Merge branch 'main' into issue-37210-to-sql-truncate

Author: gmcrocetti

ci/code_checks.sh

@@ -72,7 +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.RangeIndex.from_range PR01,SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \

doc/source/reference/window.rst

@@ -35,6 +35,7 @@ Rolling window functions
    Rolling.skew
    Rolling.kurt
    Rolling.apply
+   Rolling.pipe
    Rolling.aggregate
    Rolling.quantile
    Rolling.sem
@@ -76,6 +77,7 @@ Expanding window functions
    Expanding.skew
    Expanding.kurt
    Expanding.apply
+   Expanding.pipe
    Expanding.aggregate
    Expanding.quantile
    Expanding.sem

doc/source/user_guide/io.rst

@@ -2340,6 +2340,7 @@ Read a URL with no options:
 .. code-block:: ipython
 
    In [320]: url = "https://www.fdic.gov/resources/resolutions/bank-failures/failed-bank-list"
+
    In [321]: pd.read_html(url)
    Out[321]:
    [                         Bank NameBank           CityCity StateSt  ...              Acquiring InstitutionAI Closing DateClosing FundFund
@@ -2366,6 +2367,7 @@ Read a URL while passing headers alongside the HTTP request:
 .. code-block:: ipython
 
    In [322]: url = 'https://www.sump.org/notes/request/' # HTTP request reflector
+
    In [323]: pd.read_html(url)
    Out[323]:
    [                   0                    1
@@ -2378,14 +2380,16 @@ Read a URL while passing headers alongside the HTTP request:
     1              Host:         www.sump.org
     2        User-Agent:    Python-urllib/3.8
     3        Connection:                close]
+
    In [324]: headers = {
-   In [325]:    'User-Agent':'Mozilla Firefox v14.0',
-   In [326]:    'Accept':'application/json',
-   In [327]:    'Connection':'keep-alive',
-   In [328]:    'Auth':'Bearer 2*/f3+fe68df*4'
-   In [329]: }
-   In [340]: pd.read_html(url, storage_options=headers)
-   Out[340]:
+      .....:    'User-Agent':'Mozilla Firefox v14.0',
+      .....:    'Accept':'application/json',
+      .....:    'Connection':'keep-alive',
+      .....:    'Auth':'Bearer 2*/f3+fe68df*4'
+      .....: }
+
+   In [325]: pd.read_html(url, storage_options=headers)
+   Out[325]:
    [                   0                    1
     0     Remote Socket:  51.15.105.256:51760
     1  Protocol Version:             HTTP/1.1

doc/source/whatsnew/v2.3.0.rst

@@ -35,8 +35,8 @@ Other enhancements
 - The semantics for the ``copy`` keyword in ``__array__`` methods (i.e. called
   when using ``np.array()`` or ``np.asarray()`` on pandas objects) has been
   updated to work correctly with NumPy >= 2 (:issue:`57739`)
+- The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns when backed by PyArrow (:issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
--
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_230.notable_bug_fixes:

