Definition at line 103 of file ModulekNN.h.
|
void | ComputeMetric (UInt_t ifrac) |
| compute scale factor for each variable (dimension) so that distance is computed uniformly along each dimension compute width of interval that includes (100 - 2*ifrac)% of events below, assume that in fVar each vector of values is sorted
|
|
MsgLogger & | Log () const |
| message logger
|
|
Node< Event > * | Optimize (UInt_t optimize_depth) |
| Optimize() balances binary tree for first odepth levels for each depth we split sorted depth % dimension variables into \( 2^{odepth} \) parts.
|
|
const Event | Scale (const Event &event) const |
| scale each event variable so that rms of variables is approximately 1.0 this allows comparisons of variables with distinct scales and units
|
|
#include <TMVA/ModulekNN.h>
◆ VarMap
◆ ModulekNN()
TMVA::kNN::ModulekNN::ModulekNN |
( |
| ) |
|
◆ ~ModulekNN()
TMVA::kNN::ModulekNN::~ModulekNN |
( |
| ) |
|
◆ Add()
void TMVA::kNN::ModulekNN::Add |
( |
const Event & |
event | ) |
|
◆ Clear()
void TMVA::kNN::ModulekNN::Clear |
( |
| ) |
|
◆ ComputeMetric()
void TMVA::kNN::ModulekNN::ComputeMetric |
( |
UInt_t |
ifrac | ) |
|
|
private |
compute scale factor for each variable (dimension) so that distance is computed uniformly along each dimension compute width of interval that includes (100 - 2*ifrac)% of events below, assume that in fVar each vector of values is sorted
Definition at line 542 of file ModulekNN.cxx.
◆ Fill()
Bool_t TMVA::kNN::ModulekNN::Fill |
( |
const UShort_t |
odepth, |
|
|
UInt_t |
ifrac, |
|
|
const std::string & |
option = "" |
|
) |
| |
◆ Find() [1/2]
Bool_t TMVA::kNN::ModulekNN::Find |
( |
Event |
event, |
|
|
UInt_t |
nfind = 100 , |
|
|
const std::string & |
option = "count" |
|
) |
| const |
find in tree if tree has been filled then search for nfind closest events if metic (fVarScale map) is computed then rescale event variables using previously computed width of variable distribution
Definition at line 348 of file ModulekNN.cxx.
◆ Find() [2/2]
Bool_t TMVA::kNN::ModulekNN::Find |
( |
UInt_t |
nfind, |
|
|
const std::string & |
option |
|
) |
| const |
◆ GetEventVec()
const EventVec & TMVA::kNN::ModulekNN::GetEventVec |
( |
| ) |
const |
|
inline |
◆ GetkNNEvent()
const Event & TMVA::kNN::ModulekNN::GetkNNEvent |
( |
| ) |
const |
|
inline |
◆ GetkNNList()
const List & TMVA::kNN::ModulekNN::GetkNNList |
( |
| ) |
const |
|
inline |
◆ GetMetric()
const std::map< Int_t, Double_t > & TMVA::kNN::ModulekNN::GetMetric |
( |
| ) |
const |
|
inline |
◆ GetRndmThreadLocal()
static TRandom3 & TMVA::kNN::ModulekNN::GetRndmThreadLocal |
( |
| ) |
|
|
inlinestaticprivate |
◆ GetVarMap()
◆ Log()
MsgLogger & TMVA::kNN::ModulekNN::Log |
( |
| ) |
const |
|
inlineprivate |
◆ Optimize()
Optimize() balances binary tree for first odepth levels for each depth we split sorted depth % dimension variables into \( 2^{odepth} \) parts.
Definition at line 449 of file ModulekNN.cxx.
◆ Print() [1/2]
void TMVA::kNN::ModulekNN::Print |
( |
| ) |
const |
◆ Print() [2/2]
void TMVA::kNN::ModulekNN::Print |
( |
std::ostream & |
os | ) |
const |
◆ Scale()
scale each event variable so that rms of variables is approximately 1.0 this allows comparisons of variables with distinct scales and units
Definition at line 628 of file ModulekNN.cxx.
◆ fCount
◆ fDimn
UInt_t TMVA::kNN::ModulekNN::fDimn |
|
private |
◆ fEvent
EventVec TMVA::kNN::ModulekNN::fEvent |
|
private |
◆ fkNNEvent
Event TMVA::kNN::ModulekNN::fkNNEvent |
|
mutableprivate |
◆ fkNNList
List TMVA::kNN::ModulekNN::fkNNList |
|
mutableprivate |
◆ fLogger
◆ fTree
◆ fVar
VarMap TMVA::kNN::ModulekNN::fVar |
|
private |
◆ fVarScale
The documentation for this class was generated from the following files: