Merge remote-tracking branch 'upstream/main' into sty/ruff

pandas-dev · Jan 23, 2024 · 2ea6780 · 2ea6780
2 parents 359736e + 3c96b8f
commit 2ea6780
Show file tree

Hide file tree

Showing 166 changed files with 1,457 additions and 834 deletions.
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -92,7 +92,10 @@ jobs:
           - name: "Numpy Dev"
             env_file: actions-311-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
-            test_args: "-W error::DeprecationWarning -W error::FutureWarning"
+            # Currently restricted the warnings that error to Deprecation Warnings from numpy
+            # done since pyarrow isn't compatible with numpydev always
+            # TODO: work with pyarrow to revert this?
+            test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -130,7 +130,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - pyright@1.1.339
+        - pyright@1.1.347
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues
@@ -188,9 +188,6 @@ repos:
             # Check for deprecated messages without sphinx directive
             |(DEPRECATED|DEPRECATE|Deprecated)(:|,|\.)
 
-            # {foo!r} instead of {repr(foo)}
-            |!r}
-
             # builtin filter function
             |(?<!def)[\(\s]filter\(
         types_or: [python, cython, rst]

diff --git a/LICENSE b/LICENSE
@@ -3,7 +3,7 @@ BSD 3-Clause License
 Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team
 All rights reserved.
 
-Copyright (c) 2011-2023, Open source contributors.
+Copyright (c) 2011-2024, Open source contributors.
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

diff --git a/asv_bench/benchmarks/algos/isin.py b/asv_bench/benchmarks/algos/isin.py
@@ -61,8 +61,8 @@ def setup(self, dtype):
                 self.series = Series(
                     Index([f"i-{i}" for i in range(N)], dtype=object), dtype=dtype
                 )
-            except ImportError:
-                raise NotImplementedError
+            except ImportError as err:
+                raise NotImplementedError from err
             self.values = list(self.series[:2])
 
         else:

diff --git a/asv_bench/benchmarks/array.py b/asv_bench/benchmarks/array.py
@@ -76,8 +76,8 @@ class ArrowStringArray:
     def setup(self, multiple_chunks):
         try:
             import pyarrow as pa
-        except ImportError:
-            raise NotImplementedError
+        except ImportError as err:
+            raise NotImplementedError from err
         strings = np.array([str(i) for i in range(10_000)], dtype=object)
         if multiple_chunks:
             chunks = [strings[i : i + 100] for i in range(0, len(strings), 100)]

diff --git a/asv_bench/benchmarks/multiindex_object.py b/asv_bench/benchmarks/multiindex_object.py
@@ -223,14 +223,20 @@ def time_categorical_level(self):
 
 class Equals:
     def setup(self):
-        idx_large_fast = RangeIndex(100000)
-        idx_small_slow = date_range(start="1/1/2012", periods=1)
-        self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
-
+        self.mi = MultiIndex.from_product(
+            [
+                date_range("2000-01-01", periods=1000),
+                RangeIndex(1000),
+            ]
+        )
+        self.mi_deepcopy = self.mi.copy(deep=True)
         self.idx_non_object = RangeIndex(1)
 
+    def time_equals_deepcopy(self):
+        self.mi.equals(self.mi_deepcopy)
+
     def time_equals_non_object_index(self):
-        self.mi_large_slow.equals(self.idx_non_object)
+        self.mi.equals(self.idx_non_object)
 
 
 class SetOperations:

diff --git a/asv_bench/benchmarks/strings.py b/asv_bench/benchmarks/strings.py
@@ -21,8 +21,8 @@ def setup(self, dtype):
             self.s = Series(
                 Index([f"i-{i}" for i in range(10000)], dtype=object), dtype=dtype
             )
-        except ImportError:
-            raise NotImplementedError
+        except ImportError as err:
+            raise NotImplementedError from err
 
 
 class Construction:

diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -65,37 +65,132 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX01, 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=EX01,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
+    MSG='Validate docstrings (EX01, EX03, 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
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX01,EX03,EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT02,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Partially validate docstrings (EX03)' ;  echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX03 --ignore_functions \
-        pandas.Series.plot.line \
-        pandas.Series.to_sql \
-        pandas.errors.SettingWithCopyWarning \
-        pandas.errors.SpecificationError \
-        pandas.errors.UndefinedVariableError \
-        pandas.read_json \
-        pandas.io.formats.style.Styler.to_latex \
-        pandas.read_parquet \
-        pandas.DataFrame.to_sql \
-        pandas.io.formats.style.Styler.map \
-        pandas.io.formats.style.Styler.apply_index \
-        pandas.io.formats.style.Styler.map_index \
-        pandas.io.formats.style.Styler.format \
-        pandas.io.formats.style.Styler.set_tooltips \
-        pandas.io.formats.style.Styler.set_uuid \
-        pandas.io.formats.style.Styler.pipe \
-        pandas.io.formats.style.Styler.highlight_between \
-        pandas.io.formats.style.Styler.highlight_quantile \
-        pandas.io.formats.style.Styler.background_gradient \
-        pandas.io.formats.style.Styler.text_gradient \
-        pandas.DataFrame.values \
-        pandas.DataFrame.groupby \
-        pandas.DataFrame.sort_values \
-        pandas.DataFrame.plot.hexbin \
-        pandas.DataFrame.plot.line \
+    MSG='Partially validate docstrings (PR02)' ;  echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=PR02 --ignore_functions \
+        pandas.io.formats.style.Styler.to_excel\
+        pandas.CategoricalIndex.rename_categories\
+        pandas.CategoricalIndex.reorder_categories\
+        pandas.CategoricalIndex.add_categories\
+        pandas.CategoricalIndex.remove_categories\
+        pandas.CategoricalIndex.set_categories\
+        pandas.IntervalIndex.set_closed\
+        pandas.IntervalIndex.contains\
+        pandas.IntervalIndex.overlaps\
+        pandas.IntervalIndex.to_tuples\
+        pandas.DatetimeIndex.round\
+        pandas.DatetimeIndex.floor\
+        pandas.DatetimeIndex.ceil\
+        pandas.DatetimeIndex.month_name\
+        pandas.DatetimeIndex.day_name\
+        pandas.DatetimeIndex.to_period\
+        pandas.DatetimeIndex.std\
+        pandas.TimedeltaIndex.round\
+        pandas.TimedeltaIndex.floor\
+        pandas.TimedeltaIndex.ceil\
+        pandas.PeriodIndex\
+        pandas.PeriodIndex.strftime\
+        pandas.Series.clip\
+        pandas.Series.rename_axis\
+        pandas.Series.interpolate\
+        pandas.Series.dt.to_period\
+        pandas.Series.dt.tz_localize\
+        pandas.Series.dt.tz_convert\
+        pandas.Series.dt.strftime\
+        pandas.Series.dt.round\
+        pandas.Series.dt.floor\
+        pandas.Series.dt.ceil\
+        pandas.Series.dt.month_name\
+        pandas.Series.dt.day_name\
+        pandas.Series.str.wrap\
+        pandas.Series.cat.rename_categories\
+        pandas.Series.cat.reorder_categories\
+        pandas.Series.cat.add_categories\
+        pandas.Series.cat.remove_categories\
+        pandas.Series.cat.set_categories\
+        pandas.Series.plot\
+        pandas.Series.plot.bar\
+        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\
+        pandas.DataFrame.plot.line\
+        pandas.DataFrame.plot.pie\
+        pandas.tseries.offsets.DateOffset\
+        pandas.tseries.offsets.BusinessDay\
+        pandas.tseries.offsets.BDay\
+        pandas.tseries.offsets.BusinessHour\
+        pandas.tseries.offsets.CustomBusinessDay\
+        pandas.tseries.offsets.CDay\
+        pandas.tseries.offsets.CustomBusinessHour\
+        pandas.tseries.offsets.MonthEnd\
+        pandas.tseries.offsets.MonthBegin\
+        pandas.tseries.offsets.BusinessMonthEnd\
+        pandas.tseries.offsets.BMonthEnd\
+        pandas.tseries.offsets.BusinessMonthBegin\
+        pandas.tseries.offsets.BMonthBegin\
+        pandas.tseries.offsets.CustomBusinessMonthEnd\
+        pandas.tseries.offsets.CBMonthEnd\
+        pandas.tseries.offsets.CustomBusinessMonthBegin\
+        pandas.tseries.offsets.CBMonthBegin\
+        pandas.tseries.offsets.SemiMonthEnd\
+        pandas.tseries.offsets.SemiMonthBegin\
+        pandas.tseries.offsets.Week\
+        pandas.tseries.offsets.WeekOfMonth\
+        pandas.tseries.offsets.LastWeekOfMonth\
+        pandas.tseries.offsets.BQuarterEnd\
+        pandas.tseries.offsets.BQuarterBegin\
+        pandas.tseries.offsets.QuarterEnd\
+        pandas.tseries.offsets.QuarterBegin\
+        pandas.tseries.offsets.BYearEnd\
+        pandas.tseries.offsets.BYearBegin\
+        pandas.tseries.offsets.YearEnd\
+        pandas.tseries.offsets.YearBegin\
+        pandas.tseries.offsets.FY5253\
+        pandas.tseries.offsets.FY5253Quarter\
+        pandas.tseries.offsets.Easter\
+        pandas.tseries.offsets.Day\
+        pandas.tseries.offsets.Hour\
+        pandas.tseries.offsets.Minute\
+        pandas.tseries.offsets.Second\
+        pandas.tseries.offsets.Milli\
+        pandas.tseries.offsets.Micro\
+        pandas.tseries.offsets.Nano\
+        pandas.describe_option\
+        pandas.reset_option\
+        pandas.get_option\
+        pandas.set_option\
+        pandas.Timestamp.max\
+        pandas.Timestamp.min\
+        pandas.Timestamp.resolution\
+        pandas.Timedelta.max\
+        pandas.Timedelta.min\
+        pandas.Timedelta.resolution\
+        pandas.Interval\
+        pandas.Grouper\
+        pandas.core.groupby.SeriesGroupBy.apply\
+        pandas.core.groupby.SeriesGroupBy.transform\
+        pandas.core.groupby.DataFrameGroupBy.transform\
+        pandas.core.groupby.DataFrameGroupBy.nth\
+        pandas.core.groupby.DataFrameGroupBy.rolling\
+        pandas.core.groupby.SeriesGroupBy.idxmax\
+        pandas.core.groupby.SeriesGroupBy.idxmin\
+        pandas.core.groupby.SeriesGroupBy.nth\
+        pandas.core.groupby.SeriesGroupBy.rolling\
+        pandas.core.groupby.DataFrameGroupBy.hist\
+        pandas.core.groupby.DataFrameGroupBy.plot\
+        pandas.core.groupby.SeriesGroupBy.plot\
+        pandas.read_hdf\
+        pandas.HDFStore.append\
+        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
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

diff --git a/ci/deps/actions-39-minimum_versions.yaml b/ci/deps/actions-39-minimum_versions.yaml
@@ -22,7 +22,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil=2.8.2
-  - numpy=1.22.4
+  - numpy=1.23.5
   - pytz=2020.1
 
   # optional dependencies

diff --git a/ci/run_tests.sh b/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 fEs -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=loadfile $TEST_ARGS $COVERAGE $PYTEST_TARGET"
 
 if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""

diff --git a/doc/scripts/eval_performance.py b/doc/scripts/eval_performance.py
@@ -17,7 +17,7 @@ def bench_with(n, times=10, repeat=3, engine="numexpr"):
     return (
         np.array(
             timeit(
-                f"df.eval(s, engine={repr(engine)})",
+                f"df.eval(s, engine={engine!r})",
                 setup=setup_common % (n, setup_with),
                 repeat=repeat,
                 number=times,
@@ -34,7 +34,7 @@ def bench_subset(n, times=20, repeat=3, engine="numexpr"):
     return (
         np.array(
             timeit(
-                f"df.query(s, engine={repr(engine)})",
+                f"df.query(s, engine={engine!r})",
                 setup=setup_common % (n, setup_subset),
                 repeat=repeat,
                 number=times,
@@ -55,7 +55,7 @@ def bench(mn=3, mx=7, num=100, engines=("python", "numexpr"), verbose=False):
     for engine in engines:
         for i, n in enumerate(r):
             if verbose & (i % 10 == 0):
-                print(f"engine: {repr(engine)}, i == {i:d}")
+                print(f"engine: {engine!r}, i == {i:d}")
             ev_times = bench_with(n, times=1, repeat=1, engine=engine)
             ev.loc[i, engine] = np.mean(ev_times)
             qu_times = bench_subset(n, times=1, repeat=1, engine=engine)

diff --git a/doc/source/getting_started/install.rst b/doc/source/getting_started/install.rst
@@ -21,7 +21,7 @@ Instructions for installing :ref:`from source <install.source>`,
 Python version support
 ----------------------
 
-Officially Python 3.9, 3.10 and 3.11.
+Officially Python 3.9, 3.10, 3.11 and 3.12.
 
 Installing pandas
 -----------------
@@ -203,7 +203,7 @@ pandas requires the following dependencies.
 ================================================================ ==========================
 Package                                                          Minimum supported version
 ================================================================ ==========================
-`NumPy <https://numpy.org>`__                                    1.22.4
+`NumPy <https://numpy.org>`__                                    1.23.5
 `python-dateutil <https://dateutil.readthedocs.io/en/stable/>`__ 2.8.2
 `pytz <https://pypi.org/project/pytz/>`__                        2020.1
 `tzdata <https://pypi.org/project/tzdata/>`__                    2022.7

diff --git a/doc/source/reference/frame.rst b/doc/source/reference/frame.rst
@@ -49,6 +49,7 @@ Conversion
    DataFrame.infer_objects
    DataFrame.copy
    DataFrame.bool
+   DataFrame.to_numpy
 
 Indexing, iteration
 ~~~~~~~~~~~~~~~~~~~

diff --git a/doc/source/whatsnew/index.rst b/doc/source/whatsnew/index.rst
@@ -10,13 +10,13 @@ This is the list of changes to pandas between each release. For full details,
 see the `commit logs <https://github.com/pandas-dev/pandas/commits/>`_. For install and
 upgrade instructions, see :ref:`install`.
 
-Version 2.3
+Version 3.0
 -----------
 
 .. toctree::
    :maxdepth: 2
 
-   v2.3.0
+   v3.0.0
 
 
 Version 2.2
@@ -25,6 +25,7 @@ Version 2.2
 .. toctree::
    :maxdepth: 2
 
+   v2.2.1
    v2.2.0
 
 Version 2.1

diff --git a/doc/source/whatsnew/v2.1.4.rst b/doc/source/whatsnew/v2.1.4.rst
@@ -42,4 +42,4 @@ Bug fixes
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.1.3..v2.1.4|HEAD
+.. contributors:: v2.1.3..v2.1.4