doc/source/whatsnew/v3.0.0.rst

@@ -30,6 +30,7 @@ Other enhancements
 ^^^^^^^^^^^^^^^^^^
 - :class:`pandas.api.typing.FrozenList` is available for typing the outputs of :attr:`MultiIndex.names`, :attr:`MultiIndex.codes` and :attr:`MultiIndex.levels` (:issue:`58237`)
 - :class:`pandas.api.typing.SASReader` is available for typing the output of :func:`read_sas` (:issue:`55689`)
+- :class:`pandas.api.typing.NoDefault` is available for typing ``no_default``
 - :func:`DataFrame.to_excel` now raises an ``UserWarning`` when the character count in a cell exceeds Excel's limitation of 32767 characters (:issue:`56954`)
 - :func:`pandas.merge` now validates the ``how`` parameter input (merge type) (:issue:`59435`)
 - :func:`read_spss` now supports kwargs to be passed to pyreadstat (:issue:`56356`)
@@ -44,13 +45,15 @@ Other enhancements
 - Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 - :meth:`Styler.format_index_names` can now be used to format the index and column names (:issue:`48936` and :issue:`47489`)
 - :class:`.errors.DtypeWarning` improved to include column names when mixed data types are detected (:issue:`58174`)
+- :class:`Rolling` and :class:`Expanding` now support ``pipe`` method (:issue:`57076`)
 - :class:`Series` now supports the Arrow PyCapsule Interface for export (:issue:`59518`)
 - :func:`DataFrame.to_excel` argument ``merge_cells`` now accepts a value of ``"columns"`` to only merge :class:`MultiIndex` column header header cells (:issue:`35384`)
 - :meth:`DataFrame.corrwith` now accepts ``min_periods`` as optional arguments, as in :meth:`DataFrame.corr` and :meth:`Series.corr` (:issue:`9490`)
 - :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
 - :meth:`DataFrame.ewm` now allows ``adjust=False`` when ``times`` is provided (:issue:`54328`)
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)
 - :meth:`DataFrame.pivot_table` and :func:`pivot_table` now allow the passing of keyword arguments to ``aggfunc`` through ``**kwargs`` (:issue:`57884`)
+- :meth:`DataFrame.to_json` now encodes ``Decimal`` as strings instead of floats (:issue:`60698`)
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
 - :meth:`DataFrame.plot.scatter` argument ``c`` now accepts a column of strings, where rows with the same string are colored identically (:issue:`16827` and :issue:`16485`)
@@ -687,6 +690,7 @@ MultiIndex
 - :meth:`DataFrame.melt` would not accept multiple names in ``var_name`` when the columns were a :class:`MultiIndex` (:issue:`58033`)
 - :meth:`MultiIndex.insert` would not insert NA value correctly at unified location of index -1 (:issue:`59003`)
 - :func:`MultiIndex.get_level_values` accessing a :class:`DatetimeIndex` does not carry the frequency attribute along (:issue:`58327`, :issue:`57949`)
+- Bug in :class:`DataFrame` arithmetic operations in case of unaligned MultiIndex columns (:issue:`60498`)
 -
 
 I/O

pandas/_libs/include/pandas/vendored/ujson/lib/ultrajson.h

@@ -170,8 +170,8 @@ typedef void (*JSPFN_ITERBEGIN)(JSOBJ obj, JSONTypeContext *tc);
 typedef int (*JSPFN_ITERNEXT)(JSOBJ obj, JSONTypeContext *tc);
 typedef void (*JSPFN_ITEREND)(JSOBJ obj, JSONTypeContext *tc);
 typedef JSOBJ (*JSPFN_ITERGETVALUE)(JSOBJ obj, JSONTypeContext *tc);
-typedef char *(*JSPFN_ITERGETNAME)(JSOBJ obj, JSONTypeContext *tc,
-                                   size_t *outLen);
+typedef const char *(*JSPFN_ITERGETNAME)(JSOBJ obj, JSONTypeContext *tc,
+                                         size_t *outLen);
 typedef void *(*JSPFN_MALLOC)(size_t size);
 typedef void (*JSPFN_FREE)(void *pptr);
 typedef void *(*JSPFN_REALLOC)(void *base, size_t size);

pandas/_libs/src/parser/tokenizer.c

@@ -148,7 +148,7 @@ int parser_init(parser_t *self) {
   self->warn_msg = NULL;
 
   // token stream
-  self->stream = malloc(STREAM_INIT_SIZE * sizeof(char));
+  self->stream = malloc(STREAM_INIT_SIZE);
   if (self->stream == NULL) {
     parser_cleanup(self);
     return PARSER_OUT_OF_MEMORY;
@@ -221,9 +221,8 @@ static int make_stream_space(parser_t *self, size_t nbytes) {
   char *orig_ptr = (void *)self->stream;
   TRACE(("\n\nmake_stream_space: nbytes = %zu.  grow_buffer(self->stream...)\n",
          nbytes))
-  self->stream =
-      (char *)grow_buffer((void *)self->stream, self->stream_len,
-                          &self->stream_cap, nbytes * 2, sizeof(char), &status);
+  self->stream = (char *)grow_buffer((void *)self->stream, self->stream_len,
+                                     &self->stream_cap, nbytes * 2, 1, &status);
   TRACE(("make_stream_space: self->stream=%p, self->stream_len = %zu, "
          "self->stream_cap=%zu, status=%zu\n",
          self->stream, self->stream_len, self->stream_cap, status))

pandas/_libs/src/vendored/ujson/lib/ultrajsonenc.c

@@ -920,7 +920,7 @@ Perhaps implement recursion detection */
 void encode(JSOBJ obj, JSONObjectEncoder *enc, const char *name,
             size_t cbName) {
   const char *value;
-  char *objName;
+  const char *objName;
   int count;
   JSOBJ iterObj;
   size_t szlen;