Unpin pycodestyle (#25789)

environment.yml

@@ -19,7 +19,7 @@ dependencies:
   - hypothesis>=3.82
   - isort
   - moto
-  - pycodestyle=2.4
+  - pycodestyle
   - pytest>=4.0.2
   - pytest-mock
   - sphinx

pandas/_libs/__init__.py

@@ -2,4 +2,4 @@
 # flake8: noqa
 
 from .tslibs import (
-    iNaT, NaT, Timestamp, Timedelta, OutOfBoundsDatetime, Period)
+    iNaT, NaT, NaTType, Timestamp, Timedelta, OutOfBoundsDatetime, Period)

pandas/_libs/tslibs/__init__.py

@@ -2,7 +2,7 @@
 # flake8: noqa
 
 from .conversion import normalize_date, localize_pydatetime, tz_convert_single
-from .nattype import NaT, iNaT, is_null_datetimelike
+from .nattype import NaT, NaTType, iNaT, is_null_datetimelike
 from .np_datetime import OutOfBoundsDatetime
 from .period import Period, IncompatibleFrequency
 from .timestamps import Timestamp

pandas/_libs/tslibs/nattype.pyx

@@ -353,7 +353,7 @@ class NaTType(_NaT):
 
         .. versionadded:: 0.23.0
         """)
-    day_name = _make_nan_func('day_name', # noqa:E128
+    day_name = _make_nan_func('day_name',  # noqa:E128
         """
         Return the day name of the Timestamp with specified locale.
 

pandas/core/arrays/array_.py

@@ -1,8 +1,12 @@
+from typing import Optional, Sequence, Union
+
+import numpy as np
+
 from pandas._libs import lib, tslibs
 
 from pandas.core.dtypes.common import (
     is_datetime64_ns_dtype, is_extension_array_dtype, is_timedelta64_ns_dtype)
-from pandas.core.dtypes.dtypes import registry
+from pandas.core.dtypes.dtypes import ExtensionDtype, registry
 
 from pandas import compat
 

pandas/core/arrays/base.py

@@ -6,6 +6,7 @@
    without warning.
 """
 import operator
+from typing import Any, Callable, Optional, Sequence, Tuple, Union
 
 import numpy as np
 
@@ -15,6 +16,7 @@
 from pandas.util._decorators import Appender, Substitution
 
 from pandas.core.dtypes.common import is_list_like
+from pandas.core.dtypes.dtypes import ExtensionDtype
 from pandas.core.dtypes.generic import ABCIndexClass, ABCSeries
 from pandas.core.dtypes.missing import isna
 
@@ -365,7 +367,7 @@ def isna(self):
         raise AbstractMethodError(self)
 
     def _values_for_argsort(self):
-        # type: () -> ndarray
+        # type: () -> np.ndarray
         """
         Return values for sorting.
 
@@ -597,7 +599,7 @@ def searchsorted(self, value, side="left", sorter=None):
         return arr.searchsorted(value, side=side, sorter=sorter)
 
     def _values_for_factorize(self):
-        # type: () -> Tuple[ndarray, Any]
+        # type: () -> Tuple[np.ndarray, Any]
         """
         Return an array and missing value suitable for factorization.
 
@@ -622,7 +624,7 @@ def _values_for_factorize(self):
         return self.astype(object), np.nan
 
     def factorize(self, na_sentinel=-1):
-        # type: (int) -> Tuple[ndarray, ExtensionArray]
+        # type: (int) -> Tuple[np.ndarray, ExtensionArray]
         """
         Encode the extension array as an enumerated type.
 

pandas/core/arrays/datetimelike.py

@@ -1,11 +1,12 @@
 # -*- coding: utf-8 -*-
 from datetime import datetime, timedelta
 import operator
+from typing import Any, Sequence, Tuple, Union
 import warnings
 
 import numpy as np
 
-from pandas._libs import NaT, algos, iNaT, lib
+from pandas._libs import NaT, NaTType, Timestamp, algos, iNaT, lib
 from pandas._libs.tslibs.period import (
     DIFFERENT_FREQ, IncompatibleFrequency, Period)
 from pandas._libs.tslibs.timedeltas import Timedelta, delta_to_nanoseconds
@@ -350,7 +351,7 @@ def __iter__(self):
 
     @property
     def asi8(self):
-        # type: () -> ndarray
+        # type: () -> np.ndarray
         """
         Integer representation of the values.
 
@@ -461,10 +462,10 @@ def __getitem__(self, key):
     def __setitem__(
             self,
             key,    # type: Union[int, Sequence[int], Sequence[bool], slice]
-            value,  # type: Union[NaTType, Scalar, Sequence[Scalar]]
+            value,  # type: Union[NaTType, Any, Sequence[Any]]
     ):
         # type: (...) -> None
-        # I'm fudging the types a bit here. The "Scalar" above really depends
+        # I'm fudging the types a bit here. "Any" above really depends
         # on type(self). For PeriodArray, it's Period (or stuff coercible
         # to a period in from_sequence). For DatetimeArray, it's Timestamp...
         # I don't know if mypy can do that, possibly with Generics.

pandas/core/arrays/datetimes.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from datetime import datetime, time, timedelta
 import textwrap
+from typing import Union
 import warnings
 
 import numpy as np

pandas/core/arrays/integer.py

@@ -510,7 +510,7 @@ def value_counts(self, dropna=True):
         return Series(array, index=index)
 
     def _values_for_argsort(self):
-        # type: () -> ndarray
+        # type: () -> np.ndarray
         """Return values for sorting.
 
         Returns

pandas/core/arrays/period.py

@@ -1,11 +1,12 @@
 # -*- coding: utf-8 -*-
 from datetime import timedelta
 import operator
+from typing import Any, Callable, Optional, Sequence, Union
 
 import numpy as np
 
 from pandas._libs.tslibs import (
-    NaT, frequencies as libfrequencies, iNaT, period as libperiod)
+    NaT, NaTType, frequencies as libfrequencies, iNaT, period as libperiod)
 from pandas._libs.tslibs.fields import isleapyear_arr
 from pandas._libs.tslibs.period import (
     DIFFERENT_FREQ, IncompatibleFrequency, Period, get_period_field_arr,
@@ -23,7 +24,7 @@
 from pandas.core.dtypes.missing import isna, notna
 
 import pandas.core.algorithms as algos
-from pandas.core.arrays import datetimelike as dtl
+from pandas.core.arrays import ExtensionArray, datetimelike as dtl
 import pandas.core.common as com
 
 from pandas.tseries import frequencies
@@ -536,11 +537,14 @@ def _sub_period(self, other):
     @Appender(dtl.DatetimeLikeArrayMixin._addsub_int_array.__doc__)
     def _addsub_int_array(
             self,
-            other,   # type: Union[Index, ExtensionArray, np.ndarray[int]]
-            op      # type: Callable[Any, Any]
+            other,      # type: Union[ExtensionArray, np.ndarray[int]]
+            op          # type: Callable[Any, Any]
     ):
         # type: (...) -> PeriodArray
 
+        # TODO: ABCIndexClass is a valid type for other but had to be excluded
+        # due to length of Py2 compatability comment; add back in once migrated
+        # to Py3 syntax
         assert op in [operator.add, operator.sub]
         if op is operator.sub:
             other = -other

pandas/core/arrays/sparse.py

@@ -6,13 +6,14 @@
 import numbers
 import operator
 import re
+from typing import Any, Callable, Union
 import warnings
 
 import numpy as np
 
 from pandas._libs import index as libindex, lib
 import pandas._libs.sparse as splib
-from pandas._libs.sparse import BlockIndex, IntIndex
+from pandas._libs.sparse import BlockIndex, IntIndex, SparseIndex
 from pandas._libs.tslibs import NaT
 import pandas.compat as compat
 from pandas.compat.numpy import function as nv
@@ -372,7 +373,7 @@ def _subtype_with_str(self):
 
 
 def _get_fill(arr):
-    # type: (SparseArray) -> ndarray
+    # type: (SparseArray) -> np.ndarray
     """
     Create a 0-dim ndarray containing the fill value
 

pandas/core/base.py

@@ -24,6 +24,7 @@
 
 from pandas.core import algorithms, common as com
 from pandas.core.accessor import DirNamesMixin
+from pandas.core.arrays import ExtensionArray
 import pandas.core.nanops as nanops
 
 _shared_docs = dict()

pandas/core/common.py

@@ -9,6 +9,7 @@
 from datetime import datetime, timedelta
 from functools import partial
 import inspect
+from typing import Any
 
 import numpy as np
 

pandas/core/dtypes/base.py

@@ -1,4 +1,6 @@
 """Extend pandas with custom array types"""
+from typing import List, Optional, Type
+
 import numpy as np
 
 from pandas.errors import AbstractMethodError
@@ -211,7 +213,7 @@ def __str__(self):
 
     @property
     def type(self):
-        # type: () -> type
+        # type: () -> Type
         """
         The scalar type for the array, e.g. ``int``
 

pandas/core/dtypes/dtypes.py

@@ -937,7 +937,7 @@ def construct_from_string(cls, string):
 
         if (string.lower() == 'interval' or
            cls._match.search(string) is not None):
-                return cls(string)
+            return cls(string)
 
         msg = ('Incorrectly formatted string passed to constructor. '
                'Valid formats include Interval or Interval[dtype] '

pandas/core/frame.py

@@ -19,6 +19,7 @@
 import sys
 import warnings
 from textwrap import dedent
+from typing import List, Union
 
 import numpy as np
 import numpy.ma as ma

pandas/core/groupby/groupby.py

@@ -12,6 +12,7 @@ class providing the base-class of operations.
 import datetime
 from functools import partial, wraps
 import types
+from typing import Optional, Type
 import warnings
 
 import numpy as np
@@ -1040,7 +1041,7 @@ def _bool_agg(self, val_test, skipna):
         """
 
         def objs_to_bool(vals):
-            # type: (np.ndarray) -> (np.ndarray, typing.Type)
+            # type: (np.ndarray) -> (np.ndarray, Type)
             if is_object_dtype(vals):
                 vals = np.array([bool(x) for x in vals])
             else:
@@ -1049,7 +1050,7 @@ def objs_to_bool(vals):
             return vals.view(np.uint8), np.bool
 
         def result_to_bool(result, inference):
-            # type: (np.ndarray, typing.Type) -> np.ndarray
+            # type: (np.ndarray, Type) -> np.ndarray
             return result.astype(inference, copy=False)
 
         return self._get_cythonized_result('group_any_all', self.grouper,
@@ -1738,7 +1739,7 @@ def quantile(self, q=0.5, interpolation='linear'):
         """
 
         def pre_processor(vals):
-            # type: (np.ndarray) -> (np.ndarray, Optional[typing.Type])
+            # type: (np.ndarray) -> (np.ndarray, Optional[Type])
             if is_object_dtype(vals):
                 raise TypeError("'quantile' cannot be performed against "
                                 "'object' dtypes!")
@@ -1753,7 +1754,7 @@ def pre_processor(vals):
             return vals, inference
 
         def post_processor(vals, inference):
-            # type: (np.ndarray, Optional[typing.Type]) -> np.ndarray
+            # type: (np.ndarray, Optional[Type]) -> np.ndarray
             if inference:
                 # Check for edge case
                 if not (is_integer_dtype(inference) and
@@ -2016,7 +2017,7 @@ def _get_cythonized_result(self, how, grouper, aggregate=False,
             Function to be applied to result of Cython function. Should accept
             an array of values as the first argument and type inferences as its
             second argument, i.e. the signature should be
-            (ndarray, typing.Type).
+            (ndarray, Type).
         **kwargs : dict
             Extra arguments to be passed back to Cython funcs
 

pandas/core/indexes/base.py

@@ -1,6 +1,7 @@
 from datetime import datetime, timedelta
 import operator
 from textwrap import dedent
+from typing import Union
 import warnings
 
 import numpy as np

pandas/core/internals/blocks.py

@@ -3,6 +3,7 @@
 import functools
 import inspect
 import re
+from typing import Any, List
 import warnings
 
 import numpy as np
@@ -1826,8 +1827,11 @@ def interpolate(self, method='pad', axis=0, inplace=False, limit=None,
                                  limit=limit),
             placement=self.mgr_locs)
 
-    def shift(self, periods, axis=0, fill_value=None):
-        # type: (int, Optional[BlockPlacement], Any) -> List[ExtensionBlock]
+    def shift(self,
+              periods,                  # type: int
+              axis=0,                   # type: libinternals.BlockPlacement
+              fill_value=None):         # type: Any
+        # type: (...) -> List[ExtensionBlock]
         """
         Shift the block by `periods`.
 

pandas/core/internals/managers.py

@@ -4,6 +4,7 @@
 import itertools
 import operator
 import re
+from typing import List, Optional, Union
 
 import numpy as np
 
@@ -18,6 +19,7 @@
     _NS_DTYPE, is_datetimelike_v_numeric, is_extension_array_dtype,
     is_extension_type, is_list_like, is_numeric_v_string_like, is_scalar)
 import pandas.core.dtypes.concat as _concat
+from pandas.core.dtypes.dtypes import ExtensionDtype
 from pandas.core.dtypes.generic import ABCExtensionArray, ABCSeries
 from pandas.core.dtypes.missing import isna
 

pandas/io/formats/format.py

@@ -440,7 +440,6 @@ def _chk_truncate(self):
         max_rows = self.max_rows
 
         if max_cols == 0 or max_rows == 0:  # assume we are in the terminal
-                                            # (why else = 0)
             (w, h) = get_terminal_size()
             self.w = w
             self.h = h

pandas/tests/frame/test_alter_axes.py

@@ -201,7 +201,8 @@ def test_set_index_pass_arrays_duplicate(self, frame_of_index_cols, drop,
         # need to adapt first drop for case that both keys are 'A' --
         # cannot drop the same column twice;
         # use "is" because == would give ambiguous Boolean error for containers
-        first_drop = False if (keys[0] is 'A' and keys[1] is 'A') else drop
+        first_drop = False if (
+            keys[0] is 'A' and keys[1] is 'A') else drop  # noqa: F632
 
         # to test against already-tested behaviour, we add sequentially,
         # hence second append always True; must wrap keys in list, otherwise
@@ -1272,7 +1273,7 @@ def test_rename_axis_style_raises(self):
             df.rename(id, mapper=id)
 
     def test_reindex_api_equivalence(self):
-            # equivalence of the labels/axis and index/columns API's
+        # equivalence of the labels/axis and index/columns API's
         df = DataFrame([[1, 2, 3], [3, 4, 5], [5, 6, 7]],
                        index=['a', 'b', 'c'],
                        columns=['d', 'e', 'f'])

pandas/tests/groupby/test_apply.py

@@ -9,7 +9,7 @@
 
 
 def test_apply_issues():
-        # GH 5788
+    # GH 5788
 
     s = """2011.05.16,00:00,1.40893
 2011.05.16,01:00,1.40760