Merge remote-tracking branch 'upstream/main' into 49277_tmp

# Conflicts:
#	doc/source/whatsnew/v1.5.2.rst

Author: phofl

.github/workflows/32-bit-linux.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/code-checks.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
 
 env:
   ENV_FILE: environment.yml
@@ -88,7 +86,7 @@ jobs:
         echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Typing
+    - name: Typing + pylint
       uses: pre-commit/[email protected]
       with:
         extra_args: --hook-stage manual --all-files

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

@@ -5,14 +5,12 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
 
 env:
   ENV_FILE: environment.yml

.github/workflows/macos-windows.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/python-dev.yml

@@ -25,12 +25,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/sdist.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     types: [labeled, opened, synchronize, reopened]
     paths-ignore:
       - "doc/**"
@@ -30,7 +28,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{matrix.python-version}}-sdist
@@ -42,7 +40,7 @@ jobs:
         fetch-depth: 0
 
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -86,6 +84,8 @@ jobs:
           pip install numpy==1.20.3 ;;
         3.10)
           pip install numpy==1.21.2 ;;
+        3.11)
+          pip install numpy==1.23.2 ;;
         esac
 
     - name: Import pandas

.github/workflows/ubuntu.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/wheels.yml

@@ -72,14 +72,22 @@ jobs:
         env:
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 
-      # Used to test the built wheels
-      - uses: actions/setup-python@v4
+      # Used to test(Windows-only) and push the built wheels
+      # You might need to use setup-python separately
+      # if the new Python-dev version
+      # is unavailable on conda-forge.
+      - uses: conda-incubator/setup-miniconda@v2
         with:
+          auto-update-conda: true
           python-version: ${{ matrix.python[1] }}
+          activate-environment: test
+          channels: conda-forge, anaconda
+          channel-priority: true
+          mamba-version: "*"
 
       - name: Test wheels (Windows 64-bit only)
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
-        shell: cmd
+        shell: cmd /C CALL {0}
         run: |
           python ci/test_wheels.py wheelhouse
 
@@ -88,26 +96,15 @@ jobs:
           name: ${{ matrix.python[0] }}-${{ startsWith(matrix.buildplat[1], 'macosx') && 'macosx' || matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
 
-      # Used to push the built wheels
-      # TODO: once Python 3.11 is available on conda, de-dup with
-      # setup python above
-      - uses: conda-incubator/setup-miniconda@v2
-        with:
-          auto-update-conda: true
-          # Really doesn't matter what version we upload with
-          # just the version we test with
-          python-version: '3.8'
-          channels: conda-forge
-          channel-priority: true
-          mamba-version: "*"
 
       - name: Install anaconda client
         if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
+        shell: bash -el {0}
         run: conda install -q -y anaconda-client
 
 
       - name: Upload wheels
-        if: success()
+        if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
         shell: bash -el {0}
         env:
           PANDAS_STAGING_UPLOAD_TOKEN: ${{ secrets.PANDAS_STAGING_UPLOAD_TOKEN }}
@@ -180,11 +177,12 @@ jobs:
 
       - name: Install anaconda client
         if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
+        shell: bash -el {0}
         run: |
           conda install -q -y anaconda-client
 
       - name: Upload sdist
-        if: success()
+        if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
         shell: bash -el {0}
         env:
           PANDAS_STAGING_UPLOAD_TOKEN: ${{ secrets.PANDAS_STAGING_UPLOAD_TOKEN }}

.pre-commit-config.yaml

@@ -18,16 +18,16 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/python/black
-    rev: 22.8.0
+    rev: 22.10.0
     hooks:
     -   id: black
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.1
+    rev: v2.2.2
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.1.8
+    rev: v0.2.1
     hooks:
     -   id: cython-lint
 -   repo: https://github.com/pre-commit/pre-commit-hooks
@@ -60,15 +60,16 @@ repos:
         - flake8-bugbear==22.7.1
         - pandas-dev-flaker==0.5.0
 -   repo: https://github.com/pycqa/pylint
-    rev: v2.15.3
+    rev: v2.15.5
     hooks:
     -   id: pylint
+        stages: [manual]
 -   repo: https://github.com/PyCQA/isort
     rev: 5.10.1
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.38.2
+    rev: v3.2.0
     hooks:
     -   id: pyupgrade
         args: [--py38-plus]
@@ -83,7 +84,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.6.1
+    rev: v0.6.7
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/asottile/yesqa

README.md

@@ -166,6 +166,6 @@ You can also triage issues which may include reproducing bug reports, or asking
 
 Or maybe through using pandas you have an idea of your own or are looking for something in the documentation and thinking ‘this can be improved’...you can do something about it!
 
-Feel free to ask questions on the [mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata) or on [Gitter](https://gitter.im/pydata/pandas).
+Feel free to ask questions on the [mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata) or on [Slack](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack).
 
 As contributors and maintainers to this project, you are expected to abide by pandas' code of conduct. More information can be found at: [Contributor Code of Conduct](https://github.com/pandas-dev/.github/blob/master/CODE_OF_CONDUCT.md)

asv_bench/benchmarks/attrs_caching.py

@@ -15,7 +15,7 @@ def setup(self):
         self.cur_index = self.df.index
 
     def time_get_index(self):
-        self.foo = self.df.index
+        self.df.index
 
     def time_set_index(self):
         self.df.index = self.cur_index

asv_bench/benchmarks/frame_methods.py

@@ -28,26 +28,6 @@ def time_frame_get_numeric_data(self):
         self.df._get_numeric_data()
 
 
-class Lookup:
-    def setup(self):
-        self.df = DataFrame(np.random.randn(10000, 8), columns=list("abcdefgh"))
-        self.df["foo"] = "bar"
-        self.row_labels = list(self.df.index[::10])[:900]
-        self.col_labels = list(self.df.columns) * 100
-        self.row_labels_all = np.array(
-            list(self.df.index) * len(self.df.columns), dtype="object"
-        )
-        self.col_labels_all = np.array(
-            list(self.df.columns) * len(self.df.index), dtype="object"
-        )
-
-    def time_frame_fancy_lookup(self):
-        self.df.lookup(self.row_labels, self.col_labels)
-
-    def time_frame_fancy_lookup_all(self):
-        self.df.lookup(self.row_labels_all, self.col_labels_all)
-
-
 class Reindex:
     def setup(self):
         N = 10**3

asv_bench/benchmarks/groupby.py

@@ -310,7 +310,7 @@ def time_different_python_functions_multicol(self, df):
         df.groupby(["key1", "key2"]).agg([sum, min, max])
 
     def time_different_python_functions_singlecol(self, df):
-        df.groupby("key1").agg([sum, min, max])
+        df.groupby("key1")[["value1", "value2", "value3"]].agg([sum, min, max])
 
 
 class GroupStrings:

asv_bench/benchmarks/index_cached_properties.py

@@ -70,6 +70,3 @@ def time_engine(self, index_type):
 
     def time_inferred_type(self, index_type):
         self.idx.inferred_type
-
-    def time_is_all_dates(self, index_type):
-        self.idx.is_all_dates

asv_bench/benchmarks/inference.py

@@ -223,7 +223,7 @@ class ToDatetimeFormat:
     def setup(self):
         N = 100000
         self.s = Series(["19MAY11", "19MAY11:00:00:00"] * N)
-        self.s2 = self.s.str.replace(":\\S+$", "")
+        self.s2 = self.s.str.replace(":\\S+$", "", regex=True)
 
         self.same_offset = ["10/11/2018 00:00:00.045-07:00"] * N
         self.diff_offset = [

asv_bench/benchmarks/io/hdf.py

@@ -43,7 +43,7 @@ def setup(self):
             np.random.randn(N, 100), index=date_range("1/1/2000", periods=N)
         )
         self.df_dc = DataFrame(
-            np.random.randn(N, 10), columns=["C%03d" % i for i in range(10)]
+            np.random.randn(N, 10), columns=[f"C{i:03d}" for i in range(10)]
         )
 
         self.fname = "__test__.h5"

asv_bench/benchmarks/join_merge.py

@@ -22,26 +22,6 @@
     from pandas import ordered_merge as merge_ordered
 
 
-class Append:
-    def setup(self):
-        self.df1 = DataFrame(np.random.randn(10000, 4), columns=["A", "B", "C", "D"])
-        self.df2 = self.df1.copy()
-        self.df2.index = np.arange(10000, 20000)
-        self.mdf1 = self.df1.copy()
-        self.mdf1["obj1"] = "bar"
-        self.mdf1["obj2"] = "bar"
-        self.mdf1["int1"] = 5
-        self.mdf1 = self.mdf1._consolidate()
-        self.mdf2 = self.mdf1.copy()
-        self.mdf2.index = self.df2.index
-
-    def time_append_homogenous(self):
-        self.df1.append(self.df2)
-
-    def time_append_mixed(self):
-        self.mdf1.append(self.mdf2)
-
-
 class Concat:
 
     params = [0, 1]

asv_bench/benchmarks/multiindex_object.py

@@ -369,10 +369,14 @@ def setup(self, dtype):
         }
 
         self.midx = data[dtype]
-        self.values = self.midx[:100]
+        self.values_small = self.midx[:100]
+        self.values_large = self.midx[100:]
 
-    def time_isin(self, dtype):
-        self.midx.isin(self.values)
+    def time_isin_small(self, dtype):
+        self.midx.isin(self.values_small)
+
+    def time_isin_large(self, dtype):
+        self.midx.isin(self.values_large)
 
 
 from .pandas_vb_common import setup  # noqa: F401 isort:skip