fix CI build errors:

TST: Check pytables<3.5.1 when skipping (pandas-dev#25773)

* TST: Check pytables<3.5.1 when skipping

3.5.1 was made available on conda, causing
'xfail_non_writeable' tests to fail.

* TST: Skip geopandas downstream test

xref pandas-devgh-25778

added 'except NULL' for get_c_string_buf_and_size in util.pxd(bug without)

fixed lint error

Fixed code issue from compat with new numpydoc (pandas-dev#26188)

fixed docstring

Author: anmyachev

environment.yml

@@ -21,7 +21,8 @@ dependencies:
   - moto
   - pytest>=4.0
   - sphinx
-  - numpydoc
+  - numpydoc>=0.9.0
+  - pip
 
   # optional
   - beautifulsoup4>=4.2.1

pandas/_libs/tslibs/nattype.pyx

@@ -331,7 +331,7 @@ 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/_libs/tslibs/util.pxd

@@ -34,8 +34,10 @@ cdef extern from *:
         } while(0)
     #endif
     """
-    void PyUnicode_AsUTF8AndSize(object py_string, const char* buffer, Py_ssize_t* length)
-    void PyBytes_AsStringAndSize(object py_string, char** buffer, Py_ssize_t* length)
+    void PyUnicode_AsUTF8AndSize(object py_string,
+                                 const char* buffer, Py_ssize_t* length)
+    void PyBytes_AsStringAndSize(object py_string,
+                                 char** buffer, Py_ssize_t* length)
 
 cdef extern from "Python.h":
     # Note: importing extern-style allows us to declare these as nogil
@@ -256,8 +258,8 @@ cdef inline bint is_nan(object val):
     return is_complex_object(val) and val != val
 
 
-cdef inline const char* get_c_string_buf_and_size(object py_string,
-                                                  Py_ssize_t *length) except NULL:
+cdef inline const char* get_c_string_buf_and_size(
+    object py_string, Py_ssize_t *length) except NULL:
     """
     Extract internal char* buffer of unicode or bytes object `py_string` with
     getting length of this internal buffer saved in `length`.

pandas/core/arrays/array_.py

@@ -7,11 +7,10 @@
 from pandas import compat
 
 
-def array(data,         # type: Sequence[object]
-          dtype=None,   # type: Optional[Union[str, np.dtype, ExtensionDtype]]
-          copy=True,    # type: bool
+def array(data,
+          dtype=None,
+          copy=True,
           ):
-    # type: (...) -> ExtensionArray
     """
     Create an array.
 

pandas/core/arrays/base.py

@@ -181,7 +181,6 @@ def _from_factorized(cls, values, original):
     # ------------------------------------------------------------------------
 
     def __getitem__(self, item):
-        # type (Any) -> Any
         """
         Select a subset of self.
 
@@ -213,7 +212,6 @@ def __getitem__(self, item):
         raise AbstractMethodError(self)
 
     def __setitem__(self, key, value):
-        # type: (Union[int, np.ndarray], Any) -> None
         """
         Set one or more values inplace.
 
@@ -261,7 +259,6 @@ def __setitem__(self, key, value):
         )
 
     def __len__(self):
-        # type: () -> int
         """
         Length of this array
 
@@ -286,31 +283,27 @@ def __iter__(self):
     # ------------------------------------------------------------------------
     @property
     def dtype(self):
-        # type: () -> ExtensionDtype
         """
         An instance of 'ExtensionDtype'.
         """
         raise AbstractMethodError(self)
 
     @property
     def shape(self):
-        # type: () -> Tuple[int, ...]
         """
         Return a tuple of the array dimensions.
         """
         return (len(self),)
 
     @property
     def ndim(self):
-        # type: () -> int
         """
         Extension Arrays are only allowed to be 1-dimensional.
         """
         return 1
 
     @property
     def nbytes(self):
-        # type: () -> int
         """
         The number of bytes needed to store this object in memory.
         """
@@ -342,7 +335,6 @@ def astype(self, dtype, copy=True):
         return np.array(self, dtype=dtype, copy=copy)
 
     def isna(self):
-        # type: () -> Union[ExtensionArray, np.ndarray]
         """
         A 1-D array indicating if each value is missing.
 
@@ -365,7 +357,6 @@ def isna(self):
         raise AbstractMethodError(self)
 
     def _values_for_argsort(self):
-        # type: () -> ndarray
         """
         Return values for sorting.
 
@@ -597,7 +588,6 @@ 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]
         """
         Return an array and missing value suitable for factorization.
 
