From f3c76f034a2ecb57d1cd05a30f969ffb90c41ab5 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Mon, 24 Jan 2022 12:34:19 -0800
Subject: [PATCH 1/8] CLN: typo fixups, avoid warnings in test_eval

---
 pandas/core/arrays/_mixins.py              |  4 ++--
 pandas/core/arrays/datetimes.py            |  1 -
 pandas/core/internals/blocks.py            | 17 ++++++++++-------
 pandas/tests/computation/test_eval.py      |  2 +-
 pandas/tests/io/parser/test_unsupported.py |  2 +-
 5 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/pandas/core/arrays/_mixins.py b/pandas/core/arrays/_mixins.py
index a40be5a988f26..3446d5fc43a65 100644
--- a/pandas/core/arrays/_mixins.py
+++ b/pandas/core/arrays/_mixins.py
@@ -180,7 +180,7 @@ def _values_for_argsort(self) -> np.ndarray:
     def argmin(self, axis: int = 0, skipna: bool = True):  # type:ignore[override]
         # override base class by adding axis keyword
         validate_bool_kwarg(skipna, "skipna")
-        if not skipna and self.isna().any():
+        if not skipna and self._hasna:
             raise NotImplementedError
         return nargminmax(self, "argmin", axis=axis)
 
@@ -188,7 +188,7 @@ def argmin(self, axis: int = 0, skipna: bool = True):  # type:ignore[override]
     def argmax(self, axis: int = 0, skipna: bool = True):  # type:ignore[override]
         # override base class by adding axis keyword
         validate_bool_kwarg(skipna, "skipna")
-        if not skipna and self.isna().any():
+        if not skipna and self._hasna:
             raise NotImplementedError
         return nargminmax(self, "argmax", axis=axis)
 
diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
index 87acadc01faad..9c262fa37d760 100644
--- a/pandas/core/arrays/datetimes.py
+++ b/pandas/core/arrays/datetimes.py
@@ -2289,7 +2289,6 @@ def maybe_convert_dtype(data, copy: bool):
         copy = False
 
     elif is_extension_array_dtype(data.dtype) and not is_datetime64tz_dtype(data.dtype):
-        # Includes categorical
         # TODO: We have no tests for these
         data = np.array(data, dtype=np.object_)
         copy = False
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 3d4f53530b89c..93696b0da97d8 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -367,14 +367,16 @@ def iget(self, i: int | tuple[int, int] | tuple[slice, int]):
         # "Union[int, integer[Any]]"
         return self.values[i]  # type: ignore[index]
 
-    def set_inplace(self, locs, values) -> None:
+    def set_inplace(self, locs, values: ArrayLike) -> None:
         """
         Modify block values in-place with new item value.
 
         Notes
         -----
-        `set` never creates a new array or new Block, whereas `setitem` _may_
-        create a new array and always creates a new Block.
+        `set_inplace` never creates a new array or new Block, whereas `setitem`
+        _may_ create a new array and always creates a new Block.
+
+        Caller is responsible for checking values.dtype == self.dtype.
         """
         self.values[locs] = values
 
@@ -1183,7 +1185,7 @@ def where(self, other, cond) -> list[Block]:
         icond, noop = validate_putmask(values, ~cond)
         if noop:
             # GH-39595: Always return a copy; short-circuit up/downcasting
-            return self.copy()
+            return [self.copy()]
 
         if other is lib.no_default:
             other = self.fill_value
@@ -1375,7 +1377,8 @@ def setitem(self, indexer, value):
 
         values = self.values
         if values.ndim == 2:
-            # TODO: string[pyarrow] tests break if we transpose unconditionally
+            # TODO(GH#45419): string[pyarrow] tests break if we transpose
+            #  unconditionally
             values = values.T
         check_setitem_lengths(indexer, value, values)
         values[indexer] = value
@@ -1396,7 +1399,7 @@ def where(self, other, cond) -> list[Block]:
         if noop:
             # GH#44181, GH#45135
             # Avoid a) raising for Interval/PeriodDtype and b) unnecessary object upcast
-            return self.copy()
+            return [self.copy()]
 
         try:
             res_values = arr._where(cond, other).T
@@ -1597,7 +1600,7 @@ def iget(self, i: int | tuple[int, int] | tuple[slice, int]):
                 raise IndexError(f"{self} only contains one item")
             return self.values
 
