Resolved attribute(s) <attr> missing from ...

from pyspark.sql import SparkSession
import pandas as pd
from pyspark.sql.functions import pandas_udf, PandasUDFType
from pyspark.sql.types import *

spark = SparkSession \
 .builder \
 .master("local[*]") \
 .appName("bug") \
 .getOrCreate()
spark.sparkContext.setLogLevel("ERROR")
spark.conf.set("spark.sql.execution.arrow.enabled", "true")

df = spark.createDataFrame(
 [
 (1, "Joey", "Richard", None),
 (2, "Stephane", "Boudreau", 36),
 (2, "Rejean", "Lapierre", 34)
 ],
 ["id", "first_name", "last", "age"]
)

@pandas_udf("integer", PandasUDFType.SCALAR)
def plus_five(p):
 return p.age + 5

df2 = df.fillna({"age": 99}).withColumn("age_5", plus_five(df.age))

df2.show()

Traceback (most recent call last):Traceback (most recent call last):  File "/usr/local/Cellar/apache-spark/2.4.5/libexec/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco  File "/usr/local/Cellar/apache-spark/2.4.5/libexec/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_valuepy4j.protocol.Py4JJavaError: An error occurred while calling o70.withColumn.: org.apache.spark.sql.AnalysisException: Resolved attribute(s) age#3L missing from id#0L,first_name#1,last#2,age#12L in operator !Project [id#0L, first_name#1, last#2, age#12L, plus_five(age#3L) AS age_5#18]. Attribute(s) with the same name appear in the operation: age. Please check if the right attribute(s) are used.;;!Project [id#0L, first_name#1, last#2, age#12L, plus_five(age#3L) AS age_5#18]+- Project [id#0L, first_name#1, last#2, coalesce(age#3L, cast(99 as bigint)) AS age#12L]   +- LogicalRDD [id#0L, first_name#1, last#2, age#3L], false
 at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:43) at org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:95) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:369) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:86) at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:126) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:86) at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:95) at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:108) at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201) at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105) at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:58) at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:56) at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:48) at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:3412) at org.apache.spark.sql.Dataset.select(Dataset.scala:1340) at org.apache.spark.sql.Dataset.withColumns(Dataset.scala:2258) at org.apache.spark.sql.Dataset.withColumn(Dataset.scala:2225) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:748)During handling of the above exception, another exception occurred:
Traceback (most recent call last):  File "/Users/yvesrichard/Documents/projects/premise/spark-play/bug.py", line 29, in <module>    df2 = df.fillna({"age": 99}).withColumn("age_5", plus_five(df.age))  File "/usr/local/Cellar/apache-spark/2.4.5/libexec/python/lib/pyspark.zip/pyspark/sql/dataframe.py", line 1997, in withColumn  File "/usr/local/Cellar/apache-spark/2.4.5/libexec/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__  File "/usr/local/Cellar/apache-spark/2.4.5/libexec/python/lib/pyspark.zip/pyspark/sql/utils.py", line 69, in decopyspark.sql.utils.AnalysisException: 'Resolved attribute(s) age#3L missing from id#0L,first_name#1,last#2,age#12L in operator !Project [id#0L, first_name#1, last#2, age#12L, plus_five(age#3L) AS age_5#18]. Attribute(s) with the same name appear in the operation: age. Please check if the right attribute(s) are used.;;\n!Project [id#0L, first_name#1, last#2, age#12L, plus_five(age#3L) AS age_5#18]\n+- Project [id#0L, first_name#1, last#2, coalesce(age#3L, cast(99 as bigint)) AS age#12L]\n   +- LogicalRDD [id#0L, first_name#1, last#2, age#3L], false\n'