example_logisticregression_ce.cpp

 
#include <iostream>
#include <Pds/Ra>
#include <Pds/Ml>
        
int main(void)
{
    Pds::IterationConf Conf;    Conf.Show=true; Conf.SetMinError(1e-07);
    Pds::Vector Yp;
    Pds::ClassificationMetrics Metrics;
        
    // Generating data
    unsigned int L=100000;
    Pds::Matrix X;
    Pds::Vector Y;
    Pds::DataSet::Classification::LoadDataLine(L,X,Y);
    Pds::Vector W(X.Ncol()+1);
    
    // Split data set in {Training,Cross-validation,Test}
    Pds::DataSetBlock Dat=Pds::DataSet::Split(X,Y,6,2,2);
    
    // Create W using training data
    W.Fill(0.1);    Conf.SetAlpha(0.1);
    Pds::Ra::Tic();
    W=Pds::LogisticModel::FittingGradientCrossEntropy(Conf,Dat.Xtr,Dat.Ytr,W);
    W.T().Print("W:\n");
    Pds::Ra::Toc();
    
    // Testing W with testing data set
    Yp=Pds::LogisticModel::Classify(W,Dat.Xcv);
    
    // Metrics  
    Metrics = Pds::ClassificationMetrics::Optimal(Yp,Dat.Ycv);
    Metrics.Print("\n");
    
    // Testing W with testing data set
    Yp=Pds::LogisticModel::Classify(W,Dat.Xtt);
    
    Metrics = Pds::ClassificationMetrics::Calculate(Metrics.Threshold,Yp,Dat.Ytt);
    Metrics.Print("\n");
    
    return 0;
}