Changeset 7693 for trunk/MagicSoft/Mars/mranforest/MRanForest.cc

Timestamp:

05/05/06 07:46:50 (19 years ago)

Author:

tbretz

Message:

*** empty log message ***

File:

• trunk/MagicSoft/Mars/mranforest/MRanForest.cc (modified) (14 diffs)

trunk/MagicSoft/Mars/mranforest/MRanForest.cc

@@ -51 +51 @@
 #include "MParList.h"
 
+#include "MArrayI.h"
+#include "MArrayF.h"
+
 #include "MLog.h"
 #include "MLogManip.h"
@@ -301 +304 @@
 
     fHadTrue.Set(numdata);
-    fHadTrue.Reset(0);
+    fHadTrue.Reset();
 
     for (Int_t j=0;j<numdata;j++)
@@ -312 +315 @@
     // setup labels for classification/regression
     fClass.Set(numdata);
-    fClass.Reset(0);
+    fClass.Reset();
 
     if (fClassify)
@@ -320 +323 @@
     // allocating and initializing arrays
     fHadEst.Set(numdata);
-    fHadEst.Reset(0);
+    fHadEst.Reset();
 
     fNTimesOutBag.Set(numdata);
-    fNTimesOutBag.Reset(0);
+    fNTimesOutBag.Reset();
 
     fDataSort.Set(dim*numdata);
-    fDataSort.Reset(0);
+    fDataSort.Reset();
 
     fDataRang.Set(dim*numdata);
-    fDataRang.Reset(0);
+    fDataRang.Reset();
 
     Bool_t useweights = fWeight.GetSize()==numdata;
@@ -438 +441 @@
 
         if(calcResolution)
-            *fLog << "no. of tree  no. of nodes  resolution in % (from oob-data -> overest. of error)" << endl;
+            *fLog << "TreeNum BagSize NumNodes TestSize res/% (from oob-data -> overest. of error)" << endl;
         else
-            *fLog << "no. of tree  no. of nodes  rms in % (from oob-data -> overest. of error)" << endl;
+            *fLog << "TreeNum BagSize NumNodes TestSize rms/% (from oob-data -> overest. of error)" << endl;
                      //        12345678901234567890123456789012345678901234567890
     }
@@ -450 +453 @@
     // bootstrap aggregating (bagging) -> sampling with replacement:
 
-    TArrayF classpopw(nclass);
-    TArrayI jinbag(numdata); // Initialization includes filling with 0
-    TArrayF winbag(numdata); // Initialization includes filling with 0
+    MArrayF classpopw(nclass);
+    MArrayI jinbag(numdata); // Initialization includes filling with 0
+    MArrayF winbag(numdata); // Initialization includes filling with 0
 
     float square=0;
@@ -463 +466 @@
         // all events in the training sample
   
-        const Int_t k = Int_t(gRandom->Rndm()*numdata);
+        const Int_t k = gRandom->Integer(numdata);
 
         if(fClassify)
@@ -472 +475 @@
         mean  +=fHadTrue[k]*fWeight[k];
         square+=fHadTrue[k]*fHadTrue[k]*fWeight[k];
-  
-        winbag[k]+=fWeight[k];
+
+        winbag[k]+=fWeight[k]; // Increase weight if chosen more than once
         jinbag[k]=1;
-
     }
 
@@ -483 +485 @@
     // In bagging procedure ca. 2/3 of all elements in the original
     // training sample are used to build the in-bag data
-    TArrayI datsortinbag=fDataSort;
-    Int_t ninbag=0;
-
-    ModifyDataSort(datsortinbag, ninbag, jinbag);
-
-    fRanTree->GrowTree(fMatrix,fHadTrue,fClass,datsortinbag,fDataRang,classpopw,mean,square,
+    const MArrayF hadtrue(fHadTrue.GetSize(), fHadTrue.GetArray());
+    const MArrayI fclass(fClass.GetSize(), fClass.GetArray());
+    const MArrayI datarang(fDataRang.GetSize(), fDataRang.GetArray());
+
+    MArrayI datsortinbag(fDataSort.GetSize(), fDataSort.GetArray());
+
+    ModifyDataSort(datsortinbag, jinbag);
+
+    fRanTree->GrowTree(fMatrix,hadtrue,fclass,datsortinbag,datarang,classpopw,mean,square,
                        jinbag,winbag,nclass);
 
@@ -501 +506 @@
     // determined from oob-data is underestimated, but can still be taken as upper limit.
 
+    Int_t ninbag = 0;
     for (Int_t ievt=0;ievt<numdata;ievt++)
     {
         if (jinbag[ievt]>0)
+        {
+            ninbag++;
             continue;
+        }
 
         fHadEst[ievt] +=fRanTree->TreeHad((*fMatrix), ievt);
         fNTimesOutBag[ievt]++;
-
     }
 
@@ -529 +537 @@
     //-------------------------------------------------------------------
     // give running output
-    *fLog << setw(5)  << fTreeNo;
-    *fLog << setw(18) << fRanTree->GetNumEndNodes();
+    *fLog << setw(4) << fTreeNo;
+    *fLog << Form(" %8.1f", 100.*ninbag/numdata);
+    *fLog << setw(9) << fRanTree->GetNumEndNodes();
+    *fLog << Form("  %9.1f", 100.*n/numdata);
     *fLog << Form("%18.2f", ferr*100.);
     *fLog << endl;
@@ -563 +573 @@
         {
             v[n]=(*fMatrix)(n,mvar);
-            isort[n]=n;
+            //isort[n]=n;
 
             if(TMath::IsNaN(v[n]))
@@ -607 +617 @@
 }
 
-void MRanForest::ModifyDataSort(TArrayI &datsortinbag, Int_t ninbag, const TArrayI &jinbag)
+// Reoves all indices which are not in the bag from the datsortinbag
+void MRanForest::ModifyDataSort(MArrayI &datsortinbag, const MArrayI &jinbag)
 {
     const Int_t numdim=GetNumDim();
     const Int_t numdata=GetNumData();
 
-    ninbag=0;
+    Int_t ninbag=0;
     for (Int_t n=0;n<numdata;n++)
         if(jinbag[n]==1) ninbag++;
@@ -618 +629 @@
     for(Int_t m=0;m<numdim;m++)
     {
+        Int_t *subsort = &datsortinbag[m*numdata];
+
         Int_t k=0;
-        Int_t nt=0;
-        for(Int_t n=0;n<numdata;n++)
+        for(Int_t n=0;n<ninbag;n++)
         {
-            if(jinbag[datsortinbag[m*numdata+k]]==1)
+            if(jinbag[subsort[k]]==1)
             {
-                datsortinbag[m*numdata+nt]=datsortinbag[m*numdata+k];
+                subsort[n] = subsort[k];
                 k++;
             }else{
-                for(Int_t j=1;j<numdata-k;j++)
+                for(Int_t j=k+1;j<numdata;j++)
                 {
-                    if(jinbag[datsortinbag[m*numdata+k+j]]==1)
+                    if(jinbag[subsort[j]]==1)
                     {
-                        datsortinbag[m*numdata+nt]=datsortinbag[m*numdata+k+j];
-                        k+=j+1;
+                        subsort[n] = subsort[j];
+                        k = j+1;
                         break;
                     }
                 }
             }
-            nt++;
-            if(nt>=ninbag) break;
         }
     }