As input data is used a toy-MC sample consisting of two gaussian distributions.
The output file "TMVA.root" can be analysed with the use of dedicated macros (simply say: root -l <macro.C>), which can be conveniently invoked through a GUI that will appear at the end of the run of this macro. Launch the GUI via the command:
Cross evaluation is a special case of k-folds cross validation where the splitting into k folds is computed deterministically. This ensures that the a given event will always end up in the same fold.
In addition all resulting classifiers are saved and can be applied to new data using MethodCrossValidation
. One requirement for this to work is a splitting function that is evaluated for each event to determine into what fold it goes (for training/evaluation) or to what classifier (for application).
Cross evaluation uses a deterministic split to partition the data into folds called the split expression. The expression can be any valid TFormula
as long as all parts used are defined.
For each event the split expression is evaluated to a number and the event is put in the fold corresponding to that number.
The split expression has access to all spectators and variables defined in the dataloader. Additionally, the number of folds in the split can be accessed with NumFolds
(or numFolds
).
DataSetInfo : [dataset] : Added class "Regression"
: Add Tree TreeR of type Regression with 10000 events
--- TMVACrossValidationRegression: Using input file: ./files/tmva_reg_example.root
: Dataset[dataset] : Class index : 0 name : Regression
<HEADER> Factory : You are running ROOT Version: 6.26/11, Nov 16, 2022
:
: _/_/_/_/_/ _| _| _| _| _|_|
: _/ _|_| _|_| _| _| _| _|
: _/ _| _| _| _| _| _|_|_|_|
: _/ _| _| _| _| _| _|
: _/ _| _| _| _| _|
:
: ___________TMVA Version 4.2.1, Feb 5, 2015
:
: Rebuilding Dataset dataset
: Building event vectors for type 2 Regression
: Dataset[dataset] : create input formulas for tree TreeR
<HEADER> DataSetFactory : [dataset] : Number of events in input trees
:
: Number of training and testing events
: ---------------------------------------------------------------------------
: Regression -- training events : 9999
: Regression -- testing events : 1
: Regression -- training and testing events: 10000
:
<HEADER> DataSetInfo : Correlation matrix (Regression):
: ------------------------
: var1 var2
: var1: +1.000 +0.002
: var2: +0.002 +1.000
: ------------------------
<HEADER> DataSetFactory : [dataset] :
:
:
:
: ========================================
: ========================================
:
<HEADER> Factory : Booking method: BDTG_fold1
:
: the option NegWeightTreatment=InverseBoostNegWeights does not exist for BoostType=Grad
: --> change to new default NegWeightTreatment=Pray
: Regression Loss Function: Huber
: Training 500 Decision Trees ... patience please
: Elapsed time for training with 4999 events: 1.29 sec
: Dataset[dataset] : Create results for training
: Dataset[dataset] : Evaluation of BDTG_fold1 on training sample
: Dataset[dataset] : Elapsed time for evaluation of 4999 events: 0.213 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
: Creating xml weight file: dataset/weights/TMVACrossValidationRegression_BDTG_fold1.weights.xml
<HEADER> Factory : Test all methods
<HEADER> Factory : Test method: BDTG_fold1 for Regression performance
:
: Dataset[dataset] : Create results for testing
: Dataset[dataset] : Evaluation of BDTG_fold1 on testing sample
: Dataset[dataset] : Elapsed time for evaluation of 5000 events: 0.214 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
<HEADER> Factory : Evaluate all methods
: Evaluate regression method: BDTG_fold1
: TestRegression (testing)
: Calculate regression for all events
: Elapsed time for evaluation of 5000 events: 0.214 sec
: TestRegression (training)
: Calculate regression for all events
: Elapsed time for evaluation of 4999 events: 0.215 sec
:
: Evaluation results ranked by smallest RMS on test sample:
: ("Bias" quotes the mean deviation of the regression from true target.
: "MutInf" is the "Mutual Information" between regression and target.
: Indicated by "_T" are the corresponding "truncated" quantities ob-
: tained when removing events deviating more than 2sigma from average.)
