Merge branch 'main' into fix/as_index_false_returns_multiindex

Author: undermyumbrella1

ci/code_checks.sh

@@ -80,10 +80,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.CategoricalIndex.codes SA01" \
         -i "pandas.CategoricalIndex.ordered SA01" \
         -i "pandas.DataFrame.__dataframe__ SA01" \
-        -i "pandas.DataFrame.__iter__ SA01" \
         -i "pandas.DataFrame.at_time PR01" \
-        -i "pandas.DataFrame.columns SA01" \
-        -i "pandas.DataFrame.droplevel SA01" \
         -i "pandas.DataFrame.hist RT03" \
         -i "pandas.DataFrame.infer_objects RT03" \
         -i "pandas.DataFrame.kurt RT03,SA01" \
@@ -93,7 +90,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.median RT03,SA01" \
         -i "pandas.DataFrame.min RT03" \
         -i "pandas.DataFrame.plot PR02,SA01" \
-        -i "pandas.DataFrame.pop SA01" \
         -i "pandas.DataFrame.prod RT03" \
         -i "pandas.DataFrame.product RT03" \
         -i "pandas.DataFrame.reorder_levels SA01" \
@@ -107,67 +103,49 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.to_markdown SA01" \
         -i "pandas.DataFrame.to_parquet RT03" \
         -i "pandas.DataFrame.var PR01,RT03,SA01" \
-        -i "pandas.DatetimeIndex.ceil SA01" \
-        -i "pandas.DatetimeIndex.date SA01" \
         -i "pandas.DatetimeIndex.day_of_year SA01" \
         -i "pandas.DatetimeIndex.dayofyear SA01" \
-        -i "pandas.DatetimeIndex.floor SA01" \
         -i "pandas.DatetimeIndex.freqstr SA01" \
         -i "pandas.DatetimeIndex.indexer_at_time PR01,RT03" \
         -i "pandas.DatetimeIndex.indexer_between_time RT03" \
         -i "pandas.DatetimeIndex.inferred_freq SA01" \
         -i "pandas.DatetimeIndex.is_leap_year SA01" \
-        -i "pandas.DatetimeIndex.quarter SA01" \
-        -i "pandas.DatetimeIndex.round SA01" \
-        -i "pandas.DatetimeIndex.snap PR01,RT03,SA01" \
+        -i "pandas.DatetimeIndex.snap PR01,RT03" \
         -i "pandas.DatetimeIndex.std PR01,RT03" \
-        -i "pandas.DatetimeIndex.time SA01" \
-        -i "pandas.DatetimeIndex.timetz SA01" \
         -i "pandas.DatetimeIndex.to_period RT03" \
         -i "pandas.DatetimeIndex.to_pydatetime RT03,SA01" \
-        -i "pandas.DatetimeIndex.tz SA01" \
         -i "pandas.DatetimeIndex.tz_convert RT03" \
         -i "pandas.DatetimeTZDtype SA01" \
         -i "pandas.DatetimeTZDtype.tz SA01" \
         -i "pandas.DatetimeTZDtype.unit SA01" \
         -i "pandas.Grouper PR02" \
-        -i "pandas.HDFStore.info RT03,SA01" \
-        -i "pandas.HDFStore.keys SA01" \
         -i "pandas.HDFStore.put PR01,SA01" \
-        -i "pandas.HDFStore.select SA01" \
         -i "pandas.HDFStore.walk SA01" \
         -i "pandas.Index PR07" \
         -i "pandas.Index.T SA01" \
         -i "pandas.Index.append PR07,RT03,SA01" \
-        -i "pandas.Index.astype SA01" \
         -i "pandas.Index.copy PR07,SA01" \
         -i "pandas.Index.difference PR07,RT03,SA01" \
         -i "pandas.Index.drop PR07,SA01" \
         -i "pandas.Index.drop_duplicates RT03" \
         -i "pandas.Index.droplevel RT03,SA01" \
         -i "pandas.Index.dropna RT03,SA01" \
-        -i "pandas.Index.dtype SA01" \
         -i "pandas.Index.duplicated RT03" \
         -i "pandas.Index.empty GL08" \
-        -i "pandas.Index.equals SA01" \
         -i "pandas.Index.fillna RT03" \
         -i "pandas.Index.get_indexer PR07,SA01" \
         -i "pandas.Index.get_indexer_for PR01,SA01" \
         -i "pandas.Index.get_indexer_non_unique PR07,SA01" \
         -i "pandas.Index.get_loc PR07,RT03,SA01" \
         -i "pandas.Index.get_slice_bound PR07" \
-        -i "pandas.Index.hasnans SA01" \
         -i "pandas.Index.identical PR01,SA01" \
         -i "pandas.Index.inferred_type SA01" \
         -i "pandas.Index.insert PR07,RT03,SA01" \
         -i "pandas.Index.intersection PR07,RT03,SA01" \
         -i "pandas.Index.item SA01" \
         -i "pandas.Index.join PR07,RT03,SA01" \
-        -i "pandas.Index.map SA01" \
         -i "pandas.Index.memory_usage RT03" \
-        -i "pandas.Index.name SA01" \
         -i "pandas.Index.names GL08" \
-        -i "pandas.Index.nbytes SA01" \
         -i "pandas.Index.nunique RT03" \
         -i "pandas.Index.putmask PR01,RT03" \
         -i "pandas.Index.ravel PR01,RT03" \
@@ -287,34 +265,28 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.cat.reorder_categories PR01,PR02" \
         -i "pandas.Series.cat.set_categories PR01,PR02" \
         -i "pandas.Series.div PR07" \
-        -i "pandas.Series.droplevel SA01" \
         -i "pandas.Series.dt.as_unit PR01,PR02" \
-        -i "pandas.Series.dt.ceil PR01,PR02,SA01" \
+        -i "pandas.Series.dt.ceil PR01,PR02" \
         -i "pandas.Series.dt.components SA01" \
-        -i "pandas.Series.dt.date SA01" \
         -i "pandas.Series.dt.day_name PR01,PR02" \
         -i "pandas.Series.dt.day_of_year SA01" \
         -i "pandas.Series.dt.dayofyear SA01" \
         -i "pandas.Series.dt.days SA01" \
         -i "pandas.Series.dt.days_in_month SA01" \
         -i "pandas.Series.dt.daysinmonth SA01" \
-        -i "pandas.Series.dt.floor PR01,PR02,SA01" \
+        -i "pandas.Series.dt.floor PR01,PR02" \
         -i "pandas.Series.dt.freq GL08" \
         -i "pandas.Series.dt.is_leap_year SA01" \
         -i "pandas.Series.dt.microseconds SA01" \
         -i "pandas.Series.dt.month_name PR01,PR02" \
         -i "pandas.Series.dt.nanoseconds SA01" \
         -i "pandas.Series.dt.normalize PR01" \
-        -i "pandas.Series.dt.quarter SA01" \
         -i "pandas.Series.dt.qyear GL08" \
-        -i "pandas.Series.dt.round PR01,PR02,SA01" \
+        -i "pandas.Series.dt.round PR01,PR02" \
         -i "pandas.Series.dt.seconds SA01" \
         -i "pandas.Series.dt.strftime PR01,PR02" \
-        -i "pandas.Series.dt.time SA01" \
-        -i "pandas.Series.dt.timetz SA01" \
         -i "pandas.Series.dt.to_period PR01,PR02,RT03" \
         -i "pandas.Series.dt.total_seconds PR01" \
-        -i "pandas.Series.dt.tz SA01" \
         -i "pandas.Series.dt.tz_convert PR01,PR02,RT03" \
         -i "pandas.Series.dt.tz_localize PR01,PR02" \
         -i "pandas.Series.dt.unit GL08" \
@@ -344,7 +316,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.mod PR07" \
         -i "pandas.Series.mode SA01" \
         -i "pandas.Series.mul PR07" \
-        -i "pandas.Series.nbytes SA01" \
         -i "pandas.Series.ne PR07,SA01" \
         -i "pandas.Series.nunique RT03" \
         -i "pandas.Series.pad PR01,SA01" \
@@ -432,14 +403,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.total_seconds SA01" \
         -i "pandas.Timedelta.view SA01" \
         -i "pandas.TimedeltaIndex.as_unit RT03,SA01" \
-        -i "pandas.TimedeltaIndex.ceil SA01" \
         -i "pandas.TimedeltaIndex.components SA01" \
         -i "pandas.TimedeltaIndex.days SA01" \
-        -i "pandas.TimedeltaIndex.floor SA01" \
         -i "pandas.TimedeltaIndex.inferred_freq SA01" \
         -i "pandas.TimedeltaIndex.microseconds SA01" \
         -i "pandas.TimedeltaIndex.nanoseconds SA01" \
-        -i "pandas.TimedeltaIndex.round SA01" \
         -i "pandas.TimedeltaIndex.seconds SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp PR07,SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -458,6 +458,7 @@ Other
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which caused an exception when using NumPy attributes via ``@`` notation, e.g., ``df.eval("@np.floor(a)")``. (:issue:`58041`)
+- Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which did not allow to use ``tan`` function. (:issue:`55091`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)
 - Bug in :meth:`DataFrame.transform` that was returning the wrong order unless the index was monotonically increasing. (:issue:`57069`)
 - Bug in :meth:`DataFrame.where` where using a non-bool type array in the function would return a ``ValueError`` instead of a ``TypeError`` (:issue:`56330`)

pandas/_libs/lib.pyx

@@ -477,7 +477,7 @@ def has_infs(const floating[:] arr) -> bool:
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def has_only_ints_or_nan(floating[:] arr) -> bool:
+def has_only_ints_or_nan(const floating[:] arr) -> bool:
     cdef:
         floating val
         intp_t i
@@ -631,7 +631,7 @@ ctypedef fused int6432_t:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def is_range_indexer(ndarray[int6432_t, ndim=1] left, Py_ssize_t n) -> bool:
+def is_range_indexer(const int6432_t[:] left, Py_ssize_t n) -> bool:
     """
     Perform an element by element comparison on 1-d integer arrays, meant for indexer
     comparisons
@@ -652,7 +652,7 @@ def is_range_indexer(ndarray[int6432_t, ndim=1] left, Py_ssize_t n) -> bool:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def is_sequence_range(ndarray[int6432_t, ndim=1] sequence, int64_t step) -> bool:
+def is_sequence_range(const int6432_t[:] sequence, int64_t step) -> bool:
     """
     Check if sequence is equivalent to a range with the specified step.
     """

pandas/_libs/reshape.pyx

@@ -19,7 +19,7 @@ from pandas._libs.lib cimport c_is_list_like
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def unstack(numeric_object_t[:, :] values, const uint8_t[:] mask,
+def unstack(const numeric_object_t[:, :] values, const uint8_t[:] mask,
             Py_ssize_t stride, Py_ssize_t length, Py_ssize_t width,
             numeric_object_t[:, :] new_values, uint8_t[:, :] new_mask) -> None:
     """
@@ -80,7 +80,7 @@ def unstack(numeric_object_t[:, :] values, const uint8_t[:] mask,
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def explode(ndarray[object] values):
+def explode(object[:] values):
     """
     transform array list-likes to long form
     preserve non-list entries

pandas/core/arrays/datetimelike.py

@@ -1825,6 +1825,11 @@ def strftime(self, date_format: str) -> npt.NDArray[np.object_]:
     ------
     ValueError if the `freq` cannot be converted.
 
+    See Also
+    --------
+    DatetimeIndex.floor : Perform floor operation on the data to the specified `freq`.
+    DatetimeIndex.snap : Snap time stamps to nearest occurring frequency.
+
     Notes
     -----
     If the timestamps have a timezone, {op}ing will take place relative to the

pandas/core/arrays/datetimes.py

@@ -593,6 +593,13 @@ def tz(self) -> tzinfo | None:
         datetime.tzinfo, pytz.tzinfo.BaseTZInfo, dateutil.tz.tz.tzfile, or None
             Returns None when the array is tz-naive.
 
+        See Also
+        --------
+        DatetimeIndex.tz_localize : Localize tz-naive DatetimeIndex to a
+            given time zone, or remove timezone from a tz-aware DatetimeIndex.
+        DatetimeIndex.tz_convert : Convert tz-aware DatetimeIndex from
+            one time zone to another.
+
         Examples
         --------
         For Series:
@@ -1391,6 +1398,14 @@ def time(self) -> npt.NDArray[np.object_]:
 
         The time part of the Timestamps.
 
+        See Also
+        --------
+        DatetimeIndex.timetz : Returns numpy array of :class:`datetime.time`
+            objects with timezones. The time part of the Timestamps.
+        DatetimeIndex.date : Returns numpy array of python :class:`datetime.date`
+            objects. Namely, the date part of Timestamps without time and timezone
+            information.
+
         Examples
         --------
         For Series:
@@ -1428,6 +1443,12 @@ def timetz(self) -> npt.NDArray[np.object_]:
 
         The time part of the Timestamps.
 
+        See Also
+        --------
+        DatetimeIndex.time : Returns numpy array of :class:`datetime.time` objects.
+            The time part of the Timestamps.
+        DatetimeIndex.tz : Return the timezone.
+
         Examples
         --------
         For Series:
@@ -1462,6 +1483,14 @@ def date(self) -> npt.NDArray[np.object_]:
         Namely, the date part of Timestamps without time and
         timezone information.
 
+        See Also
+        --------
+        DatetimeIndex.time : Returns numpy array of :class:`datetime.time` objects.
+            The time part of the Timestamps.
+        DatetimeIndex.year : The year of the datetime.
+        DatetimeIndex.month : The month as January=1, December=12.
+        DatetimeIndex.day : The day of the datetime.
+
         Examples
         --------
         For Series:
@@ -1836,6 +1865,12 @@ def isocalendar(self) -> DataFrame:
         """
         The quarter of the date.
 
+        See Also
+        --------
+        DatetimeIndex.snap : Snap time stamps to nearest occurring frequency.
+        DatetimeIndex.time : Returns numpy array of datetime.time objects.
+            The time part of the Timestamps.
+
         Examples
         --------
         For Series:

pandas/core/base.py

@@ -419,6 +419,11 @@ def nbytes(self) -> int:
         """
         Return the number of bytes in the underlying data.
 
+        See Also
+        --------
+        Series.ndim : Number of dimensions of the underlying data.
+        Series.size : Return the number of elements in the underlying data.
+
         Examples
         --------
         For Series:

pandas/core/computation/ops.py

@@ -45,6 +45,7 @@
 _unary_math_ops = (
     "sin",
     "cos",
+    "tan",
     "exp",
     "log",
     "expm1",

pandas/core/frame.py

@@ -4012,7 +4012,6 @@ def _get_value(self, index, col, takeable: bool = False) -> Scalar:
             return series._values[index]
 
         series = self._get_item(col)
-        engine = self.index._engine
 
         if not isinstance(self.index, MultiIndex):
             # CategoricalIndex: Trying to use the engine fastpath may give incorrect
@@ -4023,7 +4022,7 @@ def _get_value(self, index, col, takeable: bool = False) -> Scalar:
 
         # For MultiIndex going through engine effectively restricts us to
         #  same-length tuples; see test_get_set_value_no_partial_indexing
-        loc = engine.get_loc(index)
+        loc = self.index._engine.get_loc(index)
         return series._values[loc]
 
     def isetitem(self, loc, value) -> None:
@@ -5535,6 +5534,11 @@ def pop(self, item: Hashable) -> Series:
         Series
             Series representing the item that is dropped.
 
+        See Also
+        --------
+        DataFrame.drop: Drop specified labels from rows or columns.
+        DataFrame.drop_duplicates: Return DataFrame with duplicate rows removed.
+
         Examples
         --------
         >>> df = pd.DataFrame(
@@ -12893,6 +12897,11 @@ def isin_(x):
             """
                 The column labels of the DataFrame.
 
+                See Also
+                --------
+                DataFrame.index: The index (row labels) of the DataFrame.
+                DataFrame.axes: Return a list representing the axes of the DataFrame.
+
                 Examples
                 --------
                 >>> df = pd.DataFrame({'A': [1, 2], 'B': [3, 4]})
@@ -12921,12 +12930,12 @@ def _to_dict_of_blocks(self):
         Return a dict of dtype -> Constructor Types that
         each is a homogeneous dtype.
 
-        Internal ONLY - only works for BlockManager
+        Internal ONLY.
         """
         mgr = self._mgr
         return {
             k: self._constructor_from_mgr(v, axes=v.axes).__finalize__(self)
-            for k, v in mgr.to_dict().items()
+            for k, v in mgr.to_iter_dict()
         }
 
     @property

pandas/core/generic.py

@@ -783,6 +783,12 @@ def droplevel(self, level: IndexLabel, axis: Axis = 0) -> Self:
         {klass}
             {klass} with requested index / column level(s) removed.
 
+        See Also
+        --------
+        DataFrame.replace : Replace values given in `to_replace` with `value`.
+        DataFrame.pivot : Return reshaped DataFrame organized by given
+            index / column values.
+
         Examples
         --------
         >>> df = (
@@ -1862,6 +1868,11 @@ def __iter__(self) -> Iterator:
         iterator
             Info axis as iterator.
 
+        See Also
+        --------
+        DataFrame.items : Iterate over (column name, Series) pairs.
+        DataFrame.itertuples : Iterate over DataFrame rows as namedtuples.
+
         Examples
         --------
         >>> df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})

pandas/core/indexers/objects.py

@@ -53,11 +53,8 @@ class BaseIndexer:
     >>> from pandas.api.indexers import BaseIndexer
     >>> class CustomIndexer(BaseIndexer):
     ...     def get_window_bounds(self, num_values, min_periods, center, closed, step):
-    ...         start = np.empty(num_values, dtype=np.int64)
-    ...         end = np.empty(num_values, dtype=np.int64)
-    ...         for i in range(num_values):
-    ...             start[i] = i
-    ...             end[i] = i + self.window_size
+    ...         start = np.arange(num_values, dtype=np.int64)
+    ...         end = np.arange(num_values, dtype=np.int64) + self.window_size
     ...         return start, end
     >>> df = pd.DataFrame({"values": range(5)})
     >>> indexer = CustomIndexer(window_size=2)