在pyspark中将空值替换/转换为空数组

from pyspark.sql import SparkSession
from pyspark.sql.functions import col
from pyspark.sql.functions import udf
from pyspark.sql.types import *

spark = SparkSession.builder.appName("ReplaceNullArray").getOrCreate()

data = [("John", 25, None), 
        ("Alice", None, [1, 2, 3]), 
        ("Bob", 30, None)]
df = spark.createDataFrame(data, ["name", "age", "array_column"])
df.show()

def replace_null_with_empty_array(array_column):
    if array_column is None:
        return []
    else:
        return array_column

replace_null_with_empty_array_udf = udf(replace_null_with_empty_array, ArrayType(IntegerType()))

df = df.withColumn("array_column", replace_null_with_empty_array_udf(col("array_column")))
df.show()

+-----+----+------------+
| name| age|array_column|
+-----+----+------------+
| John|  25|          []|
|Alice|null|   [1, 2, 3]|
|  Bob|  30|          []|
+-----+----+------------+