Please read tips for efficient and successful posting and posting code
ROOT Version: 6.21/01
Platform: Ubuntu 18.04.4 LTS
Compiler: gcc
I am using RDataframe to do some filter but since some column are purely NaN. So the codes can not run.
oid filter(){
int count_e = 0;
int count_m = 0;
ROOT::RDataFrame old("UnnormedTree","higgsino_10_eos.root");
auto cut = [&count_e, &count_m](float a1, float pt) {
if (a1 == 2 && pt < 10*1000.0 && count_e < 50000 ){
count_e +=1;
return true;
}
if (a1 == 6 && pt< 10*1000.0 && count_m < 50000){
count_m +=1;
return true;
}
return false;
};
old.Filter(cut,{"truth_type","ROC_slicing_lep_pT"}).Snapshot("UnnormedTree", "filtered_higgsino10.root");
}
It can run correctly with the a tree without NaN. But when running a file with NaN column the error shows
Error in <TRint::HandleTermInput()>: std::runtime_error caught: Unknown columns: lep_core57,lep_coreCone,lep_pu_corr20,lep_pu_corr30,lep_pu_corr40,lep_pt_corr20,lep_pt_corr30,lep_pt_corr40
We have also tried to blacklist those features.
void filter(){
int count_e = 0;
int count_m = 0;
ROOT::RDataFrame old("UnnormedTree","higgsino_10_eos.root");
// your blacklist
static const std::vector<std::string> blacklist = {"lep_core57","lep_coreCone","lep_pu_corr20","lep_pu_corr30","lep_pu_corr40","lep_pt_corr20","lep_pt_corr30","lep_pt_corr40"};
//define those problematic columns
int my_number = 42;
auto old_0 = old;
auto old_1 = old;
for(auto i =0; i < blacklist.size(); i++){
old_0 = old_1;
old_1 = old_0.Define(blacklist[i], to_string(my_number))
}
// get good_cols
TFile f = TFile("higgsino_10_eos.root");
TTree* t = (TTree*) f.Get("UnnormedTree");
TObjArray* name_array = t->GetListOfBranches();
std::vector<string> good_cols;
for(int i = 0; i < name_array->GetEntries(); ++i)
{
auto value = name_array->At(i)->GetName();
if(std::find(blacklist.begin(), blacklist.end(), value) != blacklist.end()){
good_cols.push_back(value);
}
}
auto cut = [&count_e, &count_m](float a1, float pt) {
if (a1 == 2 && pt < 10*1000.0 && count_e < 50000 ){
count_e +=1;
return true;
}
if (a1 == 6 && pt< 10*1000.0 && count_m < 50000){
count_m +=1;
return true;
}
return false;
};
old_1.Filter(cut,{"truth_type","ROC_slicing_lep_pT"}).Snapshot("UnnormedTree", "unnormed_filtered_higgsino10.root",good_cols);
}
But still we get the same error.
Thanks so much！