[ 
https://issues.apache.org/jira/browse/SPARK-41872?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sandeep Singh updated SPARK-41872:
----------------------------------
    Description: 
{code:java}
row = self.spark.createDataFrame([("Alice", None, None, None)], 
schema).fillna(True).first()
self.assertEqual(row.age, None){code}
{code:java}
Traceback (most recent call last):
  File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", 
line 231, in test_fillna
    self.assertEqual(row.age, None)
AssertionError: nan != None{code}
 
{code:java}
row = (
    self.spark.createDataFrame([("Alice", 10, None)], schema)
    .replace(10, 20, subset=["name", "height"])
    .first()
)
self.assertEqual(row.name, "Alice")
self.assertEqual(row.age, 10)
self.assertEqual(row.height, None) {code}
{code:java}
Traceback (most recent call last):   File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", 
line 372, in test_replace     self.assertEqual(row.height, None) 
AssertionError: nan != None
{code}

  was:
{code:java}
row = self.spark.createDataFrame([("Alice", None, None, None)], 
schema).fillna(True).first()
self.assertEqual(row.age, None){code}
{code:java}
Traceback (most recent call last):
  File 
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", 
line 231, in test_fillna
    self.assertEqual(row.age, None)
AssertionError: nan != None{code}


> Fix DataFrame createDataframe handling of None
> ----------------------------------------------
>
>                 Key: SPARK-41872
>                 URL: https://issues.apache.org/jira/browse/SPARK-41872
>             Project: Spark
>          Issue Type: Sub-task
>          Components: Connect
>    Affects Versions: 3.4.0
>            Reporter: Sandeep Singh
>            Priority: Major
>
> {code:java}
> row = self.spark.createDataFrame([("Alice", None, None, None)], 
> schema).fillna(True).first()
> self.assertEqual(row.age, None){code}
> {code:java}
> Traceback (most recent call last):
>   File 
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py",
>  line 231, in test_fillna
>     self.assertEqual(row.age, None)
> AssertionError: nan != None{code}
>  
> {code:java}
> row = (
>     self.spark.createDataFrame([("Alice", 10, None)], schema)
>     .replace(10, 20, subset=["name", "height"])
>     .first()
> )
> self.assertEqual(row.name, "Alice")
> self.assertEqual(row.age, 10)
> self.assertEqual(row.height, None) {code}
> {code:java}
> Traceback (most recent call last):   File 
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py",
>  line 372, in test_replace     self.assertEqual(row.height, None) 
> AssertionError: nan != None
> {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