CLN refactor rest of core

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)
 

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)
 
 
 # ---- #

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

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])}"

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
@@ -974,15 +973,14 @@ def value_counts(
         NaN    1
         dtype: int64
         """
-        result = value_counts(
+        return value_counts(
             self,
             sort=sort,
             ascending=ascending,
             normalize=normalize,
             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)

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

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):

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: