CLN/STY: various code cleanups (#31162)

Author: ShaharNaveh

pandas/core/computation/align.py

@@ -1,4 +1,5 @@
-"""Core eval alignment algorithms
+"""
+Core eval alignment algorithms.
 """
 
 from functools import partial, wraps

pandas/core/computation/eval.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-
 """
 Top level ``eval`` module.
 """
@@ -26,30 +25,29 @@ def _check_engine(engine: Optional[str]) -> str:
     Parameters
     ----------
     engine : str
+        String to validate.
 
     Raises
     ------
     KeyError
-      * If an invalid engine is passed
+      * If an invalid engine is passed.
     ImportError
-      * If numexpr was requested but doesn't exist
+      * If numexpr was requested but doesn't exist.
 
     Returns
     -------
-    string engine
+    str
+        Engine name.
     """
     from pandas.core.computation.check import _NUMEXPR_INSTALLED
 
     if engine is None:
-        if _NUMEXPR_INSTALLED:
-            engine = "numexpr"
-        else:
-            engine = "python"
+        engine = "numexpr" if _NUMEXPR_INSTALLED else "python"
 
     if engine not in _engines:
-        valid = list(_engines.keys())
+        valid_engines = list(_engines.keys())
         raise KeyError(
-            f"Invalid engine {repr(engine)} passed, valid engines are {valid}"
+            f"Invalid engine '{engine}' passed, valid engines are {valid_engines}"
         )
 
     # TODO: validate this in a more general way (thinking of future engines
@@ -58,10 +56,8 @@ def _check_engine(engine: Optional[str]) -> str:
     if engine == "numexpr":
         if not _NUMEXPR_INSTALLED:
             raise ImportError(
-                "'numexpr' is not installed or an "
-                "unsupported version. Cannot use "
-                "engine='numexpr' for query/eval "
-                "if 'numexpr' is not installed"
+                "'numexpr' is not installed or an unsupported version. Cannot use "
+                "engine='numexpr' for query/eval if 'numexpr' is not installed"
             )
 
     return engine
@@ -80,11 +76,9 @@ def _check_parser(parser: str):
     KeyError
       * If an invalid parser is passed
     """
-
     if parser not in _parsers:
         raise KeyError(
-            f"Invalid parser {repr(parser)} passed, "
-            f"valid parsers are {_parsers.keys()}"
+            f"Invalid parser '{parser}' passed, valid parsers are {_parsers.keys()}"
         )
 
 
@@ -94,8 +88,8 @@ def _check_resolvers(resolvers):
             if not hasattr(resolver, "__getitem__"):
                 name = type(resolver).__name__
                 raise TypeError(
-                    f"Resolver of type {repr(name)} does not "
-                    f"implement the __getitem__ method"
+                    f"Resolver of type '{name}' does not "
+                    "implement the __getitem__ method"
                 )
 
 
@@ -155,10 +149,8 @@ def _check_for_locals(expr: str, stack_level: int, parser: str):
         msg = "The '@' prefix is only supported by the pandas parser"
     elif at_top_of_stack:
         msg = (
-            "The '@' prefix is not allowed in "
-            "top-level eval calls, \nplease refer to "
-            "your variables by name without the '@' "
-            "prefix"
+            "The '@' prefix is not allowed in top-level eval calls.\n"
+            "please refer to your variables by name without the '@' prefix."
         )
 
     if at_top_of_stack or not_pandas_parser:
@@ -285,13 +277,14 @@ def eval(
     See the :ref:`enhancing performance <enhancingperf.eval>` documentation for
     more details.
     """
-
     inplace = validate_bool_kwarg(inplace, "inplace")
 
     if truediv is not no_default:
         warnings.warn(
-            "The `truediv` parameter in pd.eval is deprecated and will be "
-            "removed in a future version.",
+            (
+                "The `truediv` parameter in pd.eval is deprecated and "
+                "will be removed in a future version."
+            ),
             FutureWarning,
             stacklevel=2,
         )

pandas/core/computation/expressions.py

@@ -45,12 +45,9 @@ def set_use_numexpr(v=True):
 
     # choose what we are going to do
     global _evaluate, _where
-    if not _USE_NUMEXPR:
-        _evaluate = _evaluate_standard
-        _where = _where_standard
-    else:
-        _evaluate = _evaluate_numexpr
-        _where = _where_numexpr
+
+    _evaluate = _evaluate_numexpr if _USE_NUMEXPR else _evaluate_standard
+    _where = _where_numexpr if _USE_NUMEXPR else _where_standard
 
 
 def set_numexpr_threads(n=None):
@@ -63,7 +60,9 @@ def set_numexpr_threads(n=None):
 
 
 def _evaluate_standard(op, op_str, a, b):
-    """ standard evaluation """
+    """
+    Standard evaluation.
+    """
     if _TEST_MODE:
         _store_test_result(False)
     with np.errstate(all="ignore"):
@@ -176,7 +175,7 @@ def _bool_arith_check(
         if op_str in unsupported:
             warnings.warn(
                 f"evaluating in Python space because the {repr(op_str)} "
-                f"operator is not supported by numexpr for "
+                "operator is not supported by numexpr for "
                 f"the bool dtype, use {repr(unsupported[op_str])} instead"
             )
             return False
@@ -202,7 +201,6 @@ def evaluate(op, op_str, a, b, use_numexpr=True):
     use_numexpr : bool, default True
         Whether to try to use numexpr.
     """
-
     use_numexpr = use_numexpr and _bool_arith_check(op_str, a, b)
     if use_numexpr:
         return _evaluate(op, op_str, a, b)
@@ -221,10 +219,7 @@ def where(cond, a, b, use_numexpr=True):
     use_numexpr : bool, default True
         Whether to try to use numexpr.
     """
-
-    if use_numexpr:
-        return _where(cond, a, b)
-    return _where_standard(cond, a, b)
+    return _where(cond, a, b) if use_numexpr else _where_standard(cond, a, b)
 
 
 def set_test_mode(v=True):

pandas/core/frame.py

@@ -8,6 +8,7 @@
 alignment and a host of useful data manipulation methods having to do with the
 labeling information
 """
+
 import collections
 from collections import abc
 from io import StringIO
@@ -258,7 +259,6 @@
 
 Examples
 --------
-
 >>> df1 = pd.DataFrame({'lkey': ['foo', 'bar', 'baz', 'foo'],
 ...                     'value': [1, 2, 3, 5]})
 >>> df2 = pd.DataFrame({'rkey': ['foo', 'bar', 'baz', 'foo'],
@@ -491,12 +491,12 @@ def __init__(
         else:
             try:
                 arr = np.array(data, dtype=dtype, copy=copy)
-            except (ValueError, TypeError) as e:
+            except (ValueError, TypeError) as err:
                 exc = TypeError(
                     "DataFrame constructor called with "
-                    f"incompatible data and dtype: {e}"
+                    f"incompatible data and dtype: {err}"
                 )
-                raise exc from e
+                raise exc from err
 
             if arr.ndim == 0 and index is not None and columns is not None:
                 values = cast_scalar_to_array(
@@ -794,7 +794,6 @@ def to_string(
         1     2     5
         2     3     6
         """
-
         from pandas import option_context
 
         with option_context("display.max_colwidth", max_colwidth):
@@ -1583,7 +1582,6 @@ def from_records(
         -------
         DataFrame
         """
-
         # Make a copy of the input columns so we can modify it
         if columns is not None:
             columns = ensure_index(columns)
@@ -1764,7 +1762,6 @@ def to_records(
         rec.array([(b'a', 1, 0.5 ), (b'b', 2, 0.75)],
                   dtype=[('I', 'S1'), ('A', '<i8'), ('B', '<f8')])
         """
-
         if index:
             if isinstance(self.index, ABCMultiIndex):
                 # array of tuples to numpy cols. copy copy copy
@@ -2185,7 +2182,6 @@ def to_html(
         --------
         to_string : Convert DataFrame to a string.
         """
-
         if justify is not None and justify not in fmt._VALID_JUSTIFY_PARAMETERS:
             raise ValueError("Invalid value for justify parameter")
 
@@ -2359,7 +2355,6 @@ def info(
         dtypes: object(3)
         memory usage: 188.8 MB
         """
-
         if buf is None:  # pragma: no cover
             buf = sys.stdout
 
@@ -2985,7 +2980,6 @@ def _set_item(self, key, value):
         Series/TimeSeries will be conformed to the DataFrames index to
         ensure homogeneity.
         """
-
         self._ensure_valid_index(value)
         value = self._sanitize_column(key, value)
         NDFrame._set_item(self, key, value)
@@ -3045,8 +3039,7 @@ def _ensure_valid_index(self, value):
             except (ValueError, NotImplementedError, TypeError):
                 raise ValueError(
                     "Cannot set a frame with no defined index "
-                    "and a value that cannot be converted to a "
-                    "Series"
+                    "and a value that cannot be converted to a Series"
                 )
 
             self._data = self._data.reindex_axis(
@@ -3414,7 +3407,6 @@ def select_dtypes(self, include=None, exclude=None) -> "DataFrame":
         4   True  1.0
         5  False  2.0
         """
-
         if not is_list_like(include):
             include = (include,) if include is not None else ()
         if not is_list_like(exclude):
@@ -3685,11 +3677,7 @@ def lookup(self, row_labels, col_labels) -> np.ndarray:
         Returns
         -------
         numpy.ndarray
-
-        Examples
-        --------
-        values : ndarray
-            The found values
+            The found values.
         """
         n = len(row_labels)
         if n != len(col_labels):
@@ -3780,7 +3768,6 @@ def _reindex_multi(self, axes, copy, fill_value) -> "DataFrame":
         """
         We are guaranteed non-Nones in the axes.
         """
-
         new_index, row_indexer = self.index.reindex(axes["index"])
         new_columns, col_indexer = self.columns.reindex(axes["columns"])
 
@@ -4101,7 +4088,6 @@ def rename(
 
         Examples
         --------
-
         ``DataFrame.rename`` supports two calling conventions
 
         * ``(index=index_mapper, columns=columns_mapper, ...)``
@@ -5591,7 +5577,6 @@ def combine_first(self, other: "DataFrame") -> "DataFrame":
 
         Examples
         --------
-
         >>> df1 = pd.DataFrame({'A': [None, 0], 'B': [None, 4]})
         >>> df2 = pd.DataFrame({'A': [1, 1], 'B': [3, 3]})
         >>> df1.combine_first(df2)
@@ -6370,7 +6355,6 @@ def explode(self, column: Union[str, Tuple]) -> "DataFrame":
         3    3  1
         3    4  1
         """
-
         if not (is_scalar(column) or isinstance(column, tuple)):
             raise ValueError("column must be a scalar")
         if not self.columns.is_unique:
@@ -6855,7 +6839,6 @@ def apply(self, func, axis=0, raw=False, result_type=None, args=(), **kwds):
 
         Examples
         --------
-
         >>> df = pd.DataFrame([[4, 9]] * 3, columns=['A', 'B'])
         >>> df
            A  B
@@ -7050,7 +7033,6 @@ def append(
 
         Examples
         --------
-
         >>> df = pd.DataFrame([[1, 2], [3, 4]], columns=list('AB'))
         >>> df
            A  B
@@ -8432,7 +8414,6 @@ def isin(self, values) -> "DataFrame":
 
         Examples
         --------
-
         >>> df = pd.DataFrame({'num_legs': [2, 4], 'num_wings': [2, 0]},
         ...                   index=['falcon', 'dog'])
         >>> df
@@ -8493,7 +8474,7 @@ def isin(self, values) -> "DataFrame":
                 raise TypeError(
                     "only list-like or dict-like objects are allowed "
                     "to be passed to DataFrame.isin(), "
-                    f"you passed a {repr(type(values).__name__)}"
+                    f"you passed a '{type(values).__name__}'"
                 )
             return DataFrame(
                 algorithms.isin(self.values.ravel(), values).reshape(self.shape),

pandas/tests/frame/methods/test_diff.py

@@ -15,7 +15,7 @@ def test_diff(self, datetime_frame):
         )
 
         # int dtype
-        a = 10000000000000000
+        a = 10_000_000_000_000_000
         b = a + 1
         s = Series([a, b])
 

pandas/tests/test_take.py

@@ -345,7 +345,7 @@ def test_2d_float32(self):
 
     def test_2d_datetime64(self):
         # 2005/01/01 - 2006/01/01
-        arr = np.random.randint(11045376, 11360736, (5, 3)) * 100000000000
+        arr = np.random.randint(11_045_376, 11_360_736, (5, 3)) * 100_000_000_000
         arr = arr.view(dtype="datetime64[ns]")
         indexer = [0, 2, -1, 1, -1]
 
@@ -452,7 +452,7 @@ def test_take_empty(self, allow_fill):
         tm.assert_numpy_array_equal(arr, result)
 
         msg = (
-            r"cannot do a non-empty take from an empty axes.|"
+            "cannot do a non-empty take from an empty axes.|"
             "indices are out-of-bounds"
         )
         with pytest.raises(IndexError, match=msg):