[PyROOT][RDF] Support conversion of bool columns to NumPy arrays

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/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()

tree/dataframe/src/RDFUtils.cxx

@@ -384,6 +384,13 @@ unsigned int GetColumnWidth(const std::vector<std::string>& names, const unsigne
 void CheckReaderTypeMatches(const std::type_info &colType, const std::type_info &requestedType,
                             const std::string &colName)
 {
+   bool explicitlySupported = false;
+   // We want to explicitly support the reading of bools as unsigned char, as
+   // this is quite common to circumvent the std::vector<bool> specialization.
+   if (TypeID2TypeName(colType) == "bool" && TypeID2TypeName(requestedType) == "unsigned char") {
+      explicitlySupported = true;
+   }
+
    // Here we compare names and not typeinfos since they may come from two different contexts: a compiled
    // and a jitted one.
    const auto diffTypes = (0 != std::strcmp(colType.name(), requestedType.name()));
@@ -392,7 +399,7 @@ void CheckReaderTypeMatches(const std::type_info &colType, const std::type_info
       return colTClass && colTClass->InheritsFrom(TClass::GetClass(requestedType));
    };
 
-   if (diffTypes && !inheritedType()) {
+   if (!explicitlySupported && diffTypes && !inheritedType()) {
       const auto tName = TypeID2TypeName(requestedType);
       const auto colTypeName = TypeID2TypeName(colType);
       std::string errMsg = "RDataFrame: type mismatch: column \"" + colName + "\" is being used as ";