Code review of AE inclusion

Author: INFNuser

PWGHF/Core/HfAeToMseXicToPKPi.h

@@ -1,3 +1,14 @@
+// Copyright 2020-2022 CERN and copyright holders of ALICE O2.
+// See https://alice-o2.web.cern.ch/copyright for details of the copyright holders.
+// All rights not expressly granted are reserved.
+//
+// This software is distributed under the terms of the GNU General Public
+// License v3 (GPL Version 3), copied verbatim in the file "COPYING".
+//
+// In applying this license CERN does not waive the privileges and immunities
+// granted to it by virtue of its status as an Intergovernmental Organization
+// or submit itself to any jurisdiction.
+
 /// \file HfAeToMseXicToPKPi.h
 /// \brief Class to compute the mse for the Autoencoder for Xic+ → p K- π+ analysis selections
 /// \author Maria Teresa Camerlingo
@@ -13,13 +24,13 @@ namespace o2::analysis
 	template <typename TypeOutputScore = float>
 	class HfAeToMseXicToPKPi : public HfMlResponse<TypeOutputScore>
 	{
-	  public:
+		public:
 		/// Default constructor
-  		HfAeToMseXicToPKPi() = default;
-  		/// Default destructor
-  		virtual ~HfAeToMseXicToPKPi() = default;
-  		
-  		std::vector<float> yScaled, yOutRescaled;
+		HfAeToMseXicToPKPi() = default;
+		/// Default destructor
+		virtual ~HfAeToMseXicToPKPi() = default;
+		
+		std::vector<float> yScaled, yOutRescaled;
 		//private :
 		void setMinMaxScaling(std::vector<float>& yOut, std::vector<float> yIn, std::vector<float> scaleMin, std::vector<float> scaleMax)
 		{	yOut.clear();//initial clear to avoid multiple filling if setMinMax o setScaling are called more than once				
@@ -88,7 +99,7 @@ namespace o2::analysis
 				  }
 				  else{//MSE    
 						for (size_t j = 0; j < yPred.size(); ++j) { //for over the features 
-								sum += pow(((yTrueScaled).at(j) - (yPred).at(j)), 2); //has dimensions
+								sum += std::pow(((yTrueScaled).at(j) - (yPred).at(j)), 2); //has dimensions
 								LOG(debug)<<"getMse Local feature = "<<j<<" ----> input = "<<yTrueScaled.at(j)<<" AE prediction = "<< yPred.at(j);           
 						}
 						mse = sum/yPred.size(); //MSE of a candidate 

PWGHF/TableProducer/candidateSelectorXicToPKPi.cxx

@@ -87,8 +87,8 @@ struct HfCandidateSelectorXicToPKPi {
   Configurable<bool> applyMSE{"applyMSE", false, "Flag to calculate MSE for autoencoders"};
   Configurable<bool> applyMinMax{"applyMinMax", false, "Flag to MinMax feature preprocessing"};
   /// Parameter vectors for feature preprocessing - external scaling
-  Configurable<std::vector<float>> ScaleMin{"ScaleMin", {0.,0.,0.}, "vector of scaling parameter min"};  
-  Configurable<std::vector<float>> ScaleMax{"ScaleMax", {1.,1.,1.}, "vector of scaling parameter max"};
+  Configurable<std::vector<float>> scaleMin{"scaleMin", {0.,0.,0.}, "vector of scaling parameter min"};  
+  Configurable<std::vector<float>> scaleMax{"scaleMax", {1.,1.,1.}, "vector of scaling parameter max"};
   // CCDB configuration
   Configurable<std::string> ccdbUrl{"ccdbUrl", "http://alice-ccdb.cern.ch", "url of the ccdb repository"};
   Configurable<std::vector<std::string>> modelPathsCCDB{"modelPathsCCDB", std::vector<std::string>{"EventFiltering/PWGHF/BDTXic"}, "Paths of models on CCDB"};
@@ -414,25 +414,25 @@ struct HfCandidateSelectorXicToPKPi {
           isSelectedMlXicToPKPi = hfMlResponse.isSelectedMl(inputFeaturesXicToPKPi, ptCand, outputMlXicToPKPi);
           if(applyMSE){ 
 						/// fill outputAeXicToPKPi with rescaled AE output since ML output is automatically scaled
-          	hfAeResponse.unsetScaling(applyMSE, scaleType, outputMlXicToPKPi, ScaleMin, ScaleMax);      	       	
+          	hfAeResponse.unsetScaling(applyMSE, scaleType, outputMlXicToPKPi, scaleMin, scaleMax);      	       	
           	outputAeXicToPKPi = hfAeResponse.getPostprocessedOutput(); 
           	/// fill outputMSEXicToPKPi vector with MSE
-          	hfAeResponse.setScaling(applyMSE, scaleType, inputFeaturesXicToPKPi, ScaleMin, ScaleMax);         	
-          	float MsePKPi = hfAeResponse.getMse(inputFeaturesXicToPKPi, outputMlXicToPKPi); /// args are not-scaled input, automatically scaled ML output 
-          	outputMseXicToPKPi.push_back(MsePKPi);          	
+          	hfAeResponse.setScaling(applyMSE, scaleType, inputFeaturesXicToPKPi, scaleMin, scaleMax);         	
+          	float msePKPi = hfAeResponse.getMse(inputFeaturesXicToPKPi, outputMlXicToPKPi); /// args are not-scaled input, automatically scaled ML output 
+          	outputMseXicToPKPi.push_back(msePKPi);          	
           }
         }
         if (topolXicToPiKP && pidXicToPiKP) {
           std::vector<float> inputFeaturesXicToPiKP = hfMlResponse.getInputFeatures(candidate, false);
           isSelectedMlXicToPiKP = hfMlResponse.isSelectedMl(inputFeaturesXicToPiKP, ptCand, outputMlXicToPiKP);
 					if(applyMSE){ 
 						/// fill outputAeXicToPiKP with rescaled AE output since ML output is automatically scaled
-          	hfAeResponse.unsetScaling(applyMSE, scaleType, outputMlXicToPiKP, ScaleMin, ScaleMax); 
+          	hfAeResponse.unsetScaling(applyMSE, scaleType, outputMlXicToPiKP, scaleMin, scaleMax); 
           	outputAeXicToPiKP = hfAeResponse.getPostprocessedOutput();
           	/// fill outputMSEXicToPiKP vector with MSE	
-          	hfAeResponse.setScaling(applyMSE, scaleType, inputFeaturesXicToPiKP, ScaleMin, ScaleMax); 
-          	float MsePiKP = hfAeResponse.getMse(inputFeaturesXicToPiKP, outputMlXicToPiKP); /// args are not-scaled input, automatically scaled ML output 
-          	outputMseXicToPiKP.push_back(MsePiKP);	          	
+          	hfAeResponse.setScaling(applyMSE, scaleType, inputFeaturesXicToPiKP, scaleMin, scaleMax); 
+          	float msePiKP = hfAeResponse.getMse(inputFeaturesXicToPiKP, outputMlXicToPiKP); /// args are not-scaled input, automatically scaled ML output 
+          	outputMseXicToPiKP.push_back(msePiKP);	          	
           }
         }