CLN: Assorted cleanups (#27632)

Author: jbrockmendel

pandas/core/accessor.py

@@ -51,7 +51,7 @@ class PandasDelegate:
     """
 
     def _delegate_property_get(self, name, *args, **kwargs):
-        raise TypeError("You cannot access the " "property {name}".format(name=name))
+        raise TypeError("You cannot access the property {name}".format(name=name))
 
     def _delegate_property_set(self, name, value, *args, **kwargs):
         raise TypeError("The property {name} cannot be set".format(name=name))
@@ -271,8 +271,7 @@ def plot(self):
 @Appender(
     _doc
     % dict(
-        klass="DataFrame",
-        others=("register_series_accessor, " "register_index_accessor"),
+        klass="DataFrame", others=("register_series_accessor, register_index_accessor")
     )
 )
 def register_dataframe_accessor(name):
@@ -284,8 +283,7 @@ def register_dataframe_accessor(name):
 @Appender(
     _doc
     % dict(
-        klass="Series",
-        others=("register_dataframe_accessor, " "register_index_accessor"),
+        klass="Series", others=("register_dataframe_accessor, register_index_accessor")
     )
 )
 def register_series_accessor(name):
@@ -297,8 +295,7 @@ def register_series_accessor(name):
 @Appender(
     _doc
     % dict(
-        klass="Index",
-        others=("register_dataframe_accessor, " "register_series_accessor"),
+        klass="Index", others=("register_dataframe_accessor, register_series_accessor")
     )
 )
 def register_index_accessor(name):

pandas/core/arrays/base.py

@@ -14,14 +14,17 @@
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import Appender, Substitution
+from pandas.util._validators import validate_fillna_kwargs
 
-from pandas.core.dtypes.common import is_list_like
+from pandas.core.dtypes.common import is_array_like, is_list_like
 from pandas.core.dtypes.dtypes import ExtensionDtype
 from pandas.core.dtypes.generic import ABCExtensionArray, ABCIndexClass, ABCSeries
 from pandas.core.dtypes.missing import isna
 
 from pandas._typing import ArrayLike
 from pandas.core import ops
+from pandas.core.algorithms import _factorize_array, unique
+from pandas.core.missing import backfill_1d, pad_1d
 from pandas.core.sorting import nargsort
 
 _not_implemented_message = "{} does not implement {}."
@@ -484,10 +487,6 @@ def fillna(self, value=None, method=None, limit=None):
         -------
         filled : ExtensionArray with NA/NaN filled
         """
-        from pandas.api.types import is_array_like
-        from pandas.util._validators import validate_fillna_kwargs
-        from pandas.core.missing import pad_1d, backfill_1d
-
         value, method = validate_fillna_kwargs(value, method)
 
         mask = self.isna()
@@ -584,8 +583,6 @@ def unique(self):
         -------
         uniques : ExtensionArray
         """
-        from pandas import unique
-
         uniques = unique(self.astype(object))
         return self._from_sequence(uniques, dtype=self.dtype)
 
@@ -700,8 +697,6 @@ def factorize(self, na_sentinel: int = -1) -> Tuple[np.ndarray, ABCExtensionArra
         #    original ExtensionArray.
         # 2. ExtensionArray.factorize.
         #    Complete control over factorization.
-        from pandas.core.algorithms import _factorize_array
-
         arr, na_value = self._values_for_factorize()
 
         labels, uniques = _factorize_array(
@@ -874,7 +869,7 @@ def copy(self) -> ABCExtensionArray:
     def __repr__(self):
         from pandas.io.formats.printing import format_object_summary
 
-        template = "{class_name}" "{data}\n" "Length: {length}, dtype: {dtype}"
+        template = "{class_name}{data}\nLength: {length}, dtype: {dtype}"
         # the short repr has no trailing newline, while the truncated
         # repr does. So we include a newline in our template, and strip
         # any trailing newlines from format_object_summary

pandas/core/arrays/categorical.py

@@ -93,13 +93,13 @@ def f(self, other):
         if not self.ordered:
             if op in ["__lt__", "__gt__", "__le__", "__ge__"]:
                 raise TypeError(
-                    "Unordered Categoricals can only compare " "equality or not"
+                    "Unordered Categoricals can only compare equality or not"
                 )
         if isinstance(other, Categorical):
             # Two Categoricals can only be be compared if the categories are
             # the same (maybe up to ordering, depending on ordered)
 
-            msg = "Categoricals can only be compared if " "'categories' are the same."
+            msg = "Categoricals can only be compared if 'categories' are the same."
             if len(self.categories) != len(other.categories):
                 raise TypeError(msg + " Categories are different lengths")
             elif self.ordered and not (self.categories == other.categories).all():
@@ -109,7 +109,7 @@ def f(self, other):
 
             if not (self.ordered == other.ordered):
                 raise TypeError(
-                    "Categoricals can only be compared if " "'ordered' is the same"
+                    "Categoricals can only be compared if 'ordered' is the same"
                 )
             if not self.ordered and not self.categories.equals(other.categories):
                 # both unordered and different order
@@ -387,7 +387,7 @@ def __init__(
 
                 # FIXME
                 raise NotImplementedError(
-                    "> 1 ndim Categorical are not " "supported at this time"
+                    "> 1 ndim Categorical are not supported at this time"
                 )
 
             # we're inferring from values
@@ -694,7 +694,7 @@ def from_codes(cls, codes, categories=None, ordered=None, dtype=None):
                 raise ValueError(msg)
 
         if len(codes) and (codes.max() >= len(dtype.categories) or codes.min() < -1):
-            raise ValueError("codes need to be between -1 and " "len(categories)-1")
+            raise ValueError("codes need to be between -1 and len(categories)-1")
 
         return cls(codes, dtype=dtype, fastpath=True)
 
@@ -1019,7 +1019,7 @@ def reorder_categories(self, new_categories, ordered=None, inplace=False):
         inplace = validate_bool_kwarg(inplace, "inplace")
         if set(self.dtype.categories) != set(new_categories):
             raise ValueError(
-                "items in new_categories are not the same as in " "old categories"
+                "items in new_categories are not the same as in old categories"
             )
         return self.set_categories(new_categories, ordered=ordered, inplace=inplace)
 
@@ -1481,7 +1481,7 @@ def put(self, *args, **kwargs):
         """
         Replace specific elements in the Categorical with given values.
         """
-        raise NotImplementedError(("'put' is not yet implemented " "for Categorical"))
+        raise NotImplementedError(("'put' is not yet implemented for Categorical"))
 
     def dropna(self):
         """
@@ -1827,7 +1827,7 @@ def fillna(self, value=None, method=None, limit=None):
             value = np.nan
         if limit is not None:
             raise NotImplementedError(
-                "specifying a limit for fillna has not " "been implemented yet"
+                "specifying a limit for fillna has not been implemented yet"
             )
 
         codes = self._codes
@@ -1963,7 +1963,7 @@ def take_nd(self, indexer, allow_fill=None, fill_value=None):
             if fill_value in self.categories:
                 fill_value = self.categories.get_loc(fill_value)
             else:
-                msg = "'fill_value' ('{}') is not in this Categorical's " "categories."
+                msg = "'fill_value' ('{}') is not in this Categorical's categories."
                 raise TypeError(msg.format(fill_value))
 
         codes = take(self._codes, indexer, allow_fill=allow_fill, fill_value=fill_value)
@@ -2168,12 +2168,12 @@ def __setitem__(self, key, value):
             # in a 2-d case be passd (slice(None),....)
             if len(key) == 2:
                 if not com.is_null_slice(key[0]):
-                    raise AssertionError("invalid slicing for a 1-ndim " "categorical")
+                    raise AssertionError("invalid slicing for a 1-ndim categorical")
                 key = key[1]
             elif len(key) == 1:
                 key = key[0]
             else:
-                raise AssertionError("invalid slicing for a 1-ndim " "categorical")
+                raise AssertionError("invalid slicing for a 1-ndim categorical")
 
         # slicing in Series or Categorical
         elif isinstance(key, slice):
@@ -2561,9 +2561,7 @@ def __init__(self, data):
     @staticmethod
     def _validate(data):
         if not is_categorical_dtype(data.dtype):
-            raise AttributeError(
-                "Can only use .cat accessor with a " "'category' dtype"
-            )
+            raise AttributeError("Can only use .cat accessor with a 'category' dtype")
 
     def _delegate_property_get(self, name):
         return getattr(self._parent, name)
@@ -2607,7 +2605,7 @@ def name(self):
         # need to be updated. `name` will need to be removed from
         # `ok_for_cat`.
         warn(
-            "`Series.cat.name` has been deprecated. Use `Series.name` " "instead.",
+            "`Series.cat.name` has been deprecated. Use `Series.name` instead.",
             FutureWarning,
             stacklevel=2,
         )
@@ -2619,7 +2617,7 @@ def index(self):
         # need to be updated. `index` will need to be removed from
         # ok_for_cat`.
         warn(
-            "`Series.cat.index` has been deprecated. Use `Series.index` " "instead.",
+            "`Series.cat.index` has been deprecated. Use `Series.index` instead.",
             FutureWarning,
             stacklevel=2,
         )

pandas/core/arrays/datetimelike.py

@@ -1097,7 +1097,7 @@ def _sub_period_array(self, other):
             )
 
         if len(self) != len(other):
-            raise ValueError("cannot subtract arrays/indices of " "unequal length")
+            raise ValueError("cannot subtract arrays/indices of unequal length")
         if self.freq != other.freq:
             msg = DIFFERENT_FREQ.format(
                 cls=type(self).__name__, own_freq=self.freqstr, other_freq=other.freqstr

pandas/core/arrays/datetimes.py

@@ -478,7 +478,7 @@ def _generate_range(
 
         periods = dtl.validate_periods(periods)
         if freq is None and any(x is None for x in [periods, start, end]):
-            raise ValueError("Must provide freq argument if no data is " "supplied")
+            raise ValueError("Must provide freq argument if no data is supplied")
 
         if com.count_not_none(start, end, periods, freq) != 3:
             raise ValueError(
@@ -496,7 +496,7 @@ def _generate_range(
         if start is None and end is None:
             if closed is not None:
                 raise ValueError(
-                    "Closed has to be None if not both of start" "and end are defined"
+                    "Closed has to be None if not both of startand end are defined"
                 )
         if start is NaT or end is NaT:
             raise ValueError("Neither `start` nor `end` can be NaT")
@@ -786,11 +786,11 @@ def _assert_tzawareness_compat(self, other):
         elif self.tz is None:
             if other_tz is not None:
                 raise TypeError(
-                    "Cannot compare tz-naive and tz-aware " "datetime-like objects."
+                    "Cannot compare tz-naive and tz-aware datetime-like objects."
                 )
         elif other_tz is None:
             raise TypeError(
-                "Cannot compare tz-naive and tz-aware " "datetime-like objects"
+                "Cannot compare tz-naive and tz-aware datetime-like objects"
             )
 
     # -----------------------------------------------------------------
@@ -833,7 +833,7 @@ def _add_offset(self, offset):
 
         except NotImplementedError:
             warnings.warn(
-                "Non-vectorized DateOffset being applied to Series " "or DatetimeIndex",
+                "Non-vectorized DateOffset being applied to Series or DatetimeIndex",
                 PerformanceWarning,
             )
             result = self.astype("O") + offset
@@ -851,7 +851,7 @@ def _sub_datetimelike_scalar(self, other):
         if not self._has_same_tz(other):
             # require tz compat
             raise TypeError(
-                "Timestamp subtraction must have the same " "timezones or no timezones"
+                "Timestamp subtraction must have the same timezones or no timezones"
             )
 
         i8 = self.asi8
@@ -957,7 +957,7 @@ def tz_convert(self, tz):
         if self.tz is None:
             # tz naive, use tz_localize
             raise TypeError(
-                "Cannot convert tz-naive timestamps, use " "tz_localize to localize"
+                "Cannot convert tz-naive timestamps, use tz_localize to localize"
             )
 
         # No conversion since timestamps are all UTC to begin with
@@ -1125,7 +1125,7 @@ def tz_localize(self, tz, ambiguous="raise", nonexistent="raise", errors=None):
                 nonexistent = "raise"
             else:
                 raise ValueError(
-                    "The errors argument must be either 'coerce' " "or 'raise'."
+                    "The errors argument must be either 'coerce' or 'raise'."
                 )
 
         nonexistent_options = ("raise", "NaT", "shift_forward", "shift_backward")
@@ -1274,7 +1274,7 @@ def to_period(self, freq=None):
 
             if freq is None:
                 raise ValueError(
-                    "You must pass a freq argument as " "current index has none."
+                    "You must pass a freq argument as current index has none."
                 )
 
             freq = get_period_alias(freq)
@@ -2047,7 +2047,7 @@ def maybe_convert_dtype(data, copy):
         # Note: without explicitly raising here, PeriodIndex
         #  test_setops.test_join_does_not_recur fails
         raise TypeError(
-            "Passing PeriodDtype data is invalid.  " "Use `data.to_timestamp()` instead"
+            "Passing PeriodDtype data is invalid.  Use `data.to_timestamp()` instead"
         )
 
     elif is_categorical_dtype(data):
@@ -2177,7 +2177,7 @@ def validate_tz_from_dtype(dtype, tz):
         dtz = getattr(dtype, "tz", None)
         if dtz is not None:
             if tz is not None and not timezones.tz_compare(tz, dtz):
-                raise ValueError("cannot supply both a tz and a dtype" " with a tz")
+                raise ValueError("cannot supply both a tz and a dtype with a tz")
             tz = dtz
 
         if tz is not None and is_datetime64_dtype(dtype):
@@ -2216,15 +2216,15 @@ def _infer_tz_from_endpoints(start, end, tz):
         inferred_tz = timezones.infer_tzinfo(start, end)
     except Exception:
         raise TypeError(
-            "Start and end cannot both be tz-aware with " "different timezones"
+            "Start and end cannot both be tz-aware with different timezones"
         )
 
     inferred_tz = timezones.maybe_get_tz(inferred_tz)
     tz = timezones.maybe_get_tz(tz)
 
     if tz is not None and inferred_tz is not None:
         if not timezones.tz_compare(inferred_tz, tz):
-            raise AssertionError("Inferred time zone not equal to passed " "time zone")
+            raise AssertionError("Inferred time zone not equal to passed time zone")
 
     elif inferred_tz is not None:
         tz = inferred_tz