Merge branch 'master' into nui-regression

Author: alexhlim

pandas/_testing.py

@@ -1294,6 +1294,8 @@ def assert_series_equal(
     rtol=1.0e-5,
     atol=1.0e-8,
     obj="Series",
+    *,
+    check_index=True,
 ):
     """
     Check that left and right Series are equal.
@@ -1353,6 +1355,10 @@ def assert_series_equal(
     obj : str, default 'Series'
         Specify object name being compared, internally used to show appropriate
         assertion message.
+    check_index : bool, default True
+        Whether to check index equivalence. If False, then compare only values.
+
+        .. versionadded:: 1.3.0
 
     Examples
     --------
@@ -1388,18 +1394,20 @@ def assert_series_equal(
     if check_flags:
         assert left.flags == right.flags, f"{repr(left.flags)} != {repr(right.flags)}"
 
-    # index comparison
-    assert_index_equal(
-        left.index,
-        right.index,
-        exact=check_index_type,
-        check_names=check_names,
-        check_exact=check_exact,
-        check_categorical=check_categorical,
-        rtol=rtol,
-        atol=atol,
-        obj=f"{obj}.index",
-    )
+    if check_index:
+        # GH #38183
+        assert_index_equal(
+            left.index,
+            right.index,
+            exact=check_index_type,
+            check_names=check_names,
+            check_exact=check_exact,
+            check_categorical=check_categorical,
+            rtol=rtol,
+            atol=atol,
+            obj=f"{obj}.index",
+        )
+
     if check_freq and isinstance(left.index, (pd.DatetimeIndex, pd.TimedeltaIndex)):
         lidx = left.index
         ridx = right.index
@@ -1704,6 +1712,10 @@ def assert_frame_equal(
             assert col in right
             lcol = left.iloc[:, i]
             rcol = right.iloc[:, i]
+            # GH #38183
+            # use check_index=False, because we do not want to run
+            # assert_index_equal for each column,
+            # as we already checked it for the whole dataframe before.
             assert_series_equal(
                 lcol,
                 rcol,
@@ -1717,6 +1729,7 @@ def assert_frame_equal(
                 obj=f'{obj}.iloc[:, {i}] (column name="{col}")',
                 rtol=rtol,
                 atol=atol,
+                check_index=False,
             )
 
 

pandas/core/algorithms.py

@@ -11,7 +11,7 @@
 
 import numpy as np
 
-from pandas._libs import Timestamp, algos, hashtable as htable, iNaT, lib
+from pandas._libs import algos, hashtable as htable, iNaT, lib
 from pandas._typing import AnyArrayLike, ArrayLike, DtypeObj, FrameOrSeriesUnion
 from pandas.util._decorators import doc
 
@@ -59,7 +59,11 @@
 )
 from pandas.core.dtypes.missing import isna, na_value_for_dtype
 
-from pandas.core.construction import array, extract_array
+from pandas.core.construction import (
+    array,
+    ensure_wrapped_if_datetimelike,
+    extract_array,
+)
 from pandas.core.indexers import validate_indices
 
 if TYPE_CHECKING:
@@ -1906,10 +1910,7 @@ def searchsorted(arr, value, side="left", sorter=None) -> np.ndarray:
     ):
         # E.g. if `arr` is an array with dtype='datetime64[ns]'
         # and `value` is a pd.Timestamp, we may need to convert value
-        value_ser = array([value]) if is_scalar(value) else array(value)
-        value = value_ser[0] if is_scalar(value) else value_ser
-        if isinstance(value, Timestamp) and value.tzinfo is None:
-            value = value.to_datetime64()
+        arr = ensure_wrapped_if_datetimelike(arr)
 
     result = arr.searchsorted(value, side=side, sorter=sorter)
     return result

pandas/core/internals/blocks.py

@@ -37,9 +37,7 @@
 from pandas.core.dtypes.common import (
     DT64NS_DTYPE,
     TD64NS_DTYPE,
-    is_bool_dtype,
     is_categorical_dtype,
-    is_datetime64_any_dtype,
     is_datetime64_dtype,
     is_datetime64tz_dtype,
     is_dtype_equal,
@@ -53,7 +51,6 @@
     is_re,
     is_re_compilable,
     is_sparse,
-    is_timedelta64_dtype,
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import CategoricalDtype, ExtensionDtype
@@ -927,7 +924,7 @@ def setitem(self, indexer, value):
 
         else:
             # current dtype cannot store value, coerce to common dtype
-
+            # TODO: can we just use coerce_to_target_dtype for all this
             if hasattr(value, "dtype"):
                 dtype = value.dtype
 
@@ -1164,33 +1161,9 @@ def coerce_to_target_dtype(self, other):
         # if we cannot then coerce to object
         dtype, _ = infer_dtype_from(other, pandas_dtype=True)
 
-        if is_dtype_equal(self.dtype, dtype):
-            return self
-
-        if self.is_bool or is_object_dtype(dtype) or is_bool_dtype(dtype):
-            # we don't upcast to bool
-            return self.astype(object)
-
-        elif (self.is_float or self.is_complex) and (
-            is_integer_dtype(dtype) or is_float_dtype(dtype)
-        ):
-            # don't coerce float/complex to int
-            return self
+        new_dtype = find_common_type([self.dtype, dtype])
 
-        elif self.is_datetime or is_datetime64_any_dtype(dtype):
-            # The is_dtype_equal check above ensures that at most one of
-            #  these two conditions hold, so we must cast to object.
-            return self.astype(object)
-
-        elif self.is_timedelta or is_timedelta64_dtype(dtype):
-            # The is_dtype_equal check above ensures that at most one of
-            #  these two conditions hold, so we must cast to object.
-            return self.astype(object)
-
-        try:
-            return self.astype(dtype)
-        except (ValueError, TypeError, OverflowError):
-            return self.astype(object)
+        return self.astype(new_dtype, copy=False)
 
     def interpolate(
         self,