{
	int i;
	std::ifstream  finFakeAndTrue("example_RichStandard_ann_fake_and_true.txt");
	
	if(!gROOT->GetClass("TMultiLayerPerceptron"))
	    gSystem->Load("libMLP");
	
	TTree *simu = new TTree ("MonteCarlo","MontecarloData");
	Float_t x1,x2,x3,x4,x5,x6,x7,x8;


	simu->Branch("x1", &x1,"x1/F");
	simu->Branch("x2", &x2,"x2/F");
	simu->Branch("x3", &x3,"x3/F");
	simu->Branch("x4", &x4,"x4/F");
	simu->Branch("x5", &x5,"x5/F");
	simu->Branch("x6", &x6,"x6/F");
	simu->Branch("x7", &x7,"x7/F");
	simu->Branch("x8", &x8,"x8/F");
	
	Int_t maxNofFake = 3500;
	Int_t maxNofTrue = 3500;
	Int_t inputCountTrue = 0;
	Int_t inputCountFake = 0;
	
	while ( !finFakeAndTrue.eof() ){
		finFakeAndTrue >> x1  >> x2 >> x3 >> x4 >> x5 >> x6 >> x7 >> x8 ;
		if ( x8 == -1 && inputCountFake < maxNofFake){
			inputCountFake++;
			simu->Fill();
		}
		if (x8 == 1 && inputCountTrue < maxNofTrue){
			inputCountTrue++;
			simu->Fill();
		}
		if (inputCountFake >= maxNofFake&& inputCountTrue >= maxNofTrue){
			break;
		} 
	}

	TMultiLayerPerceptron network("x1,x2,x3,x4,x5,x6,x7:30:x8",simu,"Entry$+1");
	network.LoadWeights("NeuralNet_RingSelection_Weights.txt");
	//network.SetLearningMethod(network.kStochastic);
	//network.Train(500,"text,update=1");
	network.DumpWeights("NeuralNet_RingSelection_Weights.txt");
	//TH1F *h = new TH1F("Error","Error",100, 0, 1);
	
	TH1F *hANNOutputFake = new TH1F("hANNOutputFake","ANN output",100, -1.2, 1.2);
	TH1F *hANNOutputTrue = new TH1F("hANNOutputTrue","ANN optput",100, -1.2, 1.2);

	//hANNOutputTrue->SetLogx();	
	Double_t ANNCut = -.5;
	Double_t params[12];

	std::ifstream  finTest("example_RichStandard_ann_fake_and_true.txt");
	Int_t NofFakeLikeTrue = 0;
	Int_t NofTrueLikeFake = 0;
	Int_t NofTrueTest = 0;
	Int_t NofFakeTest = 0;

	while ( !finTest.eof() ){
		finTest >> x1  >> x2 >> x3 >> x4 >> x5 >> x6 >> x7 >> x8 ;
		
		if (x8 == -1)NofFakeTest++;		
		if (x8 == 1 )NofTrueTest++;
		
		params[0] =  x1;
		params[1] =  x2;
		params[2] =  x3;
		params[3] =  x4;
		params[4] =  x5;
		params[5] =  x6;
		params[6] =  x7;
		
		Double_t netEval = network.Evaluate(0,params);
		
		if (x8 == -1) hANNOutputFake->Fill(netEval);
		if (x8 == 1) hANNOutputTrue->Fill(netEval);
		
		if (netEval > ANNCut && x8 == -1) NofFakeLikeTrue++;
		if (netEval < ANNCut && x8 == 1) NofTrueLikeFake++;	
	}	
	
	cout <<"NofTrue = " <<NofTrueTest<<endl;
	cout <<"NofFake = " <<NofFakeTest<<endl;
	cout <<"Fake like True = " <<NofFakeLikeTrue<<endl;
	cout <<"True like Fake = " <<NofTrueLikeFake<<endl;
	
	hANNOutputTrue->SetLineColor(kRed);
	hANNOutputTrue->SetLineWidth(4);
	hANNOutputFake->SetLineColor(kBlue);	
	hANNOutputFake->SetLineWidth(4);	
	hANNOutputTrue->Draw();
	hANNOutputFake->Draw("Same");
	gPad->SetLogy(); 	
}