STY: concat strings that should not be seperated (#30942)

Author: ShaharNaveh

pandas/_libs/algos.pyx

@@ -914,8 +914,7 @@ def rank_1d(rank_t[:] in_arr, ties_method='average',
  ranks[argsorted[j]] = i + 1
  elif tiebreak == TIEBREAK_FIRST:
  if rank_t is object:
- raise ValueError('first not supported for '
- 'non-numeric data')
+ raise ValueError('first not supported for non-numeric data')
  else:
  for j in range(i - dups + 1, i + 1):
  ranks[argsorted[j]] = j + 1
@@ -971,8 +970,7 @@ def rank_1d(rank_t[:] in_arr, ties_method='average',
  ranks[argsorted[j]] = i + 1
  elif tiebreak == TIEBREAK_FIRST:
  if rank_t is object:
- raise ValueError('first not supported for '
- 'non-numeric data')
+ raise ValueError('first not supported for non-numeric data')
  else:
  for j in range(i - dups + 1, i + 1):
  ranks[argsorted[j]] = j + 1
@@ -1137,8 +1135,7 @@ def rank_2d(rank_t[:, :] in_arr, axis=0, ties_method='average',
  ranks[i, argsorted[i, z]] = j + 1
  elif tiebreak == TIEBREAK_FIRST:
  if rank_t is object:
- raise ValueError('first not supported '
- 'for non-numeric data')
+ raise ValueError('first not supported for non-numeric data')
  else:
  for z in range(j - dups + 1, j + 1):
  ranks[i, argsorted[i, z]] = z + 1

pandas/_libs/groupby.pyx

@@ -686,8 +686,7 @@ def _group_ohlc(floating[:, :] out,
  raise ValueError('Output array must have 4 columns')
 
  if K > 1:
- raise NotImplementedError("Argument 'values' must have only "
- "one dimension")
+ raise NotImplementedError("Argument 'values' must have only one dimension")
  out[:] = np.nan
 
  with nogil:

pandas/_libs/hashing.pyx

@@ -51,8 +51,9 @@ def hash_object_array(object[:] arr, object key, object encoding='utf8'):
  k = <bytes>key.encode(encoding)
  kb = <uint8_t *>k
  if len(k) != 16:
- raise ValueError("key should be a 16-byte string encoded, "
- f"got {k} (len {len(k)})")
+ raise ValueError(
+ f"key should be a 16-byte string encoded, got {k} (len {len(k)})"
+ )
 
  n = len(arr)
 
@@ -77,8 +78,10 @@ def hash_object_array(object[:] arr, object key, object encoding='utf8'):
  hash(val)
  data = <bytes>str(val).encode(encoding)
  else:
- raise TypeError(f"{val} of type {type(val)} is not a valid type "
- "for hashing, must be string or null")
+ raise TypeError(
+ f"{val} of type {type(val)} is not a valid type for hashing, "
+ "must be string or null"
+ )
 
  l = len(data)
  lens[i] = l

pandas/_libs/indexing.pyx

@@ -18,6 +18,7 @@ cdef class _NDFrameIndexerBase:
  if ndim is None:
  ndim = self._ndim = self.obj.ndim
  if ndim > 2:
- raise ValueError("NDFrameIndexer does not support "
- "NDFrame objects with ndim > 2")
+ raise ValueError(
+ "NDFrameIndexer does not support NDFrame objects with ndim > 2"
+ )
  return ndim

pandas/_libs/sparse.pyx

@@ -72,9 +72,9 @@ cdef class IntIndex(SparseIndex):
  """
 
  if self.npoints > self.length:
- msg = (f"Too many indices. Expected "
-  f"{self.length} but found {self.npoints}")
- raise ValueError(msg)
+ raise ValueError(
+ f"Too many indices. Expected {self.length} but found {self.npoints}"
+ )
 
  # Indices are vacuously ordered and non-negative
  # if the sequence of indices is empty.

pandas/_libs/testing.pyx

@@ -127,9 +127,9 @@ cpdef assert_almost_equal(a, b,
  # classes can't be the same, to raise error
  assert_class_equal(a, b, obj=obj)
 
- assert has_length(a) and has_length(b), ("Can't compare objects without "
-  "length, one or both is invalid: "
-  f"({a}, {b})")
+ assert has_length(a) and has_length(b), (
+ f"Can't compare objects without length, one or both is invalid: ({a}, {b})"
+ )
 
  if a_is_ndarray and b_is_ndarray:
  na, nb = a.size, b.size

pandas/_libs/tslibs/timestamps.pyx

@@ -161,8 +161,7 @@ def round_nsint64(values, mode, freq):
 
  # if/elif above should catch all rounding modes defined in enum 'RoundTo':
  # if flow of control arrives here, it is a bug
- raise ValueError("round_nsint64 called with an unrecognized "
- "rounding mode")
+ raise ValueError("round_nsint64 called with an unrecognized rounding mode")
 
 
 # ----------------------------------------------------------------------
@@ -324,8 +323,10 @@ class Timestamp(_Timestamp):
 
  Function is not implemented. Use pd.to_datetime().
  """
- raise NotImplementedError("Timestamp.strptime() is not implemented."
- "Use to_datetime() to parse date strings.")
+ raise NotImplementedError(
+ "Timestamp.strptime() is not implemented. "
+ "Use to_datetime() to parse date strings."
+ )
 
  @classmethod
  def combine(cls, date, time):
@@ -381,8 +382,9 @@ class Timestamp(_Timestamp):
  if tzinfo is not None:
  if not PyTZInfo_Check(tzinfo):
  # tzinfo must be a datetime.tzinfo object, GH#17690
- raise TypeError(f'tzinfo must be a datetime.tzinfo object, '
- f'not {type(tzinfo)}')
+ raise TypeError(
+ f"tzinfo must be a datetime.tzinfo object, not {type(tzinfo)}"
+ )
  elif tz is not None:
  raise ValueError('Can provide at most one of tz, tzinfo')
 
@@ -393,8 +395,10 @@ class Timestamp(_Timestamp):
  # User passed a date string to parse.
  # Check that the user didn't also pass a date attribute kwarg.
  if any(arg is not None for arg in _date_attributes):
- raise ValueError('Cannot pass a date attribute keyword '
- 'argument when passing a date string')
+ raise ValueError(
+ "Cannot pass a date attribute keyword "
+ "argument when passing a date string"
+ )
 
  elif ts_input is _no_input:
  # User passed keyword arguments.
@@ -578,8 +582,10 @@ timedelta}, default 'raise'
  @tz.setter
  def tz(self, value):
  # GH 3746: Prevent localizing or converting the index by setting tz
- raise AttributeError("Cannot directly set timezone. Use tz_localize() "
- "or tz_convert() as appropriate")
+ raise AttributeError(
+ "Cannot directly set timezone. "
+ "Use tz_localize() or tz_convert() as appropriate"
+ )
 
  def __setstate__(self, state):
  self.value = state[0]
@@ -598,9 +604,10 @@ timedelta}, default 'raise'
 
  if self.tz is not None:
  # GH#21333
- warnings.warn("Converting to Period representation will "
- "drop timezone information.",
- UserWarning)
+ warnings.warn(
+ "Converting to Period representation will drop timezone information.",
+ UserWarning,
+ )
 
  if freq is None:
  freq = self.freq
@@ -810,13 +817,13 @@ default 'raise'
  if ambiguous == 'infer':
  raise ValueError('Cannot infer offset with only one time.')
 
- nonexistent_options = ('raise', 'NaT', 'shift_forward',
- 'shift_backward')
+ nonexistent_options = ('raise', 'NaT', 'shift_forward', 'shift_backward')
  if nonexistent not in nonexistent_options and not isinstance(
  nonexistent, timedelta):
- raise ValueError("The nonexistent argument must be one of 'raise', "
- "'NaT', 'shift_forward', 'shift_backward' or "
- "a timedelta object")
+ raise ValueError(
+ "The nonexistent argument must be one of 'raise', "
+ "'NaT', 'shift_forward', 'shift_backward' or a timedelta object"
+ )
 
  if self.tzinfo is None:
  # tz naive, localize
@@ -833,8 +840,9 @@ default 'raise'
  value = tz_convert_single(self.value, UTC, self.tz)
  return Timestamp(value, tz=tz, freq=self.freq)
  else:
- raise TypeError('Cannot localize tz-aware Timestamp, use '
- 'tz_convert for conversions')
+ raise TypeError(
+ "Cannot localize tz-aware Timestamp, use tz_convert for conversions"
+ )
 
  def tz_convert(self, tz):
  """
@@ -857,17 +865,28 @@ default 'raise'
  """
  if self.tzinfo is None:
  # tz naive, use tz_localize
- raise TypeError('Cannot convert tz-naive Timestamp, use '
- 'tz_localize to localize')
+ raise TypeError(
+ "Cannot convert tz-naive Timestamp, use tz_localize to localize"
+ )
  else:
  # Same UTC timestamp, different time zone
  return Timestamp(self.value, tz=tz, freq=self.freq)
 
  astimezone = tz_convert
 
- def replace(self, year=None, month=None, day=None,
- hour=None, minute=None, second=None, microsecond=None,
- nanosecond=None, tzinfo=object, fold=0):
+ def replace(
+ self,
+ year=None,
+ month=None,
+ day=None,
+ hour=None,
+ minute=None,
+ second=None,
+ microsecond=None,
+ nanosecond=None,
+ tzinfo=object,
+ fold=0,
+ ):
  """
  implements datetime.replace, handles nanoseconds.
 
@@ -910,8 +929,9 @@ default 'raise'
  def validate(k, v):
  """ validate integers """
  if not is_integer_object(v):
- raise ValueError(f"value must be an integer, received "
- f"{type(v)} for {k}")
+ raise ValueError(
+ f"value must be an integer, received {type(v)} for {k}"
+ )
  return v
 
  if year is not None:

pandas/_libs/window/aggregations.pyx

@@ -1871,8 +1871,7 @@ def ewmcov(float64_t[:] input_x, float64_t[:] input_y,
  bint is_observation
 
  if <Py_ssize_t>len(input_y) != N:
- raise ValueError(f"arrays are of different lengths "
- f"({N} and {len(input_y)})")
+ raise ValueError(f"arrays are of different lengths ({N} and {len(input_y)})")
 
  output = np.empty(N, dtype=float)
  if N == 0: