorial showcases the process of setting up real-time data representation\n",
"for distributed computations.\n",
"By calling the LiveVisualize function, you can observe the canvas updating\n",
"with the intermediate results of the histograms as the\n",
"distributed computation progresses.\n",
"\n",
"\n",
"\n",
"\n",
"**Author:** Silia Taider \n",
"This notebook tutorial was automatically generated with ROOTBOOK-izer from the macro found in the ROOT repository on Tuesday, May 19, 2026 at 08:10 PM."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "11a7afdb",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:10:56.441409Z",
"iopub.status.busy": "2026-05-19T20:10:56.441265Z",
"iopub.status.idle": "2026-05-19T20:10:58.811053Z",
"shell.execute_reply": "2026-05-19T20:10:58.807962Z"
}
},
"outputs": [],
"source": [
"import ROOT\n",
"from dask.distributed import Client, LocalCluster"
]
},
{
"cell_type": "markdown",
"id": "010094f2",
"metadata": {},
"source": [
"Import the live visualization function"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "74f43742",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:10:58.826008Z",
"iopub.status.busy": "2026-05-19T20:10:58.825695Z",
"iopub.status.idle": "2026-05-19T20:10:58.959903Z",
"shell.execute_reply": "2026-05-19T20:10:58.953560Z"
}
},
"outputs": [],
"source": [
"LiveVisualize = ROOT.RDF.Distributed.LiveVisualize"
]
},
{
"cell_type": "markdown",
"id": "fb742322",
"metadata": {},
"source": [
"Point RDataFrame calls to Dask RDataFrame object"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a95ce491",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:10:58.983550Z",
"iopub.status.busy": "2026-05-19T20:10:58.983382Z",
"iopub.status.idle": "2026-05-19T20:10:59.089585Z",
"shell.execute_reply": "2026-05-19T20:10:59.089064Z"
}
},
"outputs": [],
"source": [
"RDataFrame = ROOT.RDF.Distributed.Dask.RDataFrame"
]
},
{
"cell_type": "markdown",
"id": "8fc9cafc",
"metadata": {},
"source": [
"Function to create a Dask cluster and return the client"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5c3099d9",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:10:59.116376Z",
"iopub.status.busy": "2026-05-19T20:10:59.116190Z",
"iopub.status.idle": "2026-05-19T20:10:59.232006Z",
"shell.execute_reply": "2026-05-19T20:10:59.230954Z"
}
},
"outputs": [],
"source": [
"def create_connection():\n",
" cluster = LocalCluster(n_workers=4, threads_per_worker=1, processes=True, memory_limit=\"2GiB\")\n",
" client = Client(cluster)\n",
" return client"
]
},
{
"cell_type": "markdown",
"id": "2596ae44",
"metadata": {},
"source": [
"Function to fit a Gaussian function to the plot"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "906af3f5",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:10:59.240219Z",
"iopub.status.busy": "2026-05-19T20:10:59.240064Z",
"iopub.status.idle": "2026-05-19T20:11:10.707827Z",
"shell.execute_reply": "2026-05-19T20:11:10.682154Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/py-venv/ROOT-CI/lib64/python3.12/site-packages/distributed/node.py:188: UserWarning: Port 8787 is already in use.\n",
"Perhaps you already have a cluster running?\n",
"Hosting the HTTP server on port 35171 instead\n",
" warnings.warn(\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"
\n",
"\n",
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"def fit_gaus(plot):\n",
" plot.Fit(\"gaus\", \"Q\")\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" # Setup connection to a Dask cluster\n",
" connection = create_connection()\n",
"\n",
" # Create an RDataFrame that will use Dask as a backend for computations\n",
" num_entries = 100000000\n",
" d = RDataFrame(num_entries, executor=connection, npartitions=30)\n",
"\n",
" # Define a gaussean distribution with a variable mean\n",
" dd = d.Define(\"x\", f\"gRandom->Gaus(10*rdfentry_/{num_entries}, 2)\").Define(\n",
" \"y\", f\"gRandom->Gaus(10*rdfentry_/{num_entries}, 3)\"\n",
" )\n",
" # Create a 1D and a 2D histogram using the defined columns\n",
" h_normal_1d = dd.Histo1D((\"normal_1d\", \"1D Histogram of a Normal Distribution\", 100, -10, 20), \"x\")\n",
"\n",
" h_normal_2d = dd.Histo2D(\n",
" (\"normal_2d\", \"2D Histogram of a Normal Distribution\", 100, -15, 25, 100, -15, 25), \"x\", \"y\"\n",
" )\n",
"\n",
" # Apply LiveVisualize to the histograms.\n",
" # The `fit_gaus` function will be applied to the accumulating partial result\n",
" # of the 1D histogram. The 2D histogram will not be further modified, just drawn.\n",
" # Find more details about usage of LiveVisualize in the RDataFrame docs.\n",
" LiveVisualize({h_normal_1d: fit_gaus, h_normal_2d: None})\n",
"\n",
" # Plot the histograms side by side on a canvas\n",
" c = ROOT.TCanvas(\"distrdf003\", \"distrdf003\", 1600, 400)\n",
" c.Divide(2, 1)\n",
" c.cd(1)\n",
" h_normal_1d.Draw()\n",
" c.cd(2)\n",
" h_normal_2d.Draw()\n",
"\n",
" c.Update()"
]
},
{
"cell_type": "markdown",
"id": "6ddde52a",
"metadata": {},
"source": [
"Draw all canvases "
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "4d2e91b9",
"metadata": {
"collapsed": false,
"execution": {
"iopub.execute_input": "2026-05-19T20:11:10.721413Z",
"iopub.status.busy": "2026-05-19T20:11:10.721245Z",
"iopub.status.idle": "2026-05-19T20:11:10.855383Z",
"shell.execute_reply": "2026-05-19T20:11:10.854849Z"
}
},
"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
}