Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
Tools.h
Go to the documentation of this file.
1// @(#)root/tmva $Id$
2// Author: Andreas Hoecker, Joerg Stelzer, Helge Voss, Kai Voss
3
4/**********************************************************************************
5 * Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
6 * Package: TMVA *
7 * Class : Tools *
8 * Web : http://tmva.sourceforge.net *
9 * *
10 * Description: *
11 * Global auxiliary applications and data treatment routines *
12 * *
13 * Authors (alphabetical): *
14 * Andreas Hoecker <Andreas.Hocker@cern.ch> - CERN, Switzerland *
15 * Peter Speckmayer <peter.speckmayer@cern.ch> - CERN, Switzerland *
16 * Helge Voss <Helge.Voss@cern.ch> - MPI-K Heidelberg, Germany *
17 * Kai Voss <Kai.Voss@cern.ch> - U. of Victoria, Canada *
18 * *
19 * Copyright (c) 2005: *
20 * CERN, Switzerland *
21 * U. of Victoria, Canada *
22 * MPI-K Heidelberg, Germany *
23 * *
24 * Redistribution and use in source and binary forms, with or without *
25 * modification, are permitted according to the terms listed in LICENSE *
26 * (http://tmva.sourceforge.net/LICENSE) *
27 **********************************************************************************/
28
29#ifndef ROOT_TMVA_Tools
30#define ROOT_TMVA_Tools
31
32//////////////////////////////////////////////////////////////////////////
33// //
34// Tools (namespace) //
35// //
36// Global auxiliary applications and data treatment routines //
37// //
38//////////////////////////////////////////////////////////////////////////
39
40#include <vector>
41#include <string>
42#include <sstream>
43#include <iostream>
44#if __cplusplus > 199711L
45#include <atomic>
46#endif
47
48#include "TXMLEngine.h"
49
50#include "TMatrixDSymfwd.h"
51
52#include "TMatrixDfwd.h"
53
54#include "TVectorDfwd.h"
55
56#include "TMVA/Types.h"
57
59
60#include "TString.h"
61
62#include "TMVA/MsgLogger.h"
63
64class TList;
65class TTree;
66class TH1;
67class TH2;
68class TH2F;
69class TSpline;
70class TXMLEngine;
71
72namespace TMVA {
73
74 class Event;
75 class PDF;
76 class MsgLogger;
77
78 class Tools {
79
80 private:
81
82 Tools();
83
84 public:
85
86 // destructor
87 ~Tools();
88
89 // accessor to single instance
90 static Tools& Instance();
91 static void DestroyInstance();
92
93
94 template <typename T> Double_t Mean(Long64_t n, const T *a, const Double_t *w=0);
95 template <typename Iterator, typename WeightIterator> Double_t Mean ( Iterator first, Iterator last, WeightIterator w);
96
97 template <typename T> Double_t RMS(Long64_t n, const T *a, const Double_t *w=0);
98 template <typename Iterator, typename WeightIterator> Double_t RMS(Iterator first, Iterator last, WeightIterator w);
99
100
101 // simple statistics operations on tree entries
102 void ComputeStat( const std::vector<TMVA::Event*>&,
103 std::vector<Float_t>*,
105 Double_t&, Double_t&, Double_t&, Int_t signalClass,
106 Bool_t norm = kFALSE );
107
108 // compute variance from sums
109 inline Double_t ComputeVariance( Double_t sumx2, Double_t sumx, Int_t nx );
110
111 // creates histograms normalized to one
112 TH1* projNormTH1F( TTree* theTree, const TString& theVarName,
113 const TString& name, Int_t nbins,
114 Double_t xmin, Double_t xmax, const TString& cut );
115
116 // normalize histogram by its integral
117 Double_t NormHist( TH1* theHist, Double_t norm = 1.0 );
118
119 // parser for TString phrase with items separated by a character
120 TList* ParseFormatLine( TString theString, const char * sep = ":" );
121
122 // parse option string for ANN methods
123 std::vector<Int_t>* ParseANNOptionString( TString theOptions, Int_t nvar,
124 std::vector<Int_t>* nodes );
125
126 // returns the square-root of a symmetric matrix: symMat = sqrtMat*sqrtMat
128
129 // returns the covariance matrix of of the different classes (and the sum)
130 // given the event sample
131 std::vector<TMatrixDSym*>* CalcCovarianceMatrices( const std::vector<Event*>& events, Int_t maxCls, VariableTransformBase* transformBase=0 );
132 std::vector<TMatrixDSym*>* CalcCovarianceMatrices( const std::vector<const Event*>& events, Int_t maxCls, VariableTransformBase* transformBase=0 );
133
134
135 // turns covariance into correlation matrix
136 const TMatrixD* GetCorrelationMatrix( const TMatrixD* covMat );
137
138 // check spline quality by comparison with initial histogram
139 Bool_t CheckSplines( const TH1*, const TSpline* );
140
141 // normalization of variable output
143
144 // return separation of two histograms
145 Double_t GetSeparation( TH1* S, TH1* B ) const;
146 Double_t GetSeparation( const PDF& pdfS, const PDF& pdfB ) const;
147
148 // vector rescaling
149 std::vector<Double_t> MVADiff( std::vector<Double_t>&, std::vector<Double_t>& );
150 void Scale( std::vector<Double_t>&, Double_t );
151 void Scale( std::vector<Float_t>&, Float_t );
152
153 // re-arrange a vector of arrays (vectors) in a way such that the first array
154 // is ordered, and the other arrays reshuffled accordingly
155 void UsefulSortDescending( std::vector< std::vector<Double_t> >&, std::vector<TString>* vs = 0 );
156 void UsefulSortAscending ( std::vector< std::vector<Double_t> >&, std::vector<TString>* vs = 0 );
157
158 void UsefulSortDescending( std::vector<Double_t>& );
159 void UsefulSortAscending ( std::vector<Double_t>& );
160
161 Int_t GetIndexMaxElement ( std::vector<Double_t>& );
162 Int_t GetIndexMinElement ( std::vector<Double_t>& );
163
164 // check if input string contains regular expression
166 TString ReplaceRegularExpressions( const TString& s, const TString& replace = "+" );
167
168 // routines for formatted output -----------------
169 void FormattedOutput( const std::vector<Double_t>&, const std::vector<TString>&,
170 const TString titleVars, const TString titleValues, MsgLogger& logger,
171 TString format = "%+1.3f" );
172 void FormattedOutput( const TMatrixD&, const std::vector<TString>&, MsgLogger& logger );
173 void FormattedOutput( const TMatrixD&, const std::vector<TString>& vert, const std::vector<TString>& horiz,
174 MsgLogger& logger );
175
176 void WriteFloatArbitraryPrecision( Float_t val, std::ostream& os );
177 void ReadFloatArbitraryPrecision ( Float_t& val, std::istream& is );
178
179 // for histogramming
180 TString GetXTitleWithUnit( const TString& title, const TString& unit );
181 TString GetYTitleWithUnit( const TH1& h, const TString& unit, Bool_t normalised );
182
183 // Mutual Information method for non-linear correlations estimates in 2D histogram
184 // Author: Moritz Backes, Geneva (2009)
186
187 // Correlation Ratio method for non-linear correlations estimates in 2D histogram
188 // Author: Moritz Backes, Geneva (2009)
190 TH2F* TransposeHist ( const TH2F& );
191
192 // check if "silent" or "verbose" option in configuration string
193 Bool_t CheckForSilentOption ( const TString& ) const;
194 Bool_t CheckForVerboseOption( const TString& ) const;
195
196 // color information
197 const TString& Color( const TString& );
198
199 // print welcome message (to be called from, eg, .TMVAlogon)
209
210 // print TMVA citation (to be called from, eg, .TMVAlogon)
215
216 void TMVAWelcomeMessage();
218 void TMVAVersionMessage( MsgLogger& logger );
219 void ROOTVersionMessage( MsgLogger& logger );
220
221 void TMVACitation( MsgLogger& logger, ECitation citType = kPlainText );
222
223 // string tools
224
225 std::vector<TString> SplitString( const TString& theOpt, const char separator ) const;
226
227 // variables
230 MsgLogger& Log() const { return *fLogger; }
231#if __cplusplus > 199711L
232 static std::atomic<Tools*> fgTools;
233#else
234 static Tools* fgTools;
235#endif
236
237 // xml tools
238
241 void WriteTMatrixDToXML ( void* node, const char* name, TMatrixD* mat );
242 void WriteTVectorDToXML ( void* node, const char* name, TVectorD* vec );
243 void ReadTMatrixDFromXML( void* node, const char* name, TMatrixD* mat );
244 void ReadTVectorDFromXML( void* node, const char* name, TVectorD* vec );
246
247 Bool_t HasAttr ( void* node, const char* attrname );
248 template<typename T>
249 inline void ReadAttr ( void* node, const char* , T& value );
250 void ReadAttr ( void* node, const char* attrname, TString& value );
251 void ReadAttr(void *node, const char *, float &value);
252 void ReadAttr(void *node, const char *, int &value);
253 void ReadAttr(void *node, const char *, short &value);
254
255 template<typename T>
256 void AddAttr ( void* node, const char* , const T& value, Int_t precision = 16 );
257 void AddAttr ( void* node, const char* attrname, const char* value );
258 void* AddChild ( void* parent, const char* childname, const char* content = 0, bool isRootNode = false );
259 Bool_t AddRawLine ( void* node, const char * raw );
260 Bool_t AddComment ( void* node, const char* comment );
261
262 void* GetParent( void* child);
263 void* GetChild ( void* parent, const char* childname=0 );
264 void* GetNextChild( void* prevchild, const char* childname=0 );
265 const char* GetContent ( void* node );
266 const char* GetName ( void* node );
267
270 void SetXMLEngineBufferSize(int buffer) { fXMLBufferSize = buffer; }
272
274
275 private:
276
277 int fXMLBufferSize = 10000000;
278 // utilities for correlation ratio
279 Double_t GetYMean_binX( const TH2& , Int_t bin_x );
280
281 }; // Common tools
282
283 Tools& gTools(); // global accessor
284
285 //
286 // Adapts a TRandom random number generator to the interface of the ones in the
287 // standard library (STL) so that TRandom derived generators can be used with
288 // STL algorithms such as `std::shuffle`.
289 //
290 // Example:
291 // ```
292 // std::vector<double> v {0, 1, 2, 3, 4, 5};
293 // TRandom3StdEngine rng(seed);
294 // std::shuffle(v.begin(), v.end(), rng);
295 // ```
296 //
297 // Or at a lower level:
298 // ```
299 // std::vector<double> v {0, 1, 2, 3, 4, 5};
300 // RandomGenerator<TRandom3> rng(seed);
301 // std::shuffle(v.begin(), v.end(), rng);
302 // ```
303 //
304 template <typename TRandomLike, typename UIntType = UInt_t, UIntType max_val = kMaxUInt>
306 public:
307 using result_type = UIntType;
308
309 RandomGenerator(UIntType s = 0) { fRandom.SetSeed(s); }
310
311 static constexpr UIntType min() { return 0; }
312 static constexpr UIntType max() { return max_val; }
313
314 void seed(UIntType s = 0) { fRandom.SetSeed(s); }
315
316 UIntType operator()() { return fRandom.Integer(max()); }
317
318 void discard(unsigned long long z)
319 {
320 double r;
321 for (unsigned long long i = 0; i < z; ++i)
322 r = fRandom.Rndm();
323 (void) r; /* avoid unused variable warning */
324 }
325
326 private:
327 TRandomLike fRandom; // random generator
328 };
329
330} // namespace TMVA
331
332////////////////////////////////////////////////////////////////////////////////
333/// read attribute from xml
334
335template<typename T> void TMVA::Tools::ReadAttr( void* node, const char* attrname, T& value )
336{
337 // read attribute from xml
338 const char *val = xmlengine().GetAttr(node, attrname);
339 if (val == 0) {
340 const char *nodename = xmlengine().GetNodeName(node);
341 Log() << kFATAL << "Trying to read non-existing attribute '" << attrname << "' from xml node '" << nodename << "'"
342 << Endl;
343 }
344 std::stringstream s(val);
345 // coverity[tainted_data_argument]
346 s >> value;
347}
348
349////////////////////////////////////////////////////////////////////////////////
350/// add attribute to xml
351
352template<typename T>
353void TMVA::Tools::AddAttr( void* node, const char* attrname, const T& value, Int_t precision )
354{
355 std::stringstream s;
356 s.precision( precision );
357 s << std::scientific << value;
358 AddAttr( node, attrname, s.str().c_str() );
359}
360
361////////////////////////////////////////////////////////////////////////////////
362/// compute variance from given sums
363
365{
366 if (nx<2) return 0;
367 return (sumx2 - ((sumx*sumx)/static_cast<Double_t>(nx)))/static_cast<Double_t>(nx-1);
368}
369
370#endif
ROOT::R::TRInterface & r
Definition Object.C:4
#define d(i)
Definition RSha256.hxx:102
#define a(i)
Definition RSha256.hxx:99
#define h(i)
Definition RSha256.hxx:106
const Bool_t kFALSE
Definition RtypesCore.h:92
long Long_t
Definition RtypesCore.h:54
double Double_t
Definition RtypesCore.h:59
long long Long64_t
Definition RtypesCore.h:73
float Float_t
Definition RtypesCore.h:57
char name[80]
Definition TGX11.cxx:110
float xmin
float xmax
typedef void((*Func_t)())
TH1 is the base class of all histogram classes in ROOT.
Definition TH1.h:58
2-D histogram with a float per channel (see TH1 documentation)}
Definition TH2.h:251
Service class for 2-Dim histogram classes.
Definition TH2.h:30
A doubly linked list.
Definition TList.h:44
ostringstream derivative to redirect and format output
Definition MsgLogger.h:59
PDF wrapper for histograms; uses user-defined spline interpolation.
Definition PDF.h:63
UIntType operator()()
Definition Tools.h:316
void discard(unsigned long long z)
Definition Tools.h:318
TRandomLike fRandom
Definition Tools.h:327
static constexpr UIntType max()
Definition Tools.h:312
void seed(UIntType s=0)
Definition Tools.h:314
RandomGenerator(UIntType s=0)
Definition Tools.h:309
static constexpr UIntType min()
Definition Tools.h:311
UIntType result_type
Definition Tools.h:307
Global auxiliary applications and data treatment routines.
Definition Tools.h:78
void ComputeStat(const std::vector< TMVA::Event * > &, std::vector< Float_t > *, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &, Int_t signalClass, Bool_t norm=kFALSE)
sanity check
Definition Tools.cxx:214
void * GetParent(void *child)
get parent node
Definition Tools.cxx:1152
void FormattedOutput(const std::vector< Double_t > &, const std::vector< TString > &, const TString titleVars, const TString titleValues, MsgLogger &logger, TString format="%+1.3f")
formatted output of simple table
Definition Tools.cxx:899
void UsefulSortDescending(std::vector< std::vector< Double_t > > &, std::vector< TString > *vs=0)
sort 2D vector (AND in parallel a TString vector) in such a way that the "first vector is sorted" and...
Definition Tools.cxx:576
Bool_t HistoHasEquidistantBins(const TH1 &h)
Definition Tools.cxx:1499
TList * ParseFormatLine(TString theString, const char *sep=":")
Parse the string and cut into labels separated by ":".
Definition Tools.cxx:413
Double_t NormVariable(Double_t x, Double_t xmin, Double_t xmax)
normalise to output range: [-1, 1]
Definition Tools.cxx:122
void WriteFloatArbitraryPrecision(Float_t val, std::ostream &os)
writes a float value with the available precision to a stream
Definition Tools.cxx:1070
void * GetNextChild(void *prevchild, const char *childname=0)
XML helpers.
Definition Tools.cxx:1174
TString GetYTitleWithUnit(const TH1 &h, const TString &unit, Bool_t normalised)
histogramming utility
Definition Tools.cxx:1060
Double_t GetSeparation(TH1 *S, TH1 *B) const
compute "separation" defined as
Definition Tools.cxx:133
static Tools & Instance()
Definition Tools.cxx:75
TMatrixD * GetSQRootMatrix(TMatrixDSym *symMat)
square-root of symmetric matrix of course the resulting sqrtMat is also symmetric,...
Definition Tools.cxx:283
std::vector< Double_t > MVADiff(std::vector< Double_t > &, std::vector< Double_t > &)
computes difference between two vectors
Definition Tools.cxx:518
Int_t GetIndexMinElement(std::vector< Double_t > &)
find index of minimum entry in vector
Definition Tools.cxx:777
TH1 * projNormTH1F(TTree *theTree, const TString &theVarName, const TString &name, Int_t nbins, Double_t xmin, Double_t xmax, const TString &cut)
projects variable from tree into normalised histogram
Definition Tools.cxx:378
void ROOTVersionMessage(MsgLogger &logger)
prints the ROOT release number and date
Definition Tools.cxx:1337
TString ReplaceRegularExpressions(const TString &s, const TString &replace="+")
replace regular expressions helper function to remove all occurrences "$!%^&()'<>?...
Definition Tools.cxx:810
void * AddChild(void *parent, const char *childname, const char *content=0, bool isRootNode=false)
add child node
Definition Tools.cxx:1136
void ReadTVectorDFromXML(void *node, const char *name, TVectorD *vec)
Definition Tools.cxx:1279
TH1 * GetCumulativeDist(TH1 *h)
get the cumulative distribution of a histogram
Definition Tools.cxx:1772
void ReadFloatArbitraryPrecision(Float_t &val, std::istream &is)
reads a float value with the available precision from a stream
Definition Tools.cxx:1085
Bool_t AddRawLine(void *node, const char *raw)
XML helpers.
Definition Tools.cxx:1202
~Tools()
destructor
Definition Tools.cxx:113
Bool_t ContainsRegularExpression(const TString &s)
check if regular expression helper function to search for "$!%^&()'<>?= " in a string
Definition Tools.cxx:796
static void DestroyInstance()
Definition Tools.cxx:90
Double_t Mean(Long64_t n, const T *a, const Double_t *w=0)
Return the weighted mean of an array a with length n.
Definition Tools.cxx:1703
Double_t GetMutualInformation(const TH2F &)
Mutual Information method for non-linear correlations estimates in 2D histogram Author: Moritz Backes...
Definition Tools.cxx:601
std::vector< TString > SplitString(const TString &theOpt, const char separator) const
splits the option string at 'separator' and fills the list 'splitV' with the primitive strings
Definition Tools.cxx:1211
MsgLogger & Log() const
Definition Tools.h:230
const TString & Color(const TString &)
human readable color strings
Definition Tools.cxx:840
TString StringFromDouble(Double_t d)
string tools
Definition Tools.cxx:1245
int xmlenginebuffersize()
Definition Tools.h:269
Bool_t CheckForVerboseOption(const TString &) const
check if verbosity "V" set in option
Definition Tools.cxx:720
Double_t RMS(Long64_t n, const T *a, const Double_t *w=0)
Return the Standard Deviation of an array a with length n.
Definition Tools.cxx:1759
const char * GetContent(void *node)
XML helpers.
Definition Tools.cxx:1186
void * GetChild(void *parent, const char *childname=0)
get child node
Definition Tools.cxx:1162
void WriteTVectorDToXML(void *node, const char *name, TVectorD *vec)
Definition Tools.cxx:1271
Double_t ComputeVariance(Double_t sumx2, Double_t sumx, Int_t nx)
compute variance from given sums
Definition Tools.h:364
TXMLEngine & xmlengine()
Definition Tools.h:268
TXMLEngine * fXMLEngine
Definition Tools.h:271
void Scale(std::vector< Double_t > &, Double_t)
scales double vector
Definition Tools.cxx:531
Bool_t CheckSplines(const TH1 *, const TSpline *)
check quality of splining by comparing splines and histograms in each bin
Definition Tools.cxx:491
const char * GetName(void *node)
XML helpers.
Definition Tools.cxx:1194
const TMatrixD * GetCorrelationMatrix(const TMatrixD *covMat)
turns covariance into correlation matrix
Definition Tools.cxx:336
void WriteTMatrixDToXML(void *node, const char *name, TMatrixD *mat)
XML helpers.
Definition Tools.cxx:1255
MsgLogger * fLogger
Definition Tools.h:229
Double_t GetCorrelationRatio(const TH2F &)
Compute Correlation Ratio of 2D histogram to estimate functional dependency between two variables Aut...
Definition Tools.cxx:632
void ReadAttr(void *node, const char *, T &value)
read attribute from xml
Definition Tools.h:335
Bool_t AddComment(void *node, const char *comment)
Definition Tools.cxx:1144
void ReadTMatrixDFromXML(void *node, const char *name, TMatrixD *mat)
Definition Tools.cxx:1288
TString GetXTitleWithUnit(const TString &title, const TString &unit)
histogramming utility
Definition Tools.cxx:1052
void AddAttr(void *node, const char *, const T &value, Int_t precision=16)
add attribute to xml
Definition Tools.h:353
@ kHtmlLink
Definition Tools.h:214
@ kPlainText
Definition Tools.h:211
TString StringFromInt(Long_t i)
string tools
Definition Tools.cxx:1235
int fXMLBufferSize
Definition Tools.h:277
Tools()
constructor
Definition Tools.cxx:103
Double_t NormHist(TH1 *theHist, Double_t norm=1.0)
normalises histogram
Definition Tools.cxx:395
std::vector< TMatrixDSym * > * CalcCovarianceMatrices(const std::vector< Event * > &events, Int_t maxCls, VariableTransformBase *transformBase=0)
compute covariance matrices
Definition Tools.cxx:1526
Double_t GetYMean_binX(const TH2 &, Int_t bin_x)
Compute the mean in Y for a given bin X of a 2D histogram.
Definition Tools.cxx:654
void TMVACitation(MsgLogger &logger, ECitation citType=kPlainText)
kinds of TMVA citation
Definition Tools.cxx:1453
void TMVAVersionMessage(MsgLogger &logger)
prints the TMVA release number and date
Definition Tools.cxx:1328
void TMVAWelcomeMessage()
direct output, eg, when starting ROOT session -> no use of Logger here
Definition Tools.cxx:1314
std::vector< Int_t > * ParseANNOptionString(TString theOptions, Int_t nvar, std::vector< Int_t > *nodes)
parse option string for ANN methods default settings (should be defined in theOption string)
Definition Tools.cxx:455
Int_t GetIndexMaxElement(std::vector< Double_t > &)
find index of maximum entry in vector
Definition Tools.cxx:760
void SetXMLEngineBufferSize(int buffer)
Definition Tools.h:270
TH2F * TransposeHist(const TH2F &)
Transpose quadratic histogram.
Definition Tools.cxx:669
static Tools * fgTools
Definition Tools.h:234
EWelcomeMessage
Definition Tools.h:200
@ kSmall1WelcomeMsg
Definition Tools.h:205
@ kSmall2WelcomeMsg
Definition Tools.h:206
@ kLogoWelcomeMsg
Definition Tools.h:204
@ kOriginalWelcomeMsgColor
Definition Tools.h:207
@ kOriginalWelcomeMsgBW
Definition Tools.h:208
@ kBlockWelcomeMsg
Definition Tools.h:202
@ kStandardWelcomeMsg
Definition Tools.h:200
@ kIsometricWelcomeMsg
Definition Tools.h:201
@ kLeanWelcomeMsg
Definition Tools.h:203
Bool_t HasAttr(void *node, const char *attrname)
add attribute from xml
Definition Tools.cxx:1106
void UsefulSortAscending(std::vector< std::vector< Double_t > > &, std::vector< TString > *vs=0)
sort 2D vector (AND in parallel a TString vector) in such a way that the "first vector is sorted" and...
Definition Tools.cxx:550
const TString fRegexp
Definition Tools.h:228
Bool_t CheckForSilentOption(const TString &) const
check for "silence" option in configuration option string
Definition Tools.cxx:703
Linear interpolation class.
Base class for spline implementation containing the Draw/Paint methods.
Definition TSpline.h:31
Basic string class.
Definition TString.h:136
A TTree represents a columnar dataset.
Definition TTree.h:79
const char * GetNodeName(XMLNodePointer_t xmlnode)
returns name of xmlnode
const char * GetAttr(XMLNodePointer_t xmlnode, const char *name)
returns value of attribute for xmlnode
Double_t x[n]
Definition legend1.C:17
const Int_t n
Definition legend1.C:16
create variable transformations
Tools & gTools()
MsgLogger & Endl(MsgLogger &ml)
Definition MsgLogger.h:158
Definition first.py:1
auto * m
Definition textangle.C:8