CLN: assorted (#51775)

* CLN: assorted

* more specific

* more accurate

Author: jbrockmendel

doc/source/whatsnew/v2.0.0.rst

@@ -790,7 +790,6 @@ Other API changes
 Deprecations
 ~~~~~~~~~~~~
 - Deprecated parsing datetime strings with system-local timezone to ``tzlocal``, pass a ``tz`` keyword or explicitly call ``tz_localize`` instead (:issue:`50791`)
-- Deprecated silently dropping unrecognized timezones when parsing strings to datetimes (:issue:`18702`)
 - Deprecated argument ``infer_datetime_format`` in :func:`to_datetime` and :func:`read_csv`, as a strict version of it is now the default (:issue:`48621`)
 - Deprecated behavior of :func:`to_datetime` with ``unit`` when parsing strings, in a future version these will be parsed as datetimes (matching unit-less behavior) instead of cast to floats. To retain the old behavior, cast strings to numeric types before calling :func:`to_datetime` (:issue:`50735`)
 - Deprecated :func:`pandas.io.sql.execute` (:issue:`50185`)

doc/source/whatsnew/v2.1.0.rst

@@ -92,6 +92,7 @@ Other API changes
 
 Deprecations
 ~~~~~~~~~~~~
+- Deprecated silently dropping unrecognized timezones when parsing strings to datetimes (:issue:`18702`)
 - Deprecating pinning ``group.name`` to each group in :meth:`SeriesGroupBy.aggregate` aggregations; if your operation requires utilizing the groupby keys, iterate over the groupby object instead (:issue:`41090`)
 - Deprecated ``axis=1`` in :meth:`DataFrame.groupby` and in :class:`Grouper` constructor, do ``frame.T.groupby(...)`` instead (:issue:`51203`)
 - Deprecated passing a :class:`DataFrame` to :meth:`DataFrame.from_records`, use :meth:`DataFrame.set_index` or :meth:`DataFrame.drop` instead (:issue:`51353`)

pandas/_libs/arrays.pyx

@@ -126,11 +126,12 @@ cdef class NDArrayBacked:
 
     @property
     def size(self) -> int:
-        return self._ndarray.size
+        # TODO(cython3): use self._ndarray.size
+        return cnp.PyArray_SIZE(self._ndarray)
 
     @property
     def nbytes(self) -> int:
-        return self._ndarray.nbytes
+        return cnp.PyArray_NBYTES(self._ndarray)
 
     def copy(self, order="C"):
         cdef:

pandas/_libs/parsers.pyi

@@ -67,3 +67,10 @@ class TextReader:
     def close(self) -> None: ...
     def read(self, rows: int | None = ...) -> dict[int, ArrayLike]: ...
     def read_low_memory(self, rows: int | None) -> list[dict[int, ArrayLike]]: ...
+
+# _maybe_upcast, na_values are only exposed for testing
+na_values: dict
+
+def _maybe_upcast(
+    arr, use_nullable_dtypes: bool = ..., dtype_backend: str = ...
+) -> np.ndarray: ...

pandas/_libs/tslib.pyx

@@ -695,7 +695,7 @@ def array_to_datetime_with_tz(ndarray values, tzinfo tz):
             if ts is NaT:
                 ival = NPY_NAT
             else:
-                if ts.tz is not None:
+                if ts.tzinfo is not None:
                     ts = ts.tz_convert(tz)
                 else:
                     # datetime64, tznaive pydatetime, int, float

pandas/_libs/tslibs/conversion.pyx

@@ -176,6 +176,9 @@ cpdef inline (int64_t, int) precision_from_unit(
         multiplier = periods_per_second(out_reso)
         m = multiplier * 2629746
     else:
+        # Careful: if get_conversion_factor raises, the exception does
+        #  not propagate, instead we get a warning about an ignored exception.
+        #  https://github.com/pandas-dev/pandas/pull/51483#discussion_r1115198951
         m = get_conversion_factor(reso, out_reso)
 
     p = <int>log10(m)  # number of digits in 'm' minus 1

pandas/_libs/tslibs/offsets.pyx

@@ -4096,7 +4096,7 @@ cpdef to_offset(freq):
 
     Returns
     -------
-    DateOffset or None
+    BaseOffset subclass or None
 
     Raises
     ------

pandas/_libs/tslibs/src/datetime/np_datetime.c

@@ -224,29 +224,6 @@ static npy_int64 days_to_yearsdays(npy_int64 *days_) {
     return year + 2000;
 }
 
-/*
- * Adjusts a datetimestruct based on a seconds offset. Assumes
- * the current values are valid.
- */
-NPY_NO_EXPORT void add_seconds_to_datetimestruct(npy_datetimestruct *dts,
-                                                 int seconds) {
-    int minutes;
-
-    dts->sec += seconds;
-    if (dts->sec < 0) {
-        minutes = dts->sec / 60;
-        dts->sec = dts->sec % 60;
-        if (dts->sec < 0) {
-            --minutes;
-            dts->sec += 60;
-        }
-        add_minutes_to_datetimestruct(dts, minutes);
-    } else if (dts->sec >= 60) {
-        minutes = dts->sec / 60;
-        dts->sec = dts->sec % 60;
-        add_minutes_to_datetimestruct(dts, minutes);
-    }
-}
 
 /*
  * Fills in the year, month, day in 'dts' based on the days

pandas/_libs/tslibs/tzconversion.pyx

@@ -153,7 +153,6 @@ cdef int64_t tz_localize_to_utc_single(
         return val
 
     elif is_utc(tz) or tz is None:
-        # TODO: test with non-nano
         return val
 
     elif is_tzlocal(tz):

pandas/_testing/asserters.py

@@ -1179,8 +1179,8 @@ def assert_frame_equal(
 
     # compare by blocks
     if by_blocks:
-        rblocks = right._to_dict_of_blocks()
-        lblocks = left._to_dict_of_blocks()
+        rblocks = right._to_dict_of_blocks(copy=False)
+        lblocks = left._to_dict_of_blocks(copy=False)
         for dtype in list(set(list(lblocks.keys()) + list(rblocks.keys()))):
             assert dtype in lblocks
             assert dtype in rblocks