在Pyspark中插入Null时间戳值

from pyspark.sql import SparkSession
from pyspark.sql.functions import lit
from pyspark.sql.types import TimestampType

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据集
data = [("John", None), ("Alice", "2022-01-01 12:00:00")]

# 创建DataFrame
df = spark.createDataFrame(data, ["name", "timestamp"])

# 将Null时间戳值插入到DataFrame中
df = df.withColumn("timestamp", lit(None).cast(TimestampType()))

# 显示DataFrame
df.show()

+-----+---------+
| name|timestamp|
+-----+---------+
| John|     null|
|Alice|     null|
+-----+---------+