Merge branch 'main' into shiny-new-feature

Author: Chiwendaiyue

doc/source/user_guide/10min.rst

@@ -318,7 +318,9 @@ Setting a new column automatically aligns the data by the indexes:
 
 .. ipython:: python
 
-   s1 = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range("20130102", periods=6))
+   s1 = pd.Series(
+      [1, 2, 3, 4, 5, 6],
+      index=pd.date_range("20130102", periods=6))
    s1
    df["F"] = s1
 

doc/source/whatsnew/v3.0.0.rst

@@ -656,6 +656,7 @@ Other API changes
   an empty ``RangeIndex`` or empty ``Index`` with object dtype when determining
   the dtype of the resulting Index (:issue:`60797`)
 - :class:`IncompatibleFrequency` now subclasses ``TypeError`` instead of ``ValueError``. As a result, joins with mismatched frequencies now cast to object like other non-comparable joins, and arithmetic with indexes with mismatched frequencies align (:issue:`55782`)
+- :class:`Series` "flex" methods like :meth:`Series.add` no longer allow passing a :class:`DataFrame` for ``other``; use the DataFrame reversed method instead (:issue:`46179`)
 - :meth:`CategoricalIndex.append` no longer attempts to cast different-dtype indexes to the caller's dtype (:issue:`41626`)
 - :meth:`ExtensionDtype.construct_array_type` is now a regular method instead of a ``classmethod`` (:issue:`58663`)
 - Comparison operations between :class:`Index` and :class:`Series` now consistently return :class:`Series` regardless of which object is on the left or right (:issue:`36759`)
@@ -875,6 +876,7 @@ Other Removals
 - Removed the ``method`` keyword in ``ExtensionArray.fillna``, implement ``ExtensionArray._pad_or_backfill`` instead (:issue:`53621`)
 - Removed the attribute ``dtypes`` from :class:`.DataFrameGroupBy` (:issue:`51997`)
 - Enforced deprecation of ``argmin``, ``argmax``, ``idxmin``, and ``idxmax`` returning a result when ``skipna=False`` and an NA value is encountered or all values are NA values; these operations will now raise in such cases (:issue:`33941`, :issue:`51276`)
+- Enforced deprecation of storage option "pyarrow_numpy" for :class:`StringDtype` (:issue:`60152`)
 - Removed specifying ``include_groups=True`` in :class:`.DataFrameGroupBy.apply` and :class:`.Resampler.apply` (:issue:`7155`)
 
 .. ---------------------------------------------------------------------------
@@ -1000,6 +1002,7 @@ Numeric
 - Bug in :meth:`Series.dot` returning ``object`` dtype for :class:`ArrowDtype` and nullable-dtype data (:issue:`61375`)
 - Bug in :meth:`Series.std` and :meth:`Series.var` when using complex-valued data (:issue:`61645`)
 - Bug in ``np.matmul`` with :class:`Index` inputs raising a ``TypeError`` (:issue:`57079`)
+- Bug in arithmetic operations between objects with numpy-nullable dtype and :class:`ArrowDtype` incorrectly raising (:issue:`58602`)
 
 Conversion
 ^^^^^^^^^^
@@ -1014,6 +1017,7 @@ Strings
 ^^^^^^^
 - Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
+- Bug in multiplication with a :class:`StringDtype` incorrectly allowing multiplying by bools; explicitly cast to integers instead (:issue:`62595`)
 
 Interval
 ^^^^^^^^
@@ -1054,6 +1058,7 @@ MultiIndex
 - :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`)
 - Bug in :class:`DataFrame` arithmetic operations with :class:`Series` in case of unaligned MultiIndex (:issue:`61009`)
+- Bug in :meth:`MultiIndex.union` raising when indexes have duplicates with differing names (:issue:`62059`)
 - Bug in :meth:`MultiIndex.from_tuples` causing wrong output with input of type tuples having NaN values (:issue:`60695`, :issue:`60988`)
 - Bug in :meth:`DataFrame.__setitem__` where column alignment logic would reindex the assigned value with an empty index, incorrectly setting all values to ``NaN``.(:issue:`61841`)
 - Bug in :meth:`DataFrame.reindex` and :meth:`Series.reindex` where reindexing :class:`Index` to a :class:`MultiIndex` would incorrectly set all values to ``NaN``.(:issue:`60923`)

pandas/_config/config.py

@@ -503,6 +503,7 @@ def option_context(*args) -> Generator[None]:
         )
 
     ops = tuple(zip(args[::2], args[1::2], strict=True))
+    undo: tuple[tuple[Any, Any], ...] = ()
     try:
         undo = tuple((pat, get_option(pat)) for pat, val in ops)
         for pat, val in ops:

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

@@ -37,9 +37,8 @@ typedef struct {
   int (*parser_trim_buffers)(parser_t *);
   int (*tokenize_all_rows)(parser_t *, const char *);
   int (*tokenize_nrows)(parser_t *, size_t, const char *);
-  int64_t (*str_to_int64)(const char *, int64_t, int64_t, int *, char);
-  uint64_t (*str_to_uint64)(uint_state *, const char *, int64_t, uint64_t,
-                            int *, char);
+  int64_t (*str_to_int64)(const char *, int *, char);
+  uint64_t (*str_to_uint64)(uint_state *, const char *, int *, char);
   double (*xstrtod)(const char *, char **, char, char, char, int, int *, int *);
   double (*precise_xstrtod)(const char *, char **, char, char, char, int, int *,
                             int *);
@@ -87,12 +86,10 @@ static PandasParser_CAPI *PandasParserAPI = NULL;
   PandasParserAPI->tokenize_all_rows((self), (encoding_errors))
 #define tokenize_nrows(self, nrows, encoding_errors)                           \
   PandasParserAPI->tokenize_nrows((self), (nrows), (encoding_errors))
-#define str_to_int64(p_item, int_min, int_max, error, t_sep)                   \
-  PandasParserAPI->str_to_int64((p_item), (int_min), (int_max), (error),       \
-                                (t_sep))
-#define str_to_uint64(state, p_item, int_max, uint_max, error, t_sep)          \
-  PandasParserAPI->str_to_uint64((state), (p_item), (int_max), (uint_max),     \
-                                 (error), (t_sep))
+#define str_to_int64(p_item, error, t_sep)                                     \
+  PandasParserAPI->str_to_int64((p_item), (error), (t_sep))
+#define str_to_uint64(state, p_item, error, t_sep)                             \
+  PandasParserAPI->str_to_uint64((state), (p_item), (error), (t_sep))
 #define xstrtod(p, q, decimal, sci, tsep, skip_trailing, error, maybe_int)     \
   PandasParserAPI->xstrtod((p), (q), (decimal), (sci), (tsep),                 \
                            (skip_trailing), (error), (maybe_int))

pandas/_libs/include/pandas/parser/tokenizer.h

@@ -208,10 +208,9 @@ void uint_state_init(uint_state *self);
 
 int uint64_conflict(uint_state *self);
 
-uint64_t str_to_uint64(uint_state *state, const char *p_item, int64_t int_max,
-                       uint64_t uint_max, int *error, char tsep);
-int64_t str_to_int64(const char *p_item, int64_t int_min, int64_t int_max,
-                     int *error, char tsep);
+uint64_t str_to_uint64(uint_state *state, const char *p_item, int *error,
+                       char tsep);
+int64_t str_to_int64(const char *p_item, int *error, char tsep);
 double xstrtod(const char *p, char **q, char decimal, char sci, char tsep,
                int skip_trailing, int *error, int *maybe_int);
 double precise_xstrtod(const char *p, char **q, char decimal, char sci,

pandas/_libs/parsers.pyx

@@ -63,11 +63,6 @@ from numpy cimport (
 cnp.import_array()
 
 from pandas._libs cimport util
-from pandas._libs.util cimport (
-    INT64_MAX,
-    INT64_MIN,
-    UINT64_MAX,
-)
 
 from pandas._libs import lib
 
@@ -281,10 +276,8 @@ cdef extern from "pandas/parser/pd_parser.h":
     int tokenize_all_rows(parser_t *self, const char *encoding_errors) nogil
     int tokenize_nrows(parser_t *self, size_t nrows, const char *encoding_errors) nogil
 
-    int64_t str_to_int64(char *p_item, int64_t int_min,
-                         int64_t int_max, int *error, char tsep) nogil
-    uint64_t str_to_uint64(uint_state *state, char *p_item, int64_t int_max,
-                           uint64_t uint_max, int *error, char tsep) nogil
+    int64_t str_to_int64(char *p_item,  int *error, char tsep) nogil
+    uint64_t str_to_uint64(uint_state *state, char *p_item, int *error, char tsep) nogil
 
     double xstrtod(const char *p, char **q, char decimal,
                    char sci, char tsep, int skip_trailing,
@@ -1855,15 +1848,13 @@ cdef int _try_uint64_nogil(parser_t *parser, int64_t col,
                 data[i] = 0
                 continue
 
-            data[i] = str_to_uint64(state, word, INT64_MAX, UINT64_MAX,
-                                    &error, parser.thousands)
+            data[i] = str_to_uint64(state, word, &error, parser.thousands)
             if error != 0:
                 return error
     else:
         for i in range(lines):
             COLITER_NEXT(it, word)
-            data[i] = str_to_uint64(state, word, INT64_MAX, UINT64_MAX,
-                                    &error, parser.thousands)
+            data[i] = str_to_uint64(state, word, &error, parser.thousands)
             if error != 0:
                 return error
 
@@ -1920,15 +1911,13 @@ cdef int _try_int64_nogil(parser_t *parser, int64_t col,
                 data[i] = NA
                 continue
 
-            data[i] = str_to_int64(word, INT64_MIN, INT64_MAX,
-                                   &error, parser.thousands)
+            data[i] = str_to_int64(word, &error, parser.thousands)
             if error != 0:
                 return error
     else:
         for i in range(lines):
             COLITER_NEXT(it, word)
-            data[i] = str_to_int64(word, INT64_MIN, INT64_MAX,
-                                   &error, parser.thousands)
+            data[i] = str_to_int64(word, &error, parser.thousands)
             if error != 0:
                 return error