pandas-dev · gupta-paras · Oct 12, 2023 · Oct 11, 2023 · Oct 11, 2023 · Oct 11, 2023
diff --git a/doc/source/user_guide/timeseries.rst b/doc/source/user_guide/timeseries.rst
@@ -896,9 +896,9 @@ into ``freq`` keyword arguments. The available date offsets and associated frequ
     :class:`~pandas.tseries.offsets.BQuarterBegin`, ``'BQS'``, "business quarter begin"
     :class:`~pandas.tseries.offsets.FY5253Quarter`, ``'REQ'``, "retail (aka 52-53 week) quarter"
     :class:`~pandas.tseries.offsets.YearEnd`, ``'Y'``, "calendar year end"
-    :class:`~pandas.tseries.offsets.YearBegin`, ``'AS'`` or ``'BYS'``,"calendar year begin"
-    :class:`~pandas.tseries.offsets.BYearEnd`, ``'BA'``, "business year end"
-    :class:`~pandas.tseries.offsets.BYearBegin`, ``'BAS'``, "business year begin"
+    :class:`~pandas.tseries.offsets.YearBegin`, ``'YS'`` or ``'BYS'``,"calendar year begin"
+    :class:`~pandas.tseries.offsets.BYearEnd`, ``'BY'``, "business year end"
+    :class:`~pandas.tseries.offsets.BYearBegin`, ``'BYS'``, "business year begin"
     :class:`~pandas.tseries.offsets.FY5253`, ``'RE'``, "retail (aka 52-53 week) year"
     :class:`~pandas.tseries.offsets.Easter`, None, "Easter holiday"
     :class:`~pandas.tseries.offsets.BusinessHour`, ``'bh'``, "business hour"
@@ -1259,9 +1259,9 @@ frequencies. We will refer to these aliases as *offset aliases*.
     "QS", "quarter start frequency"
     "BQS", "business quarter start frequency"
     "Y", "year end frequency"
-    "BA, BY", "business year end frequency"
-    "AS, YS", "year start frequency"
-    "BAS, BYS", "business year start frequency"
+    "BY", "business year end frequency"
+    "YS", "year start frequency"
+    "BYS", "business year start frequency"
     "h", "hourly frequency"
     "bh", "business hour frequency"
     "cbh", "custom business hour frequency"
@@ -1692,7 +1692,7 @@ the end of the interval.
 .. warning::
 
     The default values for ``label`` and ``closed`` is '**left**' for all
-    frequency offsets except for 'ME', 'Y', 'Q', 'BM', 'BA', 'BQ', and 'W'
+    frequency offsets except for 'ME', 'Y', 'Q', 'BM', 'BY', 'BQ', and 'W'
     which all have a default of 'right'.
 
     This might unintendedly lead to looking ahead, where the value for a later

diff --git a/doc/source/whatsnew/v0.20.0.rst b/doc/source/whatsnew/v0.20.0.rst
@@ -886,11 +886,23 @@ This would happen with a ``lexsorted``, but non-monotonic levels. (:issue:`15622
 
 This is *unchanged* from prior versions, but shown for illustration purposes:
 
-.. ipython:: python
+.. code-block:: python
 
-   df = pd.DataFrame(np.arange(6), columns=['value'],
-                     index=pd.MultiIndex.from_product([list('BA'), range(3)]))
-   df
+   In [81]: df = pd.DataFrame(np.arange(6), columns=['value'],
+      ....:                   index=pd.MultiIndex.from_product([list('BA'), range(3)]))
+      ....:
+   In [82]: df
+
+   Out[82]:
+        value
+   B 0      0
+     1      1
+     2      2
+   A 0      3
+     1      4
+     2      5
+
+   [6 rows x 1 columns]
 
 .. code-block:: python
 

diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst
@@ -348,6 +348,7 @@ I/O
 - Bug in :func:`read_csv` with ``engine="pyarrow"`` where ``usecols`` wasn't working with a csv with no headers (:issue:`54459`)
 - Bug in :func:`read_excel`, with ``engine="xlrd"`` (``xls`` files) erroring when file contains NaNs/Infs (:issue:`54564`)
 - Bug in :func:`to_excel`, with ``OdsWriter`` (``ods`` files) writing boolean/string value (:issue:`54994`)
+- Bug in :meth:`DataFrame.to_json` OverflowError with np.long* dtypes (:issue:`55403`)
 - Bug in :meth:`pandas.read_excel` with an ODS file without cached formatted cell for float values (:issue:`55219`)
 
 Period
@@ -394,6 +395,7 @@ Other
 ^^^^^
 - Bug in :func:`cut` incorrectly allowing cutting of timezone-aware datetimes with timezone-naive bins (:issue:`54964`)
 - Bug in :meth:`DataFrame.apply` where passing ``raw=True`` ignored ``args`` passed to the applied function (:issue:`55009`)
+- Bug in rendering ``inf`` values inside a a :class:`DataFrame` with the ``use_inf_as_na`` option enabled (:issue:`55483`)
 - Bug in rendering a :class:`Series` with a :class:`MultiIndex` when one of the index level's names is 0 not having that name displayed (:issue:`55415`)
 -
 

diff --git a/pandas/_libs/include/pandas/vendored/ujson/lib/ultrajson.h b/pandas/_libs/include/pandas/vendored/ujson/lib/ultrajson.h
@@ -138,19 +138,20 @@ typedef int64_t JSLONG;
 #endif
 
 enum JSTYPES {
-  JT_NULL,     // NULL
-  JT_TRUE,     // boolean true
-  JT_FALSE,    // boolean false
-  JT_INT,      // (JSINT32 (signed 32-bit))
-  JT_LONG,     // (JSINT64 (signed 64-bit))
-  JT_DOUBLE,   // (double)
-  JT_BIGNUM,   // integer larger than sys.maxsize
-  JT_UTF8,     // (char 8-bit)
-  JT_ARRAY,    // Array structure
-  JT_OBJECT,   // Key/Value structure
-  JT_INVALID,  // Internal, do not return nor expect
-  JT_POS_INF,  // Positive infinity
-  JT_NEG_INF,  // Negative infinity
+  JT_NULL,        // NULL
+  JT_TRUE,        // boolean true
+  JT_FALSE,       // boolean false
+  JT_INT,         // (JSINT32 (signed 32-bit))
+  JT_LONG,        // (JSINT64 (signed 64-bit))
+  JT_DOUBLE,      // (double)
+  JT_BIGNUM,      // integer larger than sys.maxsize
+  JT_UTF8,        // (char 8-bit)
+  JT_ARRAY,       // Array structure
+  JT_OBJECT,      // Key/Value structure
+  JT_INVALID,     // Internal, do not return nor expect
+  JT_POS_INF,     // Positive infinity
+  JT_NEG_INF,     // Negative infinity
+  JT_LONG_DOUBLE  // Long Double
 };
 
 typedef void * JSOBJ;
@@ -181,7 +182,7 @@ typedef struct __JSONObjectEncoder {
                                 size_t *_outLen);
   JSINT64 (*getLongValue)(JSOBJ obj, JSONTypeContext *tc);
   JSINT32 (*getIntValue)(JSOBJ obj, JSONTypeContext *tc);
-  double (*getDoubleValue)(JSOBJ obj, JSONTypeContext *tc);
+  long double (*getLongDoubleValue)(JSOBJ obj, JSONTypeContext *tc);
   const char *(*getBigNumStringValue)(JSOBJ obj, JSONTypeContext *tc,
                                 size_t *_outLen);
 

diff --git a/pandas/_libs/missing.pyi b/pandas/_libs/missing.pyi
@@ -14,4 +14,3 @@ def isneginf_scalar(val: object) -> bool: ...
 def checknull(val: object, inf_as_na: bool = ...) -> bool: ...
 def isnaobj(arr: np.ndarray, inf_as_na: bool = ...) -> npt.NDArray[np.bool_]: ...
 def is_numeric_na(values: np.ndarray) -> npt.NDArray[np.bool_]: ...
-def is_float_nan(values: np.ndarray) -> npt.NDArray[np.bool_]: ...
diff --git a/pandas/_libs/missing.pyx b/pandas/_libs/missing.pyx
@@ -255,31 +255,6 @@ cdef bint checknull_with_nat_and_na(object obj):
     return checknull_with_nat(obj) or obj is C_NA
 
 
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def is_float_nan(values: ndarray) -> ndarray:
-    """
-    True for elements which correspond to a float nan
-
-    Returns
-    -------
-    ndarray[bool]
-    """
-    cdef:
-        ndarray[uint8_t] result
-        Py_ssize_t i, N
-        object val
-
-    N = len(values)
-    result = np.zeros(N, dtype=np.uint8)
-
-    for i in range(N):
-        val = values[i]
-        if util.is_nan(val):
-            result[i] = True
-    return result.view(bool)
-
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def is_numeric_na(values: ndarray) -> ndarray:

diff --git a/pandas/_libs/src/vendored/ujson/lib/ultrajsonenc.c b/pandas/_libs/src/vendored/ujson/lib/ultrajsonenc.c
@@ -74,7 +74,7 @@ The extra 2 bytes are for the quotes around the string
 */
 #define RESERVE_STRING(_len) (2 + ((_len)*6))
 
-static const double g_pow10[] = {1,
+static const long double g_pow10[] = {1,
                                  10,
                                  100,
                                  1000,
@@ -784,29 +784,29 @@ void Buffer_AppendLongUnchecked(JSONObjectEncoder *enc, JSINT64 value) {
     enc->offset += (wstr - (enc->offset));
 }
 
-int Buffer_AppendDoubleUnchecked(JSOBJ obj, JSONObjectEncoder *enc,
-                                 double value) {
+int Buffer_AppendLongDoubleUnchecked(JSOBJ obj, JSONObjectEncoder *enc,
+                                 long double value) {
     /* if input is beyond the thresholds, revert to exponential */
-    const double thres_max = (double)1e16 - 1;
-    const double thres_min = (double)1e-15;
+    const long double thres_max = (long double)1e16 - 1;
+    const long double thres_min = (long double)1e-15;
     char precision_str[20];
     int count;
-    double diff = 0.0;
+    long double diff = 0.0;
     char *str = enc->offset;
     char *wstr = str;
     unsigned long long whole;
-    double tmp;
+    long double tmp;
     unsigned long long frac;
     int neg;
-    double pow10;
+    long double pow10;
 
     if (value == HUGE_VAL || value == -HUGE_VAL) {
-        SetError(obj, enc, "Invalid Inf value when encoding double");
+        SetError(obj, enc, "Invalid Inf value when encoding long double");
         return FALSE;
     }
 
     if (!(value == value)) {
-        SetError(obj, enc, "Invalid Nan value when encoding double");
+        SetError(obj, enc, "Invalid Nan value when encoding long double");
         return FALSE;
     }
 
@@ -942,7 +942,7 @@ void encode(JSOBJ obj, JSONObjectEncoder *enc, const char *name,
     This reservation must hold
 
     length of _name as encoded worst case +
-    maxLength of double to string OR maxLength of JSLONG to string
+    maxLength of long double to string OR maxLength of JSLONG to string
     */
 
     Buffer_Reserve(enc, 256 + RESERVE_STRING(cbName));
@@ -1076,9 +1076,9 @@ void encode(JSOBJ obj, JSONObjectEncoder *enc, const char *name,
             break;
         }
 
-        case JT_DOUBLE: {
-            if (!Buffer_AppendDoubleUnchecked(obj, enc,
-                                              enc->getDoubleValue(obj, &tc))) {
+        case JT_LONG_DOUBLE: {
+            if (!Buffer_AppendLongDoubleUnchecked(obj, enc,
+                                              enc->getLongDoubleValue(obj, &tc))) {
                 enc->endTypeContext(obj, &tc);
                 enc->level--;
                 return;

diff --git a/pandas/_libs/src/vendored/ujson/python/objToJSON.c b/pandas/_libs/src/vendored/ujson/python/objToJSON.c
@@ -105,7 +105,7 @@ typedef struct __TypeContext {
     PyObject *attrList;
     PyObject *iterator;
 
-    double doubleValue;
+    long double longDoubleValue;
     JSINT64 longValue;
 
     char *cStr;
@@ -164,7 +164,7 @@ static TypeContext *createTypeContext(void) {
     pc->index = 0;
     pc->size = 0;
     pc->longValue = 0;
-    pc->doubleValue = 0.0;
+    pc->longDoubleValue = (long double) 0.0;
     pc->cStr = NULL;
     pc->npyarr = NULL;
     pc->pdblock = NULL;
@@ -1494,8 +1494,8 @@ void Object_beginTypeContext(JSOBJ _obj, JSONTypeContext *tc) {
         if (npy_isnan(val) || npy_isinf(val)) {
             tc->type = JT_NULL;
         } else {
-            pc->doubleValue = val;
-            tc->type = JT_DOUBLE;
+            pc->longDoubleValue = (long double) val;
+            tc->type = JT_LONG_DOUBLE;
         }
         return;
     } else if (PyBytes_Check(obj)) {
@@ -1507,8 +1507,8 @@ void Object_beginTypeContext(JSOBJ _obj, JSONTypeContext *tc) {
         tc->type = JT_UTF8;
         return;
     } else if (object_is_decimal_type(obj)) {
-        pc->doubleValue = PyFloat_AsDouble(obj);
-        tc->type = JT_DOUBLE;
+        pc->longDoubleValue = (long double) PyFloat_AsDouble(obj);
+        tc->type = JT_LONG_DOUBLE;
         return;
     } else if (PyDateTime_Check(obj) || PyDate_Check(obj)) {
         if (object_is_nat_type(obj)) {
@@ -1605,10 +1605,16 @@ void Object_beginTypeContext(JSOBJ _obj, JSONTypeContext *tc) {
                                   PyArray_DescrFromType(NPY_BOOL));
         tc->type = (pc->longValue) ? JT_TRUE : JT_FALSE;
         return;
-    } else if (PyArray_IsScalar(obj, Float) || PyArray_IsScalar(obj, Double)) {
-        PyArray_CastScalarToCtype(obj, &(pc->doubleValue),
+    } else if (PyArray_IsScalar(obj, Float) ||
+               PyArray_IsScalar(obj, Double)) {
+        PyArray_CastScalarToCtype(obj, &(pc->longDoubleValue),
                                   PyArray_DescrFromType(NPY_DOUBLE));
-        tc->type = JT_DOUBLE;
+        tc->type = JT_LONG_DOUBLE;
+        return;
+    } else if (PyArray_IsScalar(obj, LongDouble)) {
+        PyArray_CastScalarToCtype(obj, &(pc->longDoubleValue),
+                                  PyArray_DescrFromType(NPY_LONGDOUBLE));
+        tc->type = JT_LONG_DOUBLE;
         return;
     } else if (PyArray_Check(obj) && PyArray_CheckScalar(obj)) {
         PyErr_Format(PyExc_TypeError,
@@ -1925,8 +1931,8 @@ JSINT64 Object_getLongValue(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
     return GET_TC(tc)->longValue;
 }
 
-double Object_getDoubleValue(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
-    return GET_TC(tc)->doubleValue;
+long double Object_getLongDoubleValue(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
+    return GET_TC(tc)->longDoubleValue;
 }
 
 const char *Object_getBigNumStringValue(JSOBJ obj, JSONTypeContext *tc,
@@ -1970,7 +1976,6 @@ PyObject *objToJSON(PyObject *Py_UNUSED(self), PyObject *args,
     if (PyDateTimeAPI == NULL) {
         return NULL;
     }
-
     PandasDateTime_IMPORT;
     if (PandasDateTimeAPI == NULL) {
         return NULL;
@@ -2006,7 +2011,7 @@ PyObject *objToJSON(PyObject *Py_UNUSED(self), PyObject *args,
         Object_getStringValue,
         Object_getLongValue,
         NULL,  // getIntValue is unused
-        Object_getDoubleValue,
+        Object_getLongDoubleValue,
         Object_getBigNumStringValue,
         Object_iterBegin,
         Object_iterNext,

diff --git a/pandas/_libs/tslibs/dtypes.pyx b/pandas/_libs/tslibs/dtypes.pyx
@@ -192,9 +192,6 @@ OFFSET_TO_PERIOD_FREQSTR: dict = {
     "BQS": "Q",
     "QS": "Q",
     "BQ": "Q",
-    "BA": "Y",
-    "AS": "Y",
-    "BAS": "Y",
     "MS": "M",
     "D": "D",
     "B": "B",
@@ -205,9 +202,9 @@ OFFSET_TO_PERIOD_FREQSTR: dict = {
     "ns": "ns",
     "h": "h",
     "Q": "Q",
-    "Y": "Y",
     "W": "W",
     "ME": "M",
+    "Y": "Y",
     "BY": "Y",
     "YS": "Y",
     "BYS": "Y",
@@ -244,6 +241,45 @@ DEPR_ABBREVS: dict[str, str]= {
     "A-SEP": "Y-SEP",
     "A-OCT": "Y-OCT",
     "A-NOV": "Y-NOV",
+    "BA": "BY",
+    "BA-DEC": "BY-DEC",
+    "BA-JAN": "BY-JAN",
+    "BA-FEB": "BY-FEB",
+    "BA-MAR": "BY-MAR",
+    "BA-APR": "BY-APR",
+    "BA-MAY": "BY-MAY",
+    "BA-JUN": "BY-JUN",
+    "BA-JUL": "BY-JUL",
+    "BA-AUG": "BY-AUG",
+    "BA-SEP": "BY-SEP",
+    "BA-OCT": "BY-OCT",
+    "BA-NOV": "BY-NOV",
+    "AS": "YS",
+    "AS-DEC": "YS-DEC",
+    "AS-JAN": "YS-JAN",
+    "AS-FEB": "YS-FEB",
+    "AS-MAR": "YS-MAR",
+    "AS-APR": "YS-APR",
+    "AS-MAY": "YS-MAY",
+    "AS-JUN": "YS-JUN",
+    "AS-JUL": "YS-JUL",
+    "AS-AUG": "YS-AUG",
+    "AS-SEP": "YS-SEP",
+    "AS-OCT": "YS-OCT",
+    "AS-NOV": "YS-NOV",
+    "BAS": "BYS",
+    "BAS-DEC": "BYS-DEC",
+    "BAS-JAN": "BYS-JAN",
+    "BAS-FEB": "BYS-FEB",
+    "BAS-MAR": "BYS-MAR",
+    "BAS-APR": "BYS-APR",
+    "BAS-MAY": "BYS-MAY",
+    "BAS-JUN": "BYS-JUN",
+    "BAS-JUL": "BYS-JUL",
+    "BAS-AUG": "BYS-AUG",
+    "BAS-SEP": "BYS-SEP",
+    "BAS-OCT": "BYS-OCT",
+    "BAS-NOV": "BYS-NOV",
     "H": "h",
     "BH": "bh",
     "CBH": "cbh",

diff --git a/pandas/_libs/tslibs/fields.pyx b/pandas/_libs/tslibs/fields.pyx
@@ -253,8 +253,8 @@ def get_start_end_field(
         # month of year. Other offsets use month, startingMonth as ending
         # month of year.
 
-        if (freqstr[0:2] in ["MS", "QS", "AS"]) or (
-                freqstr[1:3] in ["MS", "QS", "AS"]):
+        if (freqstr[0:2] in ["MS", "QS", "YS"]) or (
+                freqstr[1:3] in ["MS", "QS", "YS"]):
             end_month = 12 if month_kw == 1 else month_kw - 1
             start_month = month_kw
         else: