STYLE fix: pylint "consider-using-in" warning (#49213)

* consider-using-in

* consider-using-in

* remove consider using in from pyproject.toml to add it to pylint

* after running pre-commit chacks

Co-authored-by: carlotta <[email protected]>

Author: fabinca

pandas/core/computation/pytables.py

@@ -211,15 +211,15 @@ def stringify(value):
 
         kind = ensure_decoded(self.kind)
         meta = ensure_decoded(self.meta)
-        if kind == "datetime64" or kind == "datetime":
+        if kind in ("datetime64", "datetime"):
             if isinstance(v, (int, float)):
                 v = stringify(v)
             v = ensure_decoded(v)
             v = Timestamp(v)
             if v.tz is not None:
                 v = v.tz_convert("UTC")
             return TermValue(v, v.value, kind)
-        elif kind == "timedelta64" or kind == "timedelta":
+        elif kind in ("timedelta64", "timedelta"):
             if isinstance(v, str):
                 v = Timedelta(v).value
             else:

pandas/core/frame.py

@@ -1754,7 +1754,7 @@ def from_dict(
                     # error: Incompatible types in assignment (expression has type
                     # "List[Any]", variable has type "Dict[Any, Any]")
                     data = list(data.values())  # type: ignore[assignment]
-        elif orient == "columns" or orient == "tight":
+        elif orient in ("columns", "tight"):
             if columns is not None:
                 raise ValueError(f"cannot use columns parameter with orient='{orient}'")
         else:  # pragma: no cover

pandas/core/indexes/base.py

@@ -4066,7 +4066,7 @@ def _check_indexing_method(
                     "method='nearest' not implemented yet "
                     "for MultiIndex; see GitHub issue 9365"
                 )
-            elif method == "pad" or method == "backfill":
+            elif method in ("pad", "backfill"):
                 if tolerance is not None:
                     raise NotImplementedError(
                         "tolerance not implemented yet for MultiIndex"

pandas/core/indexes/datetimelike.py

@@ -663,7 +663,7 @@ def _get_insert_freq(self, loc: int, item):
             if self.size:
                 if item is NaT:
                     pass
-                elif (loc == 0 or loc == -len(self)) and item + self.freq == self[0]:
+                elif loc in (0, -len(self)) and item + self.freq == self[0]:
                     freq = self.freq
                 elif (loc == len(self)) and item - self.freq == self[-1]:
                     freq = self.freq

pandas/core/indexes/range.py

@@ -833,11 +833,11 @@ def delete(self, loc) -> Index:  # type: ignore[override]
         # In some cases we can retain RangeIndex, see also
         #  DatetimeTimedeltaMixin._get_delete_Freq
         if is_integer(loc):
-            if loc == 0 or loc == -len(self):
+            if loc in (0, -len(self)):
                 return self[1:]
-            if loc == -1 or loc == len(self) - 1:
+            if loc in (-1, len(self) - 1):
                 return self[:-1]
-            if len(self) == 3 and (loc == 1 or loc == -2):
+            if len(self) == 3 and loc in (1, -2):
                 return self[::2]
 
         elif lib.is_list_like(loc):

pandas/core/nanops.py

@@ -183,7 +183,7 @@ def _bn_ok_dtype(dtype: DtypeObj, name: str) -> bool:
 
 def _has_infs(result) -> bool:
     if isinstance(result, np.ndarray):
-        if result.dtype == "f8" or result.dtype == "f4":
+        if result.dtype in ("f8", "f4"):
             # Note: outside of an nanops-specific test, we always have
             #  result.ndim == 1, so there is no risk of this ravel making a copy.
             return lib.has_infs(result.ravel("K"))

pandas/core/ops/__init__.py

@@ -397,7 +397,7 @@ def _maybe_align_series_as_frame(frame: DataFrame, series: Series, axis: AxisInt
     rvalues = series._values
     if not isinstance(rvalues, np.ndarray):
         # TODO(EA2D): no need to special-case with 2D EAs
-        if rvalues.dtype == "datetime64[ns]" or rvalues.dtype == "timedelta64[ns]":
+        if rvalues.dtype in ("datetime64[ns]", "timedelta64[ns]"):
             # We can losslessly+cheaply cast to ndarray
             rvalues = np.asarray(rvalues)
         else:

pandas/io/formats/excel.py

@@ -277,7 +277,7 @@ def _border_style(self, style: str | None, width: str | None, color: str | None)
             # Return "none" will keep "border" in style dictionary
             return "none"
 
-        if style == "none" or style == "hidden":
+        if style in ("none", "hidden"):
             return "none"
 
         width_name = self._get_width_name(width)

pandas/io/formats/style.py

@@ -4210,7 +4210,7 @@ def css_calc(x, left: float, right: float, align: str, color: str | list | tuple
         z, align = align(values), "zero"
     elif isinstance(align, (float, int)):
         z, align = float(align), "zero"
-    elif not (align == "left" or align == "right" or align == "zero"):
+    elif align not in ("left", "right", "zero"):
         raise ValueError(
             "`align` should be in {'left', 'right', 'mid', 'mean', 'zero'} or be a "
             "value defining the center line or a callable that returns a float"

pandas/io/formats/style_render.py

@@ -2228,14 +2228,14 @@ def _parse_latex_css_conversion(styles: CSSList) -> CSSList:
     """
 
     def font_weight(value, arg):
-        if value == "bold" or value == "bolder":
+        if value in ("bold", "bolder"):
             return "bfseries", f"{arg}"
         return None
 
     def font_style(value, arg):
         if value == "italic":
             return "itshape", f"{arg}"
-        elif value == "oblique":
+        if value == "oblique":
             return "slshape", f"{arg}"
         return None
 

pandas/io/html.py

@@ -527,7 +527,7 @@ def _expand_colspan_rowspan(
 
                 # Append the text from this <td>, colspan times
                 text = _remove_whitespace(self._text_getter(td))
-                if self.extract_links == "all" or self.extract_links == section:
+                if self.extract_links in ("all", section):
                     href = self._href_getter(td)
                     text = (text, href)
                 rowspan = int(self._attr_getter(td, "rowspan") or 1)

pandas/io/json/_json.py

@@ -1146,7 +1146,7 @@ def _try_convert_data(
                     pass
 
         # don't coerce 0-len data
-        if len(data) and (data.dtype == "float" or data.dtype == "object"):
+        if len(data) and data.dtype in ("float", "object"):
 
             # coerce ints if we can
             try:

pandas/io/parsers/python_parser.py

@@ -788,9 +788,9 @@ def _next_iter_line(self, row_num: int) -> list[Scalar] | None:
             assert isinstance(line, list)
             return line
         except csv.Error as e:
-            if (
-                self.on_bad_lines == self.BadLineHandleMethod.ERROR
-                or self.on_bad_lines == self.BadLineHandleMethod.WARN
+            if self.on_bad_lines in (
+                self.BadLineHandleMethod.ERROR,
+                self.BadLineHandleMethod.WARN,
             ):
                 msg = str(e)
 
@@ -1013,9 +1013,9 @@ def _rows_to_cols(self, content: list[list[Scalar]]) -> list[np.ndarray]:
                         new_l = self.on_bad_lines(l)
                         if new_l is not None:
                             content.append(new_l)
-                    elif (
-                        self.on_bad_lines == self.BadLineHandleMethod.ERROR
-                        or self.on_bad_lines == self.BadLineHandleMethod.WARN
+                    elif self.on_bad_lines in (
+                        self.BadLineHandleMethod.ERROR,
+                        self.BadLineHandleMethod.WARN,
                     ):
                         row_num = self.pos - (content_len - i + footers)
                         bad_lines.append((row_num, actual_len))

pandas/io/parsers/readers.py

@@ -2229,7 +2229,7 @@ def _merge_with_dialect_properties(
 
         # Don't warn if the default parameter was passed in,
         # even if it conflicts with the dialect (gh-23761).
-        if provided != parser_default and provided != dialect_val:
+        if provided not in (parser_default, dialect_val):
             msg = (
                 f"Conflicting values for '{param}': '{provided}' was "
                 f"provided, but the dialect specifies '{dialect_val}'. "

pandas/io/pytables.py

@@ -618,7 +618,7 @@ def __contains__(self, key: str) -> bool:
         node = self.get_node(key)
         if node is not None:
             name = node._v_pathname
-            if name == key or name[1:] == key:
+            if key in (name, name[1:]):
                 return True
         return False
 
@@ -3006,7 +3006,7 @@ def read_index_node(
         attrs = node._v_attrs
         factory, kwargs = self._get_index_factory(attrs)
 
-        if kind == "date" or kind == "object":
+        if kind in ("date", "object"):
             index = factory(
                 _unconvert_index(
                     data, kind, encoding=self.encoding, errors=self.errors
@@ -5243,7 +5243,7 @@ def __init__(
             # see if we have a passed coordinate like
             with suppress(ValueError):
                 inferred = lib.infer_dtype(where, skipna=False)
-                if inferred == "integer" or inferred == "boolean":
+                if inferred in ("integer", "boolean"):
                     where = np.asarray(where)
                     if where.dtype == np.bool_:
                         start, stop = self.start, self.stop

pandas/io/sas/sas7bdat.py

@@ -431,10 +431,7 @@ def _process_page_metadata(self) -> None:
             subheader_processor = self._subheader_processors[subheader_index]
 
             if subheader_processor is None:
-                f1 = (
-                    subheader_compression == const.compressed_subheader_id
-                    or subheader_compression == 0
-                )
+                f1 = subheader_compression in (const.compressed_subheader_id, 0)
                 f2 = subheader_type == const.compressed_subheader_type
                 if self.compression and f1 and f2:
                     self._current_page_data_subheader_pointers.append(

pandas/io/sql.py

@@ -1178,7 +1178,7 @@ def _sqlalchemy_type(self, col):
             Time,
         )
 
-        if col_type == "datetime64" or col_type == "datetime":
+        if col_type in ("datetime64", "datetime"):
             # GH 9086: TIMESTAMP is the suggested type if the column contains
             # timezone information
             try:

pandas/io/stata.py

@@ -2178,7 +2178,7 @@ def _dtype_to_default_stata_fmt(
         return "%9.0g"
     elif dtype == np.int32:
         return "%12.0g"
-    elif dtype == np.int8 or dtype == np.int16:
+    elif dtype in (np.int8, np.int16):
         return "%8.0g"
     else:  # pragma : no cover
         raise NotImplementedError(f"Data type {dtype} not supported.")

pandas/tests/apply/test_frame_apply.py

@@ -1342,7 +1342,7 @@ def test_size_as_str(how, axis):
     # Just a string attribute arg same as calling df.arg
     # on the columns
     result = getattr(df, how)("size", axis=axis)
-    if axis == 0 or axis == "index":
+    if axis in (0, "index"):
         expected = Series(df.shape[0], index=df.columns)
     else:
         expected = Series(df.shape[1], index=df.index)

pandas/tests/apply/test_frame_transform.py

@@ -69,7 +69,7 @@ def test_transform_empty_listlike(float_frame, ops, frame_or_series):
 @pytest.mark.parametrize("box", [dict, Series])
 def test_transform_dictlike(axis, float_frame, box):
     # GH 35964
-    if axis == 0 or axis == "index":
+    if axis in (0, "index"):
         e = float_frame.columns[0]
         expected = float_frame[[e]].transform(np.abs)
     else:

pandas/tests/apply/test_str.py

@@ -236,7 +236,7 @@ def test_agg_cython_table_transform_frame(df, func, expected, axis):
     # GH 21224
     # test transforming functions in
     # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
-    if axis == "columns" or axis == 1:
+    if axis in ("columns", 1):
         # operating blockwise doesn't let us preserve dtypes
         expected = expected.astype("float64")
 
@@ -273,7 +273,7 @@ def test_transform_groupby_kernel_frame(request, axis, float_frame, op):
     # GH 35964
 
     args = [0.0] if op == "fillna" else []
-    if axis == 0 or axis == "index":
+    if axis in (0, "index"):
         ones = np.ones(float_frame.shape[0])
     else:
         ones = np.ones(float_frame.shape[1])
@@ -286,7 +286,7 @@ def test_transform_groupby_kernel_frame(request, axis, float_frame, op):
     float_frame["E"] = float_frame["A"].copy()
     assert len(float_frame._mgr.arrays) > 1
 
-    if axis == 0 or axis == "index":
+    if axis in (0, "index"):
         ones = np.ones(float_frame.shape[0])
     else:
         ones = np.ones(float_frame.shape[1])

pandas/tests/frame/methods/test_interpolate.py

@@ -383,7 +383,7 @@ def test_interp_string_axis(self, axis_name, axis_number):
     @pytest.mark.parametrize("method", ["ffill", "bfill", "pad"])
     def test_interp_fillna_methods(self, request, axis, method, using_array_manager):
         # GH 12918
-        if using_array_manager and (axis == 1 or axis == "columns"):
+        if using_array_manager and axis in (1, "columns"):
             # TODO(ArrayManager) support axis=1
             td.mark_array_manager_not_yet_implemented(request)
 

pandas/tests/indexes/test_setops.py

@@ -103,7 +103,7 @@ def test_union_different_types(index_flat, index_flat2, request):
         # complex objects non-sortable
         warn = RuntimeWarning
 
-    any_uint64 = idx1.dtype == np.uint64 or idx2.dtype == np.uint64
+    any_uint64 = np.uint64 in (idx1.dtype, idx2.dtype)
     idx1_signed = is_signed_integer_dtype(idx1.dtype)
     idx2_signed = is_signed_integer_dtype(idx2.dtype)
 

pandas/tests/indexing/multiindex/test_slice.py

@@ -35,7 +35,7 @@ def test_per_axis_per_level_getitem(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (a == "A1" or a == "A2" or a == "A3") and (c == "C1" or c == "C3")
+                if a in ("A1", "A2", "A3") and c in ("C1", "C3")
             ]
         ]
         tm.assert_frame_equal(result, expected)
@@ -49,8 +49,7 @@ def test_per_axis_per_level_getitem(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (a == "A1" or a == "A2" or a == "A3")
-                and (c == "C1" or c == "C2" or c == "C3")
+                if a in ("A1", "A2", "A3") and c in ("C1", "C2", "C3")
             ]
         ]
         result = df.loc[(slice("A1", "A3"), slice(None), slice("C1", "C3")), :]
@@ -121,7 +120,7 @@ def test_per_axis_per_level_getitem(self):
                     d,
                 )
                 for a, b, c, d in s.index.values
-                if (a == "A1" or a == "A2" or a == "A3") and (c == "C1" or c == "C3")
+                if a in ("A1", "A2", "A3") and c in ("C1", "C3")
             ]
         ]
         tm.assert_series_equal(result, expected)
@@ -416,7 +415,7 @@ def test_per_axis_per_level_doc_examples(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (a == "A1" or a == "A2" or a == "A3") and (c == "C1" or c == "C3")
+                if a in ("A1", "A2", "A3") and c in ("C1", "C3")
             ]
         ]
         tm.assert_frame_equal(result, expected)
@@ -433,7 +432,7 @@ def test_per_axis_per_level_doc_examples(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (c == "C1" or c == "C3")
+                if c in ("C1", "C3")
             ]
         ]
         tm.assert_frame_equal(result, expected)
@@ -494,7 +493,7 @@ def test_loc_axis_arguments(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (a == "A1" or a == "A2" or a == "A3") and (c == "C1" or c == "C3")
+                if a in ("A1", "A2", "A3") and c in ("C1", "C3")
             ]
         ]
         tm.assert_frame_equal(result, expected)
@@ -509,7 +508,7 @@ def test_loc_axis_arguments(self):
                     d,
                 )
                 for a, b, c, d in df.index.values
-                if (c == "C1" or c == "C3")
+                if c in ("C1", "C3")
             ]
         ]
         tm.assert_frame_equal(result, expected)

pandas/tests/io/excel/test_readers.py

@@ -1222,7 +1222,7 @@ def test_read_excel_nrows_non_integer_parameter(self, read_ext):
             ("testmultiindex", "both", [0, 1], [0, 1], None),
             ("testmultiindex", "mi_column_name", [0, 1], 0, None),
             ("testskiprows", "skiprows_list", None, None, [0, 2]),
-            ("testskiprows", "skiprows_list", None, None, lambda x: x == 0 or x == 2),
+            ("testskiprows", "skiprows_list", None, None, lambda x: x in (0, 2)),
         ],
     )
     def test_read_excel_nrows_params(

pandas/tests/io/json/test_pandas.py

@@ -24,7 +24,7 @@
 
 
 def assert_json_roundtrip_equal(result, expected, orient):
-    if orient == "records" or orient == "values":
+    if orient in ("records", "values"):
         expected = expected.reset_index(drop=True)
     if orient == "values":
         expected.columns = range(len(expected.columns))

pandas/tests/util/test_assert_series_equal.py

@@ -115,9 +115,7 @@ def test_less_precise(data1, data2, dtype, decimals):
     s1 = Series([data1], dtype=dtype)
     s2 = Series([data2], dtype=dtype)
 
-    if (decimals == 5 or decimals == 10) or (
-        decimals >= 3 and abs(data1 - data2) >= 0.0005
-    ):
+    if decimals in (5, 10) or (decimals >= 3 and abs(data1 - data2) >= 0.0005):
         if is_extension_array_dtype(dtype):
             msg = "ExtensionArray are different"
         else:

pandas/tseries/frequencies.py

@@ -642,7 +642,7 @@ def _is_quarterly(rule: str) -> bool:
 
 def _is_monthly(rule: str) -> bool:
     rule = rule.upper()
-    return rule == "M" or rule == "BM"
+    return rule in ("M", "BM")
 
 
 def _is_weekly(rule: str) -> bool:

pandas/tseries/holiday.py

@@ -54,9 +54,9 @@ def next_monday_or_tuesday(dt: datetime) -> datetime:
     (because Monday is already taken by adjacent holiday on the day before)
     """
     dow = dt.weekday()
-    if dow == 5 or dow == 6:
+    if dow in (5, 6):
         return dt + timedelta(2)
-    elif dow == 0:
+    if dow == 0:
         return dt + timedelta(1)
     return dt