-    def set_inplace(self, locs, values) -> None:
+    def set_inplace(self, locs, values: ArrayLike) -> None:
         # NB: This is a misnomer, is supposed to be inplace but is not,
         #  see GH#33457
         # When an ndarray, we should have locs.tolist() == [0]
diff --git a/pandas/tests/computation/test_eval.py b/pandas/tests/computation/test_eval.py
index 94b1f5d2717a4..bf74e11ae247a 100644
--- a/pandas/tests/computation/test_eval.py
+++ b/pandas/tests/computation/test_eval.py
@@ -797,7 +797,7 @@ def _is_datetime(x):
 
 
 def should_warn(*args):
-    not_mono = not any(map(operator.attrgetter("is_monotonic"), args))
+    not_mono = not any(map(operator.attrgetter("is_monotonic_increasing"), args))
     only_one_dt = reduce(operator.xor, map(_is_datetime, args))
     return not_mono and only_one_dt
 
diff --git a/pandas/tests/io/parser/test_unsupported.py b/pandas/tests/io/parser/test_unsupported.py
index e223378b600e0..67f155817582c 100644
--- a/pandas/tests/io/parser/test_unsupported.py
+++ b/pandas/tests/io/parser/test_unsupported.py
@@ -166,7 +166,7 @@ def test_on_bad_lines_callable_python_only(self, all_parsers):
             parser.read_csv(sio, on_bad_lines=bad_lines_func)
 
 
-def test_close_file_handle_on_invalide_usecols(all_parsers):
+def test_close_file_handle_on_invalid_usecols(all_parsers):
     # GH 45384
     parser = all_parsers
 

From 75700a93a4e78223cc0f1faa7cda74117d68ca57 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Tue, 25 Jan 2022 11:52:16 -0800
Subject: [PATCH 2/8] check only needed in older numpy

---
 pandas/core/array_algos/putmask.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/pandas/core/array_algos/putmask.py b/pandas/core/array_algos/putmask.py
index daf7d0bd3f213..1082f8d71af01 100644
--- a/pandas/core/array_algos/putmask.py
+++ b/pandas/core/array_algos/putmask.py
@@ -12,6 +12,7 @@
     ArrayLike,
     npt,
 )
+from pandas.compat import np_version_under1p20
 
 from pandas.core.dtypes.cast import (
     can_hold_element,
@@ -126,7 +127,8 @@ def putmask_without_repeat(
     mask : np.ndarray[bool]
     new : Any
     """
-    new = setitem_datetimelike_compat(values, mask.sum(), new)
+    if np_version_under1p20:
+        new = setitem_datetimelike_compat(values, mask.sum(), new)
 
     if getattr(new, "ndim", 0) >= 1:
         new = new.astype(values.dtype, copy=False)

From 57839655daa83fb38b4f63fe2bb9851fb3728207 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 27 Jan 2022 10:46:24 -0800
Subject: [PATCH 3/8] supress warnings

---
 pandas/util/_test_decorators.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/pandas/util/_test_decorators.py b/pandas/util/_test_decorators.py
index 33bde4e69b042..78ef335adf948 100644
--- a/pandas/util/_test_decorators.py
+++ b/pandas/util/_test_decorators.py
@@ -80,6 +80,12 @@ def safe_import(mod_name: str, min_version: str | None = None):
             message=".*Int64Index.*",
         )
 
+        warnings.filterwarnings(
+            "ignore",
+            category=DeprecationWarning,
+            message="distutils Version classes are deprecated.*",
+        )
+
         try:
             mod = __import__(mod_name)
         except ImportError:

From 9dd3b705dac5ae4d7d0951eda5364aeee89d47a9 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 27 Jan 2022 11:16:06 -0800
Subject: [PATCH 4/8] mypy fixup

---
 pandas/core/internals/blocks.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 93696b0da97d8..accacbf464434 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -1605,7 +1605,11 @@ def set_inplace(self, locs, values: ArrayLike) -> None:
         #  see GH#33457
         # When an ndarray, we should have locs.tolist() == [0]
         # When a BlockPlacement we should have list(locs) == [0]
-        self.values = values
+
+        # error: Incompatible types in assignment (expression has type
+        # "Union[ExtensionArray, ndarray[Any, Any]]", variable has type
+        # "ExtensionArray")
+        self.values = values  # type: ignore[assignment]
         try:
             # TODO(GH33457) this can be removed
             self._cache.clear()

From 6a4d26776bedad91e2a6ca6515ed73e51b0cc4a1 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Fri, 18 Feb 2022 19:06:56 -0800
Subject: [PATCH 5/8] TYP/CLN: assorted

---
 pandas/core/internals/array_manager.py    |  5 +++--
 pandas/core/internals/blocks.py           | 15 +++++----------
 pandas/core/internals/managers.py         |  4 ++--
 pandas/core/util/hashing.py               | 19 +++++++++++++------
 pandas/tests/frame/indexing/test_where.py | 14 ++------------
 pandas/tests/indexing/test_loc.py         |  6 +++---
 6 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/pandas/core/internals/array_manager.py b/pandas/core/internals/array_manager.py
index c7ec4f35e0ff1..3e499c99ac144 100644
--- a/pandas/core/internals/array_manager.py
+++ b/pandas/core/internals/array_manager.py
@@ -21,6 +21,7 @@
 from pandas._typing import (
     ArrayLike,
     DtypeObj,
+    npt,
 )
 from pandas.util._validators import validate_bool_kwarg
 
@@ -568,7 +569,7 @@ def reindex_indexer(
     def _reindex_indexer(
         self: T,
         new_axis,
-        indexer,
+        indexer: npt.NDArray[np.intp] | None,
         axis: int,
         fill_value=None,
         allow_dups: bool = False,
@@ -579,7 +580,7 @@ def _reindex_indexer(
         Parameters
         ----------
         new_axis : Index
-        indexer : ndarray of int64 or None
+        indexer : ndarray[intp] or None
         axis : int
         fill_value : object, default None
         allow_dups : bool, default False
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 5acba7960111e..57cc88613cb7d 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -87,7 +87,6 @@
     replace_regex,
     should_use_regex,
 )
-from pandas.core.array_algos.take import take_nd
 from pandas.core.array_algos.transforms import shift
 from pandas.core.arrays import (
     Categorical,
@@ -827,19 +826,14 @@ def set_inplace(self, locs, values: ArrayLike) -> None:
 
     def take_nd(
         self,
-        indexer,
+        indexer: npt.NDArray[np.intp],
         axis: int,
         new_mgr_locs: BlockPlacement | None = None,
         fill_value=lib.no_default,
     ) -> Block:
         """
-        Take values according to indexer and return them as a block.bb
-
+        Take values according to indexer and return them as a block.
         """
-        # algos.take_nd dispatches for DatetimeTZBlock, CategoricalBlock
-        # so need to preserve types
-        # sparse is treated like an ndarray, but needs .get_values() shaping
-
         values = self.values
 
         if fill_value is lib.no_default:
@@ -848,6 +842,7 @@ def take_nd(
         else:
             allow_fill = True
 
+        # Note: algos.take_nd has upcast logic similar to coerce_to_target_dtype
         new_values = algos.take_nd(
             values, indexer, axis=axis, allow_fill=allow_fill, fill_value=fill_value
         )
@@ -1727,7 +1722,7 @@ def is_numeric(self):
 
     def take_nd(
         self,
-        indexer,
+        indexer: npt.NDArray[np.intp],
         axis: int = 0,
         new_mgr_locs: BlockPlacement | None = None,
         fill_value=lib.no_default,
@@ -2259,7 +2254,7 @@ def to_native_types(
     """convert to our native types format"""
     if isinstance(values, Categorical):
         # GH#40754 Convert categorical datetimes to datetime array
-        values = take_nd(
+        values = algos.take_nd(
             values.categories._values,
             ensure_platform_int(values._codes),
             fill_value=na_rep,
diff --git a/pandas/core/internals/managers.py b/pandas/core/internals/managers.py
index 6297a7578ccd4..4b8f1aae75b1b 100644
--- a/pandas/core/internals/managers.py
+++ b/pandas/core/internals/managers.py
@@ -597,7 +597,7 @@ def consolidate(self: T) -> T:
     def reindex_indexer(
         self: T,
         new_axis: Index,
-        indexer,
+        indexer: npt.NDArray[np.intp] | None,
         axis: int,
         fill_value=None,
         allow_dups: bool = False,
@@ -610,7 +610,7 @@ def reindex_indexer(
         Parameters
         ----------
         new_axis : Index
-        indexer : ndarray of int64 or None
+        indexer : ndarray[intp] or None
         axis : int
         fill_value : object, default None
         allow_dups : bool, default False
diff --git a/pandas/core/util/hashing.py b/pandas/core/util/hashing.py
index 79db60ab5a7ce..5a5e46e0227aa 100644
--- a/pandas/core/util/hashing.py
+++ b/pandas/core/util/hashing.py
@@ -16,7 +16,10 @@
 
 from pandas._libs import lib
 from pandas._libs.hashing import hash_object_array
-from pandas._typing import ArrayLike
+from pandas._typing import (
+    ArrayLike,
+    npt,
+)
 
 from pandas.core.dtypes.common import (
     is_categorical_dtype,
@@ -44,7 +47,9 @@
 _default_hash_key = "0123456789123456"
 
 
-def combine_hash_arrays(arrays: Iterator[np.ndarray], num_items: int) -> np.ndarray:
+def combine_hash_arrays(
+    arrays: Iterator[np.ndarray], num_items: int
+) -> npt.NDArray[np.uint64]:
     """
     Parameters
     ----------
@@ -172,7 +177,7 @@ def hash_tuples(
     vals: MultiIndex | Iterable[tuple[Hashable, ...]],
     encoding: str = "utf8",
     hash_key: str = _default_hash_key,
-) -> np.ndarray:
+) -> npt.NDArray[np.uint64]:
     """
     Hash an MultiIndex / listlike-of-tuples efficiently.
 
