ENH: Include column for ea comparison in asserters (#50323)

* ENH: Include column for ea comparison in asserters

* Add gh ref

* Fix test

* Add gh ref

* Split tests

Author: phofl

doc/source/whatsnew/v2.0.0.rst

@@ -93,6 +93,7 @@ Other enhancements
 - :func:`timedelta_range` now supports a ``unit`` keyword ("s", "ms", "us", or "ns") to specify the desired resolution of the output index (:issue:`49824`)
 - :meth:`DataFrame.to_json` now supports a ``mode`` keyword with supported inputs 'w' and 'a'. Defaulting to 'w', 'a' can be used when lines=True and orient='records' to append record oriented json lines to an existing json file. (:issue:`35849`)
 - Added ``name`` parameter to :meth:`IntervalIndex.from_breaks`, :meth:`IntervalIndex.from_arrays` and :meth:`IntervalIndex.from_tuples` (:issue:`48911`)
+- Improve exception message when using :func:`assert_frame_equal` on a :class:`DataFrame` to include the column that is compared (:issue:`50323`)
 - Improved error message for :func:`merge_asof` when join-columns were duplicated (:issue:`50102`)
 - Added :meth:`Index.infer_objects` analogous to :meth:`Series.infer_objects` (:issue:`50034`)
 - Added ``copy`` parameter to :meth:`Series.infer_objects` and :meth:`DataFrame.infer_objects`, passing ``False`` will avoid making copies for series or columns that are already non-object or where no better dtype can be inferred (:issue:`50096`)

pandas/_testing/asserters.py

@@ -680,6 +680,7 @@ def assert_extension_array_equal(
     check_exact: bool = False,
     rtol: float = 1.0e-5,
     atol: float = 1.0e-8,
+    obj: str = "ExtensionArray",
 ) -> None:
     """
     Check that left and right ExtensionArrays are equal.
@@ -702,6 +703,11 @@ def assert_extension_array_equal(
         Absolute tolerance. Only used when check_exact is False.
 
         .. versionadded:: 1.1.0
+    obj : str, default 'ExtensionArray'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+
+        .. versionadded:: 2.0.0
 
     Notes
     -----
@@ -719,7 +725,7 @@ def assert_extension_array_equal(
     assert isinstance(left, ExtensionArray), "left is not an ExtensionArray"
     assert isinstance(right, ExtensionArray), "right is not an ExtensionArray"
     if check_dtype:
-        assert_attr_equal("dtype", left, right, obj="ExtensionArray")
+        assert_attr_equal("dtype", left, right, obj=f"Attributes of {obj}")
 
     if (
         isinstance(left, DatetimeLikeArrayMixin)
@@ -729,21 +735,24 @@ def assert_extension_array_equal(
         # Avoid slow object-dtype comparisons
         # np.asarray for case where we have a np.MaskedArray
         assert_numpy_array_equal(
-            np.asarray(left.asi8), np.asarray(right.asi8), index_values=index_values
+            np.asarray(left.asi8),
+            np.asarray(right.asi8),
+            index_values=index_values,
+            obj=obj,
         )
         return
 
     left_na = np.asarray(left.isna())
     right_na = np.asarray(right.isna())
     assert_numpy_array_equal(
-        left_na, right_na, obj="ExtensionArray NA mask", index_values=index_values
+        left_na, right_na, obj=f"{obj} NA mask", index_values=index_values
     )
 
     left_valid = left[~left_na].to_numpy(dtype=object)
     right_valid = right[~right_na].to_numpy(dtype=object)
     if check_exact:
         assert_numpy_array_equal(
-            left_valid, right_valid, obj="ExtensionArray", index_values=index_values
+            left_valid, right_valid, obj=obj, index_values=index_values
         )
     else:
         _testing.assert_almost_equal(
@@ -752,7 +761,7 @@ def assert_extension_array_equal(
             check_dtype=bool(check_dtype),
             rtol=rtol,
             atol=atol,
-            obj="ExtensionArray",
+            obj=obj,
             index_values=index_values,
         )
 
