pyspark根据groupby列获取流数据的不同值

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

# 创建SparkSession
spark = SparkSession.builder.appName("GroupByExample").getOrCreate()

# 创建示例数据
data = [("Alice", 25), ("Bob", 30), ("Alice", 35), ("Bob", 40), ("Alice", 45)]
df = spark.createDataFrame(data, ["Name", "Age"])

# 根据Name列进行分组，并获取Age列的不同值
result = df.groupBy("Name").agg(collect_set("Age").alias("Distinct_Ages"))

# 显示结果
result.show(truncate=False)

+-----+-------------+
|Name |Distinct_Ages|
+-----+-------------+
|Alice|[25, 35, 45] |
|Bob  |[40, 30]     |
+-----+-------------+