Merge branch 'main' into np-array-copy-keyword

Author: mtsokol

.github/workflows/comment-commands.yml

@@ -24,12 +24,10 @@ jobs:
     concurrency:
       group: ${{ github.actor }}-preview-docs
     steps:
-      - run: |
-          if curl --output /dev/null --silent --head --fail "https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"; then
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "Website preview of this PR available at: https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          else
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "No preview found for PR #${{ github.event.issue.number }}. Did the docs build complete?"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          fi
+      - uses: pandas-dev/github-doc-previewer@master
+        with:
+          previewer-server: "https://pandas.pydata.org/preview"
+          artifact-job: "Doc Build and Upload"
   asv_run:
     runs-on: ubuntu-22.04
     # TODO: Support more benchmarking options later, against different branches, against self, etc

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

@@ -90,10 +90,3 @@ jobs:
         name: website
         path: web/build
         retention-days: 14
-
-    - name: Trigger web/doc preview
-      run: curl -X POST https://pandas.pydata.org/preview/submit/$RUN_ID/$PR_ID/
-      env:
-        RUN_ID: ${{ github.run_id }}
-        PR_ID: ${{ github.event.pull_request.number }}
-      if: github.event_name == 'pull_request'

.github/workflows/unit-tests.yml

@@ -73,18 +73,6 @@ jobs:
             env_file: actions-312.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.11 (warnings)"
-            env_file: actions-311.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
-          - name: "Copy-on-Write 3.10 (warnings)"
-            env_file: actions-310.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
-          - name: "Copy-on-Write 3.9 (warnings)"
-            env_file: actions-39.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"

.pre-commit-config.yaml

@@ -101,8 +101,6 @@ repos:
 -   repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:
-      - id: python-check-blanket-noqa
-      - id: python-check-blanket-type-ignore
       - id: rst-backticks
       - id: rst-directive-colons
         types: [text]  # overwrite types: [rst]

asv_bench/asv.conf.json

@@ -41,7 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
-        "Cython": ["3.0.5"],
+        "Cython": ["3.0"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

asv_bench/benchmarks/algos/isin.py

@@ -59,7 +59,8 @@ def setup(self, dtype):
         elif dtype in ["str", "string[python]", "string[pyarrow]"]:
             try:
                 self.series = Series(
-                    Index([f"i-{i}" for i in range(N)], dtype=object), dtype=dtype
+                    Index([f"i-{i}" for i in range(N)], dtype=object)._values,
+                    dtype=dtype,
                 )
             except ImportError as err:
                 raise NotImplementedError from err

asv_bench/benchmarks/frame_methods.py

@@ -593,8 +593,6 @@ def setup(self):
         N = 10000
         # this is the worst case, where every column has NaNs.
         arr = np.random.randn(N, 100)
-        # NB: we need to set values in array, not in df.values, otherwise
-        #  the benchmark will be misleading for ArrayManager
         arr[::2] = np.nan
 
         self.df = DataFrame(arr)

asv_bench/benchmarks/strings.py

@@ -19,7 +19,8 @@ class Dtypes:
     def setup(self, dtype):
         try:
             self.s = Series(
-                Index([f"i-{i}" for i in range(10000)], dtype=object), dtype=dtype
+                Index([f"i-{i}" for i in range(10000)], dtype=object)._values,
+                dtype=dtype,
             )
         except ImportError as err:
             raise NotImplementedError from err

ci/code_checks.sh

@@ -93,7 +93,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.TimedeltaIndex.ceil\
         pandas.PeriodIndex\
         pandas.PeriodIndex.strftime\
-        pandas.Series.clip\
         pandas.Series.rename_axis\
         pandas.Series.dt.to_period\
         pandas.Series.dt.tz_localize\
@@ -115,7 +114,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Series.plot.barh\
         pandas.Series.plot.line\
         pandas.Series.plot.pie\
-        pandas.DataFrame.clip\
         pandas.DataFrame.plot\
         pandas.DataFrame.plot.bar\
         pandas.DataFrame.plot.barh\
@@ -181,10 +179,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.core.groupby.SeriesGroupBy.rolling\
         pandas.core.groupby.DataFrameGroupBy.hist\
         pandas.core.groupby.DataFrameGroupBy.plot\
+        pandas.core.groupby.DataFrameGroupBy.corrwith\
         pandas.core.groupby.SeriesGroupBy.plot\
         pandas.core.window.rolling.Rolling.quantile\
-        pandas.core.window.expanding.Expanding.quantile\
-        pandas.api.extensions.ExtensionArray.argsort # There should be no backslash in the final line, please keep this comment in the last ignored function
+        pandas.core.window.expanding.Expanding.quantile # There should be no backslash in the final line, please keep this comment in the last ignored function
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

doc/source/reference/arrays.rst

@@ -539,6 +539,21 @@ To create a Series of dtype ``category``, use ``cat = s.astype(dtype)`` or
 If the :class:`Series` is of dtype :class:`CategoricalDtype`, ``Series.cat`` can be used to change the categorical
 data. See :ref:`api.series.cat` for more.
 
+More methods are available on :class:`Categorical`:
+
+.. autosummary::
+   :toctree: api/
+
+   Categorical.as_ordered
+   Categorical.as_unordered
+   Categorical.set_categories
+   Categorical.rename_categories
+   Categorical.reorder_categories
+   Categorical.add_categories
+   Categorical.remove_categories
+   Categorical.remove_unused_categories
+   Categorical.map
+
 .. _api.arrays.sparse:
 
 Sparse