Merge remote-tracking branch 'upstream/main' into bisect

Author: simonjayhawkins

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,4 @@
-- [ ] closes #xxxx
-- [ ] tests added / passed
-- [ ] Ensure all linting tests pass, see [here](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#pre-commit) for how to run them
-- [ ] whatsnew entry
+- [ ] closes #xxxx (Replace xxxx with the Github issue number)
+- [ ] [Tests added and passed](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#writing-tests) if fixing a bug or adding a new feature
+- [ ] All [code checks passed](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#pre-commit).
+- [ ] Added an entry in the latest `doc/source/whatsnew/vX.X.X.rst` file if fixing a bug or adding a new feature.

.github/workflows/assign.yml

@@ -4,11 +4,10 @@ on:
     types: created
 
 jobs:
-  one:
+  issue_assign:
     runs-on: ubuntu-latest
     steps:
     - if: github.event.comment.body == 'take'
-      name:
       run: |
         echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"
         curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"assignees": ["${{ github.event.comment.user.login }}"]}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/assignees

.github/workflows/code-checks.yml

@@ -74,7 +74,7 @@ jobs:
 
     - name: Install pyright
       # note: keep version in sync with .pre-commit-config.yaml
-      run: npm install -g [email protected].202
+      run: npm install -g [email protected].212
 
     - name: Build Pandas
       id: build

.github/workflows/datamanger.yml

@@ -9,6 +9,8 @@ on:
     branches:
       - main
       - 1.4.x
+    paths-ignore:
+      - "doc/**"
 
 env:
   ENV_FILE: environment.yml
@@ -26,12 +28,9 @@ jobs:
           AWS_SECRET_ACCESS_KEY: foobar_secret
         ports:
           - 5000:5000
-    strategy:
-      matrix:
-        pattern: ["not slow and not network and not clipboard", "slow"]
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-data_manager-${{ matrix.pattern }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-data_manager
       cancel-in-progress: true
 
     steps:
@@ -46,12 +45,9 @@ jobs:
     - name: Run tests
       env:
         PANDAS_DATA_MANAGER: array
-        PATTERN: ${{ matrix.pattern }}
+        PATTERN: "not network and not clipboard"
         PYTEST_WORKERS: "auto"
         PYTEST_TARGET: pandas
       run: |
         source activate pandas-dev
         ci/run_tests.sh
-
-    - name: Print skipped tests
-      run: python ci/print_skipped.py

.github/workflows/docbuild-and-upload.yml

@@ -40,12 +40,7 @@ jobs:
     - name: Build documentation
       run: |
         source activate pandas-dev
-        doc/make.py --warnings-are-errors | tee sphinx.log ; exit ${PIPESTATUS[0]}
-
-    # This can be removed when the ipython directive fails when there are errors,
-    # including the `tee sphinx.log` in te previous step (https://github.com/ipython/ipython/issues/11547)
-    - name: Check ipython directive errors
-      run: "! grep -B10 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
+        doc/make.py --warnings-are-errors
 
     - name: Install ssh key
       run: |

.github/workflows/posix.yml

@@ -26,18 +26,14 @@ jobs:
       matrix:
         settings: [
           [actions-38-downstream_compat.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
-          [actions-38-minimum_versions.yaml, "slow", "", "", "", "", ""],
-          [actions-38-minimum_versions.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
+          [actions-38-minimum_versions.yaml, "not clipboard", "", "", "", "", ""],
           [actions-38.yaml, "not slow and not network", "language-pack-it xsel", "it_IT.utf8", "it_IT.utf8", "", ""],
           [actions-38.yaml, "not slow and not network", "language-pack-zh-hans xsel", "zh_CN.utf8", "zh_CN.utf8", "", ""],
-          [actions-38.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-38.yaml, "slow", "", "", "", "", ""],
+          [actions-38.yaml, "not clipboard", "", "", "", "", ""],
           [actions-pypy-38.yaml, "not slow and not clipboard", "", "", "", "", "--max-worker-restart 0"],
-          [actions-39.yaml, "slow", "", "", "", "", ""],
-          [actions-39.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-310-numpydev.yaml, "not slow and not network", "xclip", "", "", "deprecate", "-W error"],
-          [actions-310.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-310.yaml, "slow", "", "", "", "", ""],
+          [actions-39.yaml, "not clipboard", "", "", "", "", ""],
+          [actions-310-numpydev.yaml, "not slow and not network", "xsel", "", "", "deprecate", "-W error"],
+          [actions-310.yaml, "not clipboard", "", "", "", "", ""],
         ]
       fail-fast: false
     env:
@@ -54,7 +50,7 @@ jobs:
       COVERAGE: ${{ !contains(matrix.settings[0], 'pypy') }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.settings[0] }}-${{ matrix.settings[1] }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.settings[0] }}-${{ matrix.settings[1] }}-${{ matrix.settings[2] }}
       cancel-in-progress: true
 
     services:
@@ -154,9 +150,6 @@ jobs:
         path: test-data.xml
       if: failure()
 
-    - name: Print skipped tests
-      run: python ci/print_skipped.py
-
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v2
       with:

.github/workflows/python-dev.yml

@@ -85,10 +85,6 @@ jobs:
         path: test-data.xml
       if: failure()
 
-    - name: Print skipped tests
-      run: |
-        python ci/print_skipped.py
-
     - name: Report Coverage
       run: |
         coverage report -m

.pre-commit-config.yaml

@@ -4,7 +4,7 @@ ci:
     autofix_prs: false
 repos:
 -   repo: https://github.com/MarcoGorelli/absolufy-imports
-    rev: v0.3.0
+    rev: v0.3.1
     hooks:
     -   id: absolufy-imports
         files: ^pandas/
@@ -16,7 +16,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/python/black
-    rev: 21.12b0
+    rev: 22.1.0
     hooks:
     -   id: black
 -   repo: https://github.com/codespell-project/codespell
@@ -50,7 +50,7 @@ repos:
         - flake8==4.0.1
         - flake8-comprehensions==3.7.0
         - flake8-bugbear==21.3.2
-        - pandas-dev-flaker==0.2.0
+        - pandas-dev-flaker==0.4.0
 -   repo: https://github.com/PyCQA/isort
     rev: 5.10.1
     hooks:
@@ -84,8 +84,8 @@ repos:
         pass_filenames: false
         types: [python]
         stages: [manual]
-        # note: keep version in sync with .github/workflows/ci.yml
-        additional_dependencies: ['[email protected].202']
+        # note: keep version in sync with .github/workflows/code-checks.yml
+        additional_dependencies: ['[email protected].212']
 -   repo: local
     hooks:
     -   id: flake8-rst

asv_bench/benchmarks/algorithms.py

@@ -34,7 +34,7 @@ class Factorize:
     param_names = ["unique", "sort", "dtype"]
 
     def setup(self, unique, sort, dtype):
-        N = 10 ** 5
+        N = 10**5
         string_index = tm.makeStringIndex(N)
         string_arrow = None
         if dtype == "string[pyarrow]":
@@ -74,7 +74,7 @@ class Duplicated:
     param_names = ["unique", "keep", "dtype"]
 
     def setup(self, unique, keep, dtype):
-        N = 10 ** 5
+        N = 10**5
         data = {
             "int": pd.Index(np.arange(N), dtype="int64"),
             "uint": pd.Index(np.arange(N), dtype="uint64"),
@@ -97,7 +97,7 @@ def time_duplicated(self, unique, keep, dtype):
 
 class Hashing:
     def setup_cache(self):
-        N = 10 ** 5
+        N = 10**5
 
         df = pd.DataFrame(
             {
@@ -145,7 +145,7 @@ class Quantile:
     param_names = ["quantile", "interpolation", "dtype"]
 
     def setup(self, quantile, interpolation, dtype):
-        N = 10 ** 5
+        N = 10**5
         data = {
             "int": np.arange(N),
             "uint": np.arange(N).astype(np.uint64),
@@ -158,7 +158,7 @@ def time_quantile(self, quantile, interpolation, dtype):
 
 
 class SortIntegerArray:
-    params = [10 ** 3, 10 ** 5]
+    params = [10**3, 10**5]
 
     def setup(self, N):
         data = np.arange(N, dtype=float)

asv_bench/benchmarks/algos/isin.py

@@ -49,7 +49,7 @@ def setup(self, dtype):
 
         elif dtype in ["category[object]", "category[int]"]:
             # Note: sizes are different in this case than others
-            n = 5 * 10 ** 5
+            n = 5 * 10**5
             sample_size = 100
 
             arr = list(np.random.randint(0, n // 10, size=n))
@@ -174,7 +174,7 @@ class IsinWithArange:
 
     def setup(self, dtype, M, offset_factor):
         offset = int(M * offset_factor)
-        tmp = Series(np.random.randint(offset, M + offset, 10 ** 6))
+        tmp = Series(np.random.randint(offset, M + offset, 10**6))
         self.series = tmp.astype(dtype)
         self.values = np.arange(M).astype(dtype)
 
@@ -191,8 +191,8 @@ class IsInFloat64:
     param_names = ["dtype", "title"]
 
     def setup(self, dtype, title):
-        N_many = 10 ** 5
-        N_few = 10 ** 6
+        N_many = 10**5
+        N_few = 10**6
         self.series = Series([1, 2], dtype=dtype)
 
         if title == "many_different_values":
@@ -240,10 +240,10 @@ class IsInForObjects:
     param_names = ["series_type", "vals_type"]
 
     def setup(self, series_type, vals_type):
-        N_many = 10 ** 5
+        N_many = 10**5
 
         if series_type == "nans":
-            ser_vals = np.full(10 ** 4, np.nan)
+            ser_vals = np.full(10**4, np.nan)
         elif series_type == "short":
             ser_vals = np.arange(2)
         elif series_type == "long":
@@ -254,7 +254,7 @@ def setup(self, series_type, vals_type):
         self.series = Series(ser_vals).astype(object)
 
         if vals_type == "nans":
-            values = np.full(10 ** 4, np.nan)
+            values = np.full(10**4, np.nan)
         elif vals_type == "short":
             values = np.arange(2)
         elif vals_type == "long":
@@ -277,7 +277,7 @@ class IsInLongSeriesLookUpDominates:
     param_names = ["dtype", "MaxNumber", "series_type"]
 
     def setup(self, dtype, MaxNumber, series_type):
-        N = 10 ** 7
+        N = 10**7
 
         if series_type == "random_hits":
             array = np.random.randint(0, MaxNumber, N)
@@ -304,15 +304,15 @@ class IsInLongSeriesValuesDominate:
     param_names = ["dtype", "series_type"]
 
     def setup(self, dtype, series_type):
-        N = 10 ** 7
+        N = 10**7
 
         if series_type == "random":
             vals = np.random.randint(0, 10 * N, N)
         if series_type == "monotone":
             vals = np.arange(N)
 
         self.values = vals.astype(dtype.lower())
-        M = 10 ** 6 + 1
+        M = 10**6 + 1
         self.series = Series(np.arange(M)).astype(dtype)
 
     def time_isin(self, dtypes, series_type):

asv_bench/benchmarks/arithmetic.py

@@ -59,7 +59,7 @@ def time_frame_op_with_scalar(self, dtype, scalar, op):
 class OpWithFillValue:
     def setup(self):
         # GH#31300
-        arr = np.arange(10 ** 6)
+        arr = np.arange(10**6)
         df = DataFrame({"A": arr})
         ser = df["A"]
 
@@ -93,7 +93,7 @@ class MixedFrameWithSeriesAxis:
     param_names = ["opname"]
 
     def setup(self, opname):
-        arr = np.arange(10 ** 6).reshape(1000, -1)
+        arr = np.arange(10**6).reshape(1000, -1)
         df = DataFrame(arr)
         df["C"] = 1.0
         self.df = df
@@ -201,7 +201,7 @@ def teardown(self, use_numexpr, threads):
 
 class Ops2:
     def setup(self):
-        N = 10 ** 3
+        N = 10**3
         self.df = DataFrame(np.random.randn(N, N))
         self.df2 = DataFrame(np.random.randn(N, N))
 
@@ -258,7 +258,7 @@ class Timeseries:
     param_names = ["tz"]
 
     def setup(self, tz):
-        N = 10 ** 6
+        N = 10**6
         halfway = (N // 2) - 1
         self.s = Series(date_range("20010101", periods=N, freq="T", tz=tz))
         self.ts = self.s[halfway]
@@ -280,7 +280,7 @@ def time_timestamp_ops_diff_with_shift(self, tz):
 
 class IrregularOps:
     def setup(self):
-        N = 10 ** 5
+        N = 10**5
         idx = date_range(start="1/1/2000", periods=N, freq="s")
         s = Series(np.random.randn(N), index=idx)
         self.left = s.sample(frac=1)
@@ -304,7 +304,7 @@ class CategoricalComparisons:
     param_names = ["op"]
 
     def setup(self, op):
-        N = 10 ** 5
+        N = 10**5
         self.cat = pd.Categorical(list("aabbcd") * N, ordered=True)
 
     def time_categorical_op(self, op):
@@ -317,7 +317,7 @@ class IndexArithmetic:
     param_names = ["dtype"]
 
     def setup(self, dtype):
-        N = 10 ** 6
+        N = 10**6
         indexes = {"int": "makeIntIndex", "float": "makeFloatIndex"}
         self.index = getattr(tm, indexes[dtype])(N)
 
@@ -343,7 +343,7 @@ class NumericInferOps:
     param_names = ["dtype"]
 
     def setup(self, dtype):
-        N = 5 * 10 ** 5
+        N = 5 * 10**5
         self.df = DataFrame(
             {"A": np.arange(N).astype(dtype), "B": np.arange(N).astype(dtype)}
         )
@@ -367,7 +367,7 @@ def time_modulo(self, dtype):
 class DateInferOps:
     # from GH 7332
     def setup_cache(self):
-        N = 5 * 10 ** 5
+        N = 5 * 10**5
         df = DataFrame({"datetime64": np.arange(N).astype("datetime64[ms]")})
         df["timedelta"] = df["datetime64"] - df["datetime64"]
         return df
@@ -388,7 +388,7 @@ class AddOverflowScalar:
     param_names = ["scalar"]
 
     def setup(self, scalar):
-        N = 10 ** 6
+        N = 10**6
         self.arr = np.arange(N)
 
     def time_add_overflow_scalar(self, scalar):
@@ -397,7 +397,7 @@ def time_add_overflow_scalar(self, scalar):
 
 class AddOverflowArray:
     def setup(self):
-        N = 10 ** 6
+        N = 10**6
         self.arr = np.arange(N)
         self.arr_rev = np.arange(-N, 0)
         self.arr_mixed = np.array([1, -1]).repeat(N / 2)