@@ -622,7 +612,6 @@ def _values_for_factorize(self):
         return self.astype(object), np.nan
 
     def factorize(self, na_sentinel=-1):
-        # type: (int) -> Tuple[ndarray, ExtensionArray]
         """
         Encode the extension array as an enumerated type.
 
@@ -725,7 +714,6 @@ def repeat(self, repeats, axis=None):
     # ------------------------------------------------------------------------
 
     def take(self, indices, allow_fill=False, fill_value=None):
-        # type: (Sequence[int], bool, Optional[Any]) -> ExtensionArray
         """
         Take elements from an array.
 
@@ -815,7 +803,6 @@ def take(self, indices, allow_fill=False, fill_value=None):
         raise AbstractMethodError(self)
 
     def copy(self, deep=False):
-        # type: (bool) -> ExtensionArray
         """
         Return a copy of the array.
 
@@ -852,7 +839,6 @@ def __repr__(self):
                                dtype=self.dtype)
 
     def _formatter(self, boxed=False):
-        # type: (bool) -> Callable[[Any], Optional[str]]
         """Formatting function for scalar values.
 
         This is used in the default '__repr__'. The returned formatting
@@ -880,7 +866,6 @@ def _formatter(self, boxed=False):
         return repr
 
     def _formatting_values(self):
-        # type: () -> np.ndarray
         # At the moment, this has to be an array since we use result.dtype
         """
         An array of values to be printed in, e.g. the Series repr
@@ -897,7 +882,6 @@ def _formatting_values(self):
 
     @classmethod
     def _concat_same_type(cls, to_concat):
-        # type: (Sequence[ExtensionArray]) -> ExtensionArray
         """
         Concatenate multiple array
 
@@ -920,7 +904,6 @@ def _concat_same_type(cls, to_concat):
 
     @property
     def _ndarray_values(self):
-        # type: () -> np.ndarray
         """
         Internal pandas method for lossy conversion to a NumPy ndarray.
 

pandas/core/arrays/datetimelike.py

@@ -58,7 +58,6 @@ def _get_attributes_dict(self):
 
     @property
     def _scalar_type(self):
-        # type: () -> Union[type, Tuple[type]]
         """The scalar associated with this datelike
 
         * PeriodArray : Period
@@ -68,7 +67,6 @@ def _scalar_type(self):
         raise AbstractMethodError(self)
 
     def _scalar_from_string(self, value):
-        # type: (str) -> Union[Period, Timestamp, Timedelta, NaTType]
         """
         Construct a scalar type from a string.
 
@@ -89,7 +87,6 @@ def _scalar_from_string(self, value):
         raise AbstractMethodError(self)
 
     def _unbox_scalar(self, value):
-        # type: (Union[Period, Timestamp, Timedelta, NaTType]) -> int
         """
         Unbox the integer value of a scalar `value`.
 
@@ -109,7 +106,6 @@ def _unbox_scalar(self, value):
         raise AbstractMethodError(self)
 
     def _check_compatible_with(self, other):
-        # type: (Union[Period, Timestamp, Timedelta, NaTType]) -> None
         """
         Verify that `self` and `other` are compatible.
 
@@ -350,7 +346,6 @@ def __iter__(self):
 
     @property
     def asi8(self):
-        # type: () -> ndarray
         """
         Integer representation of the values.
 
@@ -460,10 +455,9 @@ def __getitem__(self, key):
 
     def __setitem__(
             self,
-            key,    # type: Union[int, Sequence[int], Sequence[bool], slice]
-            value,  # type: Union[NaTType, Scalar, Sequence[Scalar]]
+            key,
+            value,
     ):
-        # type: (...) -> None
         # I'm fudging the types a bit here. The "Scalar" 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...

pandas/core/arrays/datetimes.py

@@ -274,7 +274,7 @@ class DatetimeArray(dtl.DatetimeLikeArrayMixin,
     # Constructors
 
     _attributes = ["freq", "tz"]
-    _dtype = None  # type: Union[np.dtype, DatetimeTZDtype]
+    _dtype = None
     _freq = None
 
     def __init__(self, values, dtype=_NS_DTYPE, freq=None, copy=False):
@@ -514,7 +514,6 @@ def _box_func(self):
 
     @property
     def dtype(self):
-        # type: () -> Union[np.dtype, DatetimeTZDtype]
         """
         The dtype for the DatetimeArray.
 

pandas/core/arrays/integer.py

@@ -510,7 +510,6 @@ def value_counts(self, dropna=True):
         return Series(array, index=index)
 
     def _values_for_argsort(self):
-        # type: () -> ndarray
         """Return values for sorting.
 
         Returns

pandas/core/arrays/period.py

@@ -180,7 +180,6 @@ def _simple_new(cls, values, freq=None, **kwargs):
 
     @classmethod
     def _from_sequence(cls, scalars, dtype=None, copy=False):
-        # type: (Sequence[Optional[Period]], PeriodDtype, bool) -> PeriodArray
         if dtype:
             freq = dtype.freq
         else:
@@ -243,7 +242,6 @@ def _generate_range(cls, start, end, periods, freq, fields):
     # DatetimeLike Interface
 
     def _unbox_scalar(self, value):
-        # type: (Union[Period, NaTType]) -> int
         if value is NaT:
             return value.value
         elif isinstance(value, self._scalar_type):
@@ -255,7 +253,6 @@ def _unbox_scalar(self, value):
                              .format(val=value))
 
     def _scalar_from_string(self, value):
-        # type: (str) -> Period
         return Period(value, freq=self.freq)
 
     def _check_compatible_with(self, other):
@@ -536,10 +533,9 @@ 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,
+            op
     ):
-        # type: (...) -> PeriodArray
 
         assert op in [operator.add, operator.sub]
         if op is operator.sub:
@@ -710,7 +706,6 @@ def _raise_on_incompatible(left, right):
 # Constructor Helpers
 
 def period_array(data, freq=None, copy=False):
-    # type: (Sequence[Optional[Period]], Optional[Tick]) -> PeriodArray
     """
     Construct a new PeriodArray from a sequence of Period scalars.
 

pandas/core/arrays/sparse.py

@@ -79,7 +79,6 @@ class SparseDtype(ExtensionDtype):
     _metadata = ('_dtype', '_fill_value', '_is_na_fill_value')
 
     def __init__(self, dtype=np.float64, fill_value=None):
-        # type: (Union[str, np.dtype, 'ExtensionDtype', type], Any) -> None
         from pandas.core.dtypes.missing import na_value_for_dtype
         from pandas.core.dtypes.common import (
             pandas_dtype, is_string_dtype, is_scalar
@@ -372,7 +371,6 @@ def _subtype_with_str(self):
 
 
 def _get_fill(arr):
-    # type: (SparseArray) -> ndarray
     """
     Create a 0-dim ndarray containing the fill value
 
@@ -413,7 +411,6 @@ def _sparse_array_op(left, right, op, name):
     -------
     SparseArray
     """
-    # type: (SparseArray, SparseArray, Callable, str) -> Any
     if name.startswith('__'):
         # For lookups in _libs.sparse we need non-dunder op name
         name = name[2:-2]
@@ -672,7 +669,6 @@ def __init__(self, data, sparse_index=None, index=None, fill_value=None,
 
     @classmethod
     def _simple_new(cls, sparse_array, sparse_index, dtype):
-        # type: (np.ndarray, SparseIndex, SparseDtype) -> 'SparseArray'
         new = cls([])
         new._sparse_index = sparse_index
         new._sparse_values = sparse_array

pandas/core/base.py

@@ -785,7 +785,6 @@ def base(self):
 
     @property
     def array(self):
-        # type: () -> ExtensionArray
         """
         The ExtensionArray of the data backing this Series or Index.
 

pandas/core/common.py

@@ -91,7 +91,6 @@ def maybe_box_datetimelike(value):
 
 
 def is_bool_indexer(key):
-    # type: (Any) -> bool
     """
     Check whether `key` is a valid boolean indexer.
 

pandas/core/dtypes/base.py

@@ -64,7 +64,6 @@ def __ne__(self, other):
 
     @property
     def names(self):
-        # type: () -> Optional[List[str]]
         """Ordered list of field names, or None if there are no fields.
 
         This is for compatibility with NumPy arrays, and may be removed in the

pandas/core/dtypes/dtypes.py

@@ -937,8 +937,8 @@ def construct_from_string(cls, string):
             raise TypeError(msg.format(typ=type(string)))
 
         if (string.lower() == 'interval' or
-            cls._match.search(string) is not None):
-                return cls(string)
+                cls._match.search(string) is not None):
+            return cls(string)
 
         msg = ('Incorrectly formatted string passed to constructor. '
                'Valid formats include Interval or Interval[dtype] '

pandas/core/frame.py

@@ -6191,11 +6191,10 @@ def diff(self, periods=1, axis=0):
     # Function application
 
     def _gotitem(self,
-                 key,           # type: Union[str, List[str]]
-                 ndim,          # type: int
-                 subset=None    # type: Union[Series, DataFrame, None]
+                 key,
+                 ndim,
+                 subset=None
                  ):
-        # type: (...) -> Union[Series, DataFrame]
         """
         Sub-classes to define. Return a sliced object.