Merge branch 'main' into bug#60723

doc/source/whatsnew/v3.0.0.rst

@@ -791,6 +791,7 @@ ExtensionArray
 ^^^^^^^^^^^^^^
 - Bug in :class:`Categorical` when constructing with an :class:`Index` with :class:`ArrowDtype` (:issue:`60563`)
 - Bug in :meth:`.arrays.ArrowExtensionArray.__setitem__` which caused wrong behavior when using an integer array with repeated values as a key (:issue:`58530`)
+- Bug in :meth:`ArrowExtensionArray.factorize` where NA values were dropped when input was dictionary-encoded even when dropna was set to False(:issue:`60567`)
 - Bug in :meth:`api.types.is_datetime64_any_dtype` where a custom :class:`ExtensionDtype` would return ``False`` for array-likes (:issue:`57055`)
 - Bug in comparison between object with :class:`ArrowDtype` and incompatible-dtyped (e.g. string vs bool) incorrectly raising instead of returning all-``False`` (for ``==``) or all-``True`` (for ``!=``) (:issue:`59505`)
 - Bug in constructing pandas data structures when passing into ``dtype`` a string of the type followed by ``[pyarrow]`` while PyArrow is not installed would raise ``NameError`` rather than ``ImportError`` (:issue:`57928`)

pandas/core/arrays/arrow/array.py

@@ -1208,7 +1208,12 @@ def factorize(
             data = data.cast(pa.int64())
 
         if pa.types.is_dictionary(data.type):
-            encoded = data
+            if null_encoding == "encode":
+                # dictionary encode does nothing if an already encoded array is given
+                data = data.cast(data.type.value_type)
+                encoded = data.dictionary_encode(null_encoding=null_encoding)
+            else:
+                encoded = data
         else:
             encoded = data.dictionary_encode(null_encoding=null_encoding)
         if encoded.length() == 0:

pandas/tests/extension/test_arrow.py

@@ -3329,6 +3329,18 @@ def test_factorize_chunked_dictionary():
     tm.assert_index_equal(res_uniques, exp_uniques)
 
 
+def test_factorize_dictionary_with_na():
+    # GH#60567
+    arr = pd.array(
+        ["a1", pd.NA], dtype=ArrowDtype(pa.dictionary(pa.int32(), pa.utf8()))
+    )
+    indices, uniques = arr.factorize(use_na_sentinel=False)
+    expected_indices = np.array([0, 1], dtype=np.intp)
+    expected_uniques = pd.array(["a1", None], dtype=ArrowDtype(pa.string()))
+    tm.assert_numpy_array_equal(indices, expected_indices)
+    tm.assert_extension_array_equal(uniques, expected_uniques)
+
+
 def test_dictionary_astype_categorical():
     # GH#56672
     arrs = [