Merge branch 'main' into remove-tests

Dockerfile

@@ -11,4 +11,5 @@ RUN apt-get install -y libhdf5-dev libgles2-mesa-dev
 RUN python -m pip install --upgrade pip
 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:

ci/code_checks.sh

@@ -504,7 +504,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.to_timedelta64 SA01" \
         -i "pandas.Timedelta.total_seconds SA01" \
         -i "pandas.Timedelta.view SA01" \
-        -i "pandas.TimedeltaIndex PR01" \
         -i "pandas.TimedeltaIndex.as_unit RT03,SA01" \
         -i "pandas.TimedeltaIndex.ceil SA01" \
         -i "pandas.TimedeltaIndex.components SA01" \
@@ -797,8 +796,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.io.formats.style.Styler.clear SA01" \
         -i "pandas.io.formats.style.Styler.concat RT03,SA01" \
         -i "pandas.io.formats.style.Styler.export RT03" \
-        -i "pandas.io.formats.style.Styler.format RT03" \
-        -i "pandas.io.formats.style.Styler.format_index RT03" \
         -i "pandas.io.formats.style.Styler.from_custom_template SA01" \
         -i "pandas.io.formats.style.Styler.hide RT03,SA01" \
         -i "pandas.io.formats.style.Styler.highlight_between RT03" \
@@ -808,7 +805,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.io.formats.style.Styler.highlight_quantile RT03" \
         -i "pandas.io.formats.style.Styler.map RT03" \
         -i "pandas.io.formats.style.Styler.map_index RT03" \
-        -i "pandas.io.formats.style.Styler.relabel_index RT03" \
         -i "pandas.io.formats.style.Styler.set_caption RT03,SA01" \
         -i "pandas.io.formats.style.Styler.set_properties RT03,SA01" \
         -i "pandas.io.formats.style.Styler.set_sticky RT03,SA01" \
@@ -1022,7 +1018,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.DateOffset.rule_code GL08" \
         -i "pandas.tseries.offsets.Day PR02" \
         -i "pandas.tseries.offsets.Day.copy SA01" \
-        -i "pandas.tseries.offsets.Day.delta GL08" \
         -i "pandas.tseries.offsets.Day.freqstr SA01" \
         -i "pandas.tseries.offsets.Day.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Day.kwds SA01" \
@@ -1075,7 +1070,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.FY5253Quarter.year_has_extra_week GL08" \
         -i "pandas.tseries.offsets.Hour PR02" \
         -i "pandas.tseries.offsets.Hour.copy SA01" \
-        -i "pandas.tseries.offsets.Hour.delta GL08" \
         -i "pandas.tseries.offsets.Hour.freqstr SA01" \
         -i "pandas.tseries.offsets.Hour.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Hour.kwds SA01" \
@@ -1098,7 +1092,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.LastWeekOfMonth.weekday GL08" \
         -i "pandas.tseries.offsets.Micro PR02" \
         -i "pandas.tseries.offsets.Micro.copy SA01" \
-        -i "pandas.tseries.offsets.Micro.delta GL08" \
         -i "pandas.tseries.offsets.Micro.freqstr SA01" \
         -i "pandas.tseries.offsets.Micro.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Micro.kwds SA01" \
@@ -1109,7 +1102,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Micro.rule_code GL08" \
         -i "pandas.tseries.offsets.Milli PR02" \
         -i "pandas.tseries.offsets.Milli.copy SA01" \
-        -i "pandas.tseries.offsets.Milli.delta GL08" \
         -i "pandas.tseries.offsets.Milli.freqstr SA01" \
         -i "pandas.tseries.offsets.Milli.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Milli.kwds SA01" \
@@ -1120,7 +1112,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Milli.rule_code GL08" \
         -i "pandas.tseries.offsets.Minute PR02" \
         -i "pandas.tseries.offsets.Minute.copy SA01" \
-        -i "pandas.tseries.offsets.Minute.delta GL08" \
         -i "pandas.tseries.offsets.Minute.freqstr SA01" \
         -i "pandas.tseries.offsets.Minute.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Minute.kwds SA01" \
@@ -1151,7 +1142,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.MonthEnd.rule_code GL08" \
         -i "pandas.tseries.offsets.Nano PR02" \
         -i "pandas.tseries.offsets.Nano.copy SA01" \
-        -i "pandas.tseries.offsets.Nano.delta GL08" \
         -i "pandas.tseries.offsets.Nano.freqstr SA01" \
         -i "pandas.tseries.offsets.Nano.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Nano.kwds SA01" \
@@ -1184,7 +1174,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.QuarterEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.Second PR02" \
         -i "pandas.tseries.offsets.Second.copy SA01" \
-        -i "pandas.tseries.offsets.Second.delta GL08" \
         -i "pandas.tseries.offsets.Second.freqstr SA01" \
         -i "pandas.tseries.offsets.Second.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Second.kwds SA01" \
@@ -1217,7 +1206,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.SemiMonthEnd.rule_code GL08" \
         -i "pandas.tseries.offsets.Tick GL08" \
         -i "pandas.tseries.offsets.Tick.copy SA01" \
-        -i "pandas.tseries.offsets.Tick.delta GL08" \
         -i "pandas.tseries.offsets.Tick.freqstr SA01" \
         -i "pandas.tseries.offsets.Tick.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Tick.kwds SA01" \

ci/deps/actions-310.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
@@ -57,7 +57,7 @@ dependencies:
   - zstandard>=0.19.0
 
   - pip:
-    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - tzdata>=2022.7
     - pytest-localserver>=0.7.1

ci/deps/actions-311-downstream_compat.yaml

@@ -28,7 +28,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
@@ -72,6 +72,6 @@ dependencies:
   - pyyaml
   - py
   - pip:
-    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - tzdata>=2022.7

ci/deps/actions-311-numpydev.yaml

@@ -13,10 +13,7 @@ dependencies:
   # test dependencies
   - pytest>=7.3.2
   - pytest-cov
-  # Once pytest-cov > 4 comes out, unpin this
-  # Right now, a DeprecationWarning related to rsyncdir
-  # causes an InternalError within pytest
-  - pytest-xdist>=2.2.0, <3
+  - pytest-xdist>=2.2.0
   - hypothesis>=6.46.1
 
   # pandas dependencies

ci/deps/actions-311.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
@@ -57,6 +57,6 @@ dependencies:
   - zstandard>=0.19.0
 
   - pip:
-    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - pytest-localserver>=0.7.1

ci/deps/actions-312.yaml

@@ -26,15 +26,15 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
   - gcsfs>=2022.11.0
   - jinja2>=3.1.2
   - lxml>=4.9.2
   - matplotlib>=3.6.3
-  # - numba>=0.56.4
+  - numba>=0.56.4
   - numexpr>=2.8.4
   - odfpy>=1.4.1
   - qtpy>=2.3.0
@@ -44,7 +44,7 @@ dependencies:
   - pyarrow>=10.0.1
   - pymysql>=1.0.2
   - pyreadstat>=1.2.0
-  # - pytables>=3.8.0
+  - pytables>=3.8.0
   - python-calamine>=0.1.7
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
@@ -57,7 +57,7 @@ dependencies:
   - zstandard>=0.19.0
 
   - pip:
-    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - tzdata>=2022.7
     - pytest-localserver>=0.7.1

ci/deps/actions-39-minimum_versions.yaml

@@ -29,7 +29,7 @@ dependencies:
   - beautifulsoup4=4.11.2
   - blosc=1.21.3
   - bottleneck=1.3.6
-  - fastparquet=2023.04.0
+  - fastparquet=2023.10.0
   - fsspec=2022.11.0
   - html5lib=1.1
   - hypothesis=6.46.1
@@ -60,6 +60,6 @@ dependencies:
   - zstandard=0.19.0
 
   - pip:
-    - adbc-driver-postgresql==0.8.0
+    - adbc-driver-postgresql==0.10.0
     - adbc-driver-sqlite==0.8.0
     - tzdata==2022.7

ci/deps/actions-39.yaml

@@ -26,7 +26,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
@@ -57,7 +57,7 @@ dependencies:
   - zstandard>=0.19.0
 
   - pip:
-    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - tzdata>=2022.7
     - pytest-localserver>=0.7.1

ci/deps/circle-310-arm64.yaml

@@ -27,7 +27,7 @@ dependencies:
   - beautifulsoup4>=4.11.2
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.04.0
+  - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1

ci/run_tests.sh

@@ -10,7 +10,7 @@ echo PYTHONHASHSEED=$PYTHONHASHSEED
 
 COVERAGE="-s --cov=pandas --cov-report=xml --cov-append --cov-config=pyproject.toml"
 
-PYTEST_CMD="MESONPY_EDITABLE_VERBOSE=1 PYTHONDEVMODE=1 PYTHONWARNDEFAULTENCODING=1 pytest -r fE -n $PYTEST_WORKERS --dist=loadfile $TEST_ARGS $COVERAGE $PYTEST_TARGET"
+PYTEST_CMD="MESONPY_EDITABLE_VERBOSE=1 PYTHONDEVMODE=1 PYTHONWARNDEFAULTENCODING=1 pytest -r fE -n $PYTEST_WORKERS --dist=worksteal $TEST_ARGS $COVERAGE $PYTEST_TARGET"
 
 if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""

doc/source/development/contributing_docstring.rst

@@ -940,7 +940,7 @@ Finally, docstrings can also be appended to with the ``doc`` decorator.
 
 In this example, we'll create a parent docstring normally (this is like
 ``pandas.core.generic.NDFrame``). Then we'll have two children (like
-``pandas.core.series.Series`` and ``pandas.core.frame.DataFrame``). We'll
+``pandas.core.series.Series`` and ``pandas.DataFrame``). We'll
 substitute the class names in this docstring.
 
 .. code-block:: python

doc/source/development/maintaining.rst

@@ -151,15 +151,15 @@ and then run::
     git bisect start
     git bisect good v1.4.0
     git bisect bad v1.5.0
-    git bisect run bash -c "python setup.py build_ext -j 4; python t.py"
+    git bisect run bash -c "python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true; python t.py"
 
 This finds the first commit that changed the behavior. The C extensions have to be
 rebuilt at every step, so the search can take a while.
 
 Exit bisect and rebuild the current version::
 
     git bisect reset
-    python setup.py build_ext -j 4
+    python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
 
 Report your findings under the corresponding issue and ping the commit author to get
 their input.

doc/source/getting_started/install.rst

@@ -346,7 +346,7 @@ SQLAlchemy                2.0.0              postgresql,     SQL support for dat
                                              sql-other
 psycopg2                  2.9.6              postgresql      PostgreSQL engine for sqlalchemy
 pymysql                   1.0.2              mysql           MySQL engine for sqlalchemy
-adbc-driver-postgresql    0.8.0              postgresql      ADBC Driver for PostgreSQL
+adbc-driver-postgresql    0.10.0             postgresql      ADBC Driver for PostgreSQL
 adbc-driver-sqlite        0.8.0              sql-other       ADBC Driver for SQLite
 ========================= ================== =============== =============================================================
 
@@ -361,7 +361,7 @@ Dependency                Minimum Version    pip extra        Notes
 PyTables                  3.8.0              hdf5             HDF5-based reading / writing
 blosc                     1.21.3             hdf5             Compression for HDF5; only available on ``conda``
 zlib                                         hdf5             Compression for HDF5
-fastparquet               2023.04.0          -                Parquet reading / writing (pyarrow is default)
+fastparquet               2023.10.0          -                Parquet reading / writing (pyarrow is default)
 pyarrow                   10.0.1             parquet, feather Parquet, ORC, and feather reading / writing
 pyreadstat                1.2.0              spss             SPSS files (.sav) reading
 odfpy                     1.4.1              excel            Open document format (.odf, .ods, .odt) reading / writing

doc/source/reference/offset_frequency.rst

@@ -1042,7 +1042,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Tick.delta
     Tick.freqstr
     Tick.kwds
     Tick.name
@@ -1077,7 +1076,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Day.delta
     Day.freqstr
     Day.kwds
     Day.name
@@ -1112,7 +1110,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Hour.delta
     Hour.freqstr
     Hour.kwds
     Hour.name
@@ -1147,7 +1144,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Minute.delta
     Minute.freqstr
     Minute.kwds
     Minute.name
@@ -1182,7 +1178,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Second.delta
     Second.freqstr
     Second.kwds
     Second.name
@@ -1217,7 +1212,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Milli.delta
     Milli.freqstr
     Milli.kwds
     Milli.name
@@ -1252,7 +1246,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Micro.delta
     Micro.freqstr
     Micro.kwds
     Micro.name
@@ -1287,7 +1280,6 @@ Properties
 .. autosummary::
    :toctree: api/
 
-    Nano.delta
     Nano.freqstr
     Nano.kwds
     Nano.name