[python] Extend RDataFrame to Numpy array conversion of boolean types

* Use ROOT::RVec as the single data structure to recover all types of values via the Take operation. This helps avoiding issues with vectors of boolean values, whether they are visible as the 'bool' or 'Bool_t' C++ types.
* Add a test that checks both 'bool' and 'Bool_t' types. For the latter, it is required to write a TTree branch.

Author: vepadulano

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

@@ -296,19 +296,17 @@ def RDataFrameAsNumpy(
     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
 
         # If the column type is a class, make sure cling knows about it
         tclass = ROOT.TClass.GetClass(column_type)
         if tclass and not tclass.GetClassInfo():
             raise RuntimeError(
                 f'The column named "{column}" is of type "{column_type}", which is not known to the ROOT interpreter. Please load the corresponding header files or dictionaries.'
             )
-
-        result_ptrs[column] = df.Take[column_type](column)
+        # We take the values via ROOT::RVec to avoid having to deal with std::vector<bool>
+        # This uses one single data structure for all array types, which exposes the array interface
+        # allowing zero-copy conversion to numpy array
+        result_ptrs[column] = df.Take[f"{column_type}, ROOT::RVec<{column_type}>"](column)
 
     result = AsNumpyResult(result_ptrs, columns)
 

bindings/pyroot/pythonizations/test/rdataframe_asnumpy.py

@@ -7,7 +7,7 @@
 import numpy as np
 import ROOT
 from ROOT._pythonization._rdataframe import _clone_asnumpyresult
-
+import os
 
 def make_tree(*dtypes):
     """
@@ -90,10 +90,22 @@ def test_branch_bool(self):
         Test bool data-type as a special case since we cannot adopt
         the std::vector<bool> with numpy arrays
         """
-        df = ROOT.RDataFrame(2).Define("x", "bool(rdfentry_)")
+        treename = "test_branch_bool"
+        filename = "test_branch_bool.root"
+        # Snapshot a TTree so that column 'x' will be of type 'Bool_t'
+        ROOT.RDataFrame(2).Define("x", "bool(rdfentry_)").Snapshot(treename, filename)
+        # The column 'y' will instead have type 'bool'
+        df = ROOT.RDataFrame(treename, filename).Define("y", "bool(rdfentry_)")
+        self.assertEqual(df.GetColumnType("x"), "Bool_t")
+        self.assertEqual(df.GetColumnType("y"), "bool")
         npy = df.AsNumpy()
-        self.assertFalse(bool(npy["x"][0]))
-        self.assertTrue(bool(npy["x"][1]))
+        # Both numpy arrays should have dtype bool
+        self.assertEqual(npy["x"].dtype, bool)
+        self.assertEqual(npy["y"].dtype, bool)
+        self.assertFalse(npy["x"][0])
+        self.assertTrue(npy["x"][1])
+        self.assertFalse(npy["y"][0])
+        self.assertTrue(npy["y"][1])
 
     def test_read_array(self):
         """