Merge branch 'main' into ngroup-axis-1

Author: rhshadrach

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,8 +17,8 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this bug exists on the [main branch]
-            (https://pandas.pydata.org/docs/dev/getting_started/install.html#installing-the-development-version-of-pandas)
+            I have confirmed this bug exists on the
+            [main branch](https://pandas.pydata.org/docs/dev/getting_started/install.html#installing-the-development-version-of-pandas)
             of pandas.
   - type: textarea
     id: example

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

@@ -46,12 +46,6 @@ jobs:
     - name: Build Pandas
       uses: ./.github/actions/build_pandas
 
-    - name: Set up maintainers cache
-      uses: actions/cache@v3
-      with:
-        path: maintainers.json
-        key: maintainers
-
     - name: Build website
       run: python web/pandas_web.py web/pandas --target-path=web/build
 

.github/workflows/macos-windows.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, windows-latest]
-        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
+        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     name: ${{ format('{0} {1}', matrix.os, matrix.env_file) }}

.github/workflows/python-dev.yml

@@ -23,12 +23,14 @@ name: Python Dev
 on:
   push:
     branches:
-      - main
-      - 1.5.x
+#      - main
+#      - 1.5.x
+      - None
   pull_request:
     branches:
-      - main
-      - 1.5.x
+#      - main
+#      - 1.5.x
+      - None
     paths-ignore:
       - "doc/**"
 

.github/workflows/ubuntu.yml

@@ -27,7 +27,7 @@ jobs:
     timeout-minutes: 180
     strategy:
       matrix:
-        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
+        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
         pattern: ["not single_cpu", "single_cpu"]
         pyarrow_version: ["7", "8", "9", "10"]
         include:
@@ -77,7 +77,7 @@ jobs:
           - name: "Numpy Dev"
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
-            test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
+            test_args: "-W error::DeprecationWarning -W error::FutureWarning"
             error_on_warnings: "0"
         exclude:
           - env_file: actions-38.yaml
@@ -92,6 +92,12 @@ jobs:
             pyarrow_version: "8"
           - env_file: actions-39.yaml
             pyarrow_version: "9"
+          - env_file: actions-311.yaml
+            pyarrow_version: "7"
+          - env_file: actions-311.yaml
+            pyarrow_version: "8"
+          - env_file: actions-311.yaml
+            pyarrow_version: "9"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}
     env:

.pre-commit-config.yaml

@@ -443,6 +443,3 @@ repos:
         types: [python]
         files: ^pandas/tests
         language: python
-        exclude: |
-            (?x)
-            ^pandas/tests/generic/test_generic.py  # GH50380

asv_bench/benchmarks/array.py

@@ -93,7 +93,7 @@ def time_setitem(self, multiple_chunks):
             self.array[i] = "foo"
 
     def time_setitem_list(self, multiple_chunks):
-        indexer = list(range(0, 50)) + list(range(-50, 0))
+        indexer = list(range(0, 50)) + list(range(-1000, 0, 50))
         self.array[indexer] = ["foo"] * len(indexer)
 
     def time_setitem_slice(self, multiple_chunks):

asv_bench/benchmarks/io/hdf.py

@@ -128,9 +128,17 @@ def setup(self, format):
         self.df["object"] = tm.makeStringIndex(N)
         self.df.to_hdf(self.fname, "df", format=format)
 
+        # Numeric df
+        self.df1 = self.df.copy()
+        self.df1 = self.df1.reset_index()
+        self.df1.to_hdf(self.fname, "df1", format=format)
+
     def time_read_hdf(self, format):
         read_hdf(self.fname, "df")
 
+    def peakmem_read_hdf(self, format):
+        read_hdf(self.fname, "df")
+
     def time_write_hdf(self, format):
         self.df.to_hdf(self.fname, "df", format=format)
 

asv_bench/benchmarks/io/json.py

@@ -294,7 +294,8 @@ def time_float_longint_str_lines(self):
 class ToJSONMem:
     def setup_cache(self):
         df = DataFrame([[1]])
-        frames = {"int": df, "float": df.astype(float)}
+        df2 = DataFrame(range(8), date_range("1/1/2000", periods=8, freq="T"))
+        frames = {"int": df, "float": df.astype(float), "datetime": df2}
 
         return frames
 
@@ -308,5 +309,10 @@ def peakmem_float(self, frames):
         for _ in range(100_000):
             df.to_json()
 
+    def peakmem_time(self, frames):
+        df = frames["datetime"]
+        for _ in range(10_000):
+            df.to_json(orient="table")
+
 
 from ..pandas_vb_common import setup  # noqa: F401 isort:skip

ci/code_checks.sh

@@ -79,33 +79,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    MSG='Partially validate docstrings (RT02)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=RT02 --ignore_functions \
-    	    pandas.Series.align \
-	    pandas.Series.dt.total_seconds \
-	    pandas.Series.cat.rename_categories \
-	    pandas.Series.cat.reorder_categories \
-	    pandas.Series.cat.add_categories \
-	    pandas.Series.cat.remove_categories \
-	    pandas.Series.cat.remove_unused_categories \
-	    pandas.Index.all \
-	    pandas.Index.any \
-	    pandas.MultiIndex.drop \
-	    pandas.DatetimeIndex.to_pydatetime \
-	    pandas.TimedeltaIndex.to_pytimedelta \
-	    pandas.core.groupby.SeriesGroupBy.apply \
-	    pandas.core.groupby.DataFrameGroupBy.apply \
-	    pandas.io.formats.style.Styler.export \
-	    pandas.api.extensions.ExtensionArray.astype \
-	    pandas.api.extensions.ExtensionArray.dropna \
-	    pandas.api.extensions.ExtensionArray.isna \
-	    pandas.api.extensions.ExtensionArray.repeat \
-	    pandas.api.extensions.ExtensionArray.unique \
-	    pandas.DataFrame.align
+    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT02, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT02,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi