CLN refactor rest of core (pandas-dev#37586)

Author: MarcoGorelli

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

@@ -150,12 +150,10 @@ 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 +167,7 @@ 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 +872,9 @@ 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 +1737,8 @@ 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 +1910,7 @@ 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/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]:

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:

pandas/core/generic.py

@@ -773,8 +773,7 @@ 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: Hashable) -> Union[Series, Any]:
         result = self[item]
@@ -1445,8 +1444,7 @@ 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__")
 
     @final
     def __nonzero__(self):
@@ -2036,8 +2034,7 @@ 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
@@ -5342,11 +5339,11 @@ 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:
             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
@@ -5467,15 +5464,13 @@ 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:
         """
@@ -5585,17 +5580,16 @@ def _is_mixed_type(self) -> bool_t:
     @final
     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
 
@@ -6265,8 +6259,7 @@ def convert_dtypes(
                 )
                 for col_name, col in self.items()
             ]
-            result = concat(results, axis=1, copy=False)
-            return result
+            return concat(results, axis=1, copy=False)
 
     # ----------------------------------------------------------------------
     # Filling NA's
@@ -7444,9 +7437,13 @@ 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 (
@@ -8235,10 +8232,9 @@ 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]
 
@@ -8647,17 +8643,19 @@ 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]}
@@ -9525,9 +9523,8 @@ 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

pandas/core/indexers.py

@@ -82,12 +82,11 @@ def is_scalar_indexer(indexer, ndim: int) -> bool:
     if ndim == 1 and is_integer(indexer):
         # GH37748: allow indexer to be an integer for Series
         return True
-    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