[ VIGRA Homepage | Function Index | Class Index | Namespaces | File List | Main Page ]
|   | VariableImportance Class Reference |  | 
Compute the variable importance. More...
#include <vigra/random_forest_3/random_forest_visitors.hxx>
 
  
 | Public Member Functions | |
| template<typename TREE , typename FEATURES , typename LABELS , typename WEIGHTS , typename SCORER , typename ITER > | |
| void | visit_after_split (TREE &tree, FEATURES &, LABELS &labels, WEIGHTS &weights, SCORER &scorer, ITER begin, ITER, ITER end) | 
| template<typename VISITORS , typename RF , typename FEATURES , typename LABELS > | |
| void | visit_after_training (VISITORS &visitors, RF &rf, const FEATURES &features, const LABELS &) | 
| template<typename RF , typename FEATURES , typename LABELS , typename WEIGHTS > | |
| void | visit_after_tree (RF &rf, const FEATURES &features, const LABELS &labels, WEIGHTS &) | 
| template<typename TREE , typename FEATURES , typename LABELS , typename WEIGHTS > | |
| void | visit_before_tree (TREE &tree, FEATURES &features, LABELS &, WEIGHTS &weights) | 
|  Public Member Functions inherited from RFVisitorBase | |
| void | activate () | 
| Activate the visitor. | |
| void | deactivate () | 
| Deactivate the visitor. | |
| bool | is_active () const | 
| Return whether the visitor is active or not. | |
| template<typename TREE , typename FEATURES , typename LABELS , typename WEIGHTS , typename SCORER , typename ITER > | |
| void | visit_after_split (TREE &, FEATURES &, LABELS &, WEIGHTS &, SCORER &, ITER, ITER, ITER) | 
| Do something after the split was made. | |
| template<typename VISITORS , typename RF , typename FEATURES , typename LABELS > | |
| void | visit_after_training (VISITORS &, RF &, const FEATURES &, const LABELS &) | 
| Do something after all trees have been learned.  More... | |
| template<typename RF , typename FEATURES , typename LABELS , typename WEIGHTS > | |
| void | visit_after_tree (RF &, FEATURES &, LABELS &, WEIGHTS &) | 
| Do something after a tree has been learned. | |
| void | visit_before_training () | 
| Do something before training starts. | |
| template<typename TREE , typename FEATURES , typename LABELS , typename WEIGHTS > | |
| void | visit_before_tree (TREE &, FEATURES &, LABELS &, WEIGHTS &) | 
| Do something before a tree has been learned.  More... | |
| Public Attributes | |
| size_t | repetition_count_ | 
| MultiArray< 2, double > | variable_importance_ | 
Compute the variable importance.
| void visit_before_tree | ( | TREE & | tree, | 
| FEATURES & | features, | ||
| LABELS & | , | ||
| WEIGHTS & | weights | ||
| ) | 
Resize the variable importance array and store in-bag / out-of-bag information.
| void visit_after_split | ( | TREE & | tree, | 
| FEATURES & | , | ||
| LABELS & | labels, | ||
| WEIGHTS & | weights, | ||
| SCORER & | scorer, | ||
| ITER | begin, | ||
| ITER | , | ||
| ITER | end | ||
| ) | 
Calculate the impurity decrease based variable importance after every split.
| void visit_after_tree | ( | RF & | rf, | 
| const FEATURES & | features, | ||
| const LABELS & | labels, | ||
| WEIGHTS & | |||
| ) | 
Compute the permutation importance.
| void visit_after_training | ( | VISITORS & | visitors, | 
| RF & | rf, | ||
| const FEATURES & | features, | ||
| const LABELS & | |||
| ) | 
Accumulate the variable importances from the single trees.
| MultiArray<2, double> variable_importance_ | 
This Array has the same entries as the R - random forest variable importance. Matrix is featureCount by (classCount +2) variable_importance_(ii,jj) is the variable importance measure of the ii-th variable according to: jj = 0 - (classCount-1) classwise permutation importance jj = rowCount(variable_importance_) -2 permutation importance jj = rowCount(variable_importance_) -1 gini decrease importance.
permutation importance: The difference between the fraction of OOB samples classified correctly before and after permuting (randomizing) the ii-th column is calculated. The ii-th column is permuted rep_cnt times.
class wise permutation importance: same as permutation importance. We only look at those OOB samples whose response corresponds to class jj.
gini decrease importance: row ii corresponds to the sum of all gini decreases induced by variable ii in each node of the random forest.
| size_t repetition_count_ | 
how often the permutation takes place
| 
© Ullrich Köthe     (ullrich.koethe@iwr.uni-heidelberg.de)  | 
html generated using doxygen and Python
 |