Fixed merge conflict

Author: DeaMariaLeon

.github/CODEOWNERS

@@ -0,0 +1,22 @@
+# github
+.github/                          @mroeschke
+
+# ci
+ci/                               @mroeschke
+
+# web
+web/                              @datapythonista
+
+# docs
+doc/cheatsheet                    @Dr-Irv
+
+# pandas
+pandas/_libs/                     @WillAyd
+pandas/_libs/tslibs/*             @MarcoGorelli
+pandas/_typing.py                 @Dr-Irv
+pandas/core/groupby/*             @rhshadrach
+pandas/core/tools/datetimes.py    @MarcoGorelli
+pandas/io/excel/*                 @rhshadrach
+pandas/io/formats/style.py        @attack68
+pandas/io/formats/style_render.py @attack68
+pandas/io/formats/templates       @attack68

.pre-commit-config.yaml

@@ -65,11 +65,7 @@ repos:
     rev: 1.6.1
     hooks:
     -   id: cpplint
-        # We don't lint all C files because we don't want to lint any that are built
-        # from Cython files nor do we want to lint C files that we didn't modify for
-        # this particular codebase (e.g. src/headers, src/klib). However,
-        # we can lint all header files since they aren't "generated" like C files are.
-        exclude: ^pandas/_libs/src/(klib|headers)/
+        exclude: ^pandas/_libs/include/pandas/vendored/klib
         args: [
             --quiet,
             '--extensions=c,h',

MANIFEST.in

@@ -57,6 +57,4 @@ prune pandas/tests/io/parser/data
 
 # Selectively re-add *.cxx files that were excluded above
 graft pandas/_libs/src
-graft pandas/_libs/tslibs/src
-include pandas/_libs/pd_parser.h
-include pandas/_libs/pd_parser.c
+graft pandas/_libs/include

asv_bench/benchmarks/join_merge.py

@@ -324,6 +324,38 @@ def time_i8merge(self, how):
         merge(self.left, self.right, how=how)
 
 
+class MergeDatetime:
+    params = [
+        [
+            ("ns", "ns"),
+            ("ms", "ms"),
+            ("ns", "ms"),
+        ],
+        [None, "Europe/Brussels"],
+    ]
+    param_names = ["units", "tz"]
+
+    def setup(self, units, tz):
+        unit_left, unit_right = units
+        N = 10_000
+        keys = Series(date_range("2012-01-01", freq="T", periods=N, tz=tz))
+        self.left = DataFrame(
+            {
+                "key": keys.sample(N * 10, replace=True).dt.as_unit(unit_left),
+                "value1": np.random.randn(N * 10),
+            }
+        )
+        self.right = DataFrame(
+            {
+                "key": keys[:8000].dt.as_unit(unit_right),
+                "value2": np.random.randn(8000),
+            }
+        )
+
+    def time_merge(self, units, tz):
+        merge(self.left, self.right)
+
+
 class MergeCategoricals:
     def setup(self):
         self.left_object = DataFrame(

ci/code_checks.sh

@@ -274,16 +274,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.TimedeltaIndex.as_unit \
         pandas.TimedeltaIndex.to_pytimedelta \
         pandas.TimedeltaIndex.mean \
-        pandas.PeriodIndex.is_leap_year \
-        pandas.PeriodIndex.minute \
-        pandas.PeriodIndex.month \
-        pandas.PeriodIndex.quarter \
-        pandas.PeriodIndex.second \
-        pandas.PeriodIndex.week \
-        pandas.PeriodIndex.weekday \
-        pandas.PeriodIndex.weekofyear \
-        pandas.PeriodIndex.year \
-        pandas.PeriodIndex.to_timestamp \
         pandas.core.window.rolling.Rolling.max \
         pandas.core.window.rolling.Rolling.cov \
         pandas.core.window.rolling.Rolling.skew \

doc/source/whatsnew/v2.0.3.rst

@@ -13,14 +13,15 @@ including other versions of pandas.
 
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
+- Fixed performance regression in merging on datetime-like columns (:issue:`53231`)
 -
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_203.bug_fixes:
 
 Bug fixes
 ~~~~~~~~~
--
+- Bug in :func:`read_csv` when defining ``dtype`` with ``bool[pyarrow]`` for the ``"c"`` and ``"python"`` engines (:issue:`53390`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_203.other:

doc/source/whatsnew/v2.1.0.rst

@@ -347,6 +347,7 @@ Numeric
 ^^^^^^^
 - Bug in :class:`RangeIndex` setting ``step`` incorrectly when being the subtrahend with minuend a numeric value (:issue:`53255`)
 - Bug in :meth:`Series.corr` and :meth:`Series.cov` raising ``AttributeError`` for masked dtypes (:issue:`51422`)
+- Bug when calling :meth:`Series.kurt` and :meth:`Series.skew` on numpy data of all zero returning a python type instead of a numpy type (:issue:`53482`)
 - Bug in :meth:`Series.mean`, :meth:`DataFrame.mean` with object-dtype values containing strings that can be converted to numbers (e.g. "2") returning incorrect numeric results; these now raise ``TypeError`` (:issue:`36703`, :issue:`44008`)
 - Bug in :meth:`DataFrame.corrwith` raising ``NotImplementedError`` for pyarrow-backed dtypes (:issue:`52314`)
 - Bug in :meth:`DataFrame.size` and :meth:`Series.size` returning 64-bit integer instead of int (:issue:`52897`)
@@ -403,6 +404,7 @@ I/O
 - Bug in :func:`read_hdf` not properly closing store after a ``IndexError`` is raised (:issue:`52781`)
 - Bug in :func:`read_html`, style elements were read into DataFrames (:issue:`52197`)
 - Bug in :func:`read_html`, tail texts were removed together with elements containing ``display:none`` style (:issue:`51629`)
+- Bug in :func:`read_sql` when reading multiple timezone aware columns with the same column name (:issue:`44421`)
 - Bug when writing and reading empty Stata dta files where dtype information was lost (:issue:`46240`)
 
 Period
@@ -440,6 +442,7 @@ Groupby/resample/rolling
 Reshaping
 ^^^^^^^^^
 - Bug in :func:`crosstab` when ``dropna=False`` would not keep ``np.nan`` in the result (:issue:`10772`)
+- Bug in :func:`merge_asof` raising ``KeyError`` for extension dtypes (:issue:`52904`)
 - Bug in :meth:`DataFrame.agg` and :meth:`Series.agg` on non-unique columns would return incorrect type when dist-like argument passed in (:issue:`51099`)
 - Bug in :meth:`DataFrame.idxmin` and :meth:`DataFrame.idxmax`, where the axis dtype would be lost for empty frames (:issue:`53265`)
 - Bug in :meth:`DataFrame.merge` not merging correctly when having ``MultiIndex`` with single level (:issue:`52331`)

pandas/_libs/groupby.pyx

@@ -91,7 +91,7 @@ cdef float64_t median_linear_mask(float64_t* a, int n, uint8_t* mask) noexcept n
         a = tmp
         n -= na_count
 
-    result = calc_median_linear(a, n, na_count)
+    result = calc_median_linear(a, n)
 
     if na_count:
         free(a)
@@ -128,15 +128,15 @@ cdef float64_t median_linear(float64_t* a, int n) noexcept nogil:
         a = tmp
         n -= na_count
 
-    result = calc_median_linear(a, n, na_count)
+    result = calc_median_linear(a, n)
 
     if na_count:
         free(a)
 
     return result
 
 
-cdef float64_t calc_median_linear(float64_t* a, int n, int na_count) noexcept nogil:
+cdef float64_t calc_median_linear(float64_t* a, int n) noexcept nogil:
     cdef:
         float64_t result
 

pandas/_libs/tslibs/src/datetime/date_conversions.h renamed to pandas/_libs/include/pandas/datetime/date_conversions.h

@@ -22,9 +22,9 @@ See NUMPY_LICENSE.txt for the license.
 #endif  // NPY_NO_DEPRECATED_API
 
 #include <numpy/ndarraytypes.h>
-#include "np_datetime.h"
-#include "np_datetime_strings.h"
-#include "date_conversions.h"
+#include "pandas/vendored/numpy/datetime/np_datetime.h"
+#include "pandas/vendored/numpy/datetime/np_datetime_strings.h"
+#include "pandas/datetime/date_conversions.h"
 
 #ifdef __cplusplus
 extern "C" {

pandas/_libs/tslibs/src/datetime/pd_datetime.h renamed to pandas/_libs/include/pandas/datetime/pd_datetime.h

@@ -14,7 +14,7 @@ extern "C" {
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
-#include "src/parser/tokenizer.h"
+#include "pandas/parser/tokenizer.h"
 
 typedef struct {
   int (*to_double)(char *, double *, char, char, int *);

pandas/_libs/src/inline_helper.h renamed to pandas/_libs/include/pandas/inline_helper.h

@@ -19,10 +19,10 @@ See LICENSE for the license
 #define ERROR_INVALID_CHARS 3
 
 #include <stdint.h>
-#include "../inline_helper.h"
-#include "../headers/portable.h"
+#include "pandas/inline_helper.h"
+#include "pandas/portable.h"
 
-#include "khash.h"
+#include "pandas/vendored/klib/khash.h"
 
 #define STREAM_INIT_SIZE 32
 

pandas/_libs/src/parser/io.h renamed to pandas/_libs/include/pandas/parser/io.h

@@ -1,9 +1,18 @@
+/*
+Copyright (c) 2016, PyData Development Team
+All rights reserved.
+
+Distributed under the terms of the BSD Simplified License.
+
+The full license is in the LICENSE file, distributed with this software.
+*/
+
 #pragma once
 
 #include <string.h>
 
 #if defined(_MSC_VER)
-#define strcasecmp( s1, s2 ) _stricmp( s1, s2 )
+#define strcasecmp(s1, s2) _stricmp(s1, s2)
 #endif
 
 // GH-23516 - works around locale perf issues

pandas/_libs/pd_parser.h renamed to pandas/_libs/include/pandas/parser/pd_parser.h

@@ -19,7 +19,7 @@ Python recipe (https://rhettinger.wordpress.com/2010/02/06/lost-knowledge/)
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include "inline_helper.h"
+#include "pandas/inline_helper.h"
 
 PANDAS_INLINE float __skiplist_nanf(void) {
     const union {

pandas/_libs/src/parser/tokenizer.h renamed to pandas/_libs/include/pandas/parser/tokenizer.h

@@ -112,7 +112,7 @@ int main() {
 #include <stdlib.h>
 #include <string.h>
 #include <limits.h>
-#include "../inline_helper.h"
+#include "pandas/inline_helper.h"
 
 
 // hooks for memory allocator, C-runtime allocator used per default

pandas/_libs/src/headers/portable.h renamed to pandas/_libs/include/pandas/portable.h

@@ -53,7 +53,7 @@ tree doesn't have cyclic references.
 
 #include <stdio.h>
 #include <wchar.h>
-#include "../../headers/portable.h"
+#include "pandas/portable.h"
 
 // Don't output any extra whitespaces when encoding
 #define JSON_NO_EXTRA_WHITESPACE

pandas/_libs/src/skiplist.h renamed to pandas/_libs/include/pandas/skiplist.h

@@ -15,7 +15,7 @@ from numpy cimport (
 )
 
 
-cdef extern from "khash_python.h":
+cdef extern from "pandas/vendored/klib/khash_python.h":
     const int KHASH_TRACE_DOMAIN
 
     ctypedef uint32_t khuint_t

pandas/_libs/src/klib/khash.h renamed to pandas/_libs/include/pandas/vendored/klib/khash.h

@@ -24,7 +24,7 @@ primitive_types = [('int64', 'int64_t'),
 
 {{for name, c_type in primitive_types}}
 
-cdef extern from "khash_python.h":
+cdef extern from "pandas/vendored/klib/khash_python.h":
     ctypedef struct kh_{{name}}_t:
         khuint_t n_buckets, size, n_occupied, upper_bound
         uint32_t *flags

pandas/_libs/src/klib/khash_python.h renamed to pandas/_libs/include/pandas/vendored/klib/khash_python.h

@@ -93,7 +93,7 @@ cdef extern from "numpy/arrayobject.h":
 cdef extern from "numpy/ndarrayobject.h":
     bint PyArray_CheckScalar(obj) nogil
 
-cdef extern from "pd_parser.h":
+cdef extern from "pandas/parser/pd_parser.h":
     int floatify(object, float64_t *result, int *maybe_int) except -1
     void PandasParser_IMPORT()
 

pandas/_libs/tslibs/src/datetime/np_datetime.h renamed to pandas/_libs/include/pandas/vendored/numpy/datetime/np_datetime.h

@@ -61,53 +61,41 @@ subdir('tslibs')
 libs_sources = {
     # Dict of extension name -> dict of {sources, include_dirs, and deps}
     # numpy include dir is implicitly included
-    'algos': {'sources': ['algos.pyx', _algos_common_helper, _algos_take_helper, _khash_primitive_helper],
-              'include_dirs': klib_include},
+    'algos': {'sources': ['algos.pyx', _algos_common_helper, _algos_take_helper, _khash_primitive_helper]},
     'arrays': {'sources': ['arrays.pyx']},
     'groupby': {'sources': ['groupby.pyx']},
     'hashing': {'sources': ['hashing.pyx']},
-    'hashtable': {'sources': ['hashtable.pyx', _khash_primitive_helper, _hashtable_class_helper, _hashtable_func_helper],
-                  'include_dirs': klib_include},
-    'index': {'sources': ['index.pyx', _index_class_helper],
-              'include_dirs': [klib_include, 'tslibs']},
+    'hashtable': {'sources': ['hashtable.pyx', _khash_primitive_helper, _hashtable_class_helper, _hashtable_func_helper]},
+    'index': {'sources': ['index.pyx', _index_class_helper]},
     'indexing': {'sources': ['indexing.pyx']},
     'internals': {'sources': ['internals.pyx']},
-    'interval': {'sources': ['interval.pyx', _intervaltree_helper],
-                'include_dirs': [klib_include, 'tslibs']},
+    'interval': {'sources': ['interval.pyx', _intervaltree_helper]},
     'join': {'sources': ['join.pyx', _khash_primitive_helper],
-             'include_dirs': klib_include,
              'deps': _khash_primitive_helper_dep},
-    'lib': {'sources': ['lib.pyx', 'src/parser/tokenizer.c'],
-            'include_dirs': [klib_include, inc_datetime]},
-    'missing': {'sources': ['missing.pyx'],
-                'include_dirs': [inc_datetime]},
-    'pandas_datetime': {'sources': ['tslibs/src/datetime/np_datetime.c',
-                                    'tslibs/src/datetime/np_datetime_strings.c',
-                                    'tslibs/src/datetime/date_conversions.c',
-                                    'tslibs/src/datetime/pd_datetime.c']},
-                        #'include_dirs':
+    'lib': {'sources': ['lib.pyx', 'src/parser/tokenizer.c']},
+    'missing': {'sources': ['missing.pyx']},
+    'pandas_datetime': {'sources': ['src/vendored/numpy/datetime/np_datetime.c',
+                                    'src/vendored/numpy/datetime/np_datetime_strings.c',
+                                    'src/datetime/date_conversions.c',
+                                    'src/datetime/pd_datetime.c']},
     'pandas_parser': {'sources': ['src/parser/tokenizer.c',
                                   'src/parser/io.c',
-                                  'pd_parser.c'],
-                      'include_dirs': [klib_include]},
+                                  'src/parser/pd_parser.c']},
     'parsers': {'sources': ['parsers.pyx', 'src/parser/tokenizer.c', 'src/parser/io.c'],
-                'include_dirs': [klib_include, 'src'],
                 'deps': _khash_primitive_helper_dep},
-    'json': {'sources': ['src/ujson/python/ujson.c',
-                         'src/ujson/python/objToJSON.c',
-                         'src/ujson/python/JSONtoObj.c',
-                         'src/ujson/lib/ultrajsonenc.c',
-                         'src/ujson/lib/ultrajsondec.c'],
-             'include_dirs': ['tslibs/src/datetime', 'src/ujson/lib', 'src/ujson/python']},
+    'json': {'sources': ['src/vendored/ujson/python/ujson.c',
+                         'src/vendored/ujson/python/objToJSON.c',
+                         'src/vendored/ujson/python/JSONtoObj.c',
+                         'src/vendored/ujson/lib/ultrajsonenc.c',
+                         'src/vendored/ujson/lib/ultrajsondec.c']},
     'ops': {'sources': ['ops.pyx']},
     'ops_dispatch': {'sources': ['ops_dispatch.pyx']},
     'properties': {'sources': ['properties.pyx']},
     'reshape': {'sources': ['reshape.pyx']},
     'sas': {'sources': ['sas.pyx']},
     'byteswap': {'sources': ['byteswap.pyx']},
     'sparse': {'sources': ['sparse.pyx', _sparse_op_helper]},
-    'tslib': {'sources': ['tslib.pyx'],
-              'include_dirs': inc_datetime},
+    'tslib': {'sources': ['tslib.pyx']},
     'testing': {'sources': ['testing.pyx']},
     'writers': {'sources': ['writers.pyx']}
 }
@@ -118,7 +106,7 @@ foreach ext_name, ext_dict : libs_sources
         ext_name,
         ext_dict.get('sources'),
         cython_args: ['--include-dir', meson.current_build_dir()],
-        include_directories: [inc_np] + ext_dict.get('include_dirs', ''),
+        include_directories: [inc_np, inc_pd],
         dependencies: ext_dict.get('deps', ''),
         subdir: 'pandas/_libs',
         install: true