Merge remote-tracking branch 'upstream/main' into examplesMay31

Author: DeaMariaLeon

.circleci/config.yml

@@ -26,7 +26,6 @@ jobs:
       image: ubuntu-2004:2022.04.1
     resource_class: arm.large
     environment:
-      ENV_FILE: ci/deps/circle-38-arm64.yaml
       TRIGGER_SOURCE: << pipeline.trigger_source >>
     steps:
       - checkout

.github/workflows/wheels.yml

@@ -73,7 +73,7 @@ jobs:
           fetch-depth: 0
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.12.3
+        uses: pypa/cibuildwheel@v2.13.0
         env:
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 

ci/code_checks.sh

@@ -258,17 +258,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.IntervalIndex.to_tuples \
         pandas.MultiIndex.dtypes \
         pandas.MultiIndex.drop \
-        pandas.DatetimeIndex \
-        pandas.DatetimeIndex.date \
-        pandas.DatetimeIndex.time \
-        pandas.DatetimeIndex.timetz \
-        pandas.DatetimeIndex.dayofyear \
-        pandas.DatetimeIndex.day_of_year \
-        pandas.DatetimeIndex.quarter \
-        pandas.DatetimeIndex.tz \
-        pandas.DatetimeIndex.freqstr \
-        pandas.DatetimeIndex.inferred_freq \
-        pandas.DatetimeIndex.indexer_at_time \
         pandas.DatetimeIndex.indexer_between_time \
         pandas.DatetimeIndex.snap \
         pandas.DatetimeIndex.as_unit \
@@ -277,7 +266,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.DatetimeIndex.mean \
         pandas.DatetimeIndex.std \
         pandas.TimedeltaIndex \
-        pandas.TimedeltaIndex.days \
         pandas.TimedeltaIndex.seconds \
         pandas.TimedeltaIndex.microseconds \
         pandas.TimedeltaIndex.nanoseconds \

doc/source/development/contributing_codebase.rst

@@ -770,7 +770,7 @@ install pandas) by typing::
     your installation is probably fine and you can start contributing!
 
 Often it is worth running only a subset of tests first around your changes before running the
-entire suite (tip: you can use the [pandas-coverage app](https://pandas-coverage.herokuapp.com/)
+entire suite (tip: you can use the [pandas-coverage app](https://pandas-coverage.herokuapp.com/))
 to find out which tests hit the lines of code you've modified, and then run only those).
 
 The easiest way to do this is with::

doc/source/getting_started/index.rst

@@ -24,7 +24,7 @@ Installation
 
         .. code-block:: bash
 
-            conda install pandas
+            conda install -c conda-forge pandas
 
     .. grid-item-card:: Prefer pip?
         :class-card: install-card

doc/source/getting_started/install.rst

@@ -295,7 +295,7 @@ Installable with ``pip install "pandas[performance]"``
 ===================================================== ================== ================== ===================================================================================================================================================================================
 Dependency                                            Minimum Version    pip extra          Notes
 ===================================================== ================== ================== ===================================================================================================================================================================================
-`numexpr <https://github.com/pydata/numexpr>`__       2.8.0              performance        Accelerates certain numerical operations by using uses multiple cores as well as smart chunking and caching to achieve large speedups
+`numexpr <https://github.com/pydata/numexpr>`__       2.8.0              performance        Accelerates certain numerical operations by using multiple cores as well as smart chunking and caching to achieve large speedups
 `bottleneck <https://github.com/pydata/bottleneck>`__ 1.3.4              performance        Accelerates certain types of ``nan`` by using specialized cython routines to achieve large speedup.
 `numba <https://github.com/numba/numba>`__            0.55.2             performance        Alternative execution engine for operations that accept ``engine="numba"`` using a JIT compiler that translates Python functions to optimized machine code using the LLVM compiler.
 ===================================================== ================== ================== ===================================================================================================================================================================================

doc/source/user_guide/basics.rst

@@ -2128,7 +2128,7 @@ different numeric dtypes will **NOT** be combined. The following example will gi
        {
            "A": pd.Series(np.random.randn(8), dtype="float16"),
            "B": pd.Series(np.random.randn(8)),
-           "C": pd.Series(np.array(np.random.randn(8), dtype="uint8")),
+           "C": pd.Series(np.random.randint(0, 255, size=8), dtype="uint8"),  # [0,255] (range of uint8)
        }
    )
    df2

doc/source/whatsnew/index.rst

@@ -24,6 +24,7 @@ Version 2.0
 .. toctree::
    :maxdepth: 2
 
+   v2.0.3
    v2.0.2
    v2.0.1
    v2.0.0

doc/source/whatsnew/v2.0.0.rst

@@ -1413,4 +1413,4 @@ Other
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v1.5.0rc0..v2.0.0|HEAD
+.. contributors:: v1.5.0rc0..v2.0.0

doc/source/whatsnew/v2.0.1.rst

@@ -65,4 +65,4 @@ Other
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.0.0..v2.0.1|HEAD
+.. contributors:: v2.0.0..v2.0.1

doc/source/whatsnew/v2.0.2.rst

@@ -54,4 +54,4 @@ Other
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.0.1..v2.0.2|HEAD
+.. contributors:: v2.0.1..v2.0.2

doc/source/whatsnew/v2.0.3.rst

@@ -0,0 +1,38 @@
+.. _whatsnew_203:
+
+What's new in 2.0.3 (July XX, 2023)
+-----------------------------------
+
+These are the changes in pandas 2.0.3. See :ref:`release` for a full changelog
+including other versions of pandas.
+
+{{ header }}
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_203.regressions:
+
+Fixed regressions
+~~~~~~~~~~~~~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_203.bug_fixes:
+
+Bug fixes
+~~~~~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_203.other:
+
+Other
+~~~~~
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_203.contributors:
+
+Contributors
+~~~~~~~~~~~~
+
+.. contributors:: v2.0.2..v2.0.3|HEAD

doc/source/whatsnew/v2.1.0.rst

@@ -97,6 +97,7 @@ Other enhancements
 - Let :meth:`DataFrame.to_feather` accept a non-default :class:`Index` and non-string column names (:issue:`51787`)
 - Performance improvement in :func:`read_csv` (:issue:`52632`) with ``engine="c"``
 - :meth:`Categorical.from_codes` has gotten a ``validate`` parameter (:issue:`50975`)
+- :meth:`DataFrame.stack` gained the ``sort`` keyword to dictate whether the resulting :class:`MultiIndex` levels are sorted (:issue:`15105`)
 - Added ``engine_kwargs`` parameter to :meth:`DataFrame.to_excel` (:issue:`53220`)
 - Performance improvement in :func:`concat` with homogeneous ``np.float64`` or ``np.float32`` dtypes (:issue:`52685`)
 - Performance improvement in :meth:`DataFrame.filter` when ``items`` is given (:issue:`52941`)
@@ -251,6 +252,7 @@ Deprecations
 - Deprecated :meth:`DataFrame.applymap`. Use the new :meth:`DataFrame.map` method instead (:issue:`52353`)
 - Deprecated :meth:`DataFrame.swapaxes` and :meth:`Series.swapaxes`, use :meth:`DataFrame.transpose` or :meth:`Series.transpose` instead (:issue:`51946`)
 - Deprecated ``freq`` parameter in :class:`PeriodArray` constructor, pass ``dtype`` instead (:issue:`52462`)
+- Deprecated allowing non-standard inputs in :func:`take`, pass either a ``numpy.ndarray``, :class:`ExtensionArray`, :class:`Index`, or :class:`Series` (:issue:`52981`)
 - Deprecated behavior of :class:`DataFrame` reductions ``sum``, ``prod``, ``std``, ``var``, ``sem`` with ``axis=None``, in a future version this will operate over both axes returning a scalar instead of behaving like ``axis=0``; note this also affects numpy functions e.g. ``np.sum(df)`` (:issue:`21597`)
 - Deprecated behavior of :func:`concat` when :class:`DataFrame` has columns that are all-NA, in a future version these will not be discarded when determining the resulting dtype (:issue:`40893`)
 - Deprecated behavior of :meth:`Series.dt.to_pydatetime`, in a future version this will return a :class:`Series` containing python ``datetime`` objects instead of an ``ndarray`` of datetimes; this matches the behavior of other :meth:`Series.dt` properties (:issue:`20306`)
@@ -351,6 +353,7 @@ Numeric
 - Bug in :meth:`Series.any`, :meth:`Series.all`, :meth:`DataFrame.any`, and :meth:`DataFrame.all` had the default value of ``bool_only`` set to ``None`` instead of ``False``; this change should have no impact on users (:issue:`53258`)
 - Bug in :meth:`Series.corr` and :meth:`Series.cov` raising ``AttributeError`` for masked dtypes (:issue:`51422`)
 - Bug in :meth:`Series.median` and :meth:`DataFrame.median` with object-dtype values containing strings that can be converted to numbers (e.g. "2") returning incorrect numeric results; these now raise ``TypeError`` (:issue:`34671`)
+- Bug in :meth:`Series.sum` converting dtype ``uint64`` to ``int64`` (:issue:`53401`)
 
 
 Conversion
@@ -396,6 +399,7 @@ I/O
 - :meth:`DataFrame.to_sql` now raising ``ValueError`` when the name param is left empty while using SQLAlchemy to connect (:issue:`52675`)
 - Bug in :func:`json_normalize`, fix json_normalize cannot parse metadata fields list type (:issue:`37782`)
 - Bug in :func:`read_csv` where it would error when ``parse_dates`` was set to a list or dictionary with ``engine="pyarrow"`` (:issue:`47961`)
+- Bug in :func:`read_csv`, with ``engine="pyarrow"`` erroring when specifying a ``dtype`` with ``index_col`` (:issue:`53229`)
 - 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`)

pandas/_libs/algos.pxd

@@ -4,7 +4,7 @@ from pandas._libs.dtypes cimport (
 )
 
 
-cdef numeric_t kth_smallest_c(numeric_t* arr, Py_ssize_t k, Py_ssize_t n) nogil
+cdef numeric_t kth_smallest_c(numeric_t* arr, Py_ssize_t k, Py_ssize_t n) noexcept nogil
 
 cdef enum TiebreakEnumType:
     TIEBREAK_AVERAGE

pandas/_libs/algos.pyx

@@ -259,7 +259,7 @@ def groupsort_indexer(const intp_t[:] index, Py_ssize_t ngroups):
     return indexer.base, counts.base
 
 
-cdef Py_ssize_t swap(numeric_t *a, numeric_t *b) nogil:
+cdef Py_ssize_t swap(numeric_t *a, numeric_t *b) noexcept nogil:
     cdef:
         numeric_t t
 
@@ -270,7 +270,8 @@ cdef Py_ssize_t swap(numeric_t *a, numeric_t *b) nogil:
     return 0
 
 
-cdef numeric_t kth_smallest_c(numeric_t* arr, Py_ssize_t k, Py_ssize_t n) nogil:
+cdef numeric_t kth_smallest_c(numeric_t* arr,
+                              Py_ssize_t k, Py_ssize_t n) noexcept nogil:
     """
     See kth_smallest.__doc__. The additional parameter n specifies the maximum
     number of elements considered in arr, needed for compatibility with usage
@@ -1062,7 +1063,7 @@ cdef void rank_sorted_1d(
     # https://github.com/cython/cython/issues/1630, only trailing arguments can
     # currently be omitted for cdef functions, which is why we keep this at the end
     const intp_t[:] labels=None,
-) nogil:
+) noexcept nogil:
     """
     See rank_1d.__doc__. Handles only actual ranking, so sorting and masking should
     be handled in the caller. Note that `out` and `grp_sizes` are modified inplace.

pandas/_libs/groupby.pyx

@@ -62,7 +62,7 @@ cdef enum InterpolationEnumType:
     INTERPOLATION_MIDPOINT
 
 
-cdef float64_t median_linear_mask(float64_t* a, int n, uint8_t* mask) nogil:
+cdef float64_t median_linear_mask(float64_t* a, int n, uint8_t* mask) noexcept nogil:
     cdef:
         int i, j, na_count = 0
         float64_t* tmp
@@ -99,7 +99,7 @@ cdef float64_t median_linear_mask(float64_t* a, int n, uint8_t* mask) nogil:
     return result
 
 
-cdef float64_t median_linear(float64_t* a, int n) nogil:
+cdef float64_t median_linear(float64_t* a, int n) noexcept nogil:
     cdef:
         int i, j, na_count = 0
         float64_t* tmp
@@ -136,7 +136,7 @@ cdef float64_t median_linear(float64_t* a, int n) nogil:
     return result
 
 
-cdef float64_t calc_median_linear(float64_t* a, int n, int na_count) nogil:
+cdef float64_t calc_median_linear(float64_t* a, int n, int na_count) noexcept nogil:
     cdef:
         float64_t result
 
@@ -1300,7 +1300,8 @@ ctypedef fused numeric_object_complex_t:
     complex128_t
 
 
-cdef bint _treat_as_na(numeric_object_complex_t val, bint is_datetimelike) nogil:
+cdef bint _treat_as_na(numeric_object_complex_t val,
+                       bint is_datetimelike) noexcept nogil:
     if numeric_object_complex_t is object:
         # Should never be used, but we need to avoid the `val != val` below
         #  or else cython will raise about gil acquisition.

pandas/_libs/hashing.pyx

@@ -110,11 +110,11 @@ def hash_object_array(
     return result.base  # .base to retrieve underlying np.ndarray
 
 
-cdef uint64_t _rotl(uint64_t x, uint64_t b) nogil:
+cdef uint64_t _rotl(uint64_t x, uint64_t b) noexcept nogil:
     return (x << b) | (x >> (64 - b))
 
 
-cdef uint64_t u8to64_le(uint8_t* p) nogil:
+cdef uint64_t u8to64_le(uint8_t* p) noexcept nogil:
     return (<uint64_t>p[0] |
             <uint64_t>p[1] << 8 |
             <uint64_t>p[2] << 16 |
@@ -145,7 +145,7 @@ cdef void _sipround(uint64_t* v0, uint64_t* v1,
 
 @cython.cdivision(True)
 cdef uint64_t low_level_siphash(uint8_t* data, size_t datalen,
-                                uint8_t* key) nogil:
+                                uint8_t* key) noexcept nogil:
     cdef uint64_t v0 = 0x736f6d6570736575ULL
     cdef uint64_t v1 = 0x646f72616e646f6dULL
     cdef uint64_t v2 = 0x6c7967656e657261ULL

pandas/_libs/hashtable_class_helper.pxi.in

@@ -13,7 +13,7 @@ complex_types = ['complex64',
 }}
 
 {{for name in complex_types}}
-cdef kh{{name}}_t to_kh{{name}}_t({{name}}_t val) nogil:
+cdef kh{{name}}_t to_kh{{name}}_t({{name}}_t val) noexcept nogil:
     cdef kh{{name}}_t res
     res.real = val.real
     res.imag = val.imag
@@ -42,7 +42,7 @@ c_types = ['khcomplex128_t',
 
 {{for c_type in c_types}}
 
-cdef bint is_nan_{{c_type}}({{c_type}} val) nogil:
+cdef bint is_nan_{{c_type}}({{c_type}} val) noexcept nogil:
     {{if c_type in {'khcomplex128_t', 'khcomplex64_t'} }}
     return val.real != val.real or val.imag != val.imag
     {{elif c_type in {'float64_t', 'float32_t'} }}
@@ -55,7 +55,7 @@ cdef bint is_nan_{{c_type}}({{c_type}} val) nogil:
 {{if c_type in {'khcomplex128_t', 'khcomplex64_t', 'float64_t', 'float32_t'} }}
 # are_equivalent_{{c_type}} is cimported via khash.pxd
 {{else}}
-cdef bint are_equivalent_{{c_type}}({{c_type}} val1, {{c_type}} val2) nogil:
+cdef bint are_equivalent_{{c_type}}({{c_type}} val1, {{c_type}} val2) noexcept nogil:
     return val1 == val2
 {{endif}}
 
@@ -163,7 +163,7 @@ ctypedef fused vector_data:
     Complex64VectorData
     StringVectorData
 
-cdef bint needs_resize(vector_data *data) nogil:
+cdef bint needs_resize(vector_data *data) noexcept nogil:
     return data.n == data.m
 
 # ----------------------------------------------------------------------

pandas/_libs/lib.pyx

@@ -1192,9 +1192,12 @@ _TYPE_MAP = {
     "u": "integer",
     "float32": "floating",
     "float64": "floating",
+    "float128": "floating",
+    "float256": "floating",
     "f": "floating",
     "complex64": "complex",
     "complex128": "complex",
+    "complex256": "complex",
     "c": "complex",
     "string": "string",
     str: "string",
@@ -1216,23 +1219,6 @@ _TYPE_MAP = {
     bytes: "bytes",
 }
 
-# types only exist on certain platform
-try:
-    np.float128
-    _TYPE_MAP["float128"] = "floating"
-except AttributeError:
-    pass
-try:
-    np.complex256
-    _TYPE_MAP["complex256"] = "complex"
-except AttributeError:
-    pass
-try:
-    np.float16
-    _TYPE_MAP["float16"] = "floating"
-except AttributeError:
-    pass
-
 
 @cython.internal
 cdef class Seen:

pandas/_libs/tslibs/ccalendar.pxd

@@ -6,14 +6,14 @@ from numpy cimport (
 
 ctypedef (int32_t, int32_t, int32_t) iso_calendar_t
 
-cdef int dayofweek(int y, int m, int d) nogil
-cdef bint is_leapyear(int64_t year) nogil
-cpdef int32_t get_days_in_month(int year, Py_ssize_t month) nogil
-cpdef int32_t get_week_of_year(int year, int month, int day) nogil
-cpdef iso_calendar_t get_iso_calendar(int year, int month, int day) nogil
-cpdef int32_t get_day_of_year(int year, int month, int day) nogil
-cpdef int get_lastbday(int year, int month) nogil
-cpdef int get_firstbday(int year, int month) nogil
+cdef int dayofweek(int y, int m, int d) noexcept nogil
+cdef bint is_leapyear(int64_t year) noexcept nogil
+cpdef int32_t get_days_in_month(int year, Py_ssize_t month) noexcept nogil
+cpdef int32_t get_week_of_year(int year, int month, int day) noexcept nogil
+cpdef iso_calendar_t get_iso_calendar(int year, int month, int day) noexcept nogil
+cpdef int32_t get_day_of_year(int year, int month, int day) noexcept nogil
+cpdef int get_lastbday(int year, int month) noexcept nogil
+cpdef int get_firstbday(int year, int month) noexcept nogil
 
 cdef dict c_MONTH_NUMBERS