@@ -214,7 +219,9 @@ def hash_tuples(
     return h
 
 
-def _hash_categorical(cat: Categorical, encoding: str, hash_key: str) -> np.ndarray:
+def _hash_categorical(
+    cat: Categorical, encoding: str, hash_key: str
+) -> npt.NDArray[np.uint64]:
     """
     Hash a Categorical by hashing its categories, and then mapping the codes
     to the hashes
@@ -257,7 +264,7 @@ def hash_array(
     encoding: str = "utf8",
     hash_key: str = _default_hash_key,
     categorize: bool = True,
-) -> np.ndarray:
+) -> npt.NDArray[np.uint64]:
     """
     Given a 1d array, return an array of deterministic integers.
 
@@ -306,7 +313,7 @@ def _hash_ndarray(
     encoding: str = "utf8",
     hash_key: str = _default_hash_key,
     categorize: bool = True,
-) -> np.ndarray:
+) -> npt.NDArray[np.uint64]:
     """
     See hash_array.__doc__.
     """
diff --git a/pandas/tests/frame/indexing/test_where.py b/pandas/tests/frame/indexing/test_where.py
index ca050a7d7db4a..46d3b00097337 100644
--- a/pandas/tests/frame/indexing/test_where.py
+++ b/pandas/tests/frame/indexing/test_where.py
@@ -769,25 +769,15 @@ def test_where_try_cast_deprecated(frame_or_series):
         obj.where(mask, -1, try_cast=False)
 
 
-def test_where_int_downcasting_deprecated(using_array_manager, request):
+def test_where_int_downcasting_deprecated():
     # GH#44597
-    if not using_array_manager:
-        mark = pytest.mark.xfail(
-            reason="After fixing a bug in can_hold_element, we don't go through "
-            "the deprecated path, and also up-cast both columns to int32 "
-            "instead of just 1."
-        )
-        request.node.add_marker(mark)
     arr = np.arange(6).astype(np.int16).reshape(3, 2)
     df = DataFrame(arr)
 
     mask = np.zeros(arr.shape, dtype=bool)
     mask[:, 0] = True
 
-    msg = "Downcasting integer-dtype"
-    warn = FutureWarning if not using_array_manager else None
-    with tm.assert_produces_warning(warn, match=msg):
-        res = df.where(mask, 2**17)
+    res = df.where(mask, 2**17)
 
     expected = DataFrame({0: arr[:, 0], 1: np.array([2**17] * 3, dtype=np.int32)})
     tm.assert_frame_equal(res, expected)
diff --git a/pandas/tests/indexing/test_loc.py b/pandas/tests/indexing/test_loc.py
index d16d086a37d3d..4702b5e5c4504 100644
--- a/pandas/tests/indexing/test_loc.py
+++ b/pandas/tests/indexing/test_loc.py
@@ -44,16 +44,16 @@
 
 
 @pytest.mark.parametrize(
-    "series, new_serie, expected_ser",
+    "series, new_series, expected_ser",
     [
         [[np.nan, np.nan, "b"], ["a", np.nan, np.nan], [False, True, True]],
         [[np.nan, "b"], ["a", np.nan], [False, True]],
     ],
 )
-def test_not_change_nan_loc(series, new_serie, expected_ser):
+def test_not_change_nan_loc(series, new_series, expected_ser):
     # GH 28403
     df = DataFrame({"A": series})
-    df["A"].loc[:] = new_serie
+    df["A"].loc[:] = new_series
     expected = DataFrame({"A": expected_ser})
     tm.assert_frame_equal(df.isna(), expected)
     tm.assert_frame_equal(df.notna(), ~expected)

From 7ae0bad416d287c5176d5f2db293bf21430ada1f Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Tue, 22 Feb 2022 11:28:00 -0800
Subject: [PATCH 6/8] TYP: assorted

---
 pandas/core/groupby/ops.py          |  8 ++++----
 pandas/core/reshape/merge.py        |  3 +--
 pandas/core/sorting.py              | 31 +++++++++++++++--------------
 pandas/core/strings/object_array.py |  2 +-
 4 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
index cf046d92dd6f3..89de9d284ecef 100644
--- a/pandas/core/groupby/ops.py
+++ b/pandas/core/groupby/ops.py
@@ -437,8 +437,8 @@ def _cython_op_ndim_compat(
         min_count: int,
         ngroups: int,
         comp_ids: np.ndarray,
-        mask: np.ndarray | None = None,
-        result_mask: np.ndarray | None = None,
+        mask: npt.NDArray[np.bool_] | None = None,
+        result_mask: npt.NDArray[np.bool_] | None = None,
         **kwargs,
     ) -> np.ndarray:
         if values.ndim == 1:
@@ -481,8 +481,8 @@ def _call_cython_op(
         min_count: int,
         ngroups: int,
         comp_ids: np.ndarray,
-        mask: np.ndarray | None,
-        result_mask: np.ndarray | None,
+        mask: npt.NDArray[np.bool_] | None,
+        result_mask: npt.NDArray[np.bool_] | None,
         **kwargs,
     ) -> np.ndarray:  # np.ndarray[ndim=2]
         orig_values = values
diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
index 44ead165fec25..46f74c5fc67e7 100644
--- a/pandas/core/reshape/merge.py
+++ b/pandas/core/reshape/merge.py
@@ -2276,14 +2276,13 @@ def _factorize_keys(
 
 
 def _sort_labels(
-    uniques: np.ndarray, left: np.ndarray, right: np.ndarray
+    uniques: np.ndarray, left: npt.NDArray[np.intp], right: npt.NDArray[np.intp]
 ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]:
 
     llength = len(left)
     labels = np.concatenate([left, right])
 
