Merge branch 'main' into outofbounds

Author: dannyi96

Diff for: .github/workflows/codeql.yml

@@ -0,0 +1,31 @@
+name: CodeQL
+on:
+  schedule:
+    # every day at midnight
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}
+  cancel-in-progress: true
+
+jobs:
+  analyze:
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language:
+          - python
+
+    steps:
+      - uses: actions/checkout@v3
+      - uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+      - uses: github/codeql-action/autobuild@v2
+      - uses: github/codeql-action/analyze@v2

Diff for: ci/code_checks.sh

@@ -78,8 +78,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05
+    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

Diff for: doc/source/reference/general_functions.rst

@@ -85,4 +85,4 @@ Importing from other DataFrame libraries
 .. autosummary::
    :toctree: api/
 
-   api.exchange.from_dataframe
+   api.interchange.from_dataframe

Diff for: pandas/_config/config.py

@@ -102,8 +102,9 @@ class RegisteredOption(NamedTuple):
 
 class OptionError(AttributeError, KeyError):
     """
-    Exception for pandas.options, backwards compatible with KeyError
-    checks.
+    Exception raised for pandas.options.
+
+    Backwards compatible with KeyError checks.
     """
 
 

Diff for: pandas/_libs/groupby.pyi

@@ -50,7 +50,7 @@ def group_any_all(
     val_test: Literal["any", "all"],
     skipna: bool,
 ) -> None: ...
-def group_add(
+def group_sum(
     out: np.ndarray,  # complexfloating_t[:, ::1]
     counts: np.ndarray,  # int64_t[::1]
     values: np.ndarray,  # ndarray[complexfloating_t, ndim=2]

Diff for: pandas/_libs/groupby.pyx

@@ -124,7 +124,7 @@ def group_median_float64(
         ndarray[intp_t] indexer
         float64_t* ptr
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     ngroups = len(counts)
     N, K = (<object>values).shape
@@ -502,7 +502,7 @@ def group_any_all(
 
 
 # ----------------------------------------------------------------------
-# group_add, group_prod, group_var, group_mean, group_ohlc
+# group_sum, group_prod, group_var, group_mean, group_ohlc
 # ----------------------------------------------------------------------
 
 ctypedef fused mean_t:
@@ -511,17 +511,17 @@ ctypedef fused mean_t:
     complex64_t
     complex128_t
 
-ctypedef fused add_t:
+ctypedef fused sum_t:
     mean_t
     object
 
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def group_add(
-    add_t[:, ::1] out,
+def group_sum(
+    sum_t[:, ::1] out,
     int64_t[::1] counts,
-    ndarray[add_t, ndim=2] values,
+    ndarray[sum_t, ndim=2] values,
     const intp_t[::1] labels,
     Py_ssize_t min_count=0,
     bint is_datetimelike=False,
@@ -531,8 +531,8 @@ def group_add(
     """
     cdef:
         Py_ssize_t i, j, N, K, lab, ncounts = len(counts)
-        add_t val, t, y
-        add_t[:, ::1] sumx, compensation
+        sum_t val, t, y
+        sum_t[:, ::1] sumx, compensation
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
@@ -546,7 +546,7 @@ def group_add(
 
     N, K = (<object>values).shape
 
-    if add_t is object:
+    if sum_t is object:
         # NB: this does not use 'compensation' like the non-object track does.
         for i in range(N):
             lab = labels[i]
@@ -588,10 +588,10 @@ def group_add(
 
                     # not nan
                     # With dt64/td64 values, values have been cast to float64
-                    #  instead if int64 for group_add, but the logic
+                    #  instead if int64 for group_sum, but the logic
                     #  is otherwise the same as in _treat_as_na
                     if val == val and not (
-                        add_t is float64_t
+                        sum_t is float64_t
                         and is_datetimelike
                         and val == <float64_t>NPY_NAT
                     ):
@@ -677,7 +677,7 @@ def group_var(
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len_values != len_labels:
         raise ValueError("len(index) != len(labels)")
@@ -745,7 +745,7 @@ def group_mean(
         Array containing unique label for each group, with its
         ordering matching up to the corresponding record in `values`.
     min_count : Py_ssize_t
-        Only used in add and prod. Always -1.
+        Only used in sum and prod. Always -1.
     is_datetimelike : bool
         True if `values` contains datetime-like entries.
     mask : ndarray[bool, ndim=2], optional
@@ -766,7 +766,7 @@ def group_mean(
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len_values != len_labels:
         raise ValueError("len(index) != len(labels)")
@@ -821,7 +821,7 @@ def group_ohlc(
         Py_ssize_t i, j, N, K, lab
         floating val
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len(labels) == 0:
         return

Diff for: pandas/_libs/interval.pyx

@@ -352,8 +352,9 @@ cdef class Interval(IntervalMixin):
 
     cdef readonly str inclusive
     """
-    Whether the interval is inclusive on the left-side, right-side, both or
-    neither.
+    String describing the inclusive side the intervals.
+
+    Either ``left``, ``right``, ``both`` or ``neither``.
     """
 
     def __init__(self, left, right, inclusive: str | None = None, closed: None | lib.NoDefault = lib.no_default):
@@ -384,10 +385,11 @@ cdef class Interval(IntervalMixin):
     @property
     def closed(self):
         """
-        Whether the interval is closed on the left-side, right-side, both or
-        neither.
+        String describing the inclusive side the intervals.
 
         .. deprecated:: 1.5.0
+
+        Either ``left``, ``right``, ``both`` or ``neither``.
         """
         warnings.warn(
             "Attribute `closed` is deprecated in favor of `inclusive`.",

Diff for: pandas/_libs/lib.pyx

@@ -1347,8 +1347,7 @@ cdef object _try_infer_map(object dtype):
 
 def infer_dtype(value: object, skipna: bool = True) -> str:
     """
-    Efficiently infer the type of a passed val, or list-like
-    array of values. Return a string describing the type.
+    Return a string label of the type of a scalar or list-like of values.
 
     Parameters
     ----------

Diff for: pandas/_libs/tslibs/nattype.pyx

@@ -446,13 +446,15 @@ class NaTType(_NaT):
         "weekday",
         """
         Return the day of the week represented by the date.
+
         Monday == 0 ... Sunday == 6.
         """,
     )
     isoweekday = _make_nan_func(
         "isoweekday",
         """
         Return the day of the week represented by the date.
+
         Monday == 1 ... Sunday == 7.
         """,
     )
@@ -533,10 +535,7 @@ class NaTType(_NaT):
     strftime = _make_error_func(
         "strftime",
         """
-        Timestamp.strftime(format)
-
-        Return a string representing the given POSIX timestamp
-        controlled by an explicit format string.
+        Return a formatted string of the Timestamp.
 
         Parameters
         ----------
@@ -680,10 +679,7 @@ class NaTType(_NaT):
     fromordinal = _make_error_func(
         "fromordinal",
         """
-        Timestamp.fromordinal(ordinal, freq=None, tz=None)
-
-        Passed an ordinal, translate and convert to a ts.
-        Note: by definition there cannot be any tz info on the ordinal itself.
+        Construct a timestamp from a a proleptic Gregorian ordinal.
 
         Parameters
         ----------
@@ -694,6 +690,10 @@ class NaTType(_NaT):
         tz : str, pytz.timezone, dateutil.tz.tzfile or None
             Time zone for the Timestamp.
 
+        Notes
+        -----
+        By definition there cannot be any tz info on the ordinal itself.
+
         Examples
         --------
         >>> pd.Timestamp.fromordinal(737425)
@@ -725,10 +725,7 @@ class NaTType(_NaT):
     now = _make_nat_func(
         "now",
         """
-        Timestamp.now(tz=None)
-
-        Return new Timestamp object representing current time local to
-        tz.
+        Return new Timestamp object representing current time local to tz.
 
