Merge branch 'main' into issue15675

snitish · web-flow · commit bad439a60565 · 2025-01-21T17:58:26.000-08:00
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -22,10 +22,11 @@ defaults:
 
 jobs:
   ubuntu:
-    runs-on: ubuntu-22.04
+    runs-on: ${{ matrix.platform }}
     timeout-minutes: 90
     strategy:
       matrix:
+        platform: [ubuntu-22.04, ubuntu-24.04-arm]
         env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
@@ -35,9 +36,11 @@ jobs:
             env_file: actions-311-downstream_compat.yaml
             pattern: "not slow and not network and not single_cpu"
             pytest_target: "pandas/tests/test_downstream.py"
+            platform: ubuntu-22.04
           - name: "Minimum Versions"
             env_file: actions-310-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
+            platform: ubuntu-22.04
           - name: "Locale: it_IT"
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -48,6 +51,7 @@ jobs:
             # Also install it_IT (its encoding is ISO8859-1) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "it_IT"
+            platform: ubuntu-22.04
           - name: "Locale: zh_CN"
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -58,25 +62,31 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
+            platform: ubuntu-22.04
           - name: "Future infer strings"
             env_file: actions-312.yaml
             pandas_future_infer_string: "1"
+            platform: ubuntu-22.04
           - name: "Future infer strings (without pyarrow)"
             env_file: actions-311.yaml
             pandas_future_infer_string: "1"
+            platform: ubuntu-22.04
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
+            platform: ubuntu-22.04
           - name: "Numpy Dev"
             env_file: actions-311-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "-W error::DeprecationWarning -W error::FutureWarning"
+            platform: ubuntu-22.04
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"
+            platform: ubuntu-22.04
       fail-fast: false
-    name: ${{ matrix.name || format('ubuntu-latest {0}', matrix.env_file) }}
+    name: ${{ matrix.name || format('{0} {1}', matrix.platform, matrix.env_file) }}
     env:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
@@ -91,7 +101,7 @@ jobs:
       REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}-${{ matrix.platform }}
       cancel-in-progress: true
 
     services:
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -94,6 +94,7 @@ jobs:
         buildplat:
         - [ubuntu-22.04, manylinux_x86_64]
         - [ubuntu-22.04, musllinux_x86_64]
+        - [ubuntu-24.04-arm, manylinux_aarch64]
         - [macos-13, macosx_x86_64]
         # Note: M1 images on Github Actions start from macOS 14
         - [macos-14, macosx_arm64]
diff --git a/pandas/_libs/groupby.pyx b/pandas/_libs/groupby.pyx
@@ -712,7 +712,7 @@ def group_sum(
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
         bint uses_mask = mask is not None
-        bint isna_entry
+        bint isna_entry, isna_result
 
     if len_values != len_labels:
         raise ValueError("len(index) != len(labels)")
@@ -744,20 +744,18 @@ def group_sum(
             for j in range(K):
                 val = values[i, j]
 
-                if not skipna and (
-                    (uses_mask and result_mask[lab, j]) or
-                    (is_datetimelike and sumx[lab, j] == NPY_NAT) or
-                    _treat_as_na(sumx[lab, j], False)
-                ):
-                    # 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 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 isna_entry:
                     nobs[lab, j] += 1
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -6890,7 +6890,8 @@ def sort_values(
             builtin :meth:`sorted` function, with the notable difference that
             this `key` function should be *vectorized*. It should expect a
             ``Series`` and return a Series with the same shape as the input.
-            It will be applied to each column in `by` independently.
+            It will be applied to each column in `by` independently. The values in the
+            returned Series will be used as the keys for sorting.
 
         Returns
         -------
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -4884,7 +4884,8 @@ def sort_values(
             builtin :meth:`sorted` function, with the notable difference that
             this `key` function should be *vectorized*. It should expect a
             ``Series`` and return a Series with the same shape as the input.
-            It will be applied to each column in `by` independently.
+            It will be applied to each column in `by` independently. The values in the
+            returned Series will be used as the keys for sorting.
 
         Returns
         -------
