[RDF] Adding interfaces to HistoNSparseD

Author: Petr Jacka

tree/dataframe/inc/ROOT/RDF/HistoModels.hxx

@@ -22,7 +22,8 @@ class THnT;
 using THnD = THnT<double>;
 template <typename T>
 class THnSparseT;
-using THnSparseD = THnSparseT<double>;
+class TArrayD;
+using THnSparseD = THnSparseT<TArrayD>;
 class TProfile;
 class TProfile2D;
 

tree/dataframe/inc/ROOT/RDF/InterfaceUtils.hxx

@@ -89,6 +89,7 @@ struct Histo1D{};
 struct Histo2D{};
 struct Histo3D{};
 struct HistoND{};
+struct HistoNSparseD{};
 struct Graph{};
 struct GraphAsymmErrors{};
 struct Profile1D{};
@@ -121,7 +122,7 @@ struct HistoUtils<T, false> {
    static bool HasAxisLimits(T &) { return true; }
 };
 
-// Generic filling (covers Histo2D, HistoND, Profile1D and Profile2D actions, with and without weights)
+// Generic filling (covers Histo2D, HistoND, HistoNSparseD, Profile1D and Profile2D actions, with and without weights)
 template <typename... ColTypes, typename ActionTag, typename ActionResultType, typename PrevNodeType>
 std::unique_ptr<RActionBase>
 BuildAction(const ColumnNames_t &bl, const std::shared_ptr<ActionResultType> &h, const unsigned int nSlots,

tree/dataframe/inc/ROOT/RDF/RInterface.hxx

@@ -40,6 +40,7 @@
 #include "TH2.h" // For Histo actions
 #include "TH3.h" // For Histo actions
 #include "THn.h"
+#include "THnSparse.h"
 #include "TProfile.h"
 #include "TProfile2D.h"
 #include "TStatistic.h"
@@ -2286,6 +2287,82 @@ public:
                                                                                       columnList.size());
    }
 
+
+   ////////////////////////////////////////////////////////////////////////////
+   /// \brief Fill and return a sparse N-dimensional histogram (*lazy action*).
+   /// \tparam FirstColumn The first type of the column the values of which are used to fill the object. Inferred if not
+   /// present.
+   /// \tparam OtherColumns A list of the other types of the columns the values of which are used to fill the
+   /// object.
+   /// \param[in] model The returned histogram will be constructed using this as a model.
+   /// \param[in] columnList
+   /// A list containing the names of the columns that will be passed when calling `Fill`.
+   ///  (N columns for unweighted filling, or N+1 columns for weighted filling)
+   /// \return the N-dimensional histogram wrapped in a RResultPtr.
+   ///
+   /// This action is *lazy*: upon invocation of this method the calculation is
+   /// booked but not executed. See RResultPtr documentation.
+   ///
+   /// ### Example usage:
+   /// ~~~{.cpp}
+   /// auto myFilledObj = myDf.HistoND<float, float, float, float>({"name","title", 4,
+   ///                                                {40,40,40,40}, {20.,20.,20.,20.}, {60.,60.,60.,60.}},
+   ///                                               {"col0", "col1", "col2", "col3"});
+   /// ~~~
+   ///
+   template <typename FirstColumn, typename... OtherColumns> // need FirstColumn to disambiguate overloads
+   RResultPtr<::THnSparseD> HistoNSparseD(const THnSparseDModel &model, const ColumnNames_t &columnList)
+   {
+      std::shared_ptr<::THnSparseD> h(nullptr);
+      {
+         ROOT::Internal::RDF::RIgnoreErrorLevelRAII iel(kError);
+         h = model.GetHistogram();
+
+         if (int(columnList.size()) == (h->GetNdimensions() + 1)) {
+            h->Sumw2();
+         } else if (int(columnList.size()) != h->GetNdimensions()) {
+            throw std::runtime_error("Wrong number of columns for the specified number of histogram axes.");
+         }
+      }
+      return CreateAction<RDFInternal::ActionTags::HistoNSparseD, FirstColumn, OtherColumns...>(columnList, h, h,
+                                                                                          fProxiedPtr);
+   }
+
+   ////////////////////////////////////////////////////////////////////////////
+   /// \brief Fill and return a sparse N-dimensional histogram (*lazy action*).
+   /// \param[in] model The returned histogram will be constructed using this as a model.
+   /// \param[in] columnList A list containing the names of the columns that will be passed when calling `Fill`
+   ///  (N columns for unweighted filling, or N+1 columns for weighted filling)
+   /// \return the N-dimensional histogram wrapped in a RResultPtr.
+   ///
+   /// This action is *lazy*: upon invocation of this method the calculation is
+   /// booked but not executed. Also see RResultPtr.
+   ///
+   /// ### Example usage:
+   /// ~~~{.cpp}
+   /// auto myFilledObj = myDf.HistoNSparseD({"name","title", 4,
+   ///                                                {40,40,40,40}, {20.,20.,20.,20.}, {60.,60.,60.,60.}},
+   ///                                               {"col0", "col1", "col2", "col3"});
+   /// ~~~
+   ///
+   RResultPtr<::THnSparseD> HistoNSparseD(const THnSparseDModel &model, const ColumnNames_t &columnList)
+   {
+      std::shared_ptr<::THnSparseD> h(nullptr);
+      {
+         ROOT::Internal::RDF::RIgnoreErrorLevelRAII iel(kError);
+         h = model.GetHistogram();
+
+         if (int(columnList.size()) == (h->GetNdimensions() + 1)) {
+            h->Sumw2();
+         } else if (int(columnList.size()) != h->GetNdimensions()) {
+            throw std::runtime_error("Wrong number of columns for the specified number of histogram axes.");
+         }
+      }
+      return CreateAction<RDFInternal::ActionTags::HistoNSparseD, RDFDetail::RInferredType>(columnList, h, h, fProxiedPtr,
+                                                                                      columnList.size());
+   }
+
+
    ////////////////////////////////////////////////////////////////////////////
    /// \brief Fill and return a TGraph object (*lazy action*).
    /// \tparam X The type of the column used to fill the x axis.

tree/dataframe/src/RDFHistoModels.cxx

@@ -20,6 +20,7 @@
 #include "TH2.h"
 #include "TH3.h"
 #include "THn.h"
+#include "THnSparse.h"
 
 /**
  * \class ROOT::RDF::TH1DModel
@@ -359,7 +360,12 @@ std::shared_ptr<::THnSparseD> THnSparseDModel::GetHistogram() const
    }
    std::shared_ptr<::THnSparseD> h;
    if (varbinning) {
-      h = std::make_shared<::THnSparseD>(fName, fTitle, fDim, fNbins.data(), fBinEdges, fChunkSize);
+      std::vector<TAxis> axes(fDim);
+      for (int idim = 0; idim < fDim; ++idim) {
+         axes[idim] = TAxis(fNbins[idim], fBinEdges[idim].data());
+      }
+      h = std::make_shared<::THnSparseD>(fName, fTitle, axes, fChunkSize);
+      // h = std::make_shared<::THnSparseD>(fName, fTitle, fDim, fNbins.data(), fBinEdges, fChunkSize);
    } else {
       h = std::make_shared<::THnSparseD>(fName, fTitle, fDim, fNbins.data(), fXmin.data(), fXmax.data(), fChunkSize);
    }