CLN: Rename "add" to "sum" in groupby (#47892)

* CLN: Rename "add" to "sum" * revert

Author: rhshadrach

pandas/_libs/groupby.pyi

@@ -50,7 +50,7 @@ def group_any_all(
  val_test: Literal["any", "all"],
  skipna: bool,
 ) -> None: ...
-def group_add(
+def group_sum(
  out: np.ndarray, # complexfloating_t[:, ::1]
  counts: np.ndarray, # int64_t[::1]
  values: np.ndarray, # ndarray[complexfloating_t, ndim=2]

pandas/_libs/groupby.pyx

@@ -124,7 +124,7 @@ def group_median_float64(
  ndarray[intp_t] indexer
  float64_t* ptr
 
- assert min_count == -1, "'min_count' only used in add and prod"
+ assert min_count == -1, "'min_count' only used in sum and prod"
 
  ngroups = len(counts)
  N, K = (<object>values).shape
@@ -502,7 +502,7 @@ def group_any_all(
 
 
 # ----------------------------------------------------------------------
-# group_add, group_prod, group_var, group_mean, group_ohlc
+# group_sum, group_prod, group_var, group_mean, group_ohlc
 # ----------------------------------------------------------------------
 
 ctypedef fused mean_t:
@@ -511,17 +511,17 @@ ctypedef fused mean_t:
  complex64_t
  complex128_t
 
-ctypedef fused add_t:
+ctypedef fused sum_t:
  mean_t
  object
 
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def group_add(
- add_t[:, ::1] out,
+def group_sum(
+ sum_t[:, ::1] out,
  int64_t[::1] counts,
- ndarray[add_t, ndim=2] values,
+ ndarray[sum_t, ndim=2] values,
  const intp_t[::1] labels,
  Py_ssize_t min_count=0,
  bint is_datetimelike=False,
@@ -531,8 +531,8 @@ def group_add(
  """
  cdef:
  Py_ssize_t i, j, N, K, lab, ncounts = len(counts)
- add_t val, t, y
- add_t[:, ::1] sumx, compensation
+ sum_t val, t, y
+ sum_t[:, ::1] sumx, compensation
  int64_t[:, ::1] nobs
  Py_ssize_t len_values = len(values), len_labels = len(labels)
 
@@ -546,7 +546,7 @@ def group_add(
 
  N, K = (<object>values).shape
 
- if add_t is object:
+ if sum_t is object:
  # NB: this does not use 'compensation' like the non-object track does.
  for i in range(N):
  lab = labels[i]
@@ -588,10 +588,10 @@ def group_add(
 
  # not nan
  # With dt64/td64 values, values have been cast to float64
- # instead if int64 for group_add, but the logic
+ # instead if int64 for group_sum, but the logic
  # is otherwise the same as in _treat_as_na
  if val == val and not (
- add_t is float64_t
+ sum_t is float64_t
  and is_datetimelike
  and val == <float64_t>NPY_NAT
  ):
@@ -677,7 +677,7 @@ def group_var(
  int64_t[:, ::1] nobs
  Py_ssize_t len_values = len(values), len_labels = len(labels)
 
- assert min_count == -1, "'min_count' only used in add and prod"
+ assert min_count == -1, "'min_count' only used in sum and prod"
 
  if len_values != len_labels:
  raise ValueError("len(index) != len(labels)")
@@ -745,7 +745,7 @@ def group_mean(
  Array containing unique label for each group, with its
  ordering matching up to the corresponding record in `values`.
  min_count : Py_ssize_t
- Only used in add and prod. Always -1.
+ Only used in sum and prod. Always -1.
  is_datetimelike : bool
  True if `values` contains datetime-like entries.
  mask : ndarray[bool, ndim=2], optional
@@ -766,7 +766,7 @@ def group_mean(
  int64_t[:, ::1] nobs
  Py_ssize_t len_values = len(values), len_labels = len(labels)
 
- assert min_count == -1, "'min_count' only used in add and prod"
+ assert min_count == -1, "'min_count' only used in sum and prod"
 
  if len_values != len_labels:
  raise ValueError("len(index) != len(labels)")
@@ -821,7 +821,7 @@ def group_ohlc(
  Py_ssize_t i, j, N, K, lab
  floating val
 
- assert min_count == -1, "'min_count' only used in add and prod"
+ assert min_count == -1, "'min_count' only used in sum and prod"
 
  if len(labels) == 0:
  return

pandas/core/groupby/groupby.py

@@ -1338,7 +1338,6 @@ def _resolve_numeric_only(
 
  if numeric_only and self.obj.ndim == 1 and not is_numeric_dtype(self.obj.dtype):
  # GH#47500
- how = "sum" if how == "add" else how
  warnings.warn(
  f"{type(self).__name__}.{how} called with "
  f"numeric_only={numeric_only} and dtype {self.obj.dtype}. This will "
@@ -1738,9 +1737,8 @@ def _cython_agg_general(
  kwd_name = "numeric_only"
  if how in ["any", "all"]:
  kwd_name = "bool_only"
- kernel = "sum" if how == "add" else how
  raise NotImplementedError(
- f"{type(self).__name__}.{kernel} does not implement {kwd_name}."
+ f"{type(self).__name__}.{how} does not implement {kwd_name}."
  )
  elif not is_ser:
  data = data.get_numeric_data(copy=False)
@@ -2417,7 +2415,7 @@ def sum(
  result = self._agg_general(
  numeric_only=numeric_only,
  min_count=min_count,
- alias="add",
+ alias="sum",
  npfunc=np.sum,
  )
 
@@ -4341,8 +4339,6 @@ def _insert_quantile_level(idx: Index, qs: npt.NDArray[np.float64]) -> MultiInde
 
 
 def warn_dropping_nuisance_columns_deprecated(cls, how: str, numeric_only) -> None:
- if how == "add":
- how = "sum"
  if numeric_only is not lib.no_default and not numeric_only:
  # numeric_only was specified and falsey but still dropped nuisance columns
  warnings.warn(

pandas/core/groupby/ops.py

@@ -121,7 +121,7 @@ def __init__(self, kind: str, how: str, has_dropped_na: bool) -> None:
 
  _CYTHON_FUNCTIONS = {
  "aggregate": {
- "add": "group_add",
+ "sum": "group_sum",
  "prod": "group_prod",
  "min": "group_min",
  "max": "group_max",
@@ -213,7 +213,7 @@ def _get_cython_vals(self, values: np.ndarray) -> np.ndarray:
  values = ensure_float64(values)
 
  elif values.dtype.kind in ["i", "u"]:
- if how in ["add", "var", "prod", "mean", "ohlc"] or (
+ if how in ["sum", "var", "prod", "mean", "ohlc"] or (
  self.kind == "transform" and self.has_dropped_na
  ):
  # result may still include NaN, so we have to cast
@@ -241,7 +241,7 @@ def _disallow_invalid_ops(self, dtype: DtypeObj, is_numeric: bool = False):
  if isinstance(dtype, CategoricalDtype):
  # NotImplementedError for methods that can fall back to a
  # non-cython implementation.
- if how in ["add", "prod", "cumsum", "cumprod"]:
+ if how in ["sum", "prod", "cumsum", "cumprod"]:
  raise TypeError(f"{dtype} type does not support {how} operations")
  elif how not in ["rank"]:
  # only "rank" is implemented in cython
@@ -258,7 +258,7 @@ def _disallow_invalid_ops(self, dtype: DtypeObj, is_numeric: bool = False):
  # TODO: same for period_dtype? no for these methods with Period
  # we raise NotImplemented if this is an invalid operation
  # entirely, e.g. adding datetimes
- if how in ["add", "prod", "cumsum", "cumprod"]:
+ if how in ["sum", "prod", "cumsum", "cumprod"]:
  raise TypeError(f"datetime64 type does not support {how} operations")
  elif is_timedelta64_dtype(dtype):
  if how in ["prod", "cumprod"]:
@@ -311,7 +311,7 @@ def _get_result_dtype(self, dtype: np.dtype) -> np.dtype:
  """
  how = self.how
 
- if how in ["add", "cumsum", "sum", "prod"]:
+ if how in ["sum", "cumsum", "sum", "prod"]:
  if dtype == np.dtype(bool):
  return np.dtype(np.int64)
  elif how in ["mean", "median", "var"]:
@@ -567,7 +567,7 @@ def _call_cython_op(
  result_mask=result_mask,
  is_datetimelike=is_datetimelike,
  )
- elif self.how in ["add"]:
+ elif self.how in ["sum"]:
  # We support datetimelike
  func(
  out=result,
@@ -625,7 +625,7 @@ def _call_cython_op(
  # e.g. if we are int64 and need to restore to datetime64/timedelta64
  # "rank" is the only member of cast_blocklist we get here
  # Casting only needed for float16, bool, datetimelike,
- # and self.how in ["add", "prod", "ohlc", "cumprod"]
+ # and self.how in ["sum", "prod", "ohlc", "cumprod"]
  res_dtype = self._get_result_dtype(orig_values.dtype)
  op_result = maybe_downcast_to_dtype(result, res_dtype)
  else:

pandas/tests/groupby/aggregate/test_cython.py

@@ -166,7 +166,7 @@ def test_cython_fail_agg():
  ("mean", np.mean),
  ("median", np.median),
  ("var", np.var),
- ("add", np.sum),
+ ("sum", np.sum),
  ("prod", np.prod),
  ("min", np.min),
  ("max", np.max),
@@ -214,7 +214,7 @@ def test_cython_agg_empty_buckets_nanops(observed):
  grps = range(0, 25, 5)
  # add / sum
  result = df.groupby(pd.cut(df["a"], grps), observed=observed)._cython_agg_general(
- "add", alt=None, numeric_only=True
+ "sum", alt=None, numeric_only=True
  )
  intervals = pd.interval_range(0, 20, freq=5, inclusive="right")
  expected = DataFrame(

pandas/tests/resample/test_datetime_index.py

@@ -61,15 +61,15 @@ def test_custom_grouper(index):
 
  # check all cython functions work
  g.ohlc() # doesn't use _cython_agg_general
- funcs = ["add", "mean", "prod", "min", "max", "var"]
+ funcs = ["sum", "mean", "prod", "min", "max", "var"]
  for f in funcs:
  g._cython_agg_general(f, alt=None, numeric_only=True)
 
  b = Grouper(freq=Minute(5), closed="right", label="right")
  g = s.groupby(b)
  # check all cython functions work
  g.ohlc() # doesn't use _cython_agg_general
- funcs = ["add", "mean", "prod", "min", "max", "var"]
+ funcs = ["sum", "mean", "prod", "min", "max", "var"]
  for f in funcs:
  g._cython_agg_general(f, alt=None, numeric_only=True)
 
@@ -414,7 +414,7 @@ def test_resample_upsampling_picked_but_not_correct():
  tm.assert_series_equal(result2, expected)
 
 
-@pytest.mark.parametrize("f", ["add", "mean", "prod", "min", "max", "var"])
+@pytest.mark.parametrize("f", ["sum", "mean", "prod", "min", "max", "var"])
 def test_resample_frame_basic_cy_funcs(f):
  df = tm.makeTimeDataFrame()