Merge branch 'issue-TM' of https://github.com/xaris96/pandas into issue-TM

Author: pelagiavlas

.github/CODEOWNERS

@@ -9,7 +9,6 @@ doc/cheatsheet                    @Dr-Irv
 doc/source/development            @noatamir
 
 # pandas
-pandas/_libs/                     @WillAyd
 pandas/_typing.py                 @Dr-Irv
 pandas/core/groupby/*             @rhshadrach
 pandas/io/excel/*                 @rhshadrach

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -31,7 +31,7 @@ body:
     attributes:
       label: Feature Description
       description: >
-        Please describe how the new feature would be implemented, using psudocode if relevant.
+        Please describe how the new feature would be implemented, using pseudocode if relevant.
       placeholder: >
         Add a new parameter to DataFrame, to_series, to return a Series if possible.
 

.github/workflows/wheels.yml

@@ -153,7 +153,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].1
+        uses: pypa/[email protected].3
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.pre-commit-config.yaml

@@ -1,4 +1,4 @@
-minimum_pre_commit_version: 2.15.0
+minimum_pre_commit_version: 4.0.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
@@ -19,13 +19,13 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+    rev: v0.11.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
         exclude: ^pandas/tests/frame/test_query_eval.py
     -   id: ruff
-        # TODO: remove autofixe-only rules when they are checked by ruff
+        # TODO: remove autofix only rules when they are checked by ruff
         name: ruff-selected-autofixes
         alias: ruff-selected-autofixes
         files: ^pandas
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.14'
+    rev: v2.14
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -95,14 +95,14 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.7
+    rev: v20.1.0
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.7.0
+    rev: v1.7.2
     hooks:
     - id: meson-fmt
       args: ['--inplace']

AfterMixed.txt

@@ -0,0 +1,17 @@
+
+=========================== short test summary info ===========================
+FAILED pandas/tests/indexes/multi/test_setops.py::test_difference_keep_ea_dtypes[Float32-val0]
+FAILED pandas/tests/indexes/multi/test_setops.py::test_symmetric_difference_keeping_ea_dtype[Float32-val0]
+FAILED pandas/tests/indexes/multi/test_setops.py::test_union_with_duplicates_keep_ea_dtype[Float32-dupe_val1]
+FAILED pandas/tests/indexes/multi/test_setops.py::test_union_keep_ea_dtype_with_na[Float32]
+FAILED pandas/tests/indexes/multi/test_setops.py::test_intersection_keep_ea_dtypes[Float32-val0]
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked[Float32-4-val22]
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked[Float32-val3-val23]
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked_na[Float32]
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_indexer_masked_na[Float32-4]
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_indexer_masked_na[Float32-2]
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[complex64-first]
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[complex64-last]
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[nullable_float-first]
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[nullable_float-last]
+==== 14 failed, 16452 passed, 221 skipped, 53 xfailed, 3 xpassed in 33.67s ====

after.txt

@@ -0,0 +1,28 @@
+XFAILED pandas/tests/indexes/test_common.py::test_sort_values_invalid_na_position[mixed-int-string-None]
+XFAILED pandas/tests/indexes/test_common.py::test_sort_values_invalid_na_position[mixed-int-string-middle]
+XFAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[mixed-int-string-first]
+XFAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[mixed-int-string-last]
+FAILED pandas/tests/indexes/test_numpy_compat.py::test_numpy_ufuncs_reductions[mixed-int-string-maximum] - TypeError: '>=' not supported between instances of 'int' and 'str'
+FAILED pandas/tests/indexes/test_numpy_compat.py::test_numpy_ufuncs_reductions[mixed-int-string-minimum] - TypeError: '<=' not supported between instances of 'int' and 'str'
+DONE FAILED pandas/tests/indexes/test_old_base.py::TestBase::test_argsort[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+DONE FAILED pandas/tests/indexes/test_old_base.py::TestBase::test_numpy_argsort[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+DONE FAILED pandas/tests/indexes/test_setops.py::test_union_same_types[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+DONE FAILED pandas/tests/indexes/test_setops.py::test_union_different_types[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+DONE FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_base[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_symmetric_difference[mixed-int-string] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_unequal[mixed-int-string-A-A-A] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_unequal[mixed-int-string-A-B-None] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_unequal[mixed-int-string-A-None-None] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_unequal[mixed-int-string-None-B-None] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_union_unequal[mixed-int-string-None-None-None] - TypeError: '<' not supported between instances of 'str' and 'int'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_intersect_unequal[mixed-int-string-A-A-A] - TypeError: '<' not supported between instances of 'int' and 'str'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_intersect_unequal[mixed-int-string-A-B-None] - TypeError: '<' not supported between instances of 'int' and 'str'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_intersect_unequal[mixed-int-string-A-None-None] - TypeError: '<' not supported between instances of 'int' and 'str'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_intersect_unequal[mixed-int-string-None-B-None] - TypeError: '<' not supported between instances of 'int' and 'str'
+FAILED pandas/tests/indexes/test_setops.py::TestSetOps::test_intersect_unequal[mixed-int-string-None-None-None] - TypeError: '<' not supported between instances of 'int' and 'str'
+
+
+
+
+
+================================================ 32 failed, 16436 passed, 221 skipped, 51 xfailed, 3 xpassed in 37.47s ================================================ 

asv_bench/benchmarks/frame_methods.py

@@ -517,7 +517,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(1000, 100))
 
         self.s = Series(np.arange(1028.0))
-        self.df2 = DataFrame({i: self.s for i in range(1028)})
+        self.df2 = DataFrame(dict.fromkeys(range(1028), self.s))
         self.df3 = DataFrame(np.random.randn(1000, 3), columns=list("ABC"))
 
     def time_apply_user_func(self):

asv_bench/benchmarks/indexing_engines.py

@@ -67,6 +67,14 @@ class NumericEngineIndexing:
     def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in [np.int16, np.int8, np.uint8]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)
@@ -115,6 +123,14 @@ def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
         dtype = dtype.lower()
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in ["int16", "int8", "uint8"]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)

before.txt

@@ -0,0 +1,16 @@
+FAILED pandas/tests/indexes/multi/test_setops.py::test_difference_keep_ea_dtypes[Float32-val0] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/multi/test_setops.py::test_symmetric_difference_keeping_ea_dtype[Float32-val0] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/multi/test_setops.py::test_union_with_duplicates_keep_ea_dtype[Float32-dupe_val1] - RuntimeWarning: invalid value encountered in cast       
+FAILED pandas/tests/indexes/multi/test_setops.py::test_union_keep_ea_dtype_with_na[Float32] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/multi/test_setops.py::test_intersection_keep_ea_dtypes[Float32-val0] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked[Float32-4-val22] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked[Float32-val3-val23] - RuntimeWarning: invalid value encountered in cast       
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_loc_masked_na[Float32] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_indexer_masked_na[Float32-4] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/numeric/test_indexing.py::TestGetIndexer::test_get_indexer_masked_na[Float32-2] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[complex64-first] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[complex64-last] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[nullable_float-first] - RuntimeWarning: invalid value encountered in cast
+FAILED pandas/tests/indexes/test_common.py::test_sort_values_with_missing[nullable_float-last] - RuntimeWarning: invalid value encountered in cast
+
+

ci/code_checks.sh

@@ -72,9 +72,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \