Fix Docstring Issues for pandas.Series.sparse.sp_values and pandas.Series.str.match (Issue #59592)

ci/code_checks.sh

@@ -100,7 +100,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.sparse.fill_value SA01" \
         -i "pandas.Series.sparse.from_coo PR07,SA01" \
         -i "pandas.Series.sparse.npoints SA01" \
-        -i "pandas.Series.sparse.sp_values SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \

pandas/core/_numba/kernels/min_max_.py

@@ -112,11 +112,9 @@ def grouped_min_max(
             continue
 
         if is_max:
-            if val > output[lab]:
-                output[lab] = val
+            output[lab] = max(val, output[lab])
         else:
-            if val < output[lab]:
-                output[lab] = val
+            output[lab] = min(val, output[lab])
 
     # Set labels that don't satisfy min_periods as np.nan
     for lab, count in enumerate(nobs):

pandas/core/arrays/sparse/array.py

@@ -601,7 +601,22 @@ def sp_index(self) -> SparseIndex:
     @property
     def sp_values(self) -> np.ndarray:
         """
-        An ndarray containing the non- ``fill_value`` values.
+        An ndarray containing the non-``fill_value`` values.
+
+        This method retrieves the non-fill values from a SparseArray. SparseArrays
+        are designed to efficiently store large arrays of data where most of the
+        elements are the same (the fill value). This method allows you to access
+        the actual data points that differ from the fill value.
+
+        Returns
+        -------
+        ndarray
+            An array containing the non-fill values.
+
+        See Also
+        --------
+        Series.sparse.fill_value : The fill value for the SparseArray.
+        arrays.SparseArray : Represents an array with sparse data.
 
         Examples
         --------
@@ -610,6 +625,7 @@ def sp_values(self) -> np.ndarray:
         >>> s.sp_values
         array([1, 2])
         """
+
         return self._sparse_values
 
     @property

pandas/core/dtypes/astype.py

@@ -125,7 +125,7 @@ def _astype_nansafe(
         )
         raise ValueError(msg)
 
-    if copy or arr.dtype == object or dtype == object:
+    if copy or object in (arr.dtype, dtype):
         # Explicit copy, or required since NumPy can't view from / to object.
         return arr.astype(dtype, copy=True)
 

pandas/core/dtypes/cast.py

@@ -683,9 +683,7 @@ def _maybe_promote(dtype: np.dtype, fill_value=np.nan):
 
         elif dtype.kind == "f":
             mst = np.min_scalar_type(fill_value)
-            if mst > dtype:
-                # e.g. mst is np.float64 and dtype is np.float32
-                dtype = mst
+            dtype = max(mst, dtype)
 
         elif dtype.kind == "c":
             mst = np.min_scalar_type(fill_value)
@@ -718,9 +716,7 @@ def _maybe_promote(dtype: np.dtype, fill_value=np.nan):
 
         elif dtype.kind == "c":
             mst = np.min_scalar_type(fill_value)
-            if mst > dtype:
-                # e.g. mst is np.complex128 and dtype is np.complex64
-                dtype = mst
+            dtype = max(mst, dtype)
 
     else:
         dtype = np.dtype(np.object_)

pandas/core/nanops.py

@@ -460,11 +460,8 @@ def newfunc(values: np.ndarray, *, axis: AxisInt | None = None, **kwargs):
             axis == 1
             and values.ndim == 2
             and values.flags["C_CONTIGUOUS"]
-            # only takes this path for wide arrays (long dataframes), for threshold see
-            # https://github.com/pandas-dev/pandas/pull/43311#issuecomment-974891737
-            and (values.shape[1] / 1000) > values.shape[0]
-            and values.dtype != object
-            and values.dtype != bool
+            and values.shape[1] / 1000 > values.shape[0]
+            and values.dtype not in (object, bool)
         ):
             arrs = list(values)
             if kwargs.get("mask") is not None:

pandas/core/strings/accessor.py

@@ -1366,6 +1366,10 @@ def match(self, pat: str, case: bool = True, flags: int = 0, na=None):
         """
         Determine if each string starts with a match of a regular expression.
 
+        This method checks if each string in the Series starts with a substring
+        that matches the given regular expression pattern. It returns a boolean
+        Series indicating whether each string meets the condition.
+
         Parameters
         ----------
         pat : str
@@ -1402,6 +1406,7 @@ def match(self, pat: str, case: bool = True, flags: int = 0, na=None):
         2   False
         dtype: bool
         """
+
         result = self._data.array._str_match(pat, case=case, flags=flags, na=na)
         return self._wrap_result(result, fill_value=na, returns_string=False)
 

pandas/io/excel/_odfreader.py

@@ -142,8 +142,7 @@ def get_sheet_data(
                         empty_cells = 0
                         table_row.extend([value] * column_repeat)
 
-            if max_row_len < len(table_row):
-                max_row_len = len(table_row)
+            max_row_len = max(max_row_len, len(table_row))
 
             row_repeat = self._get_row_repeat(sheet_row)
             if len(table_row) == 0:

pandas/tests/arithmetic/test_numeric.py

@@ -274,9 +274,7 @@ def test_numeric_arr_rdiv_tdscalar(self, three_days, numeric_idx, box_with_array
         expected = TimedeltaIndex(["3 Days", "36 Hours"])
         if isinstance(three_days, np.timedelta64):
             dtype = three_days.dtype
-            if dtype < np.dtype("m8[s]"):
-                # i.e. resolution is lower -> use lowest supported resolution
-                dtype = np.dtype("m8[s]")
+            dtype = max(dtype, np.dtype("m8[s]"))
             expected = expected.astype(dtype)
         elif type(three_days) is timedelta:
             expected = expected.astype("m8[us]")

pandas/tests/frame/test_query_eval.py

@@ -1388,7 +1388,7 @@ def test_expr_with_column_name_with_backtick_and_hash(self):
     def test_expr_with_column_name_with_backtick(self):
         # GH 59285
         df = DataFrame({"a`b": (1, 2, 3), "ab": (4, 5, 6)})
-        result = df.query("`a``b` < 2")  # noqa
+        result = df.query("`a``b` < 2")
         # Note: Formatting checks may wrongly consider the above ``inline code``.
         expected = df[df["a`b"] < 2]
         tm.assert_frame_equal(result, expected)