From 3f275aa2d7ac3529555b08a6716eb057bad80d12 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 2 Nov 2020 14:16:40 +0000
Subject: [PATCH 01/22] refactor rest of core

---
 pandas/core/aggregation.py         |  12 +--
 pandas/core/algorithms.py          |  30 +++---
 pandas/core/apply.py               |   7 +-
 pandas/core/array_algos/replace.py |   3 +-
 pandas/core/base.py                |  17 ++--
 pandas/core/common.py              |   4 +-
 pandas/core/construction.py        |  21 ++--
 pandas/core/frame.py               |   8 +-
 pandas/core/generic.py             | 151 ++++++++++++++---------------
 pandas/core/indexers.py            |  21 ++--
 pandas/core/indexing.py            |  26 ++---
 pandas/core/missing.py             |   2 +-
 pandas/core/nanops.py              |  27 ++----
 pandas/core/resample.py            |  15 +--
 pandas/core/series.py              |  60 +++++-------
 pandas/core/sorting.py             |   6 +-
 16 files changed, 188 insertions(+), 222 deletions(-)

diff --git a/pandas/core/aggregation.py b/pandas/core/aggregation.py
index c64f0bd71cf84..0af855d5a504e 100644
--- a/pandas/core/aggregation.py
+++ b/pandas/core/aggregation.py
@@ -387,7 +387,6 @@ def validate_func_kwargs(
     >>> validate_func_kwargs({'one': 'min', 'two': 'max'})
     (['one', 'two'], ['min', 'max'])
     """
-    no_arg_message = "Must provide 'func' or named aggregation **kwargs."
     tuple_given_message = "func is expected but received {} in **kwargs."
     columns = list(kwargs)
     func = []
@@ -396,6 +395,7 @@ def validate_func_kwargs(
             raise TypeError(tuple_given_message.format(type(col_func).__name__))
         func.append(col_func)
     if not columns:
+        no_arg_message = "Must provide 'func' or named aggregation **kwargs."
         raise TypeError(no_arg_message)
     return columns, func
 
@@ -497,14 +497,14 @@ def transform_dict_like(
         try:
             results[name] = transform(colg, how, 0, *args, **kwargs)
         except Exception as err:
-            if (
-                str(err) == "Function did not transform"
-                or str(err) == "No transform functions were provided"
-            ):
+            if str(err) in [
+                "Function did not transform",
+                "No transform functions were provided",
+            ]:
                 raise err
 
     # combine results
-    if len(results) == 0:
+    if not results:
         raise ValueError("Transform function failed")
     return concat(results, axis=1)
 
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index e9e04ace784b6..4c3714edc85c1 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -100,11 +100,13 @@ def _ensure_data(
         values = extract_array(values, extract_numpy=True)
 
     # we check some simple dtypes first
-    if is_object_dtype(dtype):
-        return ensure_object(np.asarray(values)), np.dtype("object")
-    elif is_object_dtype(values) and dtype is None:
+    if (
+        is_object_dtype(dtype)
+        or not is_object_dtype(dtype)
+        and is_object_dtype(values)
+        and dtype is None
+    ):
         return ensure_object(np.asarray(values)), np.dtype("object")
-
     try:
         if is_bool_dtype(values) or is_bool_dtype(dtype):
             # we are actually coercing to uint64
@@ -137,12 +139,10 @@ def _ensure_data(
             from pandas import PeriodIndex
 
             values = PeriodIndex(values)
-            dtype = values.dtype
         elif is_timedelta64_dtype(vals_dtype) or is_timedelta64_dtype(dtype):
             from pandas import TimedeltaIndex
 
             values = TimedeltaIndex(values)
-            dtype = values.dtype
         else:
             # Datetime
             if values.ndim > 1 and is_datetime64_ns_dtype(vals_dtype):
@@ -156,8 +156,7 @@ def _ensure_data(
             from pandas import DatetimeIndex
 
             values = DatetimeIndex(values)
-            dtype = values.dtype
-
+        dtype = values.dtype
         return values.asi8, dtype
 
     elif is_categorical_dtype(vals_dtype) and (
@@ -821,10 +820,9 @@ def value_counts_arraylike(values, dropna: bool):
         keys, counts = f(values, dropna)
 
         mask = isna(values)
-        if not dropna and mask.any():
-            if not isna(keys).any():
-                keys = np.insert(keys, 0, np.NaN)
-                counts = np.insert(counts, 0, mask.sum())
+        if not dropna and mask.any() and not isna(keys).any():
+            keys = np.insert(keys, 0, np.NaN)
+            counts = np.insert(counts, 0, mask.sum())
 
     keys = _reconstruct_data(keys, original.dtype, original)
 
@@ -1684,9 +1682,8 @@ def take_nd(
                     dtype, fill_value = arr.dtype, arr.dtype.type()
 
     flip_order = False
-    if arr.ndim == 2:
-        if arr.flags.f_contiguous:
-            flip_order = True
+    if arr.ndim == 2 and arr.flags.f_contiguous:
+        flip_order = True
 
     if flip_order:
         arr = arr.T
@@ -1861,8 +1858,7 @@ def searchsorted(arr, value, side="left", sorter=None):
         if isinstance(value, Timestamp) and value.tzinfo is None:
             value = value.to_datetime64()
 
-    result = arr.searchsorted(value, side=side, sorter=sorter)
-    return result
+    return arr.searchsorted(value, side=side, sorter=sorter)
 
 
 # ---- #
diff --git a/pandas/core/apply.py b/pandas/core/apply.py
index 002e260742dc5..9909b2c0dc53a 100644
--- a/pandas/core/apply.py
+++ b/pandas/core/apply.py
@@ -377,9 +377,10 @@ def wrap_results_for_axis(
             else:
                 raise
 
-        if not isinstance(results[0], ABCSeries):
-            if len(result.index) == len(self.res_columns):
-                result.index = self.res_columns
+        if not isinstance(results[0], ABCSeries) and len(result.index) == len(
+            self.res_columns
+        ):
+            result.index = self.res_columns
 
         if len(result.columns) == len(res_index):
             result.columns = res_index
diff --git a/pandas/core/array_algos/replace.py b/pandas/core/array_algos/replace.py
index 9eaa265adab2b..406ef60b2d9e7 100644
--- a/pandas/core/array_algos/replace.py
+++ b/pandas/core/array_algos/replace.py
@@ -47,8 +47,7 @@ def _check_comparison_types(
         if is_scalar(result) and isinstance(a, np.ndarray):
             type_names = [type(a).__name__, type(b).__name__]
 
-            if isinstance(a, np.ndarray):
-                type_names[0] = f"ndarray(dtype={a.dtype})"
+            type_names[0] = f"ndarray(dtype={a.dtype})"
 
             raise TypeError(
                 f"Cannot compare types {repr(type_names[0])} and {repr(type_names[1])}"
diff --git a/pandas/core/base.py b/pandas/core/base.py
index c91e4db004f2a..cc45f34032527 100644
--- a/pandas/core/base.py
+++ b/pandas/core/base.py
@@ -284,10 +284,9 @@ def _try_aggregate_string_function(self, arg: str, *args, **kwargs):
             return f
 
         f = getattr(np, arg, None)
-        if f is not None:
-            if hasattr(self, "__array__"):
-                # in particular exclude Window
-                return f(self, *args, **kwargs)
+        if f is not None and hasattr(self, "__array__"):
+            # in particular exclude Window
+            return f(self, *args, **kwargs)
 
         raise AttributeError(
             f"'{arg}' is not a valid function for '{type(self).__name__}' object"
@@ -570,8 +569,8 @@ def to_numpy(self, dtype=None, copy=False, na_value=lib.no_default, **kwargs):
         # TODO(GH-24345): Avoid potential double copy
         if copy or na_value is not lib.no_default:
             result = result.copy()
-            if na_value is not lib.no_default:
-                result[self.isna()] = na_value
+        if na_value is not lib.no_default:
+            result[self.isna()] = na_value
         return result
 
     @property
@@ -974,7 +973,7 @@ def value_counts(
         NaN    1
         dtype: int64
         """
-        result = value_counts(
+        return value_counts(
             self,
             sort=sort,
             ascending=ascending,
@@ -982,7 +981,6 @@ def value_counts(
             bins=bins,
             dropna=dropna,
         )
-        return result
 
     def unique(self):
         values = self._values
@@ -1244,8 +1242,7 @@ def searchsorted(self, value, side="left", sorter=None) -> np.ndarray:
 
     def drop_duplicates(self, keep="first"):
         duplicated = self.duplicated(keep=keep)
-        result = self[np.logical_not(duplicated)]
-        return result
+        return self[np.logical_not(duplicated)]
 
     def duplicated(self, keep="first"):
         return duplicated(self._values, keep=keep)
diff --git a/pandas/core/common.py b/pandas/core/common.py
index b860c83f89cbc..0f7228be28d3f 100644
--- a/pandas/core/common.py
+++ b/pandas/core/common.py
@@ -128,8 +128,10 @@ def is_bool_indexer(key: Any) -> bool:
             key = np.asarray(key)
 
             if not lib.is_bool_array(key):
-                na_msg = "Cannot mask with non-boolean array containing NA / NaN values"
                 if isna(key).any():
+                    na_msg = (
+                        "Cannot mask with non-boolean array containing NA / NaN values"
+                    )
                     raise ValueError(na_msg)
                 return False
             return True
diff --git a/pandas/core/construction.py b/pandas/core/construction.py
index 7901e150a7ff4..0a702849e4c4e 100644
--- a/pandas/core/construction.py
+++ b/pandas/core/construction.py
@@ -347,8 +347,7 @@ def array(
     elif is_timedelta64_ns_dtype(dtype):
         return TimedeltaArray._from_sequence(data, dtype=dtype, copy=copy)
 
-    result = PandasArray._from_sequence(data, dtype=dtype, copy=copy)
-    return result
+    return PandasArray._from_sequence(data, dtype=dtype, copy=copy)
 
 
 def extract_array(obj: AnyArrayLike, extract_numpy: bool = False) -> ArrayLike:
@@ -551,9 +550,13 @@ def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bo
         Otherwise an object array is returned.
     """
     # perf shortcut as this is the most common case
-    if isinstance(arr, np.ndarray):
-        if maybe_castable(arr) and not copy and dtype is None:
-            return arr
+    if (
+        isinstance(arr, np.ndarray)
+        and maybe_castable(arr)
+        and not copy
+        and dtype is None
+    ):
+        return arr
 
     if isinstance(dtype, ExtensionDtype) and (dtype.kind != "M" or is_sparse(dtype)):
         # create an extension array from its dtype
@@ -575,9 +578,11 @@ def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bo
 
         # Take care in creating object arrays (but iterators are not
         # supported):
-        if is_object_dtype(dtype) and (
-            is_list_like(subarr)
-            and not (is_iterator(subarr) or isinstance(subarr, np.ndarray))
+        if (
+            is_object_dtype(dtype)
+            and is_list_like(subarr)
+            and not is_iterator(subarr)
+            and not isinstance(subarr, np.ndarray)
         ):
             subarr = construct_1d_object_array_from_listlike(subarr)
         elif not is_extension_array_dtype(subarr):
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 5134529d9c21f..02cfd057169ea 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -701,7 +701,7 @@ def _repr_fits_horizontal_(self, ignore_width: bool = False) -> bool:
         # and to_string on entire frame may be expensive
         d = self
 
-        if not (max_rows is None):  # unlimited rows
+        if max_rows is not None:  # unlimited rows
             # min of two, where one may be None
             d = d.iloc[: min(max_rows, len(d))]
         else:
@@ -1934,10 +1934,10 @@ def to_records(
                 np.asarray(self.iloc[:, i]) for i in range(len(self.columns))
             ]
 
-            count = 0
             index_names = list(self.index.names)
 
             if isinstance(self.index, MultiIndex):
+                count = 0
                 for i, n in enumerate(index_names):
                     if n is None:
                         index_names[i] = f"level_{count}"
@@ -3179,7 +3179,7 @@ def _set_value(self, index, col, value, takeable: bool = False):
         takeable : interpret the index/col as indexers, default False
         """
         try:
-            if takeable is True:
+            if takeable:
                 series = self._ixs(col, axis=1)
                 series._set_value(index, value, takeable=True)
                 return
@@ -4913,7 +4913,7 @@ class    max    type
 
             multi_col = isinstance(self.columns, MultiIndex)
             for i, (lev, lab) in reversed(list(enumerate(to_insert))):
-                if not (level is None or i in level):
+                if level is not None and i not in level:
                     continue
                 name = names[i]
                 if multi_col:
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index c90ab9cceea8c..faaee91a8a707 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -501,7 +501,7 @@ def _get_block_manager_axis(cls, axis: Axis) -> int:
     def _get_axis_resolvers(self, axis: str) -> Dict[str, Union[Series, MultiIndex]]:
         # index or columns
         axis_index = getattr(self, axis)
-        d = dict()
+        d = {}
         prefix = axis[0]
 
         for i, name in enumerate(axis_index.names):
@@ -770,8 +770,7 @@ def droplevel(self: FrameOrSeries, level, axis=0) -> FrameOrSeries:
         """
         labels = self._get_axis(axis)
         new_labels = labels.droplevel(level)
-        result = self.set_axis(new_labels, axis=axis, inplace=False)
-        return result
+        return self.set_axis(new_labels, axis=axis, inplace=False)
 
     def pop(self, item: Label) -> Union[Series, Any]:
         result = self[item]
@@ -1435,8 +1434,7 @@ def __invert__(self):
             return self
 
         new_data = self._mgr.apply(operator.invert)
-        result = self._constructor(new_data).__finalize__(self, method="__invert__")
-        return result
+        return self._constructor(new_data).__finalize__(self, method="__invert__")
 
     def __nonzero__(self):
         raise ValueError(
@@ -2006,8 +2004,7 @@ def _repr_data_resource_(self):
 
             as_json = data.to_json(orient="table")
             as_json = cast(str, as_json)
-            payload = json.loads(as_json, object_pairs_hook=collections.OrderedDict)
-            return payload
+            return json.loads(as_json, object_pairs_hook=collections.OrderedDict)
 
     # ----------------------------------------------------------------------
     # I/O Methods
@@ -5265,11 +5262,11 @@ def sample(
                 "Replace has to be set to `True` when "
                 "upsampling the population `frac` > 1."
             )
-        elif n is not None and frac is None and n % 1 != 0:
+        elif frac is None and n % 1 != 0:
             raise ValueError("Only integers accepted as `n` values")
-        elif n is None and frac is not None:
+        elif n is None:
             n = int(round(frac * axis_length))
-        elif n is not None and frac is not None:
+        elif frac is not None:
             raise ValueError("Please enter a value for `frac` OR `n`, not both")
 
         # Check for negative sizes
@@ -5383,15 +5380,13 @@ def __getattr__(self, name: str):
         # Note: obj.x will always call obj.__getattribute__('x') prior to
         # calling obj.__getattr__('x').
         if (
-            name in self._internal_names_set
-            or name in self._metadata
-            or name in self._accessors
+            name not in self._internal_names_set
+            and name not in self._metadata
+            and name not in self._accessors
+            and self._info_axis._can_hold_identifiers_and_holds_name(name)
         ):
-            return object.__getattribute__(self, name)
-        else:
-            if self._info_axis._can_hold_identifiers_and_holds_name(name):
-                return self[name]
-            return object.__getattribute__(self, name)
+            return self[name]
+        return object.__getattribute__(self, name)
 
     def __setattr__(self, name: str, value) -> None:
         """
@@ -5410,19 +5405,15 @@ def __setattr__(self, name: str, value) -> None:
 