     _, new_labels = algos.safe_sort(uniques, labels, na_sentinel=-1)
-    assert new_labels.dtype == np.intp
     new_left, new_right = new_labels[:llength], new_labels[llength:]
 
     return new_left, new_right
diff --git a/pandas/core/sorting.py b/pandas/core/sorting.py
index 7ab53ccf7cb8d..21d9107a61cb7 100644
--- a/pandas/core/sorting.py
+++ b/pandas/core/sorting.py
@@ -41,6 +41,7 @@
 
 if TYPE_CHECKING:
     from pandas import MultiIndex
+    from pandas.core.arrays import ExtensionArray
     from pandas.core.indexes.base import Index
 
 
@@ -52,7 +53,7 @@ def get_indexer_indexer(
     na_position: str,
     sort_remaining: bool,
     key: IndexKeyFunc,
-) -> np.ndarray | None:
+) -> npt.NDArray[np.intp] | None:
     """
     Helper method that return the indexer according to input parameters for
     the sort_index method of DataFrame and Series.
@@ -69,7 +70,7 @@ def get_indexer_indexer(
 
     Returns
     -------
-    Optional[ndarray]
+    Optional[ndarray[intp]]
         The indexer for the new index.
     """
 
@@ -215,7 +216,7 @@ def get_compressed_ids(
     return compress_group_index(ids, sort=True)
 
 
-def is_int64_overflow_possible(shape) -> bool:
+def is_int64_overflow_possible(shape: Shape) -> bool:
     the_prod = 1
     for x in shape:
         the_prod *= int(x)
@@ -223,7 +224,7 @@ def is_int64_overflow_possible(shape) -> bool:
     return the_prod >= lib.i8max
 
 
-def decons_group_index(comp_labels, shape):
+def decons_group_index(comp_labels, shape: Shape):
     # reconstruct labels
     if is_int64_overflow_possible(shape):
         # at some point group indices are factorized,
@@ -244,7 +245,7 @@ def decons_group_index(comp_labels, shape):
 
 
 def decons_obs_group_ids(
-    comp_ids: npt.NDArray[np.intp], obs_ids, shape, labels, xnull: bool
+    comp_ids: npt.NDArray[np.intp], obs_ids, shape: Shape, labels, xnull: bool
 ):
     """
     Reconstruct labels from observed group ids.
@@ -428,7 +429,7 @@ def nargsort(
     return ensure_platform_int(indexer)
 
 
-def nargminmax(values, method: str, axis: int = 0):
+def nargminmax(values: ExtensionArray, method: str, axis: int = 0):
     """
     Implementation of np.argmin/argmax but for ExtensionArray and which
     handles missing values.
@@ -447,21 +448,21 @@ def nargminmax(values, method: str, axis: int = 0):
     func = np.argmax if method == "argmax" else np.argmin
 
     mask = np.asarray(isna(values))
-    values = values._values_for_argsort()
+    arr_values = values._values_for_argsort()
 
-    if values.ndim > 1:
+    if arr_values.ndim > 1:
         if mask.any():
             if axis == 1:
-                zipped = zip(values, mask)
+                zipped = zip(arr_values, mask)
             else:
-                zipped = zip(values.T, mask.T)
+                zipped = zip(arr_values.T, mask.T)
             return np.array([_nanargminmax(v, m, func) for v, m in zipped])
-        return func(values, axis=axis)
+        return func(arr_values, axis=axis)
 
-    return _nanargminmax(values, mask, func)
+    return _nanargminmax(arr_values, mask, func)
 
 
-def _nanargminmax(values, mask, func) -> int:
+def _nanargminmax(values: np.ndarray, mask: npt.NDArray[np.bool_], func) -> int:
     """
     See nanargminmax.__doc__.
     """
@@ -591,9 +592,9 @@ def get_indexer_dict(
     dict:
         Labels mapped to indexers.
     """
-    shape = [len(x) for x in keys]
+    shape = tuple(len(x) for x in keys)
 
