Machine Learning tutorials

Examples showing how to use Machine Learning from ROOT.

Table of contents

• Basic TMVA tutorials
  • Training
  • Applications
  • Others
• Cross validation
• New TMVA interfaces
  • RBDT
• Deep learning in TMVA
• TMVA Keras tutorials
• TMVA PyTorch tutorials
• Inference with SOFIE
  
• Data loading for training

Basic TMVA tutorials

Training

Tutorial	Description
TMVAMinimalClassification.C	Minimal self-contained example for setting up TMVA with binary classification.
TMVAMulticlass.C	Training and testing of the TMVA multiclass classification.
TMVAClassification.C	Training and testing of the TMVA classifiers.
TMVAClassificationCategory.C	Training and testing of the TMVA classifiers in categorisation mode.
TMVARegression.C	Training and testing of the TMVA classifiers.
classification.C

Applications

Tutorial	Description
TMVAMulticlassApplication.C	Using the trained multiclass classifiers within an analysis module.
TMVAClassificationApplication.C	Using the trained classifiers within an analysis module.
TMVAClassificationCategoryApplication.C	Using the trained classifiers (with categories) within an analysis module.
TMVACrossValidationApplication.C	Using TMVA for k-folds cross evaluation in application.
TMVAMulticlassApplication.C	Using trained multiclass classifiers within an analysis module.
TMVARegressionApplication.C	Using the trained regression MVAs within an analysis module.

Others

Tutorial	Description
TMVAGAexample.C	Using the genetic algorithm of TMVA.
TMVAGAexample2.C	Using the genetic algorithm of TMVA.
TMVAMultipleBackgroundExample.C	Training of signal with three different backgrounds.

Cross validation

Tutorial	Description
TMVACrossValidation.C	Using the TMVA k-folds cross evaluation.
TMVACrossValidationApplication.C	Using the TMVA k-folds cross evaluation in application.
TMVACrossValidationRegression.C	Using the TMVA k-folds cross evaluation.

New TMVA interfaces

Tutorial	Description
createData.C	Plot the variables.
tmva001_RTensor.C	Illustrate the basic features of the RTensor class, RTensor is a std::vector-like container with additional shape information.
tmva002_RDataFrameAsTensor.C	Convert the content of an RDataFrame to an RTensor object.
tmva003_RReader.C	Use modern interfaces models saved in TMVA XML files.

RBDT

Tutorial	Description
tmva100_DataPreparation.py	Prepare ROOT datasets to be nicely readable by most machine learning methods.
tmva101_Training.py	Train a machine learning model with any package reading the training data directly from ROOT files.
tmva102_Testing.py	Test a trained BDT model using the fast tree inference engine offered by TMVA and external tools such as scikit-learn.
tmva103_Application.C	Apply BDTs in C++ using the fast tree inference engine offered by TMVA.

Deep learning in TMVA

Tutorial		Description
TMVA_CNN_Classification.C	TMVA_CNN_Classification.py	TMVA Classification example using a Convolutional Neural Network.
TMVA_Higgs_Classification.C	TMVA_Higgs_Classification.py	Classification example of TMVA based on public Higgs UCI dataset.
TMVA_RNN_Classification.C	TMVA_RNN_Classification.py	TMVA Classification example using a Recurrent Neural Network.

TMVA Keras tutorials

Tutorial	Description
ApplicationClassificationKeras.py	Apply a trained model to new data.
ApplicationRegressionKeras.py	Apply a trained model to new data (regression).
ClassificationKeras.py	Classification in TMVA with neural networks trained with keras.
GenerateModel.py	Define and generate a keras model for use with TMVA.
MulticlassKeras.py	Multiclass classification in TMVA with neural networks trained with keras.
RegressionKeras.py	Regression in TMVA with neural networks trained with keras.

TMVA PyTorch tutorials

Tutorial	Description
ApplicationClassificationPyTorch.py	Apply a trained model to new data.
ApplicationRegressionPyTorch.py	Apply a trained model to new data (regression).
ClassificationPyTorch.py	Classification in TMVA with neural networks trained with PyTorch.
MulticlassPyTorch.py	Multiclass classification in TMVA with neural networks trained with PyTorch.
RegressionPyTorch.py	Regression in TMVA with neural networks trained with PyTorch.

Inference with SOFIE

Tutorial		Description
	TMVA_SOFIE_Inference.py	Using a trained model with Keras and make inference using SOFIE directly from Numpy.
TMVA_SOFIE_Keras.C		Parsing of Keras .h5 file into RModel object and further generating the .hxx header files for inference.
TMVA_SOFIE_Keras_HiggsModel.C		Run the SOFIE parser on the Keras model obtaining running TMVA_Higgs_Classification.C. You need to run that macro before this one.
	TMVA_SOFIE_Models.py	Inference with SOFIE using a set of models trained with Keras.
TMVA_SOFIE_ONNX.C		Parsing of ONNX files into RModel object and further generating the .hxx header files for inference.
TMVA_SOFIE_PyTorch.C		Parsing of PyTorch .pt file into RModel object and further generating the .hxx header files for inference.
TMVA_SOFIE_RDataFrame.C	TMVA_SOFIE_RDataFrame.py	Inference with SOFIE and RDataFrame, of a model trained with Keras.
TMVA_SOFIE_RDataFrame_JIT.C		Using a trained model with Keras and make inference using SOFIE and RDataFrame.
TMVA_SOFIE_RSofieReader.C		Using a trained model with Keras and make inference using SOFIE with the RSofieReader class.

Data loading for training

Tutorial	Description
RBatchGenerator_NumPy.py	Loading batches of events from a ROOT dataset as Python generators of numpy arrays.
RBatchGenerator_PyTorch.py	Loading batches of events from a ROOT dataset into a basic PyTorch workflow.
RBatchGenerator_TensorFlow.py	Loading batches of events from a ROOT dataset into a basic TensorFlow workflow.

Topics
	Envelope Tutorials
	TMVA Keras tutorials
	Example code which illustrates how to use keras with the python interface of TMVA.
	TMVA PyTorch tutorials
	Example code which illustrates how to use pytorch with the python interface of TMVA.

Files
file	createData.C
	Plot the variables.
file	PyTorch_Generate_CNN_Model.py
file	RBatchGenerator_filters_vectors.py
file	RBatchGenerator_NumPy.py
	Example of getting batches of events from a ROOT dataset as Python generators of numpy arrays.
file	RBatchGenerator_PyTorch.py
	Example of getting batches of events from a ROOT dataset into a basic PyTorch workflow.
file	RBatchGenerator_TensorFlow.py
	Example of getting batches of events from a ROOT dataset into a basic TensorFlow workflow.
file	tmva001_RTensor.C
	This tutorial illustrates the basic features of the RTensor class, RTensor is a std::vector-like container with additional shape information.
file	tmva002_RDataFrameAsTensor.C
	This tutorial shows how the content of an RDataFrame can be converted to an RTensor object.
file	tmva003_RReader.C
	This tutorial shows how to apply with the modern interfaces models saved in TMVA XML files.
file	tmva004_RStandardScaler.C
	This tutorial illustrates the usage of the standard scaler as preprocessing method.
file	tmva100_DataPreparation.py
	This tutorial illustrates how to prepare ROOT datasets to be nicely readable by most machine learning methods.
file	tmva101_Training.py
	This tutorial show how you can train a machine learning model with any package reading the training data directly from ROOT files.
file	tmva102_Testing.py
	This tutorial illustrates how you can test a trained BDT model using the fast tree inference engine offered by TMVA and external tools such as scikit-learn.
file	tmva103_Application.C
	This tutorial illustrates how you can conveniently apply BDTs in C++ using the fast tree inference engine offered by TMVA.
file	TMVA_CNN_Classification.C
	TMVA Classification Example Using a Convolutional Neural Network
file	TMVA_CNN_Classification.py
	TMVA Classification Example Using a Convolutional Neural Network
file	TMVA_Higgs_Classification.C
	Classification example of TMVA based on public Higgs UCI dataset
file	TMVA_Higgs_Classification.py
	Classification example of TMVA based on public Higgs UCI dataset
file	TMVA_RNN_Classification.C
	TMVA Classification Example Using a Recurrent Neural Network
file	TMVA_RNN_Classification.py
	TMVA Classification Example Using a Recurrent Neural Network
file	TMVA_SOFIE_GNN.py
file	TMVA_SOFIE_GNN_Application.C
file	TMVA_SOFIE_GNN_Parser.py
file	TMVA_SOFIE_Inference.py
	This macro provides an example of using a trained model with Keras and make inference using SOFIE directly from Numpy This macro uses as input a Keras model generated with the TMVA_Higgs_Classification.C tutorial You need to run that macro before this one.
file	TMVA_SOFIE_Keras.C
	This macro provides a simple example for the parsing of Keras .h5 file into RModel object and further generating the .hxx header files for inference.
file	TMVA_SOFIE_Keras_HiggsModel.C
	This macro run the SOFIE parser on the Keras model obtaining running TMVA_Higgs_Classification.C You need to run that macro before this one
file	TMVA_SOFIE_Models.py
	Example of inference with SOFIE using a set of models trained with Keras.
file	TMVA_SOFIE_ONNX.C
	This macro provides a simple example for the parsing of ONNX files into RModel object and further generating the .hxx header files for inference.
file	TMVA_SOFIE_PyTorch.C
	This macro provides a simple example for the parsing of PyTorch .pt file into RModel object and further generating the .hxx header files for inference.
file	TMVA_SOFIE_RDataFrame.C
	This macro provides an example of using a trained model with Keras and make inference using SOFIE and RDataFrame This macro uses as input a Keras model generated with the TMVA_Higgs_Classification.C tutorial You need to run that macro before to generate the trained Keras model Then you need to run the macro TMVA_SOFIE_Keras_HiggsModel.C to generate the corresponding header file using SOFIE.
file	TMVA_SOFIE_RDataFrame.py
	Example of inference with SOFIE and RDataFrame, of a model trained with Keras.
file	TMVA_SOFIE_RDataFrame_JIT.C
	This macro provides an example of using a trained model with Keras and make inference using SOFIE and RDataFrame This macro uses as input a Keras model generated with the TMVA_Higgs_Classification.C tutorial You need to run that macro before this one.
file	TMVA_SOFIE_RSofieReader.C
	This macro provides an example of using a trained model with Keras and make inference using SOFIE with the RSofieReader class This macro uses as input a Keras model generated with the TMVA_Higgs_Classification.C tutorial You need to run that macro before to generate the trained Keras model
file	TMVAClassification.C
	This macro provides examples for the training and testing of the TMVA classifiers.
file	TMVAClassificationApplication.C
	This macro provides a simple example on how to use the trained classifiers within an analysis module
file	TMVAClassificationCategory.C
	This macro provides examples for the training and testing of the TMVA classifiers in categorisation mode.
file	TMVAClassificationCategoryApplication.C
	This macro provides a simple example on how to use the trained classifiers (with categories) within an analysis module
file	TMVACrossValidation.C
	This macro provides an example of how to use TMVA for k-folds cross evaluation.
file	TMVACrossValidationApplication.C
	This macro provides an example of how to use TMVA for k-folds cross evaluation in application.
file	TMVACrossValidationRegression.C
	This macro provides an example of how to use TMVA for k-folds cross evaluation.
file	TMVAGAexample.C
	This executable gives an example of a very simple use of the genetic algorithm of TMVA
file	TMVAGAexample2.C
	This executable gives an example of a very simple use of the genetic algorithm of TMVA.
file	TMVAMinimalClassification.C
	Minimal self-contained example for setting up TMVA with binary classification.
file	TMVAMulticlass.C
	This macro provides a simple example for the training and testing of the TMVA multiclass classification
file	TMVAMulticlassApplication.C
	This macro provides a simple example on how to use the trained multiclass classifiers within an analysis module
file	TMVAMultipleBackgroundExample.C
	This example shows the training of signal with three different backgrounds Then in the application a tree is created with all signal and background events where the true class ID and the three classifier outputs are added finally with the application tree, the significance is maximized with the help of the TMVA genetic algorithm.
file	TMVARegression.C
	This macro provides examples for the training and testing of the TMVA classifiers.
file	TMVARegressionApplication.C
	This macro provides a simple example on how to use the trained regression MVAs within an analysis module