pyspark: collect_list()如何存储每行组中剩余元素的列表

from pyspark.sql import SparkSession
from pyspark.sql.functions import collect_list

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

# 创建示例数据
data = [("group1", "value1"),
        ("group1", "value2"),
        ("group2", "value3"),
        ("group2", "value4")]

df = spark.createDataFrame(data, ["group", "value"])

# 使用collect_list()函数将每行组中剩余元素存储为列表
result = df.groupBy("group").agg(collect_list("value").alias("value_list"))

# 显示结果
result.show(truncate=False)

+------+----------------+
|group |value_list      |
+------+----------------+
|group1|[value1, value2]|
|group2|[value3, value4]|
+------+----------------+