获取PySpark列中列表列表中第一个元素的最大值

from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import IntegerType

spark = SparkSession.builder.getOrCreate()

get_first_element = udf(lambda x: x[0], IntegerType())

data = [(1, [4, 2, 3]), (2, [1, 5, 2]), (3, [6, 2, 9])]
df = spark.createDataFrame(data, ["id", "list_col"])

max_first_element = df.select(get_first_element(df.list_col)).agg({"<lambda>(list_col)": "max"}).collect()[0][0]

print("列表列表中第一个元素的最大值为:", max_first_element)