-    group_index = get_group_index(label_list, tuple(shape), sort=True, xnull=True)
+    group_index = get_group_index(label_list, shape, sort=True, xnull=True)
     if np.all(group_index == -1):
         # Short-circuit, lib.indices_fast will return the same
         return {}
diff --git a/pandas/core/strings/object_array.py b/pandas/core/strings/object_array.py
index 6b0380a292f07..2f65ce17f93b2 100644
--- a/pandas/core/strings/object_array.py
+++ b/pandas/core/strings/object_array.py
@@ -62,7 +62,7 @@ def _str_map(
             na_value = self._str_na_value
 
         if not len(self):
-            return np.ndarray(0, dtype=dtype)
+            return np.array([], dtype=dtype)
 
         arr = np.asarray(self, dtype=object)
         mask = isna(arr)

From e3f56631f4119b8b121647524c75bfd3c05999c7 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Tue, 22 Feb 2022 12:09:50 -0800
Subject: [PATCH 7/8] avoid warnings

---
 pandas/tests/plotting/test_datetimelike.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/tests/plotting/test_datetimelike.py b/pandas/tests/plotting/test_datetimelike.py
index 1b818f57d0572..197083a9ad940 100644
--- a/pandas/tests/plotting/test_datetimelike.py
+++ b/pandas/tests/plotting/test_datetimelike.py
@@ -523,7 +523,7 @@ def test_finder_hourly(self):
 
     def test_gaps(self):
         ts = tm.makeTimeSeries()
-        ts[5:25] = np.nan
+        ts.iloc[5:25] = np.nan
         _, ax = self.plt.subplots()
         ts.plot(ax=ax)
         lines = ax.get_lines()
@@ -541,7 +541,7 @@ def test_gaps(self):
         # irregular
         ts = tm.makeTimeSeries()
         ts = ts[[0, 1, 2, 5, 7, 9, 12, 15, 20]]
-        ts[2:5] = np.nan
+        ts.iloc[2:5] = np.nan
         _, ax = self.plt.subplots()
         ax = ts.plot(ax=ax)
         lines = ax.get_lines()

From 3565ba9e729f2082871439001f9315671ee77372 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Tue, 22 Feb 2022 13:41:47 -0800
Subject: [PATCH 8/8] TYP: masks

---
 pandas/core/algorithms.py                    |  2 +-
 pandas/core/array_algos/masked_reductions.py | 37 ++++++++++----------
 pandas/core/array_algos/replace.py           |  7 ++--
 pandas/core/arrays/_mixins.py                |  2 +-
 pandas/core/arrays/masked.py                 |  6 ++--
 pandas/core/arrays/numeric.py                |  5 ++-
 pandas/core/groupby/groupby.py               |  4 +--
 pandas/core/indexes/base.py                  |  4 ++-
 pandas/core/indexes/period.py                |  3 +-
 pandas/core/internals/blocks.py              |  2 +-
 pandas/core/missing.py                       |  2 +-
 pandas/core/tools/numeric.py                 |  3 +-
 pandas/io/pytables.py                        |  3 +-
 13 files changed, 46 insertions(+), 34 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 8c10b62d83f9e..f6bda51298622 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -534,7 +534,7 @@ def factorize_array(
     na_sentinel: int = -1,
     size_hint: int | None = None,
     na_value=None,
-    mask: np.ndarray | None = None,
+    mask: npt.NDArray[np.bool_] | None = None,
 ) -> tuple[npt.NDArray[np.intp], np.ndarray]:
     """
     Factorize a numpy array to codes and uniques.
diff --git a/pandas/core/array_algos/masked_reductions.py b/pandas/core/array_algos/masked_reductions.py
index 66a3152de1499..3e59a267f7191 100644
--- a/pandas/core/array_algos/masked_reductions.py
+++ b/pandas/core/array_algos/masked_reductions.py
@@ -2,15 +2,14 @@
 masked_reductions.py is for reduction algorithms using a mask-based approach
 for missing values.
 """
+from __future__ import annotations
 
-from typing import (
-    Callable,
-    Optional,
-)
+from typing import Callable
 
 import numpy as np
 
 from pandas._libs import missing as libmissing
+from pandas._typing import npt
 
 from pandas.core.nanops import check_below_min_count
 
@@ -18,11 +17,11 @@
 def _sumprod(
     func: Callable,
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
     min_count: int = 0,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     """
     Sum or product for 1D masked array.
@@ -33,7 +32,7 @@ def _sumprod(
     values : np.ndarray
         Numpy array with the values (can be of any dtype that support the
         operation).
-    mask : np.ndarray
+    mask : np.ndarray[bool]
         Boolean numpy array (True values indicate missing values).
     skipna : bool, default True
         Whether to skip NA.
@@ -58,11 +57,11 @@ def _sumprod(
 
 def sum(
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
     min_count: int = 0,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     return _sumprod(
         np.sum, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
@@ -71,11 +70,11 @@ def sum(
 
