Skip to content

PERF: Fix groupby skipna performance #60871

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 10, 2025
Merged

PERF: Fix groupby skipna performance #60871

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
97 changes: 63 additions & 34 deletions pandas/_libs/groupby.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -753,16 +753,20 @@ def group_sum(

if uses_mask:
isna_entry = mask[i, j]
isna_result = result_mask[lab, j]
else:
isna_entry = _treat_as_na(val, is_datetimelike)
isna_result = _treat_as_na(sumx[lab, j], is_datetimelike)

if not skipna and isna_result:
# If sum is already NA, don't add to it. This is important for
# datetimelikebecause adding a value to NPY_NAT may not result
# in a NPY_NAT
continue
if not skipna:
if uses_mask:
isna_result = result_mask[lab, j]
else:
isna_result = _treat_as_na(sumx[lab, j], is_datetimelike)

if isna_result:
# If sum is already NA, don't add to it. This is important for
# datetimelikebecause adding a value to NPY_NAT may not result
# in a NPY_NAT
continue

if not isna_entry:
nobs[lab, j] += 1
Expand Down Expand Up @@ -845,14 +849,18 @@ def group_prod(

if uses_mask:
isna_entry = mask[i, j]
isna_result = result_mask[lab, j]
else:
isna_entry = _treat_as_na(val, False)
isna_result = _treat_as_na(prodx[lab, j], False)

if not skipna and isna_result:
# If prod is already NA, no need to update it
continue
if not skipna:
if uses_mask:
isna_result = result_mask[lab, j]
else:
isna_result = _treat_as_na(prodx[lab, j], False)

if isna_result:
# If prod is already NA, no need to update it
continue

if not isna_entry:
nobs[lab, j] += 1
Expand Down Expand Up @@ -919,22 +927,30 @@ def group_var(

if uses_mask:
isna_entry = mask[i, j]
isna_result = result_mask[lab, j]
elif is_datetimelike:
# With group_var, we cannot just use _treat_as_na bc
# datetimelike dtypes get cast to float64 instead of
# to int64.
isna_entry = val == NPY_NAT
isna_result = out[lab, j] == NPY_NAT
else:
isna_entry = _treat_as_na(val, is_datetimelike)
isna_result = _treat_as_na(out[lab, j], is_datetimelike)

if not skipna and isna_result:
# If aggregate is already NA, don't add to it. This is important for
# datetimelike because adding a value to NPY_NAT may not result
# in a NPY_NAT
continue
if not skipna:
if uses_mask:
isna_result = result_mask[lab, j]
elif is_datetimelike:
# With group_var, we cannot just use _treat_as_na bc
# datetimelike dtypes get cast to float64 instead of
# to int64.
isna_result = out[lab, j] == NPY_NAT
else:
isna_result = _treat_as_na(out[lab, j], is_datetimelike)

if isna_result:
# If aggregate is already NA, don't add to it. This is
# important for datetimelike because adding a value to NPY_NAT
# may not result in a NPY_NAT
continue

if not isna_entry:
nobs[lab, j] += 1
Expand Down Expand Up @@ -1232,22 +1248,30 @@ def group_mean(

if uses_mask:
isna_entry = mask[i, j]
isna_result = result_mask[lab, j]
elif is_datetimelike:
# With group_mean, we cannot just use _treat_as_na bc
# datetimelike dtypes get cast to float64 instead of
# to int64.
isna_entry = val == NPY_NAT
isna_result = sumx[lab, j] == NPY_NAT
else:
isna_entry = _treat_as_na(val, is_datetimelike)
isna_result = _treat_as_na(sumx[lab, j], is_datetimelike)

if not skipna and isna_result:
# If sum is already NA, don't add to it. This is important for
# datetimelike because adding a value to NPY_NAT may not result
# in NPY_NAT
continue
if not skipna:
if uses_mask:
isna_result = result_mask[lab, j]
elif is_datetimelike:
# With group_mean, we cannot just use _treat_as_na bc
# datetimelike dtypes get cast to float64 instead of
# to int64.
isna_result = sumx[lab, j] == NPY_NAT
else:
isna_result = _treat_as_na(sumx[lab, j], is_datetimelike)

if isna_result:
# If sum is already NA, don't add to it. This is important for
# datetimelike because adding a value to NPY_NAT may not result
# in NPY_NAT
continue

if not isna_entry:
nobs[lab, j] += 1
Expand Down Expand Up @@ -1909,15 +1933,20 @@ cdef group_min_max(

if uses_mask:
isna_entry = mask[i, j]
isna_result = result_mask[lab, j]
else:
isna_entry = _treat_as_na(val, is_datetimelike)
isna_result = _treat_as_na(group_min_or_max[lab, j],
is_datetimelike)

if not skipna and isna_result:
# If current min/max is already NA, it will always be NA
continue
if not skipna:
if uses_mask:
isna_result = result_mask[lab, j]
else:
isna_result = _treat_as_na(
group_min_or_max[lab, j], is_datetimelike
)

if isna_result:
# If current min/max is already NA, it will always be NA
continue

if not isna_entry:
nobs[lab, j] += 1
Expand Down
2 changes: 1 addition & 1 deletion pandas/core/_numba/kernels/min_max_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ def grouped_min_max(
for i in range(N):
lab = labels[i]
val = values[i]
if lab < 0 or (nobs[lab] >= 1 and np.isnan(output[lab])):
if lab < 0 or (not skipna and nobs[lab] >= 1 and np.isnan(output[lab])):
continue

if values.dtype.kind == "i" or not np.isnan(val):
Expand Down
Loading