@@ -909,6 +918,7 @@ def assert_series_equal(
                 right_values,
                 check_dtype=check_dtype,
                 index_values=np.asarray(left.index),
+                obj=str(obj),
             )
         else:
             assert_numpy_array_equal(
@@ -955,6 +965,7 @@ def assert_series_equal(
             atol=atol,
             check_dtype=check_dtype,
             index_values=np.asarray(left.index),
+            obj=str(obj),
         )
     elif is_extension_array_dtype_and_needs_i8_conversion(
         left.dtype, right.dtype
@@ -964,6 +975,7 @@ def assert_series_equal(
             right._values,
             check_dtype=check_dtype,
             index_values=np.asarray(left.index),
+            obj=str(obj),
         )
     elif needs_i8_conversion(left.dtype) and needs_i8_conversion(right.dtype):
         # DatetimeArray or TimedeltaArray
@@ -972,6 +984,7 @@ def assert_series_equal(
             right._values,
             check_dtype=check_dtype,
             index_values=np.asarray(left.index),
+            obj=str(obj),
         )
     else:
         _testing.assert_almost_equal(

pandas/tests/extension/json/test_json.py

@@ -140,7 +140,7 @@ def test_custom_asserts(self):
         self.assert_frame_equal(a.to_frame(), a.to_frame())
 
         b = pd.Series(data.take([0, 0, 1]))
-        msg = r"ExtensionArray are different"
+        msg = r"Series are different"
         with pytest.raises(AssertionError, match=msg):
             self.assert_series_equal(a, b)
 

pandas/tests/util/test_assert_frame_equal.py

@@ -366,3 +366,36 @@ def test_assert_frame_equal_check_like_categorical_midx():
         ),
     )
     tm.assert_frame_equal(left, right, check_like=True)
+
+
+def test_assert_frame_equal_ea_column_definition_in_exception_mask():
+    # GH#50323
+    df1 = DataFrame({"a": pd.Series([pd.NA, 1], dtype="Int64")})
+    df2 = DataFrame({"a": pd.Series([1, 1], dtype="Int64")})
+
+    msg = r'DataFrame.iloc\[:, 0\] \(column name="a"\) NA mask values are different'
+    with pytest.raises(AssertionError, match=msg):
+        tm.assert_frame_equal(df1, df2)
+
+
+def test_assert_frame_equal_ea_column_definition_in_exception():
+    # GH#50323
+    df1 = DataFrame({"a": pd.Series([pd.NA, 1], dtype="Int64")})
+    df2 = DataFrame({"a": pd.Series([pd.NA, 2], dtype="Int64")})
+
+    msg = r'DataFrame.iloc\[:, 0\] \(column name="a"\) values are different'
+    with pytest.raises(AssertionError, match=msg):
+        tm.assert_frame_equal(df1, df2)
+
+    with pytest.raises(AssertionError, match=msg):
+        tm.assert_frame_equal(df1, df2, check_exact=True)
+
+
+def test_assert_frame_equal_ts_column():
+    # GH#50323
+    df1 = DataFrame({"a": [pd.Timestamp("2019-12-31"), pd.Timestamp("2020-12-31")]})
+    df2 = DataFrame({"a": [pd.Timestamp("2020-12-31"), pd.Timestamp("2020-12-31")]})
+
+    msg = r'DataFrame.iloc\[:, 0\] \(column name="a"\) values are different'
+    with pytest.raises(AssertionError, match=msg):
+        tm.assert_frame_equal(df1, df2)

pandas/tests/util/test_assert_series_equal.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas.core.dtypes.common import is_extension_array_dtype
-
 import pandas as pd
 from pandas import (
     Categorical,
@@ -116,10 +114,7 @@ def test_less_precise(data1, data2, dtype, decimals):
     s2 = Series([data2], dtype=dtype)
 
     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:
-            msg = "Series values are different"
+        msg = "Series values are different"
         with pytest.raises(AssertionError, match=msg):
             tm.assert_series_equal(s1, s2, rtol=rtol)
     else:
@@ -237,9 +232,9 @@ def test_series_equal_categorical_values_mismatch(rtol):
 
 
 def test_series_equal_datetime_values_mismatch(rtol):
-    msg = """numpy array are different
+    msg = """Series are different
 
-numpy array values are different \\(100.0 %\\)
+Series values are different \\(100.0 %\\)
 \\[index\\]: \\[0, 1, 2\\]
 \\[left\\]:  \\[1514764800000000000, 1514851200000000000, 1514937600000000000\\]
 \\[right\\]: \\[1549065600000000000, 1549152000000000000, 1549238400000000000\\]"""