Misc Type Annotation fixes (#26372)

* Add type annotations to io.pytables

* Start correcting mypy errors in core.window

* Complete misc type fixes

* Fix import sort on test_groupby.py

* Update after code reviews

* Whatsnew, second rev indexing, window and pytables

* Annotate Set in core.window

* Define attributes as List[str]

Author: gwrome

doc/source/whatsnew/v0.25.0.rst

@@ -249,6 +249,7 @@ Other API Changes
 - Comparing :class:`Timestamp` with unsupported objects now returns :py:obj:`NotImplemented` instead of raising ``TypeError``. This implies that unsupported rich comparisons are delegated to the other object, and are now consistent with Python 3 behavior for ``datetime`` objects (:issue:`24011`)
 - Bug in :meth:`DatetimeIndex.snap` which didn't preserving the ``name`` of the input :class:`Index` (:issue:`25575`)
 - The ``arg`` argument in :meth:`pandas.core.groupby.DataFrameGroupBy.agg` has been renamed to ``func`` (:issue:`26089`)
+- The ``arg`` argument in :meth:`pandas.core.window._Window.aggregate` has been renamed to ``func`` (:issue:`26372`)
 
 .. _whatsnew_0250.deprecations:
 

mypy.ini

@@ -15,37 +15,4 @@ ignore_errors=True
 ignore_errors=True
 
 [mypy-pandas.core.indexes.timedeltas]
-ignore_errors=True
-
-[mypy-pandas.core.indexing]
-ignore_errors=True
-
-[mypy-pandas.core.internals.blocks]
-ignore_errors=True
-
-[mypy-pandas.core.panel]
-ignore_errors=True
-
-[mypy-pandas.core.reshape.merge]
-ignore_errors=True
-
-[mypy-pandas.core.reshape.reshape]
-ignore_errors=True
-
-[mypy-pandas.core.series]
-ignore_errors=True
-
-[mypy-pandas.core.util.hashing]
-ignore_errors=True
-
-[mypy-pandas.core.window]
-ignore_errors=True
-
-[mypy-pandas.io.pytables]
-ignore_errors=True
-
-[mypy-pandas.util._doctools]
-ignore_errors=True
-
-[mypy-pandas.util.testing]
-ignore_errors=True
+ignore_errors=True

pandas/core/base.py

@@ -1569,5 +1569,5 @@ def duplicated(self, keep='first'):
     # ----------------------------------------------------------------------
     # abstracts
 
-    def _update_inplace(self, result, **kwargs):
+    def _update_inplace(self, result, verify_is_copy=True, **kwargs):
         raise AbstractMethodError(self)

pandas/core/generic.py

@@ -6,7 +6,7 @@
 import operator
 import pickle
 from textwrap import dedent
-from typing import FrozenSet, List, Set
+from typing import Callable, FrozenSet, List, Set
 import warnings
 import weakref
 
@@ -3680,7 +3680,7 @@ class   animal   locomotion
         result._set_is_copy(self, copy=not result._is_view)
         return result
 
-    _xs = xs
+    _xs = xs  # type: Callable
 
     def select(self, crit, axis=0):
         """

pandas/core/indexing.py

@@ -88,8 +88,8 @@ class IndexingError(Exception):
 
 
 class _NDFrameIndexer(_NDFrameIndexerBase):
-    _valid_types = None
-    _exception = KeyError
+    _valid_types = None  # type: str
+    _exception = Exception
     axis = None
 
     def __call__(self, axis=None):

pandas/core/internals/blocks.py

@@ -7,7 +7,8 @@
 
 import numpy as np
 
-from pandas._libs import internals as libinternals, lib, tslib, tslibs
+from pandas._libs import lib, tslib, tslibs
+import pandas._libs.internals as libinternals
 from pandas._libs.tslibs import Timedelta, conversion, is_null_datetimelike
 from pandas.util._validators import validate_bool_kwarg
 
@@ -2050,12 +2051,15 @@ def get_values(self, dtype=None):
 class DatetimeBlock(DatetimeLikeBlockMixin, Block):
     __slots__ = ()
     is_datetime = True
-    _can_hold_na = True
 
     def __init__(self, values, placement, ndim=None):
         values = self._maybe_coerce_values(values)
         super().__init__(values, placement=placement, ndim=ndim)
 
+    @property
+    def _can_hold_na(self):
+        return True
+
     def _maybe_coerce_values(self, values):
         """Input validation for values passed to __init__. Ensure that
         we have datetime64ns, coercing if necessary.

pandas/core/reshape/merge.py

@@ -8,7 +8,8 @@
 
 import numpy as np
 
-from pandas._libs import hashtable as libhashtable, join as libjoin, lib
+from pandas._libs import hashtable as libhashtable, lib
+import pandas._libs.join as libjoin
 from pandas.errors import MergeError
 from pandas.util._decorators import Appender, Substitution
 

pandas/core/reshape/reshape.py

@@ -3,7 +3,8 @@
 
 import numpy as np
 
-from pandas._libs import algos as _algos, reshape as _reshape
+import pandas._libs.algos as _algos
+import pandas._libs.reshape as _reshape
 from pandas._libs.sparse import IntIndex
 
 from pandas.core.dtypes.cast import maybe_promote

pandas/core/util/hashing.py

@@ -5,7 +5,8 @@
 
 import numpy as np
 
-from pandas._libs import hashing, tslibs
+import pandas._libs.hashing as hashing
+import pandas._libs.tslibs as tslibs
 
 from pandas.core.dtypes.cast import infer_dtype_from_scalar
 from pandas.core.dtypes.common import (

pandas/core/window.py

@@ -5,6 +5,7 @@
 from collections import defaultdict
 from datetime import timedelta
 from textwrap import dedent
+from typing import Set
 import warnings
 
 import numpy as np
@@ -42,7 +43,7 @@
 class _Window(PandasObject, SelectionMixin):
     _attributes = ['window', 'min_periods', 'center', 'win_type',
                    'axis', 'on', 'closed']
-    exclusions = set()
+    exclusions = set()  # type: Set[str]
 
     def __init__(self, obj, window=None, min_periods=None,
                  center=False, win_type=None, axis=0, on=None, closed=None,
@@ -305,10 +306,10 @@ def _center_window(self, result, window):
                 result = np.copy(result[tuple(lead_indexer)])
         return result
 
-    def aggregate(self, arg, *args, **kwargs):
-        result, how = self._aggregate(arg, *args, **kwargs)
+    def aggregate(self, func, *args, **kwargs):
+        result, how = self._aggregate(func, *args, **kwargs)
         if result is None:
-            return self.apply(arg, raw=False, args=args, kwargs=kwargs)
+            return self.apply(func, raw=False, args=args, kwargs=kwargs)
         return result
 
     agg = aggregate
@@ -788,7 +789,7 @@ def __init__(self, obj, *args, **kwargs):
     corr = GroupByMixin._dispatch('corr', other=None, pairwise=None)
     cov = GroupByMixin._dispatch('cov', other=None, pairwise=None)
 
-    def _apply(self, func, name, window=None, center=None,
+    def _apply(self, func, name=None, window=None, center=None,
                check_minp=None, **kwargs):
         """
         Dispatch to apply; we are stripping all of the _apply kwargs and

pandas/io/pytables.py

@@ -10,6 +10,7 @@
 import os
 import re
 import time
+from typing import List, Optional, Type, Union
 import warnings
 
 import numpy as np
@@ -2297,9 +2298,9 @@ class Fixed(StringMixin):
         parent : my parent HDFStore
         group  : the group node where the table resides
         """
-    pandas_kind = None
-    obj_type = None
-    ndim = None
+    pandas_kind = None  # type: str
+    obj_type = None  # type: Type[Union[DataFrame, Series]]
+    ndim = None  # type: int
     is_table = False
 
     def __init__(self, parent, group, encoding=None, errors='strict',
@@ -2459,7 +2460,7 @@ class GenericFixed(Fixed):
     """ a generified fixed version """
     _index_type_map = {DatetimeIndex: 'datetime', PeriodIndex: 'period'}
     _reverse_index_map = {v: k for k, v in _index_type_map.items()}
-    attributes = []
+    attributes = []  # type: List[str]
 
     # indexer helpders
     def _class_to_alias(self, cls):
@@ -3052,7 +3053,7 @@ class Table(Fixed):
 
         """
     pandas_kind = 'wide_table'
-    table_type = None
+    table_type = None  # type: str
     levels = 1
     is_table = True
     is_shape_reversed = False
@@ -3873,7 +3874,7 @@ class LegacyTable(Table):
         IndexCol(name='index', axis=1, pos=0),
         IndexCol(name='column', axis=2, pos=1, index_kind='columns_kind'),
         DataCol(name='fields', cname='values', kind_attr='fields', pos=2)
-    ]
+    ]  # type: Optional[List[IndexCol]]
     table_type = 'legacy'
     ndim = 3
 
@@ -4126,7 +4127,7 @@ class AppendableFrameTable(AppendableTable):
     pandas_kind = 'frame_table'
     table_type = 'appendable_frame'
     ndim = 2
-    obj_type = DataFrame
+    obj_type = DataFrame  # type: Type[Union[DataFrame, Series]]
 
     @property
     def is_transposed(self):

pandas/util/testing.py

@@ -21,7 +21,7 @@
 from pandas._config.localization import (  # noqa:F401
     can_set_locale, get_locales, set_locale)
 
-from pandas._libs import testing as _testing
+import pandas._libs.testing as _testing
 from pandas.compat import raise_with_traceback
 
 from pandas.core.dtypes.common import (