CLN: all the things (#27647)

Thanks, @jbrockmendel.

Author: jbrockmendel

pandas/_config/config.py

@@ -110,7 +110,7 @@ def _set_option(*args, **kwargs):
     # must at least 1 arg deal with constraints later
     nargs = len(args)
     if not nargs or nargs % 2 != 0:
-        raise ValueError("Must provide an even number of non-keyword " "arguments")
+        raise ValueError("Must provide an even number of non-keyword arguments")
 
     # default to false
     silent = kwargs.pop("silent", False)
@@ -395,7 +395,7 @@ class option_context:
     def __init__(self, *args):
         if not (len(args) % 2 == 0 and len(args) >= 2):
             raise ValueError(
-                "Need to invoke as" " option_context(pat, val, [(pat, val), ...])."
+                "Need to invoke as option_context(pat, val, [(pat, val), ...])."
             )
 
         self.ops = list(zip(args[::2], args[1::2]))

pandas/compat/numpy/function.py

@@ -59,7 +59,7 @@ def __call__(self, args, kwargs, fname=None, max_fname_arg_count=None, method=No
                 )
             else:
                 raise ValueError(
-                    "invalid validation method " "'{method}'".format(method=method)
+                    "invalid validation method '{method}'".format(method=method)
                 )
 
 

pandas/core/arrays/datetimes.py

@@ -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 startand end are defined"
+                    "Closed has to be None if not both of start and end are defined"
                 )
         if start is NaT or end is NaT:
             raise ValueError("Neither `start` nor `end` can be NaT")

pandas/core/groupby/generic.py

@@ -227,7 +227,7 @@ def aggregate(self, func, *args, **kwargs):
             kwargs = {}
         elif func is None:
             # nicer error message
-            raise TypeError("Must provide 'func' or tuples of " "'(column, aggfunc).")
+            raise TypeError("Must provide 'func' or tuples of '(column, aggfunc).")
 
         func = _maybe_mangle_lambdas(func)
 
@@ -836,9 +836,7 @@ def aggregate(self, func_or_funcs=None, *args, **kwargs):
 
         relabeling = func_or_funcs is None
         columns = None
-        no_arg_message = (
-            "Must provide 'func_or_funcs' or named " "aggregation **kwargs."
-        )
+        no_arg_message = "Must provide 'func_or_funcs' or named aggregation **kwargs."
         if relabeling:
             columns = list(kwargs)
             if not PY36:

pandas/core/groupby/groupby.py

@@ -462,7 +462,7 @@ def get_converter(s):
         name_sample = names[0]
         if isinstance(index_sample, tuple):
             if not isinstance(name_sample, tuple):
-                msg = "must supply a tuple to get_group with multiple" " grouping keys"
+                msg = "must supply a tuple to get_group with multiple grouping keys"
                 raise ValueError(msg)
             if not len(name_sample) == len(index_sample):
                 try:
@@ -715,7 +715,7 @@ def f(g):
 
             else:
                 raise ValueError(
-                    "func must be a callable if args or " "kwargs are supplied"
+                    "func must be a callable if args or kwargs are supplied"
                 )
         else:
             f = func
@@ -1872,7 +1872,7 @@ def quantile(self, q=0.5, interpolation="linear"):
         def pre_processor(vals: np.ndarray) -> Tuple[np.ndarray, Optional[Type]]:
             if is_object_dtype(vals):
                 raise TypeError(
-                    "'quantile' cannot be performed against " "'object' dtypes!"
+                    "'quantile' cannot be performed against 'object' dtypes!"
                 )
 
             inference = None
@@ -2201,9 +2201,7 @@ def _get_cythonized_result(
         `Series` or `DataFrame`  with filled values
         """
         if result_is_index and aggregate:
-            raise ValueError(
-                "'result_is_index' and 'aggregate' cannot both " "be True!"
-            )
+            raise ValueError("'result_is_index' and 'aggregate' cannot both be True!")
         if post_processing:
             if not callable(pre_processing):
                 raise ValueError("'post_processing' must be a callable!")
@@ -2212,7 +2210,7 @@ def _get_cythonized_result(
                 raise ValueError("'pre_processing' must be a callable!")
             if not needs_values:
                 raise ValueError(
-                    "Cannot use 'pre_processing' without " "specifying 'needs_values'!"
+                    "Cannot use 'pre_processing' without specifying 'needs_values'!"
                 )
 
         labels, _, ngroups = grouper.group_info

pandas/core/groupby/grouper.py

@@ -25,6 +25,7 @@
 from pandas.core.arrays import Categorical, ExtensionArray
 import pandas.core.common as com
 from pandas.core.frame import DataFrame
+from pandas.core.groupby.categorical import recode_for_groupby, recode_from_groupby
 from pandas.core.groupby.ops import BaseGrouper
 from pandas.core.index import CategoricalIndex, Index, MultiIndex
 from pandas.core.series import Series
@@ -310,8 +311,6 @@ def __init__(
             # a passed Categorical
             elif is_categorical_dtype(self.grouper):
 
-                from pandas.core.groupby.categorical import recode_for_groupby
-
                 self.grouper, self.all_grouper = recode_for_groupby(
                     self.grouper, self.sort, observed
                 )
@@ -361,13 +360,10 @@ def __init__(
         # Timestamps like
         if getattr(self.grouper, "dtype", None) is not None:
             if is_datetime64_dtype(self.grouper):
-                from pandas import to_datetime
-
-                self.grouper = to_datetime(self.grouper)
+                self.grouper = self.grouper.astype("datetime64[ns]")
             elif is_timedelta64_dtype(self.grouper):
-                from pandas import to_timedelta
 
-                self.grouper = to_timedelta(self.grouper)
+                self.grouper = self.grouper.astype("timedelta64[ns]")
 
     def __repr__(self):
         return "Grouping({0})".format(self.name)
@@ -400,8 +396,6 @@ def labels(self):
     @cache_readonly
     def result_index(self):
         if self.all_grouper is not None:
-            from pandas.core.groupby.categorical import recode_from_groupby
-
             return recode_from_groupby(self.all_grouper, self.sort, self.group_index)
         return self.group_index
 
@@ -493,12 +487,12 @@ def _get_grouper(
                 elif nlevels == 0:
                     raise ValueError("No group keys passed!")
                 else:
-                    raise ValueError("multiple levels only valid with " "MultiIndex")
+                    raise ValueError("multiple levels only valid with MultiIndex")
 
             if isinstance(level, str):
                 if obj.index.name != level:
                     raise ValueError(
-                        "level name {} is not the name of the " "index".format(level)
+                        "level name {} is not the name of the index".format(level)
                     )
             elif level > 0 or level < -1:
                 raise ValueError("level > 0 or level < -1 only valid with MultiIndex")

pandas/core/groupby/ops.py

@@ -467,12 +467,12 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1, **kwargs):
         elif is_datetime64_any_dtype(values):
             if how in ["add", "prod", "cumsum", "cumprod"]:
                 raise NotImplementedError(
-                    "datetime64 type does not support {} " "operations".format(how)
+                    "datetime64 type does not support {} operations".format(how)
                 )
         elif is_timedelta64_dtype(values):
             if how in ["prod", "cumprod"]:
                 raise NotImplementedError(
-                    "timedelta64 type does not support {} " "operations".format(how)
+                    "timedelta64 type does not support {} operations".format(how)
                 )
 
         arity = self._cython_arity.get(how, 1)
@@ -489,7 +489,7 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1, **kwargs):
                 values = values.T
             if arity > 1:
                 raise NotImplementedError(
-                    "arity of more than 1 is not " "supported for the 'how' argument"
+                    "arity of more than 1 is not supported for the 'how' argument"
                 )
             out_shape = (self.ngroups,) + values.shape[1:]
 
@@ -604,9 +604,7 @@ def _aggregate(
     ):
         if values.ndim > 3:
             # punting for now
-            raise NotImplementedError(
-                "number of dimensions is currently " "limited to 3"
-            )
+            raise NotImplementedError("number of dimensions is currently limited to 3")
         elif values.ndim > 2:
             for i, chunk in enumerate(values.transpose(2, 0, 1)):
 
@@ -631,9 +629,7 @@ def _transform(
         comp_ids, _, ngroups = self.group_info
         if values.ndim > 3:
             # punting for now
-            raise NotImplementedError(
-                "number of dimensions is currently " "limited to 3"
-            )
+            raise NotImplementedError("number of dimensions is currently limited to 3")
         elif values.ndim > 2:
             for i, chunk in enumerate(values.transpose(2, 0, 1)):
 

pandas/core/indexes/accessors.py

@@ -340,4 +340,4 @@ def __new__(cls, data):
         except Exception:
             pass  # we raise an attribute error anyway
 
-        raise AttributeError("Can only use .dt accessor with datetimelike " "values")
+        raise AttributeError("Can only use .dt accessor with datetimelike values")

pandas/core/indexes/base.py

@@ -376,9 +376,7 @@ def __new__(
                             data = maybe_cast_to_integer_array(data, dtype, copy=copy)
                         elif inferred in ["floating", "mixed-integer-float"]:
                             if isna(data).any():
-                                raise ValueError(
-                                    "cannot convert float " "NaN to integer"
-                                )
+                                raise ValueError("cannot convert float NaN to integer")
 
                             if inferred == "mixed-integer-float":
                                 data = maybe_cast_to_integer_array(data, dtype)
@@ -1182,7 +1180,7 @@ def summary(self, name=None):
         .. deprecated:: 0.23.0
         """
         warnings.warn(
-            "'summary' is deprecated and will be removed in a " "future version.",
+            "'summary' is deprecated and will be removed in a future version.",
             FutureWarning,
             stacklevel=2,
         )
@@ -1521,7 +1519,7 @@ def _validate_index_level(self, level):
                 )
             elif level > 0:
                 raise IndexError(
-                    "Too many levels:" " Index has only 1 level, not %d" % (level + 1)
+                    "Too many levels: Index has only 1 level, not %d" % (level + 1)
                 )
         elif level != self.name:
             raise KeyError(
@@ -2953,7 +2951,7 @@ def get_indexer(self, target, method=None, limit=None, tolerance=None):
 
         if not self.is_unique:
             raise InvalidIndexError(
-                "Reindexing only valid with uniquely" " valued Index objects"
+                "Reindexing only valid with uniquely valued Index objects"
             )
 
         if method == "pad" or method == "backfill":
@@ -2980,7 +2978,7 @@ def _convert_tolerance(self, tolerance, target):
         # override this method on subclasses
         tolerance = np.asarray(tolerance)
         if target.size != tolerance.size and tolerance.size > 1:
-            raise ValueError("list-like tolerance size must match " "target index size")
+            raise ValueError("list-like tolerance size must match target index size")
         return tolerance
 
     def _get_fill_indexer(self, target, method, limit=None, tolerance=None):
@@ -3712,9 +3710,7 @@ def _get_leaf_sorter(labels):
             return lib.get_level_sorter(lab, ensure_int64(starts))
 
         if isinstance(self, MultiIndex) and isinstance(other, MultiIndex):
-            raise TypeError(
-                "Join on level between two MultiIndex objects " "is ambiguous"
-            )
+            raise TypeError("Join on level between two MultiIndex objects is ambiguous")
 
         left, right = self, other
 
@@ -3728,7 +3724,7 @@ def _get_leaf_sorter(labels):
 
         if not right.is_unique:
             raise NotImplementedError(
-                "Index._join_level on non-unique index " "is not implemented"
+                "Index._join_level on non-unique index is not implemented"
             )
 
         new_level, left_lev_indexer, right_lev_indexer = old_level.join(
@@ -4554,9 +4550,7 @@ def sort(self, *args, **kwargs):
         """
         Use sort_values instead.
         """
-        raise TypeError(
-            "cannot sort an Index object in-place, use " "sort_values instead"
-        )
+        raise TypeError("cannot sort an Index object in-place, use sort_values instead")
 
     def shift(self, periods=1, freq=None):
         """
@@ -5205,7 +5199,7 @@ def slice_locs(self, start=None, end=None, step=None, kind=None):
                 pass
             else:
                 if not tz_compare(ts_start.tzinfo, ts_end.tzinfo):
-                    raise ValueError("Both dates must have the " "same UTC offset")
+                    raise ValueError("Both dates must have the same UTC offset")
 
         start_slice = None
         if start is not None:
@@ -5397,12 +5391,10 @@ def _validate_for_numeric_binop(self, other, op):
 
         if isinstance(other, (Index, ABCSeries, np.ndarray)):
             if len(self) != len(other):
-                raise ValueError("cannot evaluate a numeric op with " "unequal lengths")
+                raise ValueError("cannot evaluate a numeric op with unequal lengths")
             other = com.values_from_object(other)
             if other.dtype.kind not in ["f", "i", "u"]:
-                raise TypeError(
-                    "cannot evaluate a numeric op " "with a non-numeric dtype"
-                )
+                raise TypeError("cannot evaluate a numeric op with a non-numeric dtype")
         elif isinstance(other, (ABCDateOffset, np.timedelta64, timedelta)):
             # higher up to handle
             pass
@@ -5571,7 +5563,7 @@ def logical_func(self, *args, **kwargs):
             return logical_func
 
         cls.all = _make_logical_function(
-            "all", "Return whether all elements " "are True.", np.all
+            "all", "Return whether all elements are True.", np.all
         )
         cls.any = _make_logical_function(
             "any", "Return whether any element is True.", np.any