[ 
https://issues.apache.org/jira/browse/SPARK-41823?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sandeep Singh updated SPARK-41823:
----------------------------------
    Description: 
{code:java}
File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", 
line 254, in pyspark.sql.connect.dataframe.DataFrame.drop
Failed example:
    df.join(df2, df.name == df2.name, 'inner').drop('name').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.drop[5]>", line 1, 
in <module>
        df.join(df2, df.name == df2.name, 'inner').drop('name').show()
      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: 
[AMBIGUOUS_REFERENCE] Reference `name` is ambiguous, could be: [`name`, `name`].
    Plan: {code}

  was:
{code:java}
File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", 
line 898, in pyspark.sql.connect.dataframe.DataFrame.describe
Failed example:
    df.describe(['age']).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.describe[1]>", 
line 1, in <module>
        df.describe(['age']).show()
      File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", 
line 832, in describe
        raise TypeError(f"'cols' must be list[str], but got {type(s).__name__}")
    TypeError: 'cols' must be list[str], but got list {code}


> DataFrame.join creating ambiguous column names
> ----------------------------------------------
>
>                 Key: SPARK-41823
>                 URL: https://issues.apache.org/jira/browse/SPARK-41823
>             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 254, in pyspark.sql.connect.dataframe.DataFrame.drop
> Failed example:
>     df.join(df2, df.name == df2.name, 'inner').drop('name').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.drop[5]>", line 
> 1, in <module>
>         df.join(df2, df.name == df2.name, 'inner').drop('name').show()
>       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: 
> [AMBIGUOUS_REFERENCE] Reference `name` is ambiguous, could be: [`name`, 
> `name`].
>     Plan: {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

Reply via email to