 def prod(
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
     min_count: int = 0,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     return _sumprod(
         np.prod, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
@@ -85,10 +84,10 @@ def prod(
 def _minmax(
     func: Callable,
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     """
     Reduction for 1D masked array.
@@ -99,7 +98,7 @@ def _minmax(
     values : np.ndarray
         Numpy array with the values (can be of any dtype that support the
         operation).
-    mask : np.ndarray
+    mask : np.ndarray[bool]
         Boolean numpy array (True values indicate missing values).
     skipna : bool, default True
         Whether to skip NA.
@@ -122,26 +121,26 @@ def _minmax(
 
 def min(
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     return _minmax(np.min, values=values, mask=mask, skipna=skipna, axis=axis)
 
 
 def max(
     values: np.ndarray,
-    mask: np.ndarray,
+    mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
-    axis: Optional[int] = None,
+    axis: int | None = None,
 ):
     return _minmax(np.max, values=values, mask=mask, skipna=skipna, axis=axis)
 
 
 # TODO: axis kwarg
-def mean(values: np.ndarray, mask: np.ndarray, skipna: bool = True):
+def mean(values: np.ndarray, mask: npt.NDArray[np.bool_], skipna: bool = True):
     if not values.size or mask.all():
         return libmissing.NA
     _sum = _sumprod(np.sum, values=values, mask=mask, skipna=skipna)
diff --git a/pandas/core/array_algos/replace.py b/pandas/core/array_algos/replace.py
index e26bb9fb6ebad..19a44dbfe6f6d 100644
--- a/pandas/core/array_algos/replace.py
+++ b/pandas/core/array_algos/replace.py
@@ -15,6 +15,7 @@
 from pandas._typing import (
     ArrayLike,
     Scalar,
+    npt,
 )
 
 from pandas.core.dtypes.common import (
@@ -42,7 +43,7 @@ def should_use_regex(regex: bool, to_replace: Any) -> bool:
 
 
 def compare_or_regex_search(
-    a: ArrayLike, b: Scalar | Pattern, regex: bool, mask: np.ndarray
+    a: ArrayLike, b: Scalar | Pattern, regex: bool, mask: npt.NDArray[np.bool_]
 ) -> ArrayLike | bool:
     """
     Compare two array-like inputs of the same shape or two scalar values
@@ -116,7 +117,9 @@ def _check_comparison_types(
     return result
 
 
-def replace_regex(values: ArrayLike, rx: re.Pattern, value, mask: np.ndarray | None):
+def replace_regex(
+    values: ArrayLike, rx: re.Pattern, value, mask: npt.NDArray[np.bool_] | None
+):
     """
     Parameters
     ----------
diff --git a/pandas/core/arrays/_mixins.py b/pandas/core/arrays/_mixins.py
index 3446d5fc43a65..a493cf67fff9d 100644
--- a/pandas/core/arrays/_mixins.py
+++ b/pandas/core/arrays/_mixins.py
@@ -360,7 +360,7 @@ def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
         np.putmask(self._ndarray, mask, value)
 
     def _where(
-        self: NDArrayBackedExtensionArrayT, mask: np.ndarray, value
+        self: NDArrayBackedExtensionArrayT, mask: npt.NDArray[np.bool_], value
     ) -> NDArrayBackedExtensionArrayT:
         """
         Analogue to np.where(mask, self, value)
diff --git a/pandas/core/arrays/masked.py b/pandas/core/arrays/masked.py
index 21f44dbc6a1cd..ee6d2a6ab5684 100644
--- a/pandas/core/arrays/masked.py
+++ b/pandas/core/arrays/masked.py
@@ -99,13 +99,15 @@ class BaseMaskedArray(OpsMixin, ExtensionArray):
     _internal_fill_value: Scalar
     # our underlying data and mask are each ndarrays
     _data: np.ndarray
-    _mask: np.ndarray
+    _mask: npt.NDArray[np.bool_]
 
     # Fill values used for any/all
     _truthy_value = Scalar  # bool(_truthy_value) = True
     _falsey_value = Scalar  # bool(_falsey_value) = False
 
-    def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
+    def __init__(
+        self, values: np.ndarray, mask: npt.NDArray[np.bool_], copy: bool = False
+    ):
         # values is supposed to already be validated in the subclass
         if not (isinstance(mask, np.ndarray) and mask.dtype == np.bool_):
             raise TypeError(
diff --git a/pandas/core/arrays/numeric.py b/pandas/core/arrays/numeric.py
index 958c9f7b0b3f1..724cd1c0d88ca 100644
--- a/pandas/core/arrays/numeric.py
+++ b/pandas/core/arrays/numeric.py
@@ -17,6 +17,7 @@
 from pandas._typing import (
     Dtype,
     DtypeObj,
+    npt,
 )
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import cache_readonly
@@ -219,7 +220,9 @@ class NumericArray(BaseMaskedArray):
 
     _dtype_cls: type[NumericDtype]
 
