CLN refactor rest of core

pandas/core/aggregation.py

@@ -388,7 +388,6 @@ 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 = []
@@ -397,6 +396,7 @@ 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
 
@@ -499,14 +499,14 @@ 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

@@ -114,11 +114,8 @@ def _ensure_data(
         values = extract_array(values, extract_numpy=True)
 
     # we check some simple dtypes first
-    if is_object_dtype(dtype):
+    if is_object_dtype(dtype) or (is_object_dtype(values) and dtype is None):
         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:
         if is_bool_dtype(values) or is_bool_dtype(dtype):
             # we are actually coercing to uint64
@@ -150,12 +147,10 @@ def _ensure_data(
             from pandas import PeriodIndex
 
             values = PeriodIndex(values)._data
-            dtype = values.dtype
         elif is_timedelta64_dtype(values.dtype) or is_timedelta64_dtype(dtype):
             from pandas import TimedeltaIndex
 
             values = TimedeltaIndex(values)._data
-            dtype = values.dtype
         else:
             # Datetime
             if values.ndim > 1 and is_datetime64_ns_dtype(values.dtype):
@@ -169,8 +164,7 @@ def _ensure_data(
             from pandas import DatetimeIndex
 
             values = DatetimeIndex(values)._data
-            dtype = values.dtype
-
+        dtype = values.dtype
         return values.asi8, dtype
 
     elif is_categorical_dtype(values.dtype) and (
@@ -875,10 +869,9 @@ 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)
 
@@ -1741,9 +1734,8 @@ 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
@@ -1915,8 +1907,7 @@ def searchsorted(arr, value, side="left", sorter=None) -> np.ndarray:
         # and `value` is a pd.Timestamp, we may need to convert value
         arr = ensure_wrapped_if_datetimelike(arr)
 
-    result = arr.searchsorted(value, side=side, sorter=sorter)
-    return result
+    return arr.searchsorted(value, side=side, sorter=sorter)
 
 
 # ---- #

pandas/core/apply.py

@@ -487,9 +487,10 @@ 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

@@ -49,8 +49,7 @@ 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

@@ -321,10 +321,9 @@ 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"
@@ -1046,15 +1045,14 @@ def value_counts(
         1.0    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
@@ -1317,8 +1315,7 @@ 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]
-        result = self[np.logical_not(duplicated)]  # type: ignore[index]
-        return result
+        return self[~duplicated]  # type: ignore[index]
 
     def duplicated(self, keep="first"):
         return duplicated(self._values, keep=keep)

pandas/core/construction.py

@@ -343,8 +343,7 @@ 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: object, extract_numpy: bool = False) -> Union[Any, ArrayLike]:
@@ -584,9 +583,13 @@ 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.dtype)
+        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

pandas/core/dtypes/cast.py

@@ -1301,20 +1301,18 @@ def convert_dtypes(
     return inferred_dtype
 
 
-def maybe_castable(arr: np.ndarray) -> bool:
+def maybe_castable(dtype: DtypeObj) -> 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(

pandas/core/frame.py

@@ -770,7 +770,7 @@ 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:
@@ -2029,10 +2029,10 @@ 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}"
@@ -3334,7 +3334,7 @@ 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
@@ -5041,7 +5041,7 @@ 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: