You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/11/24 09:16:48 UTC
[GitHub] [spark] viirya commented on a diff in pull request #38223: [SPARK-40770][PYTHON] Improved error messages for applyInPandas for schema mismatch
viirya commented on code in PR #38223:
URL: https://github.com/apache/spark/pull/38223#discussion_r1031240653
##########
python/pyspark/sql/tests/pandas/test_pandas_cogrouped_map.py:
##########
@@ -165,100 +148,191 @@ def merge_pandas(lft, _):
)
def test_apply_in_pandas_not_returning_pandas_dataframe(self):
- left = self.data1
- right = self.data2
+ self._test_merge_error(
+ fn=lambda lft, rgt: lft.size + rgt.size,
+ error_class=PythonException,
+ error_message_regex="Return type of the user-defined function "
+ "should be pandas.DataFrame, but is <class 'numpy.int64'>",
+ )
+
+ def test_apply_in_pandas_returning_column_names(self):
+ self._test_merge(fn=lambda lft, rgt: pd.merge(lft, rgt, on=["id", "k"]))
+ def test_apply_in_pandas_returning_no_column_names(self):
def merge_pandas(lft, rgt):
- return lft.size + rgt.size
+ res = pd.merge(lft, rgt, on=["id", "k"])
+ res.columns = range(res.columns.size)
+ return res
- with QuietTest(self.sc):
- with self.assertRaisesRegex(
- PythonException,
- "Return type of the user-defined function should be pandas.DataFrame, "
- "but is <class 'numpy.int64'>",
- ):
- (
- left.groupby("id")
- .cogroup(right.groupby("id"))
- .applyInPandas(merge_pandas, "id long, k int, v int, v2 int")
- .collect()
- )
+ self._test_merge(fn=merge_pandas)
- def test_apply_in_pandas_returning_wrong_number_of_columns(self):
- left = self.data1
- right = self.data2
+ def test_apply_in_pandas_returning_column_names_sometimes(self):
+ def merge_pandas(lft, rgt):
+ res = pd.merge(lft, rgt, on=["id", "k"])
+ if 0 in lft["id"] and lft["id"][0] % 2 == 0:
+ return res
+ res.columns = range(res.columns.size)
+ return res
+
+ self._test_merge(fn=merge_pandas)
+ def test_apply_in_pandas_returning_wrong_column_names(self):
def merge_pandas(lft, rgt):
if 0 in lft["id"] and lft["id"][0] % 2 == 0:
lft["add"] = 0
if 0 in rgt["id"] and rgt["id"][0] % 3 == 0:
rgt["more"] = 1
return pd.merge(lft, rgt, on=["id", "k"])
- with QuietTest(self.sc):
- with self.assertRaisesRegex(
- PythonException,
- "Number of columns of the returned pandas.DataFrame "
- "doesn't match specified schema. Expected: 4 Actual: 6",
- ):
- (
- # merge_pandas returns two columns for even keys while we set schema to four
- left.groupby("id")
- .cogroup(right.groupby("id"))
- .applyInPandas(merge_pandas, "id long, k int, v int, v2 int")
- .collect()
- )
+ self._test_merge_error(
+ fn=merge_pandas,
+ error_class=PythonException,
+ error_message_regex="Column names of the returned pandas.DataFrame "
+ "do not match specified schema. Unexpected: add, more Schema: id, k, v, v2\n",
Review Comment:
```suggestion
"do not match specified schema. Unexpected: add, more. Schema: id, k, v, v2\n",
```
--
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: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org