mlpack
Functions
lars_test.cpp File Reference
#include <mlpack/methods/lars/lars.hpp>
#include <mlpack/core/data/load.hpp>
#include "catch.hpp"
#include "test_catch_tools.hpp"
Include dependency graph for lars_test.cpp:

Functions

void GenerateProblem (arma::mat &X, arma::rowvec &y, size_t nPoints, size_t nDims)
 
void LARSVerifyCorrectness (arma::vec beta, arma::vec errCorr, double lambda)
 
void LassoTest (size_t nPoints, size_t nDims, bool elasticNet, bool useCholesky)
 
 TEST_CASE ("LARSTestLassoCholesky", "[LARSTest]")
 
 TEST_CASE ("LARSTestLassoGram", "[LARSTest]")
 
 TEST_CASE ("LARSTestElasticNetCholesky", "[LARSTest]")
 
 TEST_CASE ("LARSTestElasticNetGram", "[LARSTest]")
 
 TEST_CASE ("CholeskySingularityTest", "[LARSTest]")
 
 TEST_CASE ("NoCholeskySingularityTest", "[LARSTest]")
 
 TEST_CASE ("PredictTest", "[LARSTest]")
 
 TEST_CASE ("PredictRowMajorTest", "[LARSTest]")
 
 TEST_CASE ("LARSRetrainTest", "[LARSTest]")
 Make sure that if we train twice, there is no issue.
 
 TEST_CASE ("RetrainCholeskyTest", "[LARSTest]")
 Make sure if we train twice using the Cholesky decomposition, there is no issue.
 
 TEST_CASE ("TrainingAndAccessingBetaTest", "[LARSTest]")
 Make sure that we get correct solution coefficients when running training and accessing solution coefficients separately.
 
 TEST_CASE ("TrainingConstructorWithDefaultsTest", "[LARSTest]")
 Make sure that we learn the same when running training separately and through constructor. More...
 
 TEST_CASE ("TrainingConstructorWithNonDefaultsTest", "[LARSTest]")
 Make sure that we learn the same when running training separately and through constructor. More...
 
 TEST_CASE ("LARSTrainReturnCorrelation", "[LARSTest]")
 Test that LARS::Train() returns finite error value.
 
 TEST_CASE ("LARSTestComputeError", "[LARSTest]")
 Test that LARS::ComputeError() returns error value less than 1 and greater than 0.
 
 TEST_CASE ("LARSCopyConstructorTest", "[LARSTest]")
 Simple test for LARS copy constructor.
 

Detailed Description

Author
Nishant Mehta

Test for LARS.

mlpack is free software; you may redistribute it and/or modify it under the terms of the 3-clause BSD license. You should have received a copy of the 3-clause BSD license along with mlpack. If not, see http://www.opensource.org/licenses/BSD-3-Clause for more information.

Function Documentation

◆ TEST_CASE() [1/2]

TEST_CASE ( "TrainingConstructorWithDefaultsTest"  ,
""  [LARSTest] 
)

Make sure that we learn the same when running training separately and through constructor.

Test it with default parameters.

◆ TEST_CASE() [2/2]

TEST_CASE ( "TrainingConstructorWithNonDefaultsTest"  ,
""  [LARSTest] 
)

Make sure that we learn the same when running training separately and through constructor.

Test it with non default parameters.