Fix bugs

pandas/core/apply.py

@@ -485,7 +485,7 @@ def wrap_results_list_like(
  obj = self.obj
 
  try:
- return concat(results, keys=keys, axis=1, sort=False) # maybebug
+ return concat(results, keys=keys, axis=1, sort=False) # nobug
  except TypeError as err:
  # we are concatting non-NDFrame objects,
  # e.g. a list of scalars
@@ -635,10 +635,11 @@ def wrap_results_dict_like(
  keys_to_use = ktu
 
  axis: AxisInt = 0 if isinstance(obj, ABCSeries) else 1
- result = concat( # maybebug
+ result = concat( # nobug
  results,
  axis=axis,
  keys=keys_to_use,
+ sort=False,
  )
  elif any(is_ndframe):
  # There is a mix of NDFrames and scalars

pandas/core/frame.py

@@ -6130,7 +6130,7 @@ def shift(
  .shift(periods=period, freq=freq, axis=axis, fill_value=fill_value)
  .add_suffix(f"{suffix}_{period}" if suffix else f"_{period}")
  )
- return concat(shifted_dataframes, axis=1) # bug
+ return concat(shifted_dataframes, axis=1, sort=False) # nobug
  elif suffix:
  raise ValueError("Cannot specify `suffix` if `periods` is an int.")
  periods = cast(int, periods)
@@ -11168,7 +11168,7 @@ def _append_internal(
 
  from pandas.core.reshape.concat import concat
 
- result = concat( # possible bug
+ result = concat( # nobug
  [self, row_df],
  ignore_index=ignore_index,
  )
@@ -11401,7 +11401,7 @@ def join(
  )
  return res.reindex(self.index)
  else:
- return concat( # bug
+ return concat( # nobug
  frames, axis=1, join=how, verify_integrity=True, sort=sort
  )
 

pandas/core/generic.py

@@ -9507,7 +9507,7 @@ def compare(
 
  # error: List item 0 has incompatible type "NDFrame"; expected
  # "Union[Series, DataFrame]"
- diff = concat( # bug
+ diff = concat( # nobug - self and other must have same index/coluns
  [self, other], # type: ignore[list-item]
  axis=axis,
  keys=result_names,

pandas/core/groupby/groupby.py

@@ -1143,7 +1143,7 @@ def _concat_objects(
  group_levels = self._grouper.levels
  group_names = self._grouper.names
 
- result = concat( # maybebug
+ result = concat(
  values,
  axis=0,
  keys=group_keys,
@@ -1152,10 +1152,10 @@ def _concat_objects(
  sort=False,
  )
  else:
- result = concat(values, axis=0) # maybebug
+ result = concat(values, axis=0)
 
  elif not not_indexed_same:
- result = concat(values, axis=0) # maybebug
+ result = concat(values, axis=0)
 
  ax = self._selected_obj.index
  if self.dropna:
@@ -1178,7 +1178,7 @@ def _concat_objects(
  result = result.reindex(ax, axis=0)
 
  else:
- result = concat(values, axis=0) # maybebug
+ result = concat(values, axis=0)
 
  if self.obj.ndim == 1:
  name = self.obj.name

pandas/core/interchange/from_dataframe.py

@@ -144,7 +144,9 @@ def _from_dataframe(df: DataFrameXchg, allow_copy: bool = True) -> pd.DataFrame:
  elif len(pandas_dfs) == 1:
  pandas_df = pandas_dfs[0]
  else:
- pandas_df = pd.concat(pandas_dfs, axis=0, ignore_index=True, copy=False) # bug
+ pandas_df = pd.concat(
+ pandas_dfs, axis=0, ignore_index=True, copy=False
+ ) # nobug
 
  index_obj = df.metadata.get("pandas.index", None)
  if index_obj is not None:

pandas/core/reshape/melt.py

@@ -668,7 +668,7 @@ def melt_stub(df, stub: str, i, j, value_vars, sep: str):
  value_vars_flattened.extend(value_var)
  _melted.append(melt_stub(df, stub, i, j, value_var, sep))
 
- melted = concat(_melted, axis=1) # maybebug
+ melted = concat(_melted, axis=1) # nobug
  id_vars = df.columns.difference(value_vars_flattened)
  new = df[id_vars]
 

pandas/core/series.py

@@ -2994,7 +2994,7 @@ def searchsorted( # type: ignore[override]
  def _append_internal(self, to_append: Series, ignore_index: bool = False) -> Series:
  from pandas.core.reshape.concat import concat
 
- return concat([self, to_append], ignore_index=ignore_index) # maybebug
+ return concat([self, to_append], ignore_index=ignore_index) # nobug
 
  def compare(
  self,
@@ -3271,7 +3271,7 @@ def combine_first(self, other) -> Series:
  if this.dtype.kind == "M" and other.dtype.kind != "M":
  # TODO: try to match resos?
  other = to_datetime(other)
- combined = concat([this, other]) # bug
+ combined = concat([this, other]) # nobug
  combined = combined.reindex(new_index)
  return combined.__finalize__(self, method="combine_first")
 

pandas/core/strings/accessor.py

@@ -659,7 +659,7 @@ def cat(
  # align if required
  if any(not data.index.equals(x.index) for x in others):
  # Need to add keys for uniqueness in case of duplicate columns
- others = concat( # bug
+ others = concat( # nobug
  others,
  axis=1,
  join=(join if join == "inner" else "outer"),

pandas/tests/apply/test_frame_apply.py

@@ -915,6 +915,34 @@ def test_listlike_lambda(ops, by_row, expected):
  tm.assert_equal(result, expected)
 
 
+def test_listlike_datetime_index_unsorted():
+ values = [datetime(2024, 1, 1), datetime(2024, 1, 2)]
+ df = DataFrame({"a": [1, 2]}, index=[values[1], values[0]])
+ result = df.apply([lambda x: x], by_row=False)
+ expected = DataFrame(
+ [[1], [2]],
+ index=[values[1], values[0]],
+ columns=MultiIndex([["a"], ["<lambda>"]], codes=[[0], [0]]),
+ )
+ tm.assert_frame_equal(result, expected)
+
+
+def test_dictlike_datetime_index_unsorted():
+ values = [datetime(2024, 1, 1), datetime(2024, 1, 2), datetime(2024, 1, 3)]
+ df = DataFrame({"a": [1, 2], "b": [3, 4]}, index=[values[1], values[0]])
+ result = df.apply(
+ {"a": lambda x: x, "b": lambda x: x.shift(freq="D")}, by_row=False
+ )
+ expected = DataFrame(
+ {
+ "a": [1.0, 2.0, np.nan],
+ "b": [4.0, np.nan, 3.0],
+ },
+ index=[values[1], values[0], values[2]],
+ )
+ tm.assert_frame_equal(result, expected)
+
+
 @pytest.mark.parametrize(
  "ops",
  [

pandas/tests/frame/methods/test_shift.py

@@ -794,3 +794,16 @@ def test_shift_invalid_fill_value_deprecation(self):
  df["a"].shift(1, fill_value=NaT)
  with tm.assert_produces_warning(Pandas4Warning, match=msg):
  df["b"].shift(1, fill_value=NaT)
+
+ def test_shift_dt_index_multiple_periods_unsorted(self):
+ values = date_range("1/1/2000", periods=4, freq="D")
+ df = DataFrame({"a": [1, 2]}, index=[values[1], values[0]])
+ result = df.shift(periods=[1, 2], freq="D")
+ expected = DataFrame(
+ {
+ "a_1": [1.0, 2.0, np.nan],
+ "a_2": [2.0, np.nan, 1.0],
+ },
+ index=[values[2], values[1], values[3]],
+ )
+ tm.assert_frame_equal(result, expected)

pandas/tests/reshape/merge/test_join.py

@@ -1,3 +1,4 @@
+from datetime import datetime
 import re
 
 import numpy as np
@@ -671,6 +672,14 @@ def _check_diff_index(df_list, result, exp_index):
  with pytest.raises(ValueError, match=msg):
  df_list[0].join(df_list[1:], on="a")
 
+ def test_join_many_datetime_unsorted(self):
+ index = Index([datetime(2024, 1, 2), datetime(2024, 1, 1)])
+ df = DataFrame({"a": [1, 2]}, index=index)
+ df2 = DataFrame({"b": [1, 2]}, index=index)
+ result = df.join([df2], how="outer")
+ expected = DataFrame({"a": [1, 2], "b": [1, 2]}, index=index)
+ tm.assert_frame_equal(result, expected)
+
  def test_join_many_mixed(self):
  df = DataFrame(
  np.random.default_rng(2).standard_normal((8, 4)),

pandas/tests/strings/test_cat.py

@@ -1,3 +1,4 @@
+from datetime import datetime
 import re
 
 import numpy as np
@@ -343,6 +344,18 @@ def test_str_cat_align_mixed_inputs(join_type):
  s.str.cat([t, z], join=join_type)
 
 
+def test_str_cat_datetime_index_unsorted(join_type):
+ values = [datetime(2024, 1, 1), datetime(2024, 1, 2)]
+ s = Series(["a", "b"], index=[values[0], values[1]])
+ others = Series(["c", "d"], index=[values[1], values[0]])
+ result = s.str.cat(others, join=join_type)
+ if join_type == "right":
+ expected = Series(["bc", "ad"], index=[values[1], values[0]])
+ else:
+ expected = Series(["ad", "bc"], index=[values[0], values[1]])
+ tm.assert_series_equal(result, expected)
+
+
 def test_str_cat_all_na(index_or_series, index_or_series2):
  # GH 24044
  box = index_or_series