SG++-Doxygen-Documentation
sgpp::datadriven::SparseGridMiner Class Referenceabstract

SparseGridMiner models the entire mining process for data mining with sparse grids. More...

#include <SparseGridMiner.hpp>

Inheritance diagram for sgpp::datadriven::SparseGridMiner:
sgpp::datadriven::SparseGridMinerCrossValidation sgpp::datadriven::SparseGridMinerSplitting

Public Member Functions

ModelFittingBasegetModel ()
 Returns the trained model. More...
 
virtual double learn (bool verbose)=0
 Perform Learning cycle: Get samples from data source and based on the scoring procedure, generalize data by fitting and asses quality of the fit. More...
 
SparseGridMineroperator= (SparseGridMiner &&rhs)=default
 Default Move assign operator. More...
 
SparseGridMineroperator= (const SparseGridMiner &rhs)=delete
 Default copy assign operator deleted because not all members can be copied. More...
 
void setModel (ModelFittingBase *model)
 
 SparseGridMiner (ModelFittingBase *fitter, Scorer *scorer)
 Constructor. More...
 
 SparseGridMiner (const SparseGridMiner &rhs)=delete
 Copy constructor deleted - not all members can be copied or cloned . More...
 
 SparseGridMiner (SparseGridMiner &&rhs)=default
 Default Move constructor . More...
 
double test (Dataset &testDataset)
 Evaluate the model on a certain test dataset. More...
 
virtual ~SparseGridMiner ()=default
 Default destructor. More...
 

Protected Attributes

std::unique_ptr< ModelFittingBasefitter
 Fitter that trains a model based on data samples. More...
 
std::unique_ptr< Scorerscorer
 Scorer that quantifies the quality of a fit. More...
 

Detailed Description

SparseGridMiner models the entire mining process for data mining with sparse grids.

It aggregates and automates data input, fitting and validation modules and controlls the mining process.

Constructor & Destructor Documentation

sgpp::datadriven::SparseGridMiner::SparseGridMiner ( ModelFittingBase fitter,
Scorer scorer 
)

Constructor.

Parameters
fitterconfigured instance of fitter object that generalize the model. The miner instance will take ownership of the passed object.
scorerconfigured instance of scorer object that will assess the quality of the generalization provided by the fitter on testing data. The miner instance will take ownership of the passed object.
sgpp::datadriven::SparseGridMiner::SparseGridMiner ( const SparseGridMiner rhs)
delete

Copy constructor deleted - not all members can be copied or cloned .

Parameters
rhsthe object to copy from
sgpp::datadriven::SparseGridMiner::SparseGridMiner ( SparseGridMiner &&  rhs)
default

Default Move constructor .

Parameters
rhsthe object to move from
virtual sgpp::datadriven::SparseGridMiner::~SparseGridMiner ( )
virtualdefault

Default destructor.

Member Function Documentation

ModelFittingBase * sgpp::datadriven::SparseGridMiner::getModel ( )

Returns the trained model.

Returns
the trained model
virtual double sgpp::datadriven::SparseGridMiner::learn ( bool  verbose)
pure virtual

Perform Learning cycle: Get samples from data source and based on the scoring procedure, generalize data by fitting and asses quality of the fit.

Implemented in sgpp::datadriven::SparseGridMinerCrossValidation, and sgpp::datadriven::SparseGridMinerSplitting.

SparseGridMiner& sgpp::datadriven::SparseGridMiner::operator= ( SparseGridMiner &&  rhs)
default

Default Move assign operator.

Parameters
rhsthe object to move from
SparseGridMiner& sgpp::datadriven::SparseGridMiner::operator= ( const SparseGridMiner rhs)
delete

Default copy assign operator deleted because not all members can be copied.

Parameters
rhsthe object to copy from
void sgpp::datadriven::SparseGridMiner::setModel ( ModelFittingBase model)

References fitter.

double sgpp::datadriven::SparseGridMiner::test ( Dataset testDataset)

Evaluate the model on a certain test dataset.

Parameters
testDatasetdataset used quantify accuracy using sgpp::datadriven::Metric.
Returns
score of the fit.

References fitter, and scorer.

Member Data Documentation

std::unique_ptr<ModelFittingBase> sgpp::datadriven::SparseGridMiner::fitter
protected
std::unique_ptr<Scorer> sgpp::datadriven::SparseGridMiner::scorer
protected

Scorer that quantifies the quality of a fit.

(e.g. cross validation or training with testing)

Referenced by sgpp::datadriven::SparseGridMinerCrossValidation::learn(), sgpp::datadriven::SparseGridMinerSplitting::learn(), and test().


The documentation for this class was generated from the following files: