CLN: For loops, boolean conditions, misc. (#25206)

Author: mroeschke

pandas/core/arrays/categorical.py

@@ -2167,8 +2167,7 @@ def _reverse_indexer(self):
  r, counts = libalgos.groupsort_indexer(self.codes.astype('int64'),
  categories.size)
  counts = counts.cumsum()
- result = [r[counts[indexer]:counts[indexer + 1]]
- for indexer in range(len(counts) - 1)]
+ result = (r[start:end] for start, end in zip(counts, counts[1:]))
  result = dict(zip(categories, result))
  return result
 

pandas/core/arrays/datetimes.py

@@ -128,7 +128,7 @@ def _dt_array_cmp(cls, op):
  Wrap comparison operations to convert datetime-like to datetime64
  """
  opname = '__{name}__'.format(name=op.__name__)
- nat_result = True if opname == '__ne__' else False
+ nat_result = opname == '__ne__'
 
  def wrapper(self, other):
  if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):

pandas/core/arrays/integer.py

@@ -561,7 +561,7 @@ def cmp_method(self, other):
  else:
  mask = self._mask | mask
 
- result[mask] = True if op_name == 'ne' else False
+ result[mask] = op_name == 'ne'
  return result
 
  name = '__{name}__'.format(name=op.__name__)

pandas/core/arrays/period.py

@@ -46,7 +46,7 @@ def _period_array_cmp(cls, op):
  Wrap comparison operations to convert Period-like to PeriodDtype
  """
  opname = '__{name}__'.format(name=op.__name__)
- nat_result = True if opname == '__ne__' else False
+ nat_result = opname == '__ne__'
 
  def wrapper(self, other):
  op = getattr(self.asi8, opname)

pandas/core/arrays/timedeltas.py

@@ -62,7 +62,7 @@ def _td_array_cmp(cls, op):
  Wrap comparison operations to convert timedelta-like to timedelta64
  """
  opname = '__{name}__'.format(name=op.__name__)
- nat_result = True if opname == '__ne__' else False
+ nat_result = opname == '__ne__'
 
  def wrapper(self, other):
  if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):

pandas/core/computation/pytables.py

@@ -252,7 +252,7 @@ def evaluate(self):
  .format(slf=self))
 
  rhs = self.conform(self.rhs)
- values = [TermValue(v, v, self.kind) for v in rhs]
+ values = [TermValue(v, v, self.kind).value for v in rhs]
 
  if self.is_in_table:
 
@@ -263,7 +263,7 @@ def evaluate(self):
  self.filter = (
  self.lhs,
  filter_op,
- pd.Index([v.value for v in values]))
+ pd.Index(values))
 
  return self
  return None
@@ -275,7 +275,7 @@ def evaluate(self):
  self.filter = (
  self.lhs,
  filter_op,
- pd.Index([v.value for v in values]))
+ pd.Index(values))
 
  else:
  raise TypeError("passing a filterable condition to a non-table "

pandas/core/dtypes/cast.py

@@ -1111,11 +1111,9 @@ def find_common_type(types):
  # this is different from numpy, which casts bool with float/int as int
  has_bools = any(is_bool_dtype(t) for t in types)
  if has_bools:
- has_ints = any(is_integer_dtype(t) for t in types)
- has_floats = any(is_float_dtype(t) for t in types)
- has_complex = any(is_complex_dtype(t) for t in types)
- if has_ints or has_floats or has_complex:
- return np.object
+ for t in types:
+ if is_integer_dtype(t) or is_float_dtype(t) or is_complex_dtype(t):
+ return np.object
 
  return np.find_common_type(types, [])
 

pandas/core/dtypes/concat.py

@@ -123,8 +123,6 @@ def is_nonempty(x):
  except Exception:
  return True
 
- nonempty = [x for x in to_concat if is_nonempty(x)]
-
  # If all arrays are empty, there's nothing to convert, just short-cut to
  # the concatenation, #3121.
  #
@@ -148,11 +146,11 @@ def is_nonempty(x):
  elif 'sparse' in typs:
  return _concat_sparse(to_concat, axis=axis, typs=typs)
 
- extensions = [is_extension_array_dtype(x) for x in to_concat]
- if any(extensions) and axis == 1:
+ all_empty = all(not is_nonempty(x) for x in to_concat)
+ if any(is_extension_array_dtype(x) for x in to_concat) and axis == 1:
  to_concat = [np.atleast_2d(x.astype('object')) for x in to_concat]
 
- if not nonempty:
+ if all_empty:
  # we have all empties, but may need to coerce the result dtype to
  # object if we have non-numeric type operands (numpy would otherwise
  # cast this to float)

pandas/core/dtypes/dtypes.py

@@ -414,8 +414,7 @@ def _hash_categories(categories, ordered=True):
  cat_array = hash_tuples(categories)
  else:
  if categories.dtype == 'O':
- types = [type(x) for x in categories]
- if not len(set(types)) == 1:
+ if len({type(x) for x in categories}) != 1:
  # TODO: hash_array doesn't handle mixed types. It casts
  # everything to a str first, which means we treat
  # {'1', '2'} the same as {'1', 2}

pandas/core/frame.py

@@ -1535,8 +1535,8 @@ def from_records(cls, data, index=None, exclude=None, columns=None,
  result_index = Index([], name=index)
  else:
  try:
- to_remove = [arr_columns.get_loc(field) for field in index]
- index_data = [arrays[i] for i in to_remove]
+ index_data = [arrays[arr_columns.get_loc(field)]
+  for field in index]
  result_index = ensure_index_from_sequences(index_data,
  names=index)