         Parameters
         ----------
@@ -749,10 +746,9 @@ class NaTType(_NaT):
     today = _make_nat_func(
         "today",
         """
-        Timestamp.today(cls, tz=None)
+        Return the current time in the local timezone.
 
-        Return the current time in the local timezone.  This differs
-        from datetime.today() in that it can be localized to a
+        This differs from datetime.today() in that it can be localized to a
         passed timezone.
 
         Parameters
@@ -1090,7 +1086,9 @@ timedelta}, default 'raise'
     tz_localize = _make_nat_func(
         "tz_localize",
         """
-        Convert naive Timestamp to local time zone, or remove
+        Localize the Timestamp to a timezone.
+
+        Convert naive Timestamp to local time zone or remove
         timezone from timezone-aware Timestamp.
 
         Parameters

Diff for: pandas/_libs/tslibs/np_datetime.pyx

@@ -156,16 +156,16 @@ cdef inline bint cmp_scalar(int64_t lhs, int64_t rhs, int op) except -1:
 
 class OutOfBoundsDatetime(ValueError):
     """
-    Raised when the datetime is outside the range that
-    can be represented.
+    Raised when the datetime is outside the range that can be represented.
     """
     pass
 
 
 class OutOfBoundsTimedelta(ValueError):
     """
-    Raised when encountering a timedelta value that cannot be represented
-    as a timedelta64[ns].
+    Raised when encountering a timedelta value that cannot be represented.
+
+    Representation should be within a timedelta64[ns].
     """
     # Timedelta analogue to OutOfBoundsDatetime
     pass

Diff for: pandas/_libs/tslibs/offsets.pyx

@@ -585,9 +585,7 @@ cdef class BaseOffset:
 
     def apply_index(self, dtindex):
         """
-        Vectorized apply of DateOffset to DatetimeIndex,
-        raises NotImplementedError for offsets without a
-        vectorized implementation.
+        Vectorized apply of DateOffset to DatetimeIndex.
 
         .. deprecated:: 1.1.0
 
@@ -2448,8 +2446,7 @@ cdef class SemiMonthOffset(SingleConstructorOffset):
 
 cdef class SemiMonthEnd(SemiMonthOffset):
     """
-    Two DateOffset's per month repeating on the last
-    day of the month and day_of_month.
+    Two DateOffset's per month repeating on the last day of the month & day_of_month.
 
     Parameters
     ----------
@@ -2470,8 +2467,7 @@ cdef class SemiMonthEnd(SemiMonthOffset):
 
 cdef class SemiMonthBegin(SemiMonthOffset):
     """
-    Two DateOffset's per month repeating on the first
-    day of the month and day_of_month.
+    Two DateOffset's per month repeating on the first day of the month & day_of_month.
 
     Parameters
     ----------
@@ -2704,8 +2700,9 @@ cdef class WeekOfMonth(WeekOfMonthMixin):
 
 cdef class LastWeekOfMonth(WeekOfMonthMixin):
     """
-    Describes monthly dates in last week of month like "the last Tuesday of
-    each month".
+    Describes monthly dates in last week of month.
+
+    For example "the last Tuesday of each month".
 
     Parameters
     ----------
@@ -2991,8 +2988,9 @@ cdef class FY5253(FY5253Mixin):
 
 cdef class FY5253Quarter(FY5253Mixin):
     """
-    DateOffset increments between business quarter dates
-    for 52-53 week fiscal year (also known as a 4-4-5 calendar).
+    DateOffset increments between business quarter dates for 52-53 week fiscal year.
+
+    Also known as a 4-4-5 calendar.
 
     It is used by companies that desire that their
     fiscal year always end on the same day of the week.
@@ -3602,8 +3600,7 @@ def _get_offset(name: str) -> BaseOffset:
 
 cpdef to_offset(freq):
     """
-    Return DateOffset object from string or tuple representation
-    or datetime.timedelta object.
+    Return DateOffset object from string or datetime.timedelta object.
 
     Parameters
     ----------