ueshin commented on code in PR #41606:
URL: https://github.com/apache/spark/pull/41606#discussion_r1256400263
##########
python/pyspark/testing/utils.py:
##########
@@ -209,3 +219,174 @@ def check_error(
self.assertEqual(
expected, actual, f"Expected message parameters was '{expected}',
got '{actual}'"
)
+
+
+def assertDataFrameEqual(df: DataFrame, expected: DataFrame, check_row_order:
bool = False):
+ """
+ A util function to assert equality between DataFrames `df` and `expected`,
with
+ optional parameter `check_row_order`.
+
+ .. versionadded:: 3.5.0
+
+ For float values, assert approximate equality (1e-5 by default).
+
+ Parameters
+ ----------
+ df : DataFrame
+ The DataFrame that is being compared or tested.
+
+ expected : DataFrame
+ The expected result of the operation, for comparison with the actual
result.
+
+ check_row_order : bool, optional
+ A flag indicates whether the order of rows should be considered in the
comparison.
+ If set to `False` (default), the row order is not taken into account.
+ If set to `True`, the order of rows is important and will be checked
during comparison.
+
+ Examples
+ --------
+ >>> df1 = spark.createDataFrame(data=[("1", 1000), ("2", 3000)],
schema=["id", "amount"])
+ >>> df2 = spark.createDataFrame(data=[("1", 1000), ("2", 3000)],
schema=["id", "amount"])
+ >>> assertDataFrameEqual(df1, df2) # pass
+
+
+ >>> df1 = spark.createDataFrame(data=[("1", 1000.00), ("2", 3000.00),
("3", 2000.00)], \
+ schema=["id", "amount"])
+ >>> df2 = spark.createDataFrame(data=[("1", 1001.00), ("2", 3000.00),
("3", 2003.00)], \
+ schema=["id", "amount"])
+ >>> assertDataFrameEqual(df1, df2) # fail
+
+ Results do not match: ( 0.66667 % )
+ [df]
+ Row(id='1', amount=1000.0)
+
+ [expected]
+ Row(id='1', amount=1001.0)
+
+ ********************
+
+ [df]
+ Row(id='3', amount=2000.0)
+
+ [expected]
+ Row(id='3', amount=2003.0)
+
+ ********************
Review Comment:
```suggestion
>>> assertDataFrameEqual(df1, df2) # fail # doctest:
+IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
PySparkAssertionError: [DIFFERENT_ROWS] Results do not match: ( 0.66667
% )
[df]
Row(id='1', amount=1000.0)
<BLANKLINE>
[expected]
Row(id='1', amount=1001.0)
<BLANKLINE>
********************
<BLANKLINE>
[df]
Row(id='3', amount=2000.0)
<BLANKLINE>
[expected]
Row(id='3', amount=2003.0)
<BLANKLINE>
********************
<BLANKLINE>
<BLANKLINE>
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
