Merge remote-tracking branch 'upstream/main' into 240323_57972_kurtosis_low_value_cutoff

Author: dontgoto

.github/actions/run-tests/action.yml

@@ -1,16 +1,9 @@
 name: Run tests and report results
-inputs:
-  preload:
-    description: Preload arguments for sanitizer
-    required: false
-  asan_options:
-    description: Arguments for Address Sanitizer (ASAN)
-    required: false
 runs:
   using: composite
   steps:
     - name: Test
-      run: ${{ inputs.asan_options }} ${{ inputs.preload }} ci/run_tests.sh
+      run: ci/run_tests.sh
       shell: bash -el {0}
 
     - name: Publish test results

.github/workflows/unit-tests.yml

@@ -68,14 +68,6 @@ jobs:
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"
-          - name: "ASAN / UBSAN"
-            env_file: actions-311-sanitizers.yaml
-            pattern: "not slow and not network and not single_cpu and not skip_ubsan"
-            asan_options: "ASAN_OPTIONS=detect_leaks=0"
-            preload: LD_PRELOAD=$(gcc -print-file-name=libasan.so)
-            meson_args: --config-settings=setup-args="-Db_sanitize=address,undefined"
-            cflags_adds: -fno-sanitize-recover=all
-            pytest_workers: -1  # disable pytest-xdist as it swallows stderr from ASAN
       fail-fast: false
     name: ${{ matrix.name || format('ubuntu-latest {0}', matrix.env_file) }}
     env:
@@ -161,18 +153,12 @@ jobs:
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
       if: ${{ matrix.name != 'Pypy' }}
-      with:
-        preload: ${{ matrix.preload }}
-        asan_options: ${{ matrix.asan_options }}
       env:
         # Set pattern to not single_cpu if not already set
         PATTERN: ${{ env.PATTERN == '' && 'not single_cpu' || matrix.pattern }}
 
     - name: Test (single_cpu)
       uses: ./.github/actions/run-tests
-      with:
-        preload: ${{ matrix.preload }}
-        asan_options: ${{ matrix.asan_options }}
       env:
         PATTERN: 'single_cpu'
         PYTEST_WORKERS: 0

.github/workflows/wheels.yml

@@ -141,7 +141,7 @@ jobs:
 
       - name: Build normal wheels
         if: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
-        uses: pypa/cibuildwheel@v2.16.5
+        uses: pypa/cibuildwheel@v2.17.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
@@ -150,7 +150,7 @@ jobs:
 
       - name: Build nightly wheels (with NumPy pre-release)
         if: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/cibuildwheel@v2.16.5
+        uses: pypa/cibuildwheel@v2.17.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.pre-commit-config.yaml

@@ -78,7 +78,7 @@ repos:
     hooks:
     -   id: pylint
         stages: [manual]
-        args: [--load-plugins=pylint.extensions.redefined_loop_name]
+        args: [--load-plugins=pylint.extensions.redefined_loop_name, --fail-on=I0021]
     -   id: pylint
         alias: redefined-outer-name
         name: Redefining name from outer scope

Dockerfile

@@ -9,6 +9,7 @@ RUN apt-get install -y build-essential
 RUN apt-get install -y libhdf5-dev libgles2-mesa-dev
 
 RUN python -m pip install --upgrade pip
-RUN python -m pip install \
-    -r https://raw.githubusercontent.com/pandas-dev/pandas/main/requirements-dev.txt
+COPY requirements-dev.txt /tmp
+RUN python -m pip install -r /tmp/requirements-dev.txt
+RUN git config --global --add safe.directory /home/pandas
 CMD ["/bin/bash"]

asv_bench/benchmarks/categoricals.py

@@ -88,7 +88,7 @@ def setup(self):
         )
 
         for col in ("int", "float", "timestamp"):
-            self.df[col + "_as_str"] = self.df[col].astype(str)
+            self.df[f"{col}_as_str"] = self.df[col].astype(str)
 
         for col in self.df.columns:
             self.df[col] = self.df[col].astype("category")

asv_bench/benchmarks/join_merge.py

@@ -328,6 +328,23 @@ def time_i8merge(self, how):
         merge(self.left, self.right, how=how)
 
 
+class UniqueMerge:
+    params = [4_000_000, 1_000_000]
+    param_names = ["unique_elements"]
+
+    def setup(self, unique_elements):
+        N = 1_000_000
+        self.left = DataFrame({"a": np.random.randint(1, unique_elements, (N,))})
+        self.right = DataFrame({"a": np.random.randint(1, unique_elements, (N,))})
+        uniques = self.right.a.drop_duplicates()
+        self.right["a"] = concat(
+            [uniques, Series(np.arange(0, -(N - len(uniques)), -1))], ignore_index=True
+        )
+
+    def time_unique_merge(self, unique_elements):
+        merge(self.left, self.right, how="inner")
+
+
 class MergeDatetime:
     params = [
         [

asv_bench/benchmarks/timeseries.py

@@ -183,7 +183,7 @@ def setup(self):
         self.dt_ts = Series(5, rng3, dtype="datetime64[ns]")
 
     def time_resample(self):
-        self.dt_ts.resample("1S").last()
+        self.dt_ts.resample("1s").last()
 
 
 class AsOf: