[v632] Backport yesterday's fixes

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_rdataframe.py

@@ -229,6 +229,10 @@ def RDataFrameAsNumpy(df, columns=None, exclude=None, lazy=False):
     result_ptrs = {}
     for column in columns:
         column_type = df.GetColumnType(column)
+        # bool columns should be taken as unsigned chars, because NumPy stores
+        # bools in bytes - different from the std::vector<bool> returned by the
+        # action, which might do some space optimization
+        column_type = "unsigned char" if column_type == "bool" else column_type
         result_ptrs[column] = df.Take[column_type](column)
 
     result = AsNumpyResult(result_ptrs, columns)

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_rvec.py

@@ -71,14 +71,15 @@
 
 
 _array_interface_dtype_map = {
-    "float": "f",
+    "Long64_t": "i",
+    "ULong64_t": "u",
     "double": "f",
+    "float": "f",
     "int": "i",
     "long": "i",
-    "Long64_t": "i",
+    "unsigned char": "b",
     "unsigned int": "u",
     "unsigned long": "u",
-    "ULong64_t": "u",
 }
 
 

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_tmva/_tree_inference.py

@@ -12,12 +12,13 @@
 import cppyy
 
 
-def SaveXGBoost(self, xgb_model, key_name, output_path, num_inputs=None, tmp_path="/tmp", threshold_dtype="float"):
+def SaveXGBoost(self, xgb_model, key_name, output_path, num_inputs, tmp_path="/tmp", threshold_dtype="float"):
     # Extract objective
     objective_map = {
         "multi:softprob": "softmax",  # Naming the objective softmax is more common today
         "binary:logistic": "logistic",
         "reg:linear": "identity",
+        "reg:squarederror": "identity",
     }
     model_objective = xgb_model.objective
     if not model_objective in objective_map:
@@ -48,7 +49,8 @@ def SaveXGBoost(self, xgb_model, key_name, output_path, num_inputs=None, tmp_pat
 
     import json
 
-    forest = json.load(open(tmp_path, "r"))
+    with open(tmp_path, "r") as json_file:
+        forest = json.load(json_file)
 
     # Determine whether the model has a bias paramter and write bias trees
     if hasattr(xgb_model, "base_score") and "reg:" in model_objective:
@@ -96,16 +98,6 @@ def fill_arrays(node, index, inputs_base, thresholds_base):
         for i in range(num_trees):
             outputs[i] = int(i % num_outputs)
 
-    # Determine number of input variables
-    if not num_inputs is None:
-        pass
-    elif hasattr(xgb_model, "_features_count"):
-        num_inputs = xgb_model._features_count
-    else:
-        raise Exception(
-            "Failed to get number of input variables from XGBoost model. Please provide the additional keyword argument 'num_inputs' to this function."
-        )
-
     # Store arrays in a ROOT file in a folder with the given key name
     # TODO: Write single values as simple integers and not vectors.
     f = cppyy.gbl.TFile(output_path, "RECREATE")

bindings/pyroot/pythonizations/test/rdataframe_asnumpy.py

@@ -333,6 +333,18 @@ def test_cloning(self):
             self.assertSequenceEqual(
                 asnumpyres.GetValue()["x"].tolist(), np.arange(begin, end).tolist())
 
+    def test_bool_column(self):
+        """
+        Testing converting bool columns to NumPy arrays.
+        """
+        name = "bool_branch"
+        n_events = 100
+        cut = 50
+        df = ROOT.RDataFrame(n_events).Define(name, f"(int)rdfentry_ > {cut}")
+        arr = df.AsNumpy([name])[name]
+        ref = np.arange(0, n_events) > cut
+        self.assertTrue(all(arr == ref)) # test values
+        self.assertEqual(arr.dtype, ref.dtype) # test type
 
 if __name__ == '__main__':
     unittest.main()

cmake/modules/RootBuildOptions.cmake

@@ -155,8 +155,8 @@ ROOT_BUILD_OPTION(qt6web OFF "Enable support for Qt6 web-based display (requires
 ROOT_BUILD_OPTION(r OFF "Enable support for R bindings (requires R, Rcpp, and RInside)")
 ROOT_BUILD_OPTION(roofit ON "Build the advanced fitting package RooFit, and RooStats for statistical tests. If xml is available, also build HistFactory.")
 ROOT_BUILD_OPTION(roofit_multiprocess OFF "Build RooFit::MultiProcess and multi-process RooFit::TestStatistics classes (requires ZeroMQ >= 3.4.5 built with -DENABLE_DRAFTS and cppzmq).")
-ROOT_BUILD_OPTION(webgui ON "Build Web-based UI components of ROOT (requires C++17 standard or higher)")
-ROOT_BUILD_OPTION(root7 ON "Build ROOT 7 components of ROOT (requires C++17 standard or higher)")
+ROOT_BUILD_OPTION(webgui ON "Build Web-based UI components of ROOT")
+ROOT_BUILD_OPTION(root7 ON "Build ROOT 7 components of ROOT")
 ROOT_BUILD_OPTION(rpath ON "Link libraries with built-in RPATH (run-time search path)")
 ROOT_BUILD_OPTION(runtime_cxxmodules ON "Enable runtime support for C++ modules")
 ROOT_BUILD_OPTION(shadowpw OFF "Enable support for shadow passwords")

hist/hist/inc/TPrincipal.h

@@ -51,17 +51,18 @@ class TPrincipal : public TNamed {
 public:
    TPrincipal();
    ~TPrincipal() override;
-   TPrincipal(Int_t nVariables, Option_t *opt="ND");
+   TPrincipal(Long64_t nVariables, Option_t *opt="ND");
 
    virtual void       AddRow(const Double_t *x);
    void       Browse(TBrowser *b) override;
    void       Clear(Option_t *option="") override;
+   /// Return the covariance matrix. \note Only the lower diagonal of the covariance matrix is computed by the class
    const TMatrixD    *GetCovarianceMatrix() const {return &fCovarianceMatrix;}
    const TVectorD    *GetEigenValues() const      {return &fEigenValues;}
    const TMatrixD    *GetEigenVectors() const     {return &fEigenVectors;}
    TList             *GetHistograms() const {return fHistograms;}
    const TVectorD    *GetMeanValues() const       {return &fMeanValues;}
-   const Double_t    *GetRow(Int_t row);
+   const Double_t    *GetRow(Long64_t row);
    const TVectorD    *GetSigmas() const           {return &fSigmas;}
    const TVectorD    *GetUserData() const         {return &fUserData;}
    Bool_t             IsFolder() const override { return kTRUE;}

hist/hist/src/TPrincipal.cxx

@@ -250,7 +250,7 @@ TPrincipal::TPrincipal()
 ///
 /// The created object is  named "principal" by default.
 
-TPrincipal::TPrincipal(Int_t nVariables, Option_t *opt)
+TPrincipal::TPrincipal(Long64_t nVariables, Option_t *opt)
   : fMeanValues(nVariables),
     fSigmas(nVariables),
     fCovarianceMatrix(nVariables,nVariables),
@@ -260,7 +260,11 @@ TPrincipal::TPrincipal(Int_t nVariables, Option_t *opt)
     fStoreData(kFALSE)
 {
    if (nVariables <= 1) {
-      Error("TPrincipal", "You can't be serious - nVariables == 1!!!");
+      Error("TPrincipal", "You can't be serious - nVariables <= 1!!!");
+      return;
+   }
+   if (nVariables > std::numeric_limits<Int_t>::max()) {
+      Error("TPrincipal", "`nVariables` input parameter %lld is larger than the allowed maximum %d", nVariables, std::numeric_limits<Int_t>::max());
       return;
    }
 
@@ -411,6 +415,10 @@ void TPrincipal::AddRow(const Double_t *p)
 {
    if (!p)
       return;
+   if (fNumberOfDataPoints == std::numeric_limits<Int_t>::max()) {
+      Error("AddRow", "`fNumberOfDataPoints` has reached its allowed maximum %d, cannot add new row.", fNumberOfDataPoints);
+      return;
+   }
 
    // Increment the data point counter
    Int_t i,j;
@@ -510,15 +518,19 @@ void TPrincipal::Clear(Option_t *opt)
 /// It's up to the user to delete the returned array.
 /// Row 0 is the first row;
 
-const Double_t *TPrincipal::GetRow(Int_t row)
+const Double_t *TPrincipal::GetRow(Long64_t row)
 {
    if (row >= fNumberOfDataPoints)
       return nullptr;
 
    if (!fStoreData)
       return nullptr;
 
-   Int_t index   = row  * fNumberOfVariables;
+   Long64_t index   = row  * fNumberOfVariables;
+   if (index > std::numeric_limits<Int_t>::max()) {
+      Error("GetRow", "Input parameter `row` %lld x fNumberOfVariables %d goes into overflow (%lld>%d), returning nullptr.", row, fNumberOfVariables, index,  std::numeric_limits<Int_t>::max());
+      return nullptr;
+   }
    return &fUserData(index);
 }
 

requirements.txt

@@ -3,6 +3,8 @@
 # PyROOT: Interoperability with numpy arrays
 # TMVA: PyMVA interfaces
 numpy>=1.4.1
+scikit-learn
+xgboost
 
 # PyROOT: ROOT.Numba.Declare decorator
 numba>=0.47.0 ; python_version < "3.11" # See https://github.com/numba/numba/issues/8304