fixups

Author: rhshadrach

pandas/_libs/hashtable_class_helper.pxi.in

@@ -1251,7 +1251,7 @@ cdef class PyObjectHashTable(HashTable):
             int ret = 0
             object val
             khiter_t k
-            bint use_na_value, seen_na, is_na
+            bint use_na_value, seen_na = False, is_na
             intp_t na_code
 
         if return_inverse:

pandas/core/algorithms.py

@@ -548,6 +548,9 @@ def factorize_array(
         mask=mask,
         ignore_na=ignore_na,
     )
+    if na_index >= 0:
+        print(na_index)
+        uniques[na_index] = na_value
 
     # re-cast e.g. i8->dt64/td64, uint8->bool
     uniques = _reconstruct_data(uniques, original.dtype, original)

pandas/core/arrays/base.py

@@ -1050,6 +1050,7 @@ def factorize(
         )
 
         uniques_ea = self._from_factorized(uniques, self)
+        print(codes, uniques_ea)
         return codes, uniques_ea
 
     _extension_array_shared_docs[

pandas/core/arrays/datetimelike.py

@@ -1889,7 +1889,8 @@ def factorize(self, na_sentinel=-1, sort: bool = False, ignore_na: bool = True):
                 uniques = uniques[::-1]
             return codes, uniques
         # FIXME: shouldn't get here; we are ignoring sort
-        return super().factorize(na_sentinel=na_sentinel, ignore_na=ignore_na)[0]
+        result = super().factorize(na_sentinel=na_sentinel, ignore_na=ignore_na)
+        return result
 
 
 # -------------------------------------------------------------------

pandas/core/groupby/grouper.py

@@ -687,7 +687,7 @@ def _codes_and_uniques(self) -> tuple[npt.NDArray[np.signedinteger], ArrayLike]:
                 na_sentinel = None
             else:
                 na_sentinel = -1
-            codes, uniques, _ = algorithms.factorize(
+            codes, uniques = algorithms.factorize(
                 self.grouping_vector, sort=self._sort, na_sentinel=na_sentinel
             )
         return codes, uniques

pandas/core/reshape/merge.py

@@ -2243,7 +2243,7 @@ def _factorize_keys(
     # Argument 1 to "factorize" of "ObjectFactorizer" has incompatible type
     # "Union[ndarray[Any, dtype[signedinteger[_64Bit]]],
     # ndarray[Any, dtype[object_]]]"; expected "ndarray[Any, dtype[object_]]"
-    llab, _ = rizer.factorize(lk)  # type: ignore[arg-type]
+    llab, _, _ = rizer.factorize(lk)  # type: ignore[arg-type]
     # Argument 1 to "factorize" of "ObjectFactorizer" has incompatible type
     # "Union[ndarray[Any, dtype[signedinteger[_64Bit]]],
     # ndarray[Any, dtype[object_]]]"; expected "ndarray[Any, dtype[object_]]"