-    def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
+    def __init__(
+        self, values: np.ndarray, mask: npt.NDArray[np.bool_], copy: bool = False
+    ):
         checker = self._dtype_cls._checker
         if not (isinstance(values, np.ndarray) and checker(values.dtype)):
             descr = (
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
index dbff541e9568b..ecc85f12a9880 100644
--- a/pandas/core/groupby/groupby.py
+++ b/pandas/core/groupby/groupby.py
@@ -3607,13 +3607,13 @@ def tail(self, n=5):
         return self._mask_selected_obj(mask)
 
     @final
-    def _mask_selected_obj(self, mask: np.ndarray) -> NDFrameT:
+    def _mask_selected_obj(self, mask: npt.NDArray[np.bool_]) -> NDFrameT:
         """
         Return _selected_obj with mask applied to the correct axis.
 
         Parameters
         ----------
-        mask : np.ndarray
+        mask : np.ndarray[bool]
             Boolean mask to apply.
 
         Returns
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
index d7594f2483569..108646f8766a6 100644
--- a/pandas/core/indexes/base.py
+++ b/pandas/core/indexes/base.py
@@ -5548,7 +5548,9 @@ def asof(self, label):
 
         return self[loc]
 
-    def asof_locs(self, where: Index, mask: np.ndarray) -> npt.NDArray[np.intp]:
+    def asof_locs(
+        self, where: Index, mask: npt.NDArray[np.bool_]
+    ) -> npt.NDArray[np.intp]:
         """
         Return the locations (indices) of labels in the index.
 
diff --git a/pandas/core/indexes/period.py b/pandas/core/indexes/period.py
index aba834a47ffef..006f53ba06c71 100644
--- a/pandas/core/indexes/period.py
+++ b/pandas/core/indexes/period.py
@@ -23,6 +23,7 @@
 from pandas._typing import (
     Dtype,
     DtypeObj,
+    npt,
 )
 from pandas.util._decorators import doc
 from pandas.util._exceptions import find_stack_level
@@ -327,7 +328,7 @@ def _is_comparable_dtype(self, dtype: DtypeObj) -> bool:
     # ------------------------------------------------------------------------
     # Index Methods
 
-    def asof_locs(self, where: Index, mask: np.ndarray) -> np.ndarray:
+    def asof_locs(self, where: Index, mask: npt.NDArray[np.bool_]) -> np.ndarray:
         """
         where : array of timestamps
         mask : np.ndarray[bool]
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 57cc88613cb7d..42c6f03a3af93 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -735,7 +735,7 @@ def _replace_coerce(
         self,
         to_replace,
         value,
-        mask: np.ndarray,
+        mask: npt.NDArray[np.bool_],
         inplace: bool = True,
         regex: bool = False,
     ) -> list[Block]:
diff --git a/pandas/core/missing.py b/pandas/core/missing.py
index d922cfd06f7ac..46ea23e431d15 100644
--- a/pandas/core/missing.py
+++ b/pandas/core/missing.py
@@ -43,7 +43,7 @@
     from pandas import Index
 
 
-def check_value_size(value, mask: np.ndarray, length: int):
+def check_value_size(value, mask: npt.NDArray[np.bool_], length: int):
     """
     Validate the size of the values passed to ExtensionArray.fillna.
     """
diff --git a/pandas/core/tools/numeric.py b/pandas/core/tools/numeric.py
index 26197e1ac4847..ef7f4bc92e25b 100644
--- a/pandas/core/tools/numeric.py
+++ b/pandas/core/tools/numeric.py
@@ -3,6 +3,7 @@
 import numpy as np
 
 from pandas._libs import lib
+from pandas._typing import npt
 
 from pandas.core.dtypes.cast import maybe_downcast_numeric
 from pandas.core.dtypes.common import (
@@ -167,7 +168,7 @@ def to_numeric(arg, errors="raise", downcast=None):
 
     # GH33013: for IntegerArray & FloatingArray extract non-null values for casting
     # save mask to reconstruct the full array after casting
-    mask: np.ndarray | None = None
+    mask: npt.NDArray[np.bool_] | None = None
     if isinstance(values, NumericArray):
         mask = values._mask
         values = values._data[~mask]
diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
index 53b5079ed6be9..7c784c1489617 100644
--- a/pandas/io/pytables.py
+++ b/pandas/io/pytables.py
@@ -41,6 +41,7 @@
     ArrayLike,
     DtypeArg,
     Shape,
+    npt,
 )
 from pandas.compat._optional import import_optional_dependency
 from pandas.compat.pickle_compat import patch_pickle
@@ -4409,7 +4410,7 @@ def write_data_chunk(
         self,
         rows: np.ndarray,
         indexes: list[np.ndarray],
-        mask: np.ndarray | None,
+        mask: npt.NDArray[np.bool_] | None,
         values: list[np.ndarray],
     ):
         """