example_decisiontree_simple.cpp

Programa para el testeo de las funciones.Para compilar o código example_decisiontree_simple.cpp:

g++ -static -o example_decisiontree_simple example_decisiontree_simple.cpp -lpdsmlmm 

Para executar o programa:

./example_decisiontree_simple

Retornando por consola:

-------------------------
   IterationConf data    
-------------------------
    Alpha: 0.1
 MinError: 1e-07
  MaxIter: 1000
-------------------------
iter:    353 Alpha: 2.42569e-07 last_error: 9.63561e-08 
-------------------------
    Alpha: 2.42569e-07
LastError: 9.63561e-08
 LastIter: 353
-------------------------
-------------------------
   IterationConf data    
-------------------------
    Alpha: 0.1
 MinError: 1e-07
  MaxIter: 1000
-------------------------
iter:   1000 Alpha:  0.218287 last_error: 0.0393729  
-------------------------
    Alpha: 0.218287
LastError: 0.0393729
 LastIter: 1000
-------------------------
Pds::DecisionTree::Counter: 3

-----------------------------
 ClassificationMetrics data  
-----------------------------
Threshold       : 0.5
Samples         : 2000
----------------:------------
Pred.[0]/Act.[*]: 999   0
Pred.[1]/Act.[*]: 1     1000
----------------:------------
Accuracy        : 99.95%
Precision       : 99.9%
Recall          : 100%
----------------:------------
FScore          : 99.95%
-----------------------------

-----------------------------
 ClassificationMetrics data  
-----------------------------
Threshold       : 0.5
Samples         : 2000
----------------:------------
Pred.[0]/Act.[*]: 1000  0
Pred.[1]/Act.[*]: 0     1000
----------------:------------
Accuracy        : 100%
Precision       : 100%
Recall          : 100%
----------------:------------
FScore          : 100%
-----------------------------

Clasification - data

Clasification - training

Clasification - testing

Clasification - arbol

Código example_decisiontree_simple.cpp:

 
#include <iostream>
#include <Pds/Ra>
#include <Pds/Ml>
    
int main(void)
{
    Pds::ClassificationMetrics Metrics;
    Pds::Vector Yp;
    
    Pds::IterationConf Conf;
    Conf.Show=true; Conf.SetMinError(1e-07);    Conf.SetAlpha(0.1);
    
    // Load training data
    unsigned int L=1000;
    Pds::Matrix X;
    Pds::Vector Y;
    Pds::DataSet::Classification::LoadDataBand(L,X,Y);
    
    Pds::Octave::XLabel="x_1";
    Pds::Octave::YLabel="x_2";
    Pds::Octave::Plot::PointsX2DY(X,Y,"testando.m","example_decisiontree_simple_data.png");
    
    // Creando un arbol
    Pds::DecisionTree::Counter=0;
    Pds::DecisionTree Arbol(Conf,X,Y,0.8,4);
    std::cout<<"Pds::DecisionTree::Counter: "<<Pds::DecisionTree::Counter<<std::endl;
    
    // Exportando arbol en archivo en formato dot.
    Arbol.ExportDotFile("arbol.dot");
    system("dot -Tpng -o example_decisiontree_simple_arbol.png arbol.dot");
        
    // Evaluate training data
    Yp=Arbol.Evaluate(X);
    
    // Metrics of training
    Metrics = Pds::ClassificationMetrics::Calculate(0.5,Yp,Y);
    Metrics.Print("\n");
    
    Pds::Octave::Plot::PointsX2DY(X,Yp,"testando.m","example_decisiontree_simple_training.png");
    
    // Load testing data
    Pds::DataSet::Classification::LoadDataBand(L,X,Y); // Load new data
    
    // Evaluate testing data
    Yp=Arbol.Evaluate(X);
    
    // Metrics of testing
    Metrics = Pds::ClassificationMetrics::Calculate(Metrics.Threshold,Yp,Y);
    Metrics.Print("\n");
    
    Pds::Octave::Plot::PointsX2DY(X,Yp,"testando.m","example_decisiontree_simple_testing.png");
 
    return 0;
}