         # if this fails, go on to more involved attribute setting
         # (note that this matches __getattr__, above).
-        if name in self._internal_names_set:
-            object.__setattr__(self, name, value)
-        elif name in self._metadata:
+        if name in self._internal_names_set or name in self._metadata:
             object.__setattr__(self, name, value)
         else:
             try:
                 existing = getattr(self, name)
-                if isinstance(existing, Index):
+                if isinstance(existing, Index) or name not in self._info_axis:
                     object.__setattr__(self, name, value)
-                elif name in self._info_axis:
-                    self[name] = value
                 else:
-                    object.__setattr__(self, name, value)
+                    self[name] = value
             except (AttributeError, TypeError):
                 if isinstance(self, ABCDataFrame) and (is_list_like(value)):
                     warnings.warn(
@@ -5493,17 +5484,16 @@ def _is_mixed_type(self) -> bool_t:
 
     def _check_inplace_setting(self, value) -> bool_t:
         """ check whether we allow in-place setting with this type of value """
-        if self._is_mixed_type:
-            if not self._mgr.is_numeric_mixed_type:
+        if self._is_mixed_type and not self._mgr.is_numeric_mixed_type:
 
-                # allow an actual np.nan thru
-                if is_float(value) and np.isnan(value):
-                    return True
+            # allow an actual np.nan thru
+            if is_float(value) and np.isnan(value):
+                return True
 
-                raise TypeError(
-                    "Cannot do inplace boolean setting on "
-                    "mixed-types with a non np.nan value"
-                )
+            raise TypeError(
+                "Cannot do inplace boolean setting on "
+                "mixed-types with a non np.nan value"
+            )
 
         return True
 
@@ -6147,8 +6137,7 @@ def convert_dtypes(
                 )
                 for col_name, col in self.items()
             ]
-            result = pd.concat(results, axis=1, copy=False)
-            return result
+            return pd.concat(results, axis=1, copy=False)
 
     # ----------------------------------------------------------------------
     # Filling NA's
@@ -6295,9 +6284,7 @@ def fillna(
                     )
                     value = value.reindex(self.index, copy=False)
                     value = value._values
-                elif not is_list_like(value):
-                    pass
-                else:
+                elif is_list_like(value):
                     raise TypeError(
                         '"value" parameter must be a scalar, dict '
                         "or Series, but you passed a "
@@ -7584,9 +7571,13 @@ def clip(
             upper = None
 
         # GH 2747 (arguments were reversed)
-        if lower is not None and upper is not None:
-            if is_scalar(lower) and is_scalar(upper):
-                lower, upper = min(lower, upper), max(lower, upper)
+        if (
+            lower is not None
+            and upper is not None
+            and is_scalar(lower)
+            and is_scalar(upper)
+        ):
+            lower, upper = min(lower, upper), max(lower, upper)
 
         # fast-path for scalars
         if (lower is None or (is_scalar(lower) and is_number(lower))) and (
@@ -8323,10 +8314,9 @@ def first(self: FrameOrSeries, offset) -> FrameOrSeries:
         end_date = end = self.index[0] + offset
 
         # Tick-like, e.g. 3 weeks
-        if isinstance(offset, Tick):
-            if end_date in self.index:
-                end = self.index.searchsorted(end_date, side="left")
-                return self.iloc[:end]
+        if isinstance(offset, Tick) and end_date in self.index:
+            end = self.index.searchsorted(end_date, side="left")
+            return self.iloc[:end]
 
         return self.loc[:end]
 
@@ -8732,17 +8722,19 @@ def _align_frame(
 
         is_series = isinstance(self, ABCSeries)
 
-        if axis is None or axis == 0:
-            if not self.index.equals(other.index):
-                join_index, ilidx, iridx = self.index.join(
-                    other.index, how=join, level=level, return_indexers=True
-                )
+        if (axis is None or axis == 0) and not self.index.equals(other.index):
+            join_index, ilidx, iridx = self.index.join(
+                other.index, how=join, level=level, return_indexers=True
+            )
 
-        if axis is None or axis == 1:
-            if not is_series and not self.columns.equals(other.columns):
-                join_columns, clidx, cridx = self.columns.join(
-                    other.columns, how=join, level=level, return_indexers=True
-                )
+        if (
+            (axis is None or axis == 1)
+            and not is_series
+            and not self.columns.equals(other.columns)
+        ):
+            join_columns, clidx, cridx = self.columns.join(
+                other.columns, how=join, level=level, return_indexers=True
+            )
 
         if is_series:
             reindexers = {0: [join_index, ilidx]}
@@ -8767,15 +8759,17 @@ def _align_frame(
             right = right.fillna(method=method, axis=fill_axis, limit=limit)
 
         # if DatetimeIndex have different tz, convert to UTC
-        if is_datetime64tz_dtype(left.index.dtype):
-            if left.index.tz != right.index.tz:
-                if join_index is not None:
-                    # GH#33671 ensure we don't change the index on
-                    #  our original Series (NB: by default deep=False)
-                    left = left.copy()
-                    right = right.copy()
-                    left.index = join_index
-                    right.index = join_index
+        if (
+            is_datetime64tz_dtype(left.index.dtype)
+            and left.index.tz != right.index.tz
+            and join_index is not None
+        ):
+            # GH#33671 ensure we don't change the index on
+            #  our original Series (NB: by default deep=False)
+            left = left.copy()
+            right = right.copy()
+            left.index = join_index
+            right.index = join_index
 
         return (
             left.__finalize__(self),
@@ -8857,16 +8851,18 @@ def _align_series(
             right = right.fillna(fill_value, method=method, limit=limit)
 
         # if DatetimeIndex have different tz, convert to UTC
-        if is_series or (not is_series and axis == 0):
-            if is_datetime64tz_dtype(left.index.dtype):
-                if left.index.tz != right.index.tz:
-                    if join_index is not None:
-                        # GH#33671 ensure we don't change the index on
-                        #  our original Series (NB: by default deep=False)
-                        left = left.copy()
-                        right = right.copy()
-                        left.index = join_index
-                        right.index = join_index
+        if (
+            (is_series or axis == 0)
+            and is_datetime64tz_dtype(left.index.dtype)
+            and left.index.tz != right.index.tz
+            and join_index is not None
+        ):
+            # GH#33671 ensure we don't change the index on
+            #  our original Series (NB: by default deep=False)
+            left = left.copy()
+            right = right.copy()
+            left.index = join_index
+            right.index = join_index
 
         return (
             left.__finalize__(self),
@@ -9568,9 +9564,8 @@ def truncate(
             before = to_datetime(before)
             after = to_datetime(after)
 
-        if before is not None and after is not None:
-            if before > after:
-                raise ValueError(f"Truncate: {after} must be after {before}")
+        if before is not None and after is not None and before > after:
+            raise ValueError(f"Truncate: {after} must be after {before}")
 
         if len(ax) > 1 and ax.is_monotonic_decreasing:
             before, after = after, before
diff --git a/pandas/core/indexers.py b/pandas/core/indexers.py
index e48a42599a2a0..02691bc56aee5 100644
--- a/pandas/core/indexers.py
+++ b/pandas/core/indexers.py
@@ -79,12 +79,11 @@ def is_scalar_indexer(indexer, ndim: int) -> bool:
     -------
     bool
     """
-    if isinstance(indexer, tuple):
-        if len(indexer) == ndim:
-            return all(
-                is_integer(x) or (isinstance(x, np.ndarray) and x.ndim == len(x) == 1)
-                for x in indexer
-            )
+    if isinstance(indexer, tuple) and len(indexer) == ndim:
+        return all(
+            is_integer(x) or (isinstance(x, np.ndarray) and x.ndim == len(x) == 1)
+            for x in indexer
+        )
     return False
 
 
@@ -457,12 +456,12 @@ def check_array_indexer(array: AnyArrayLike, indexer: Any) -> Any:
     # indexers that are not array-like: integer, slice, Ellipsis, None)
     # In this context, tuples are not considered as array-like, as they have
     # a specific meaning in indexing (multi-dimensional indexing)
-    if is_list_like(indexer):
-        if isinstance(indexer, tuple):
-            return indexer
-    else:
+    if (
+        is_list_like(indexer)
+        and isinstance(indexer, tuple)
+        or not is_list_like(indexer)
+    ):
         return indexer
-
     # convert list-likes to array
     if not is_array_like(indexer):
         indexer = pd_array(indexer)
diff --git a/pandas/core/indexing.py b/pandas/core/indexing.py
index c2dad928845a7..32c9b451a3852 100644
--- a/pandas/core/indexing.py
+++ b/pandas/core/indexing.py
@@ -627,9 +627,7 @@ def _get_setitem_indexer(self, key):
         except TypeError as e:
 
             # invalid indexer type vs 'other' indexing errors
-            if "cannot do" in str(e):
-                raise
-            elif "unhashable type" in str(e):
+            if "cannot do" in str(e) or "unhashable type" in str(e):
                 raise
             raise IndexingError(key) from e
 
@@ -986,10 +984,7 @@ def _multi_take_opportunity(self, tup: Tuple) -> bool:
             return False
 
         # just too complicated
-        if any(com.is_bool_indexer(x) for x in tup):
-            return False
-
-        return True
+        return not any(com.is_bool_indexer(x) for x in tup)
 
     def _multi_take(self, tup: Tuple):
         """
@@ -1417,11 +1412,7 @@ def _is_scalar_access(self, key: Tuple) -> bool:
         if len(key) != self.ndim:
             return False
 
-        for k in key:
-            if not is_integer(k):
-                return False
-
-        return True
+        return all(is_integer(k) for k in key)
 
     def _validate_integer(self, key: int, axis: int) -> None:
         """
@@ -1544,12 +1535,11 @@ def _setitem_with_indexer(self, indexer, value):
 
         # if there is only one block/type, still have to take split path
         # unless the block is one-dimensional or it can hold the value
-        if not take_split_path and self.obj._mgr.blocks:
-            if self.ndim > 1:
-                # in case of dict, keys are indices
-                val = list(value.values()) if isinstance(value, dict) else value
-                blk = self.obj._mgr.blocks[0]
-                take_split_path = not blk._can_hold_element(val)
+        if not take_split_path and self.obj._mgr.blocks and self.ndim > 1:
+            # in case of dict, keys are indices
+            val = list(value.values()) if isinstance(value, dict) else value
+            blk = self.obj._mgr.blocks[0]
+            take_split_path = not blk._can_hold_element(val)
 
         # if we have any multi-indexes that have non-trivial slices
         # (not null slices) then we must take the split path, xref
diff --git a/pandas/core/missing.py b/pandas/core/missing.py
index 52536583b9b0d..78d31e0ddf581 100644
--- a/pandas/core/missing.py
+++ b/pandas/core/missing.py
@@ -156,7 +156,7 @@ def find_valid_index(values, how: str):
     if how == "first":
         idxpos = is_valid[::].argmax()
 
-    if how == "last":
+    elif how == "last":
         idxpos = len(values) - 1 - is_valid[::-1].argmax()
 
     chk_notna = is_valid[idxpos]
diff --git a/pandas/core/nanops.py b/pandas/core/nanops.py
index 8e917bb770247..6f233a87dd295 100644
--- a/pandas/core/nanops.py
+++ b/pandas/core/nanops.py
@@ -150,10 +150,7 @@ def _bn_ok_dtype(dtype: DtypeObj, name: str) -> bool:
         # further we also want to preserve NaN when all elements
         # are NaN, unlike bottleneck/numpy which consider this
         # to be 0
-        if name in ["nansum", "nanprod"]:
-            return False
-
-        return True
+        return name not in ["nansum", "nanprod"]
     return False
 
 
@@ -185,14 +182,11 @@ def _get_fill_value(
             else:
                 return -np.inf
     else:
-        if fill_value_typ is None:
-            return iNaT
+        if fill_value_typ is not None and fill_value_typ == "+inf":
+            # need the max int here
+            return np.iinfo(np.int64).max
         else:
-            if fill_value_typ == "+inf":
-                # need the max int here
-                return np.iinfo(np.int64).max
-            else:
-                return iNaT
+            return iNaT
 
 
 def _maybe_get_mask(
@@ -395,15 +389,12 @@ def _na_for_min_count(
     if fill_value is NaT:
         fill_value = values.dtype.type("NaT", "ns")
 
-    if values.ndim == 1:
-        return fill_value
-    elif axis is None:
+    if values.ndim == 1 or axis is None:
         return fill_value
     else:
         result_shape = values.shape[:axis] + values.shape[axis + 1 :]
 
-        result = np.full(result_shape, fill_value, dtype=values.dtype)
-        return result
+        return np.full(result_shape, fill_value, dtype=values.dtype)
 
 
 def nanany(
@@ -1139,12 +1130,12 @@ def nanskew(
     if isinstance(result, np.ndarray):
         result = np.where(m2 == 0, 0, result)
         result[count < 3] = np.nan
-        return result
     else:
         result = 0 if m2 == 0 else result
         if count < 3:
             return np.nan
-        return result
+
+    return result
 
 
 @disallow("M8", "m8")
diff --git a/pandas/core/resample.py b/pandas/core/resample.py
index 78d217c4688b6..f32ec008e7a70 100644
--- a/pandas/core/resample.py
+++ b/pandas/core/resample.py
@@ -176,8 +176,7 @@ def _convert_obj(self, obj):
         -------
         obj : converted object
         """
-        obj = obj._consolidate()
-        return obj
+        return obj._consolidate()
 
     def _get_binner_for_time(self):
         raise AbstractMethodError(self)
@@ -1042,12 +1041,14 @@ def _downsample(self, how, **kwargs):
             return obj
 
         # do we have a regular frequency
-        if ax.freq is not None or ax.inferred_freq is not None:
-
-            if len(self.grouper.binlabels) > len(ax) and how is None:
+        if (
+            (ax.freq is not None or ax.inferred_freq is not None)
+            and len(self.grouper.binlabels) > len(ax)
+            and how is None
+        ):
 
-                # let's do an asfreq
-                return self.asfreq()
+            # let's do an asfreq
+            return self.asfreq()
 
         # we are downsampling
         # we want to call the actual grouper method here
diff --git a/pandas/core/series.py b/pandas/core/series.py
index e4a805a18bcdb..88e7ca8929b46 100644
--- a/pandas/core/series.py
+++ b/pandas/core/series.py
@@ -410,24 +410,25 @@ def _set_axis(self, axis: int, labels, fastpath: bool = False) -> None:
         if not fastpath:
             labels = ensure_index(labels)
 
-        if labels._is_all_dates:
-            if not isinstance(labels, (DatetimeIndex, PeriodIndex, TimedeltaIndex)):
-                try:
-                    labels = DatetimeIndex(labels)
-                    # need to set here because we changed the index
-                    if fastpath:
-                        self._mgr.set_axis(axis, labels)
-                    warnings.warn(
-                        "Automatically casting object-dtype Index of datetimes to "
-                        "DatetimeIndex is deprecated and will be removed in a "
-                        "future version.  Explicitly cast to DatetimeIndex instead.",
-                        FutureWarning,
-                        stacklevel=3,
-                    )
-                except (tslibs.OutOfBoundsDatetime, ValueError):
-                    # labels may exceeds datetime bounds,
-                    # or not be a DatetimeIndex
-                    pass
+        if labels._is_all_dates and not isinstance(
+            labels, (DatetimeIndex, PeriodIndex, TimedeltaIndex)
+        ):
+            try:
+                labels = DatetimeIndex(labels)
+                # need to set here because we changed the index
+                if fastpath:
+                    self._mgr.set_axis(axis, labels)
+                warnings.warn(
+                    "Automatically casting object-dtype Index of datetimes to "
+                    "DatetimeIndex is deprecated and will be removed in a "
+                    "future version.  Explicitly cast to DatetimeIndex instead.",
+                    FutureWarning,
+                    stacklevel=3,
+                )
+            except (tslibs.OutOfBoundsDatetime, ValueError):
+                # labels may exceeds datetime bounds,
+                # or not be a DatetimeIndex
+                pass
 
         object.__setattr__(self, "_index", labels)
         if not fastpath:
@@ -1011,7 +1012,7 @@ def __setitem__(self, key, value):
             self._set_with_engine(key, value)
         except (KeyError, ValueError):
             values = self._values
-            if is_integer(key) and not self.index.inferred_type == "integer":
+            if is_integer(key) and self.index.inferred_type != "integer":
                 # positional setter
                 values[key] = value
             else:
@@ -1345,9 +1346,7 @@ def __repr__(self) -> str:
             max_rows=max_rows,
             length=show_dimensions,
         )
-        result = buf.getvalue()
-
-        return result
+        return buf.getvalue()
 
     def to_string(
         self,
@@ -1914,8 +1913,7 @@ def unique(self):
         ['b', 'a', 'c']
         Categories (3, object): ['a' < 'b' < 'c']
         """
-        result = super().unique()
-        return result
+        return super().unique()
 
     def drop_duplicates(self, keep="first", inplace=False) -> Optional["Series"]:
         """
@@ -2630,9 +2628,7 @@ def dot(self, other):
             return self._constructor(
                 np.dot(lvals, rvals), index=other.columns
             ).__finalize__(self, method="dot")
-        elif isinstance(other, Series):
-            return np.dot(lvals, rvals)
-        elif isinstance(rvals, np.ndarray):
+        elif isinstance(other, Series) or isinstance(rvals, np.ndarray):
             return np.dot(lvals, rvals)
         else:  # pragma: no cover
             raise TypeError(f"unsupported type: {type(other)}")
@@ -2729,8 +2725,7 @@ def append(self, to_append, ignore_index=False, verify_integrity=False):
         from pandas.core.reshape.concat import concat
 
         if isinstance(to_append, (list, tuple)):
-            to_concat = [self]
-            to_concat.extend(to_append)
+            to_concat = [self, *to_append]
         else:
             to_concat = [self, to_append]
         if any(isinstance(x, (ABCDataFrame,)) for x in to_concat[1:]):
@@ -2773,8 +2768,7 @@ def _binop(self, other, func, level=None, fill_value=None):
             result = func(this_vals, other_vals)
 
         name = ops.get_op_result_name(self, other)
-        ret = this._construct_result(result, name)
-        return ret
+        return this._construct_result(result, name)
 
     def _construct_result(
         self, result: Union[ArrayLike, Tuple[ArrayLike, ArrayLike]], name: Label
@@ -3825,9 +3819,7 @@ def explode(self, ignore_index: bool = False) -> "Series":
         else:
             index = self.index.repeat(counts)
 
-        result = self._constructor(values, index=index, name=self.name)
-
-        return result
+        return self._constructor(values, index=index, name=self.name)
 
     def unstack(self, level=-1, fill_value=None):
         """
diff --git a/pandas/core/sorting.py b/pandas/core/sorting.py
index 2e32a7572adc7..b2534a30662d4 100644
--- a/pandas/core/sorting.py
+++ b/pandas/core/sorting.py
@@ -217,7 +217,7 @@ def decons_group_index(comp_labels, shape):
     x = comp_labels
     for i in reversed(range(len(shape))):
         labels = (x - y) % (factor * shape[i]) // factor
-        np.putmask(labels, comp_labels < 0, -1)
+        np.putmask(labels, x < 0, -1)
         label_list.append(labels)
         y = labels * factor
         factor *= shape[i]
@@ -462,9 +462,7 @@ def _ensure_key_mapped_multiindex(
         for level in range(index.nlevels)
     ]
 
-    labels = type(index).from_arrays(mapped)
-
-    return labels
+    return type(index).from_arrays(mapped)
 
 
 def ensure_key_mapped(values, key: Optional[Callable], levels=None):

From 9c3598b3cd1c644f884a4866c898f2a93caee2fe Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 9 Nov 2020 15:47:54 +0000
Subject: [PATCH 02/22] apply some suggestions

---
 pandas/core/nanops.py  | 6 ++++--
 pandas/core/sorting.py | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/pandas/core/nanops.py b/pandas/core/nanops.py
index fbce7b7300f2e..08dc0f9e614ca 100644
--- a/pandas/core/nanops.py
+++ b/pandas/core/nanops.py
@@ -182,7 +182,7 @@ def _get_fill_value(
             else:
                 return -np.inf
     else:
-        if fill_value_typ is not None and fill_value_typ == "+inf":
+        if fill_value_typ == "+inf":
             # need the max int here
             return np.iinfo(np.int64).max
         else:
@@ -386,7 +386,9 @@ def _na_for_min_count(
     if fill_value is NaT:
         fill_value = values.dtype.type("NaT", "ns")
 
-    if values.ndim == 1 or axis is None:
+    if values.ndim == 1:
+        return fill_value
+    elif axis is None:
         return fill_value
     else:
         result_shape = values.shape[:axis] + values.shape[axis + 1 :]
diff --git a/pandas/core/sorting.py b/pandas/core/sorting.py
index 6abf8cf89d7b5..06a512cb6da11 100644
--- a/pandas/core/sorting.py
+++ b/pandas/core/sorting.py
@@ -218,7 +218,7 @@ def decons_group_index(comp_labels, shape):
     x = comp_labels
     for i in reversed(range(len(shape))):
         labels = (x - y) % (factor * shape[i]) // factor
-        np.putmask(labels, x < 0, -1)
+        labels[x < 0] = -1
         label_list.append(labels)
         y = labels * factor
         factor *= shape[i]

From 873d4303493c3940bd7fe7b59700333c54c88fe9 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 9 Nov 2020 15:48:29 +0000
Subject: [PATCH 03/22] logicalnot -> ~

---
 pandas/core/base.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/base.py b/pandas/core/base.py
index 5fbd712d72ba1..e6ee4b2d1da9c 100644
--- a/pandas/core/base.py
+++ b/pandas/core/base.py
@@ -1295,7 +1295,7 @@ def drop_duplicates(self, keep="first"):
         duplicated = self.duplicated(keep=keep)
         # pandas\core\base.py:1507: error: Value of type "IndexOpsMixin" is not
         # indexable  [index]
-        return self[np.logical_not(duplicated)]  # type: ignore[index]
+        return self[~duplicated]  # type: ignore[index]
 
     def duplicated(self, keep="first"):
         return duplicated(self._values, keep=keep)

From 31d29af7046de3a900e69c79dea36259ac5d132a Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 9 Nov 2020 15:49:42 +0000
Subject: [PATCH 04/22] parens

---
 pandas/core/algorithms.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 64315007d6f10..154323ec785bd 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -102,9 +102,9 @@ def _ensure_data(
     # we check some simple dtypes first
     if (
         is_object_dtype(dtype)
-        or not is_object_dtype(dtype)
+        or (not is_object_dtype(dtype))
         and is_object_dtype(values)
-        and dtype is None
+        and (dtype is None)
     ):
         return ensure_object(np.asarray(values)), np.dtype("object")
     try:

From 7a51410a33c1de93a3724bfdcf8389d8a0b00db7 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 9 Nov 2020 15:49:54 +0000
Subject: [PATCH 05/22] parens

---
 pandas/core/algorithms.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 154323ec785bd..1a0d97a375b73 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -101,7 +101,7 @@ def _ensure_data(
 
     # we check some simple dtypes first
     if (
-        is_object_dtype(dtype)
+        (is_object_dtype(dtype))
         or (not is_object_dtype(dtype))
         and is_object_dtype(values)
         and (dtype is None)

From a31e89d1fa3c01ba506039ff37b955e6d0f2b7b9 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Mon, 9 Nov 2020 15:50:04 +0000
Subject: [PATCH 06/22] parens

