EnricoMi commented on code in PR #38223:
URL: https://github.com/apache/spark/pull/38223#discussion_r1015075283
##########
python/pyspark/worker.py:
##########
@@ -188,22 +241,7 @@ def wrapped(key_series, value_series):
elif len(argspec.args) == 2:
key = tuple(s[0] for s in key_series)
result = f(key, pd.concat(value_series, axis=1))
-
- if not isinstance(result, pd.DataFrame):
- raise TypeError(
- "Return type of the user-defined function should be "
- "pandas.DataFrame, but is {}".format(type(result))
- )
- # the number of columns of result have to match the return type
- # but it is fine for result to have no columns at all if it is empty
- if not (
- len(result.columns) == len(return_type) or len(result.columns) ==
0 and result.empty
- ):
- raise RuntimeError(
- "Number of columns of the returned pandas.DataFrame "
- "doesn't match specified schema. "
- "Expected: {} Actual: {}".format(len(return_type),
len(result.columns))
- )
+ verify_pandas_result(result, return_type,
assign_cols_by_name(runner_conf))
Review Comment:
done
--
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-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
