BryanCutler commented on a change in pull request #24981: [SPARK-27463][PYTHON]
Support Dataframe Cogroup via Pandas UDFs
URL: https://github.com/apache/spark/pull/24981#discussion_r319257236
##########
File path: python/pyspark/worker.py
##########
@@ -359,10 +417,24 @@ def map_batch(batch):
arg_offsets, udf = read_single_udf(
pickleSer, infile, eval_type, runner_conf, udf_index=0)
udfs['f'] = udf
- split_offset = arg_offsets[0] + 1
- arg0 = ["a[%d]" % o for o in arg_offsets[1: split_offset]]
- arg1 = ["a[%d]" % o for o in arg_offsets[split_offset:]]
- mapper_str = "lambda a: f([%s], [%s])" % (", ".join(arg0), ",
".join(arg1))
+ parsed_offsets = extract_key_value_indexes()
+ keys = ["a[%d]" % (o,) for o in parsed_offsets[0][0]]
+ vals = ["a[%d]" % (o, ) for o in parsed_offsets[0][1]]
+ mapper_str = "lambda a: f([%s], [%s])" % (", ".join(keys), ",
".join(vals))
+ elif eval_type == PythonEvalType.SQL_COGROUPED_MAP_PANDAS_UDF:
+ # We assume there is only one UDF here because cogrouped map doesn't
+ # support combining multiple UDFs.
+ assert num_udfs == 1
+ arg_offsets, udf = read_single_udf(
+ pickleSer, infile, eval_type, runner_conf, udf_index=0)
+ udfs['f'] = udf
+ parsed_offsets = extract_key_value_indexes()
+ df1_keys = ["a[0][%d]" % (o, ) for o in parsed_offsets[0][0]]
+ df1_vals = ["a[0][%d]" % (o, )for o in parsed_offsets[0][1]]
Review comment:
space before `for`
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