---
 pandas/core/algorithms.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 1a0d97a375b73..0ad04fc5a15e2 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -103,7 +103,7 @@ def _ensure_data(
     if (
         (is_object_dtype(dtype))
         or (not is_object_dtype(dtype))
-        and is_object_dtype(values)
+        and (is_object_dtype(values))
         and (dtype is None)
     ):
         return ensure_object(np.asarray(values)), np.dtype("object")

From 5e053d44e9dbdade2ac04412e5d706bd1c12dc2d Mon Sep 17 00:00:00 2001
From: MarcoGorelli <m.e.gorelli@gmail.com>
Date: Mon, 23 Nov 2020 17:34:45 +0000
Subject: [PATCH 07/22] factor out _set_join_index

---
 pandas/core/generic.py | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index be630c757a333..33bb11ea8269e 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -8842,12 +8842,7 @@ def _align_frame(
             and left.index.tz != right.index.tz
             and join_index is not None
         ):
-            # GH#33671 ensure we don't change the index on
-            #  our original Series (NB: by default deep=False)
-            left = left.copy()
-            right = right.copy()
-            left.index = join_index
-            right.index = join_index
+            left, right = _set_join_index(left, right, join_index)
 
         return (
             left.__finalize__(self),
@@ -8936,12 +8931,7 @@ def _align_series(
             and left.index.tz != right.index.tz
             and join_index is not None
         ):
-            # GH#33671 ensure we don't change the index on
-            #  our original Series (NB: by default deep=False)
-            left = left.copy()
-            right = right.copy()
-            left.index = join_index
-            right.index = join_index
+            left, right = _set_join_index(left, right, join_index)
 
         return (
             left.__finalize__(self),
@@ -11355,6 +11345,18 @@ def last_valid_index(self):
         return self._find_valid_index("last")
 
 
+def _set_join_index(
+    left: Series, right: Series, join_index: Index
+) -> Tuple[Series, Series]:
+    # GH#33671 ensure we don't change the index on
+    # our original Series (NB: by default deep=False)
+    left = left.copy()
+    right = right.copy()
+    left.index = join_index
+    right.index = join_index
+    return left, right
+
+
 def _doc_parms(cls):
     """Return a tuple of the doc parms."""
     axis_descr = (

From 5f0a27833acdd18a158406e3a2040481dbd8a684 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <m.e.gorelli@gmail.com>
Date: Mon, 23 Nov 2020 17:51:38 +0000
Subject: [PATCH 08/22] :label: type

---
 pandas/core/generic.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 33bb11ea8269e..b9cfd99370a8c 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -11346,8 +11346,8 @@ def last_valid_index(self):
 
 
 def _set_join_index(
-    left: Series, right: Series, join_index: Index
-) -> Tuple[Series, Series]:
+    left: FrameOrSeries, right: FrameOrSeries, join_index: Index
+) -> Tuple[FrameOrSeries, FrameOrSeries]:
     # GH#33671 ensure we don't change the index on
     # our original Series (NB: by default deep=False)
     left = left.copy()

From 9383755c1d882ba130f052be5694ec43180a71cc Mon Sep 17 00:00:00 2001
From: MarcoGorelli <m.e.gorelli@gmail.com>
Date: Wed, 9 Dec 2020 18:56:38 +0000
Subject: [PATCH 09/22] coverage, remove putmask

---
 pandas/core/indexing.py | 4 +++-
 pandas/core/series.py   | 3 ++-
 pandas/core/sorting.py  | 2 +-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/pandas/core/indexing.py b/pandas/core/indexing.py
index 5296730099c0f..54c3e4597e21d 100644
--- a/pandas/core/indexing.py
+++ b/pandas/core/indexing.py
@@ -636,7 +636,9 @@ def _get_setitem_indexer(self, key):
         except TypeError as e:
 
             # invalid indexer type vs 'other' indexing errors
-            if "cannot do" in str(e) or "unhashable type" in str(e):
+            if "cannot do" in str(e):
+                raise
+            elif "unhashable type" in str(e):
                 raise
             raise IndexingError(key) from e
 
diff --git a/pandas/core/series.py b/pandas/core/series.py
index a6f43312ed62a..40d129080244e 100644
--- a/pandas/core/series.py
+++ b/pandas/core/series.py
@@ -2657,7 +2657,8 @@ def append(self, to_append, ignore_index=False, verify_integrity=False):
         from pandas.core.reshape.concat import concat
 
         if isinstance(to_append, (list, tuple)):
-            to_concat = [self, *to_append]
+            to_concat = [self]
+            to_concat.extend(to_append)
         else:
             to_concat = [self, to_append]
         if any(isinstance(x, (ABCDataFrame,)) for x in to_concat[1:]):
diff --git a/pandas/core/sorting.py b/pandas/core/sorting.py
index fdf02370cf4ed..81d04196aa166 100644
--- a/pandas/core/sorting.py
+++ b/pandas/core/sorting.py
@@ -218,7 +218,7 @@ def decons_group_index(comp_labels, shape):
     x = comp_labels
     for i in reversed(range(len(shape))):
         labels = (x - y) % (factor * shape[i]) // factor
-        labels[x < 0] = -1
+        np.putmask(labels, comp_labels < 0, -1)
         label_list.append(labels)
         y = labels * factor
         factor *= shape[i]

From 0d10a5bc4aa3ae99c4ee6a7892848ee34073a795 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Wed, 16 Dec 2020 15:11:34 +0000
Subject: [PATCH 10/22] pass dtype to maybe_castable directly

---
 pandas/core/construction.py |  2 +-
 pandas/core/dtypes/cast.py  | 12 +++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/pandas/core/construction.py b/pandas/core/construction.py
index 1cd5d354c45e0..d6a9ac5a9cbc1 100644
--- a/pandas/core/construction.py
+++ b/pandas/core/construction.py
@@ -558,7 +558,7 @@ def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bo
     # perf shortcut as this is the most common case
     if (
         isinstance(arr, np.ndarray)
-        and maybe_castable(arr)
+        and maybe_castable(arr.dtype)
         and not copy
         and dtype is None
     ):
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index abcc60a15c641..3c980105e45a2 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1211,20 +1211,18 @@ def convert_dtypes(
     return inferred_dtype
 
 
-def maybe_castable(arr: np.ndarray) -> bool:
+def maybe_castable(dtype: Dtype) -> bool:
     # return False to force a non-fastpath
 
-    assert isinstance(arr, np.ndarray)  # GH 37024
-
     # check datetime64[ns]/timedelta64[ns] are valid
     # otherwise try to coerce
-    kind = arr.dtype.kind
+    kind = dtype.kind
     if kind == "M":
-        return is_datetime64_ns_dtype(arr.dtype)
+        return is_datetime64_ns_dtype(dtype)
     elif kind == "m":
-        return is_timedelta64_ns_dtype(arr.dtype)
+        return is_timedelta64_ns_dtype(dtype)
 
-    return arr.dtype.name not in POSSIBLY_CAST_DTYPES
+    return dtype.name not in POSSIBLY_CAST_DTYPES
 
 
 def maybe_infer_to_datetimelike(

From 938b2d5f37139cfc5bf1610ae250a90b9273b763 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Wed, 16 Dec 2020 15:12:23 +0000
Subject: [PATCH 11/22] revert sourcery's change of moving message closer to
 usage

---
 pandas/core/common.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/pandas/core/common.py b/pandas/core/common.py
index 60f3ca168db14..622d903b03579 100644
--- a/pandas/core/common.py
+++ b/pandas/core/common.py
@@ -107,10 +107,8 @@ def is_bool_indexer(key: Any) -> bool:
             key = np.asarray(key)
 
             if not lib.is_bool_array(key):
+                na_msg = "Cannot mask with non-boolean array containing NA / NaN values"
                 if lib.infer_dtype(key) == "boolean" and isna(key).any():
-                    na_msg = (
-                        "Cannot mask with non-boolean array containing NA / NaN values"
-                    )
                     # Don't raise on e.g. ["A", "B", np.nan], see
                     #  test_loc_getitem_list_of_labels_categoricalindex_with_na
                     raise ValueError(na_msg)

From 7fda4e71c45988414f840cb98f98ca1a751127fb Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Wed, 16 Dec 2020 15:13:15 +0000
Subject: [PATCH 12/22] avoid duplicated check

---
 pandas/core/base.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/base.py b/pandas/core/base.py
index 5244952c9aeaa..defdb949b73a4 100644
--- a/pandas/core/base.py
+++ b/pandas/core/base.py
@@ -610,8 +610,8 @@ def to_numpy(self, dtype=None, copy=False, na_value=lib.no_default, **kwargs):
         # TODO(GH-24345): Avoid potential double copy
         if copy or na_value is not lib.no_default:
             result = result.copy()
-        if na_value is not lib.no_default:
-            result[self.isna()] = na_value
+            if na_value is not lib.no_default:
+                result[self.isna()] = na_value
         return result
 
     @property

From c36bf8daf30c400946f8f93fd53f0f1c7d69454e Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Wed, 16 Dec 2020 15:16:10 +0000
Subject: [PATCH 13/22] remove redundant check

---
 pandas/core/algorithms.py | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 3259094d3258c..b13538b02104c 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -110,12 +110,7 @@ def _ensure_data(
         values = extract_array(values, extract_numpy=True)
 
     # we check some simple dtypes first
-    if (
-        (is_object_dtype(dtype))
-        or (not is_object_dtype(dtype))
-        and (is_object_dtype(values))
-        and (dtype is None)
-    ):
+    if is_object_dtype(dtype) or (is_object_dtype(values) and (dtype is None)):
         return ensure_object(np.asarray(values)), np.dtype("object")
     try:
         if is_bool_dtype(values) or is_bool_dtype(dtype):

From 1f782fd0bd27060503756c1f0687ac829f568002 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <m.e.gorelli@gmail.com>
Date: Sat, 26 Dec 2020 09:13:22 +0000
Subject: [PATCH 14/22] Dtype -> DtypeObj

---
 pandas/core/dtypes/cast.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index 4320c2381b297..07e1c48075bb2 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1281,7 +1281,7 @@ def convert_dtypes(
     return inferred_dtype
 
 
-def maybe_castable(dtype: Dtype) -> bool:
+def maybe_castable(dtype: DtypeObj) -> bool:
     # return False to force a non-fastpath
 
     # check datetime64[ns]/timedelta64[ns] are valid

From 3f799553bd9e3b681c095f128da9edeefecddfae Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Sun, 17 Jan 2021 11:56:30 +0000
Subject: [PATCH 15/22] remove redundant parens

---
 pandas/core/algorithms.py | 2 +-
 pandas/core/generic.py    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 741876dbdfd33..848471009a58f 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -114,7 +114,7 @@ def _ensure_data(
         values = extract_array(values, extract_numpy=True)
 
     # we check some simple dtypes first
-    if is_object_dtype(dtype) or (is_object_dtype(values) and (dtype is None)):
+    if is_object_dtype(dtype) or (is_object_dtype(values) and dtype is None):
         return ensure_object(np.asarray(values)), np.dtype("object")
     try:
         if is_bool_dtype(values) or is_bool_dtype(dtype):
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index e1f6c7da2dffc..9471683ca00bf 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -5343,7 +5343,7 @@ def sample(
             raise ValueError("Only integers accepted as `n` values")
         elif n is None and frac is not None:
             n = round(frac * axis_length)
-        elif n is not None and frac is not None:
+        elif frac is not None:
             raise ValueError("Please enter a value for `frac` OR `n`, not both")
 
         # Check for negative sizes

From 988838325fc41b1c40d7bb2953f5385ebb10d00e Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Sun, 17 Jan 2021 11:59:14 +0000
Subject: [PATCH 16/22] use set to check for membership

---
 pandas/core/aggregation.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/core/aggregation.py b/pandas/core/aggregation.py
index 9ffe9a0568040..55863e649078d 100644
--- a/pandas/core/aggregation.py
+++ b/pandas/core/aggregation.py
@@ -499,10 +499,10 @@ def transform_dict_like(
         try:
             results[name] = transform(colg, how, 0, *args, **kwargs)
         except Exception as err:
-            if str(err) in [
+            if str(err) in {
                 "Function did not transform",
                 "No transform functions were provided",
-            ]:
+            }:
                 raise err
 
     # combine results

From 5125e5fbde280100696924cf799f4fffaebfe6e1 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 12:10:38 +0000
Subject: [PATCH 17/22] revert change in generic.py

---
 pandas/core/generic.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 88e4adf7288c9..8abc81444e8f0 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -5494,10 +5494,12 @@ def __setattr__(self, name: str, value) -> None:
         else:
             try:
                 existing = getattr(self, name)
-                if isinstance(existing, Index) or name not in self._info_axis:
+                if isinstance(existing, Index):
                     object.__setattr__(self, name, value)
-                else:
+                elif name in self._info_axis:
                     self[name] = value
+                else:
+                    object.__setattr__(self, name, value)
             except (AttributeError, TypeError):
                 if isinstance(self, ABCDataFrame) and (is_list_like(value)):
                     warnings.warn(

From d693f581e333b88c4aa629e5cc22a75ec90bfe18 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 12:12:55 +0000
Subject: [PATCH 18/22] revert _set_join_index refactoring

---
 pandas/core/generic.py | 44 ++++++++++++++++++------------------------
 1 file changed, 19 insertions(+), 25 deletions(-)

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 8abc81444e8f0..d3d8c42b66b6b 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -8675,12 +8675,15 @@ def _align_frame(
             right = right.fillna(method=method, axis=fill_axis, limit=limit)
 
         # if DatetimeIndex have different tz, convert to UTC
-        if (
-            is_datetime64tz_dtype(left.index.dtype)
-            and left.index.tz != right.index.tz
-            and join_index is not None
-        ):
-            left, right = _set_join_index(left, right, join_index)
+        if is_datetime64tz_dtype(left.index.dtype):
+            if left.index.tz != right.index.tz:
+                if join_index is not None:
+                    # GH#33671 ensure we don't change the index on
+                    #  our original Series (NB: by default deep=False)
+                    left = left.copy()
+                    right = right.copy()
+                    left.index = join_index
+                    right.index = join_index
 
         return (
             left.__finalize__(self),
@@ -8763,13 +8766,16 @@ def _align_series(
             right = right.fillna(fill_value, method=method, limit=limit)
 
         # if DatetimeIndex have different tz, convert to UTC
-        if (
-            (is_series or axis == 0)
-            and is_datetime64tz_dtype(left.index.dtype)
-            and left.index.tz != right.index.tz
-            and join_index is not None
-        ):
-            left, right = _set_join_index(left, right, join_index)
+        if is_series or (not is_series and axis == 0):
+            if is_datetime64tz_dtype(left.index.dtype):
+                if left.index.tz != right.index.tz:
+                    if join_index is not None:
+                        # GH#33671 ensure we don't change the index on
+                        #  our original Series (NB: by default deep=False)
+                        left = left.copy()
+                        right = right.copy()
+                        left.index = join_index
+                        right.index = join_index
 
         return (
             left.__finalize__(self),
@@ -11095,18 +11101,6 @@ def last_valid_index(self):
         return self._find_valid_index("last")
 
 
-def _set_join_index(
-    left: FrameOrSeries, right: FrameOrSeries, join_index: Index
-) -> Tuple[FrameOrSeries, FrameOrSeries]:
-    # GH#33671 ensure we don't change the index on
-    # our original Series (NB: by default deep=False)
-    left = left.copy()
-    right = right.copy()
-    left.index = join_index
-    right.index = join_index
-    return left, right
-
-
 def _doc_parms(cls):
     """Return a tuple of the doc params."""
 

From d4e3bd61aaba6779484f2453034cc5b79202d5a5 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 12:20:20 +0000
Subject: [PATCH 19/22] deduplicate from merge

---
 pandas/core/generic.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index d3d8c42b66b6b..be765d2cc9101 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -11101,10 +11101,6 @@ def last_valid_index(self):
         return self._find_valid_index("last")
 
 
-def _doc_parms(cls):
-    """Return a tuple of the doc params."""
-
-
 def _doc_params(cls):
     """Return a tuple of the doc params."""
     axis_descr = (

From 5559352d466d1746a59f5a2e77658fb9123db535 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 12:23:04 +0000
Subject: [PATCH 20/22] :art:

---
 pandas/core/algorithms.py | 1 +
 pandas/core/indexers.py   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index 848471009a58f..f2899bafc83a2 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -116,6 +116,7 @@ def _ensure_data(
     # we check some simple dtypes first
     if is_object_dtype(dtype) or (is_object_dtype(values) and dtype is None):
         return ensure_object(np.asarray(values)), np.dtype("object")
+
     try:
         if is_bool_dtype(values) or is_bool_dtype(dtype):
             # we are actually coercing to uint64
diff --git a/pandas/core/indexers.py b/pandas/core/indexers.py
index 3157418c88822..d5a9068fc24df 100644
--- a/pandas/core/indexers.py
+++ b/pandas/core/indexers.py
@@ -486,6 +486,7 @@ def check_array_indexer(array: AnyArrayLike, indexer: Any) -> Any:
         or not is_list_like(indexer)
     ):
         return indexer
+
     # convert list-likes to array
     if not is_array_like(indexer):
         indexer = pd_array(indexer)

From 4f14b81da002ca84131fc424dff16d54fe11de40 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 16:51:26 +0000
Subject: [PATCH 21/22] some reversions

---
 pandas/core/algorithms.py | 4 +++-
 pandas/core/apply.py      | 7 +++----
 pandas/core/generic.py    | 8 ++++++--
 pandas/core/indexers.py   | 9 ++++-----
 pandas/core/series.py     | 4 +++-
 5 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index f2899bafc83a2..6553a67df47e2 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -114,7 +114,9 @@ def _ensure_data(
         values = extract_array(values, extract_numpy=True)
 
     # we check some simple dtypes first
-    if is_object_dtype(dtype) or (is_object_dtype(values) and dtype is None):
+    if is_object_dtype(dtype):
+        return ensure_object(np.asarray(values)), np.dtype("object")
+    elif is_object_dtype(values) and dtype is None:
         return ensure_object(np.asarray(values)), np.dtype("object")
 
     try:
diff --git a/pandas/core/apply.py b/pandas/core/apply.py
index 0dc0b9e40093d..f7c7220985138 100644
--- a/pandas/core/apply.py
+++ b/pandas/core/apply.py
@@ -487,10 +487,9 @@ def wrap_results_for_axis(
             else:
                 raise
 
-        if not isinstance(results[0], ABCSeries) and len(result.index) == len(
-            self.res_columns
-        ):
-            result.index = self.res_columns
+        if not isinstance(results[0], ABCSeries):
+            if len(result.index) == len(self.res_columns):
+                result.index = self.res_columns
 
         if len(result.columns) == len(res_index):
             result.columns = res_index
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index be765d2cc9101..27b1751a5045e 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -5489,7 +5489,9 @@ def __setattr__(self, name: str, value) -> None:
 
         # if this fails, go on to more involved attribute setting
         # (note that this matches __getattr__, above).
-        if name in self._internal_names_set or name in self._metadata:
+        if name in self._internal_names_set:
+            object.__setattr__(self, name, value)
+        elif name in self._metadata:
             object.__setattr__(self, name, value)
         else:
             try:
@@ -6405,7 +6407,9 @@ def fillna(
                     )
                     value = value.reindex(self.index, copy=False)
                     value = value._values
-                elif is_list_like(value):
+                elif not is_list_like(value):
+                    pass
+                else:
                     raise TypeError(
                         '"value" parameter must be a scalar, dict '
                         "or Series, but you passed a "
diff --git a/pandas/core/indexers.py b/pandas/core/indexers.py
index d5a9068fc24df..399953fc17c73 100644
--- a/pandas/core/indexers.py
+++ b/pandas/core/indexers.py
@@ -480,11 +480,10 @@ def check_array_indexer(array: AnyArrayLike, indexer: Any) -> Any:
     # indexers that are not array-like: integer, slice, Ellipsis, None)
     # In this context, tuples are not considered as array-like, as they have
     # a specific meaning in indexing (multi-dimensional indexing)
-    if (
-        is_list_like(indexer)
-        and isinstance(indexer, tuple)
-        or not is_list_like(indexer)
-    ):
+    if is_list_like(indexer):
+        if isinstance(indexer, tuple):
+            return indexer
+    else:
         return indexer
 
     # convert list-likes to array
diff --git a/pandas/core/series.py b/pandas/core/series.py
index fb29c1b6408ac..e1399f73128e3 100644
--- a/pandas/core/series.py
+++ b/pandas/core/series.py
@@ -2558,7 +2558,9 @@ def dot(self, other):
             return self._constructor(
                 np.dot(lvals, rvals), index=other.columns
             ).__finalize__(self, method="dot")
-        elif isinstance(other, Series) or isinstance(rvals, np.ndarray):
+        elif isinstance(other, Series):
+            return np.dot(lvals, rvals)
+        elif isinstance(rvals, np.ndarray):
             return np.dot(lvals, rvals)
         else:  # pragma: no cover
             raise TypeError(f"unsupported type: {type(other)}")

From c03d87640ff2468d1aa70c6c7c046a24660f43d8 Mon Sep 17 00:00:00 2001
From: Marco Gorelli <marcogorelli@protonmail.com>
Date: Mon, 18 Jan 2021 17:00:02 +0000
Subject: [PATCH 22/22] revert maybe_castable

---
 pandas/core/construction.py | 10 +++-------
 pandas/core/dtypes/cast.py  | 12 +++++++-----
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/pandas/core/construction.py b/pandas/core/construction.py
index 5431be28775ee..2980547e23f24 100644
--- a/pandas/core/construction.py
+++ b/pandas/core/construction.py
@@ -583,13 +583,9 @@ def _try_cast(arr, dtype: Optional[DtypeObj], copy: bool, raise_cast_failure: bo
         Otherwise an object array is returned.
     """
     # perf shortcut as this is the most common case
-    if (
-        isinstance(arr, np.ndarray)
-        and maybe_castable(arr.dtype)
-        and not copy
-        and dtype is None
-    ):
-        return arr
+    if isinstance(arr, np.ndarray):
+        if maybe_castable(arr) and not copy and dtype is None:
+            return arr
 
     if isinstance(dtype, ExtensionDtype) and (dtype.kind != "M" or is_sparse(dtype)):
         # create an extension array from its dtype
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index e9b3238a74186..0941967ef6bee 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1301,18 +1301,20 @@ def convert_dtypes(
     return inferred_dtype
 
 
-def maybe_castable(dtype: DtypeObj) -> bool:
+def maybe_castable(arr: np.ndarray) -> bool:
     # return False to force a non-fastpath
 
+    assert isinstance(arr, np.ndarray)  # GH 37024
+
     # check datetime64[ns]/timedelta64[ns] are valid
     # otherwise try to coerce
-    kind = dtype.kind
+    kind = arr.dtype.kind
     if kind == "M":
-        return is_datetime64_ns_dtype(dtype)
+        return is_datetime64_ns_dtype(arr.dtype)
     elif kind == "m":
-        return is_timedelta64_ns_dtype(dtype)
+        return is_timedelta64_ns_dtype(arr.dtype)
 
-    return dtype.name not in POSSIBLY_CAST_DTYPES
+    return arr.dtype.name not in POSSIBLY_CAST_DTYPES
 
 
 def maybe_infer_to_datetimelike(