: --------------------------------------------------------------------------------------------------
: --------------------------------------------------------------------------------------------------
: dataset BDTG_fold1 : 0.133 0.0851 2.22 1.67 | 3.123 3.198
: --------------------------------------------------------------------------------------------------
:
: Evaluation results ranked by smallest RMS on training sample:
: (overtraining check)
: --------------------------------------------------------------------------------------------------
: DataSet Name: MVA Method: <Bias> <Bias_T> RMS RMS_T | MutInf MutInf_T
: --------------------------------------------------------------------------------------------------
: dataset BDTG_fold1 : 0.0474 -0.00861 2.09 1.52 | 3.136 3.206
: --------------------------------------------------------------------------------------------------
:
<HEADER> Factory : Thank you for using TMVA!
: For citation information, please visit: http://tmva.sf.net/citeTMVA.html
<HEADER> Factory : Booking method: BDTG_fold2
:
: the option NegWeightTreatment=InverseBoostNegWeights does not exist for BoostType=Grad
: --> change to new default NegWeightTreatment=Pray
: Regression Loss Function: Huber
: Training 500 Decision Trees ... patience please
: Elapsed time for training with 5000 events: 1.29 sec
: Dataset[dataset] : Create results for training
: Dataset[dataset] : Evaluation of BDTG_fold2 on training sample
: Dataset[dataset] : Elapsed time for evaluation of 5000 events: 0.212 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
: Creating xml weight file: dataset/weights/TMVACrossValidationRegression_BDTG_fold2.weights.xml
<HEADER> Factory : Test all methods
<HEADER> Factory : Test method: BDTG_fold2 for Regression performance
:
: Dataset[dataset] : Create results for testing
: Dataset[dataset] : Evaluation of BDTG_fold2 on testing sample
: Dataset[dataset] : Elapsed time for evaluation of 4999 events: 0.212 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
<HEADER> Factory : Evaluate all methods
: Evaluate regression method: BDTG_fold2
: TestRegression (testing)
: Calculate regression for all events
: Elapsed time for evaluation of 4999 events: 0.211 sec
: TestRegression (training)
: Calculate regression for all events
: Elapsed time for evaluation of 5000 events: 0.211 sec
:
: Evaluation results ranked by smallest RMS on test sample:
: ("Bias" quotes the mean deviation of the regression from true target.
: "MutInf" is the "Mutual Information" between regression and target.
: Indicated by "_T" are the corresponding "truncated" quantities ob-
: tained when removing events deviating more than 2sigma from average.)
: --------------------------------------------------------------------------------------------------
: --------------------------------------------------------------------------------------------------
: dataset BDTG_fold2 : -0.0428 -0.0362 2.33 1.72 | 3.109 3.188
: --------------------------------------------------------------------------------------------------
:
: Evaluation results ranked by smallest RMS on training sample:
: (overtraining check)
: --------------------------------------------------------------------------------------------------
: DataSet Name: MVA Method: <Bias> <Bias_T> RMS RMS_T | MutInf MutInf_T
: --------------------------------------------------------------------------------------------------
: dataset BDTG_fold2 : 0.00417 0.0137 2.05 1.51 | 3.145 3.215
: --------------------------------------------------------------------------------------------------
:
<HEADER> Factory : Thank you for using TMVA!
: For citation information, please visit: http://tmva.sf.net/citeTMVA.html
<HEADER> Factory : Booking method: BDTG
:
: Reading weightfile: dataset/weights/TMVACrossValidationRegression_BDTG_fold1.weights.xml
: Reading weight file: dataset/weights/TMVACrossValidationRegression_BDTG_fold1.weights.xml
: Reading weightfile: dataset/weights/TMVACrossValidationRegression_BDTG_fold2.weights.xml
: Reading weight file: dataset/weights/TMVACrossValidationRegression_BDTG_fold2.weights.xml
:
:
: ========================================
: Folds processed for all methods, evaluating.
: ========================================
:
<HEADER> Factory : [dataset] : Create Transformation "I" with events from all classes.
:
<HEADER> : Transformation, Variable selection :
: Input : variable 'var1' <---> Output : variable 'var1'
: Input : variable 'var2' <---> Output : variable 'var2'
<HEADER> TFHandler_Factory : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 2.4948 1.4515 [ 0.00020069 5.0000 ]
: var2: 2.4837 1.4409 [ 0.00071490 5.0000 ]
: fvalue: 134.53 84.778 [ 1.6186 394.84 ]
: -----------------------------------------------------------
: Ranking input variables (method unspecific)...
<HEADER> IdTransformation : Ranking result (top variable is best ranked)
: --------------------------------------------
: Rank : Variable : |Correlation with target|
: --------------------------------------------
: 1 : var2 : 7.607e-01
: 2 : var1 : 5.995e-01
: --------------------------------------------
<HEADER> IdTransformation : Ranking result (top variable is best ranked)
: -------------------------------------
: Rank : Variable : Mutual information
: -------------------------------------
: 1 : var1 : 2.253e+00
: 2 : var2 : 2.100e+00
: -------------------------------------
<HEADER> IdTransformation : Ranking result (top variable is best ranked)
: ------------------------------------
: Rank : Variable : Correlation Ratio
: ------------------------------------
: 1 : var2 : 2.458e+00
: 2 : var1 : 2.336e+00
: ------------------------------------
<HEADER> IdTransformation : Ranking result (top variable is best ranked)
: ----------------------------------------
: Rank : Variable : Correlation Ratio (T)
: ----------------------------------------
: 1 : var1 : 5.362e-01
: 2 : var2 : 5.109e-01
: ----------------------------------------
: Elapsed time for training with 9999 events: 5.01e-06 sec
: Dataset[dataset] : Create results for training
: Dataset[dataset] : Evaluation of BDTG on training sample
: Dataset[dataset] : Elapsed time for evaluation of 9999 events: 0.374 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
: Creating xml weight file: dataset/weights/TMVACrossValidationRegression_BDTG.weights.xml
<HEADER> Factory : Test all methods
<HEADER> Factory : Test method: BDTG for Regression performance
:
: Dataset[dataset] : Create results for testing
: Dataset[dataset] : Evaluation of BDTG on testing sample
: Dataset[dataset] : Elapsed time for evaluation of 9999 events: 0.375 sec
: Create variable histograms
: Create regression target histograms
: Create regression average deviation
: Results created
<HEADER> Factory : Evaluate all methods
: Evaluate regression method: BDTG
: TestRegression (testing)
: Calculate regression for all events
: Elapsed time for evaluation of 9999 events: 0.374 sec
: TestRegression (training)
: Calculate regression for all events
: Elapsed time for evaluation of 9999 events: 0.374 sec
<HEADER> TFHandler_BDTG : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 2.4948 1.4515 [ 0.00020069 5.0000 ]
: var2: 2.4837 1.4409 [ 0.00071490 5.0000 ]
: fvalue: 134.53 84.778 [ 1.6186 394.84 ]
: -----------------------------------------------------------
:
: Evaluation results ranked by smallest RMS on test sample:
: ("Bias" quotes the mean deviation of the regression from true target.
: "MutInf" is the "Mutual Information" between regression and target.
: Indicated by "_T" are the corresponding "truncated" quantities ob-
: tained when removing events deviating more than 2sigma from average.)
: --------------------------------------------------------------------------------------------------
: --------------------------------------------------------------------------------------------------
: dataset BDTG : 0.0449 0.0259 2.28 1.70 | 3.108 3.190
: --------------------------------------------------------------------------------------------------
:
: Evaluation results ranked by smallest RMS on training sample:
: (overtraining check)
: --------------------------------------------------------------------------------------------------
: DataSet Name: MVA Method: <Bias> <Bias_T> RMS RMS_T | MutInf MutInf_T
: --------------------------------------------------------------------------------------------------
: dataset BDTG : 0.0449 0.0259 2.28 1.70 | 3.108 3.190
: --------------------------------------------------------------------------------------------------
:
<HEADER> Dataset:dataset : Created tree 'TestTree' with 9999 events
:
<HEADER> Dataset:dataset : Created tree 'TrainTree' with 9999 events
:
<HEADER> Factory : Thank you for using TMVA!
: For citation information, please visit: http://tmva.sf.net/citeTMVA.html
: Evaluation done.
==> Wrote root file: TMVARegCv.root
==> TMVACrossValidationRegression is done!
(int) 0