[
https://issues.apache.org/jira/browse/SPARK-41831?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41831:
----------------------------------
Description:
{code:java}
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1168, in pyspark.sql.connect.dataframe.DataFrame.transform
Failed example:
df.transform(cast_all_to_int).transform(sort_columns_asc).show()
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 "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[4]>",
line 1, in <module>
df.transform(cast_all_to_int).transform(sort_columns_asc).show()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1102, in transform
result = func(self, *args, **kwargs)
File "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[2]>",
line 2, in cast_all_to_int
return input_df.select([col(col_name).cast("int") for col_name in
input_df.columns])
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 86, in select
return DataFrame.withPlan(plan.Project(self._plan, *cols),
session=self._session)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
344, in __init__
self._verify_expressions()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
350, in _verify_expressions
raise InputValidationError(
pyspark.sql.connect.plan.InputValidationError: Only Column or String can be
used for projections: '[Column<'(ColumnReference(int) (int))'>,
Column<'(ColumnReference(float) (int))'>]'.
**********************************************************************
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1179, in pyspark.sql.connect.dataframe.DataFrame.transform
Failed example:
df.transform(add_n, 1).transform(add_n, n=10).show()
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 "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[6]>",
line 1, in <module>
df.transform(add_n, 1).transform(add_n, n=10).show()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1102, in transform
result = func(self, *args, **kwargs)
File "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[5]>",
line 2, in add_n
return input_df.select([(col(col_name) + n).alias(col_name)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 86, in select
return DataFrame.withPlan(plan.Project(self._plan, *cols),
session=self._session)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
344, in __init__
self._verify_expressions()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
350, in _verify_expressions
raise InputValidationError(
pyspark.sql.connect.plan.InputValidationError: Only Column or String can be
used for projections: '[Column<'Alias(+(ColumnReference(int), Literal(1)),
(int))'>, Column<'Alias(+(ColumnReference(float), Literal(1)),
(float))'>]'.{code}
was:
{code:java}
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 401, in pyspark.sql.connect.dataframe.DataFrame.sample
Failed example:
df.sample(0.5, 3).count()
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 "<doctest pyspark.sql.connect.dataframe.DataFrame.sample[1]>", line
1, in <module>
df.sample(0.5, 3).count()
TypeError: DataFrame.sample() takes 2 positional arguments but 3 were given
**********************************************************************
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 411, in pyspark.sql.connect.dataframe.DataFrame.sample
Failed example:
df.sample(False, fraction=1.0).count()
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 "<doctest pyspark.sql.connect.dataframe.DataFrame.sample[6]>", line
1, in <module>
df.sample(False, fraction=1.0).count()
TypeError: DataFrame.sample() got multiple values for argument
'fraction'{code}
> DataFrame.transform: Only Column or String can be used for projections
> ----------------------------------------------------------------------
>
> Key: SPARK-41831
> URL: https://issues.apache.org/jira/browse/SPARK-41831
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 1168, in pyspark.sql.connect.dataframe.DataFrame.transform
> Failed example:
> df.transform(cast_all_to_int).transform(sort_columns_asc).show()
> 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 "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[4]>",
> line 1, in <module>
> df.transform(cast_all_to_int).transform(sort_columns_asc).show()
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 1102, in transform
> result = func(self, *args, **kwargs)
> File "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[2]>",
> line 2, in cast_all_to_int
> return input_df.select([col(col_name).cast("int") for col_name in
> input_df.columns])
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 86, in select
> return DataFrame.withPlan(plan.Project(self._plan, *cols),
> session=self._session)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
> 344, in __init__
> self._verify_expressions()
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
> 350, in _verify_expressions
> raise InputValidationError(
> pyspark.sql.connect.plan.InputValidationError: Only Column or String can
> be used for projections: '[Column<'(ColumnReference(int) (int))'>,
> Column<'(ColumnReference(float) (int))'>]'.
> **********************************************************************
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 1179, in pyspark.sql.connect.dataframe.DataFrame.transform
> Failed example:
> df.transform(add_n, 1).transform(add_n, n=10).show()
> 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 "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[6]>",
> line 1, in <module>
> df.transform(add_n, 1).transform(add_n, n=10).show()
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 1102, in transform
> result = func(self, *args, **kwargs)
> File "<doctest pyspark.sql.connect.dataframe.DataFrame.transform[5]>",
> line 2, in add_n
> return input_df.select([(col(col_name) + n).alias(col_name)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
> line 86, in select
> return DataFrame.withPlan(plan.Project(self._plan, *cols),
> session=self._session)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
> 344, in __init__
> self._verify_expressions()
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/plan.py", line
> 350, in _verify_expressions
> raise InputValidationError(
> pyspark.sql.connect.plan.InputValidationError: Only Column or String can
> be used for projections: '[Column<'Alias(+(ColumnReference(int), Literal(1)),
> (int))'>, Column<'Alias(+(ColumnReference(float), Literal(1)),
> (float))'>]'.{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
