[ 
https://issues.apache.org/jira/browse/SPARK-41871?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sandeep Singh updated SPARK-41871:
----------------------------------
    Description: 
{code:java}
df = self.spark.range(10e10).toDF("id")
such_a_nice_list = ["itworks1", "itworks2", "itworks3"]
hinted_df = df.hint("my awesome hint", 1.2345, "what", such_a_nice_list){code}
{code:java}
Traceback (most recent call last):
  File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", 
line 556, in test_extended_hint_types
    hinted_df = df.hint("my awesome hint", 1.2345, "what", such_a_nice_list)
  File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", 
line 482, in hint
    raise TypeError(
TypeError: param should be a int or str, but got float 1.2345{code}

  was:
{code:java}
df = self.spark.createDataFrame([("Alice", 50), ("Alice", 60)], ["name", "age"])

# shouldn't drop a non-null row
self.assertEqual(df.dropDuplicates().count(), 2)

self.assertEqual(df.dropDuplicates(["name"]).count(), 1)

self.assertEqual(df.dropDuplicates(["name", "age"]).count(), 2)

type_error_msg = "Parameter 'subset' must be a list of columns"
with self.assertRaisesRegex(TypeError, type_error_msg):
    df.dropDuplicates("name"){code}
{code:java}
Traceback (most recent call last):
  File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", 
line 128, in test_drop_duplicates
    with self.assertRaisesRegex(TypeError, type_error_msg):
AssertionError: TypeError not raised{code}


> DataFrame hint parameter can be str, list, float or int
> -------------------------------------------------------
>
>                 Key: SPARK-41871
>                 URL: https://issues.apache.org/jira/browse/SPARK-41871
>             Project: Spark
>          Issue Type: Sub-task
>          Components: Connect
>    Affects Versions: 3.4.0
>            Reporter: Sandeep Singh
>            Priority: Major
>
> {code:java}
> df = self.spark.range(10e10).toDF("id")
> such_a_nice_list = ["itworks1", "itworks2", "itworks3"]
> hinted_df = df.hint("my awesome hint", 1.2345, "what", such_a_nice_list){code}
> {code:java}
> Traceback (most recent call last):
>   File 
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py",
>  line 556, in test_extended_hint_types
>     hinted_df = df.hint("my awesome hint", 1.2345, "what", such_a_nice_list)
>   File 
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", 
> line 482, in hint
>     raise TypeError(
> TypeError: param should be a int or str, but got float 1.2345{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