More performant, more warnings

Author: rhshadrach

pandas/core/frame.py

@@ -11114,6 +11114,7 @@ def _append_internal(
         result = concat(
             [self, row_df],
             ignore_index=ignore_index,
+            sort=False,
         )
         return result.__finalize__(self, method="append")
 

pandas/core/generic.py

@@ -6521,7 +6521,7 @@ def astype(
             return self.copy(deep=False)
 
         # GH 19920: retain column metadata after concat
-        result = concat(results, axis=1)
+        result = concat(results, axis=1, sort=False)
         # GH#40810 retain subclass
         # error: Incompatible types in assignment
         # (expression has type "Self", variable has type "DataFrame")

pandas/core/groupby/groupby.py

@@ -5236,7 +5236,7 @@ def shift(
         return (
             shifted_dataframes[0]
             if len(shifted_dataframes) == 1
-            else concat(shifted_dataframes, axis=1)
+            else concat(shifted_dataframes, axis=1, sort=False)
         )
 
     @final

pandas/core/reshape/concat.py

@@ -418,10 +418,15 @@ def concat(
             non_concat_axis = [obj.index for obj in objs]
 
         if all(isinstance(index, DatetimeIndex) for index in non_concat_axis):
-            from pandas.core.indexes.api import union_indexes
-
-            no_sort_result_index = union_indexes(non_concat_axis, sort=False)
-            if not no_sort_result_index.is_monotonic_increasing:
+            warn = any(
+                id(prev) != id(curr)
+                for prev, curr in zip(non_concat_axis, non_concat_axis[1:])
+            ) and any(
+                prev[-1] > curr[0]
+                for prev, curr in zip(non_concat_axis, non_concat_axis[1:])
+                if not prev.empty and not curr.empty
+            )
+            if warn:
                 msg = (
                     "Sorting by default when concatenating all DatetimeIndex is "
                     "deprecated.  In the future, pandas will respect the default "

pandas/core/reshape/pivot.py

@@ -263,7 +263,7 @@ def pivot_table(
             pieces.append(_table)
             keys.append(getattr(func, "__name__", func))
 
-        table = concat(pieces, keys=keys, axis=1)
+        table = concat(pieces, keys=keys, axis=1, sort=False)
         return table.__finalize__(data, method="pivot_table")
 
     table = __internal_pivot_table(

pandas/io/pytables.py

@@ -1109,7 +1109,9 @@ def func(_start, _stop, _where):
             ]
 
             # concat and return
-            return concat(objs, axis=axis, verify_integrity=False)._consolidate()
+            return concat(
+                objs, axis=axis, verify_integrity=False, sort=False
+            )._consolidate()
 
         # create the iterator
         it = TableIterator(
@@ -4860,7 +4862,7 @@ def read(
         if len(frames) == 1:
             df = frames[0]
         else:
-            df = concat(frames, axis=1)
+            df = concat(frames, axis=1, sort=False)
 
         selection = Selection(self, where=where, start=start, stop=stop)
         # apply the selection filters & axis orderings

pandas/tests/io/pytables/test_append.py

@@ -7,6 +7,7 @@
 
 from pandas._libs.tslibs import Timestamp
 from pandas.compat import PY312
+from pandas.errors import Pandas4Warning
 
 import pandas as pd
 from pandas import (
@@ -887,7 +888,9 @@ def test_append_to_multiple(setup_path):
     )
     df2 = df1.copy().rename(columns="{}_2".format)
     df2["foo"] = "bar"
-    df = concat([df1, df2], axis=1)
+    msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+    with tm.assert_produces_warning(Pandas4Warning, match=msg):
+        df = concat([df1, df2], axis=1)
 
     with ensure_clean_store(setup_path) as store:
         # exceptions
@@ -928,7 +931,9 @@ def test_append_to_multiple_dropna(setup_path):
         index=date_range("2000-01-01", periods=10, freq="B"),
     ).rename(columns="{}_2".format)
     df1.iloc[1, df1.columns.get_indexer(["A", "B"])] = np.nan
-    df = concat([df1, df2], axis=1)
+    msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+    with tm.assert_produces_warning(Pandas4Warning, match=msg):
+        df = concat([df1, df2], axis=1)
 
     with ensure_clean_store(setup_path) as store:
         # dropna=True should guarantee rows are synchronized
@@ -949,7 +954,9 @@ def test_append_to_multiple_dropna_false(setup_path):
     )
     df2 = df1.copy().rename(columns="{}_2".format)
     df1.iloc[1, df1.columns.get_indexer(["A", "B"])] = np.nan
-    df = concat([df1, df2], axis=1)
+    msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+    with tm.assert_produces_warning(Pandas4Warning, match=msg):
+        df = concat([df1, df2], axis=1)
 
     with (
         ensure_clean_store(setup_path) as store,

pandas/tests/io/pytables/test_select.py

@@ -3,6 +3,7 @@
 
 from pandas._libs.tslibs import Timestamp
 from pandas.compat import PY312
+from pandas.errors import Pandas4Warning
 
 import pandas as pd
 from pandas import (
@@ -411,7 +412,9 @@ def test_select_iterator(tmp_path, setup_path):
         df2["foo"] = "bar"
         store.append("df2", df2)
 
-        df = concat([df1, df2], axis=1)
+        msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            df = concat([df1, df2], axis=1)
 
         # full selection
         expected = store.select_as_multiple(["df1", "df2"], selector="df1")
@@ -901,7 +904,9 @@ def test_select_as_multiple(setup_path):
         result = store.select_as_multiple(
             ["df1", "df2"], where=["A>0", "B>0"], selector="df1"
         )
-        expected = concat([df1, df2], axis=1)
+        msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            expected = concat([df1, df2], axis=1)
         expected = expected[(expected.A > 0) & (expected.B > 0)]
         tm.assert_frame_equal(result, expected, check_freq=False)
         # FIXME: 2021-01-20 this is failing with freq None vs 4B on some builds
@@ -910,7 +915,9 @@ def test_select_as_multiple(setup_path):
         result = store.select_as_multiple(
             ["df1", "df2"], where="index>df2.index[4]", selector="df2"
         )
-        expected = concat([df1, df2], axis=1)
+        msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            expected = concat([df1, df2], axis=1)
         expected = expected[5:]
         tm.assert_frame_equal(result, expected)
 

pandas/tests/io/pytables/test_store.py

@@ -8,6 +8,7 @@
 import pytest
 
 from pandas.compat import PY312
+from pandas.errors import Pandas4Warning
 
 import pandas as pd
 from pandas import (
@@ -732,9 +733,13 @@ def test_coordinates(setup_path):
         c = store.select_as_coordinates("df1", ["A>0", "B>0"])
         df1_result = store.select("df1", c)
         df2_result = store.select("df2", c)
-        result = concat([df1_result, df2_result], axis=1)
+        msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            result = concat([df1_result, df2_result], axis=1)
 
-        expected = concat([df1, df2], axis=1)
+        msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+        with tm.assert_produces_warning(Pandas4Warning, match=msg):
+            expected = concat([df1, df2], axis=1)
         expected = expected[(expected.A > 0) & (expected.B > 0)]
         tm.assert_frame_equal(result, expected, check_freq=False)
         # FIXME: 2021-01-18 on some (mostly windows) builds we get freq=None

pandas/tests/resample/test_datetime_index.py

@@ -602,11 +602,13 @@ def test_resample_ohlc_dataframe(unit):
     df.index = df.index.as_unit(unit)
     df.columns.name = "Cols"
     res = df.resample("h").ohlc()
-    exp = pd.concat(
-        [df["VOLUME"].resample("h").ohlc(), df["PRICE"].resample("h").ohlc()],
-        axis=1,
-        keys=df.columns,
-    )
+    msg = "Sorting by default when concatenating all DatetimeIndex is deprecated"
+    with tm.assert_produces_warning(Pandas4Warning, match=msg):
+        exp = pd.concat(
+            [df["VOLUME"].resample("h").ohlc(), df["PRICE"].resample("h").ohlc()],
+            axis=1,
+            keys=df.columns,
+        )
     assert exp.columns.names[0] == "Cols"
     tm.assert_frame_equal(exp, res)