[
https://issues.apache.org/jira/browse/SPARK-41835?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41835:
--
Description:
{code:java}
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1611, in pyspark.sql.connect.functions.transform_keys
Failed example:
df.select(transform_keys(
"data", lambda k, _: upper(k)).alias("data_upper")
).show(truncate=False)
Exception raised:
Traceback (most recent call last):
File
"/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py",
line 1350, in __run
exec(compile(example.source, filename, "single",
File "", line 1,
in
df.select(transform_keys(
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 534, in show
print(self._show_string(n, truncate, vertical))
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 423, in _show_string
).toPandas()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1031, in toPandas
return self._session.client.to_pandas(query)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
413, in to_pandas
return self._execute_and_fetch(req)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
573, in _execute_and_fetch
self._handle_error(rpc_error)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
619, in _handle_error
raise SparkConnectAnalysisException(
pyspark.sql.connect.client.SparkConnectAnalysisException:
[DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE] Cannot resolve "transform_keys(data,
lambdafunction(upper(x_11), x_11, y_12))" due to data type mismatch: Parameter
1 requires the "MAP" type, however "data" has the type "STRUCT".
Plan: 'Project [transform_keys(data#4493, lambdafunction('upper(lambda
'x_11), lambda 'x_11, lambda 'y_12, false)) AS data_upper#4496]
+- Project [0#4488L AS id#4492L, 1#4489 AS data#4493]
+- LocalRelation [0#4488L, 1#4489] {code}
> Implement `transform_keys` function
> ---
>
> Key: SPARK-41835
> URL: https://issues.apache.org/jira/browse/SPARK-41835
> Project: Spark
> Issue Type: Sub-task
> Components: Connect, PySpark
>Affects Versions: 3.4.0
>Reporter: Sandeep Singh
>Priority: Major
> Fix For: 3.4.0
>
>
> {code:java}
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
> line 1611, in pyspark.sql.connect.functions.transform_keys
> Failed example:
> df.select(transform_keys(
> "data", lambda k, _: upper(k)).alias("data_upper")
> ).show(truncate=False)
> Exception raised:
> Traceback (most recent call last):
> File
> "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py",
> line 1350, in __run
> exec(compile(example.source, filename, "single",
> File "", line
> 1, in
> df.select(transform_keys(
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 534, in show
> print(self._show_string(n, truncate, vertical))
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 423, in _show_string
> ).toPandas()
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 1031, in toPandas
> return self._session.client.to_pandas(query)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py",
> line 413, in to_pandas
> return self._execute_and_fetch(req)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py",
> line 573, in _execute_and_fetch
> self._handle_error(rpc_error)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py",
> line 619, in _handle_error
> raise SparkConnectAnalysisException(
> pyspark.sql.connect.client.SparkConnectAnalysisException:
> [DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE] Cannot resolve
> "transform_keys(data, lambdafunction(upper(x_11), x_11, y_12))" due to data
> type mismatch: Parameter 1 requires the "MAP" type, however "data" has the
> type "STRUCT".
> Plan: 'Project [transform_keys(data#4493, lambdafunction('upper(lambda
> 'x_11), lambda 'x_11, lambda 'y_12, false)) AS data_upper#4496]
> +- Project [0#4488L AS id#4492L, 1#4489 AS data#4493]
> +- LocalRelation [0#4488L, 1#4489] {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---