为聚合列提供别名，并在pyspark中使用groupBy对结果进行舍入

from pyspark.sql import SparkSession
from pyspark.sql.functions import avg

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

# 创建DataFrame
df = spark.createDataFrame([(1, "Alice", 25),
                            (2, "Bob", 30),
                            (3, "Alice", 35),
                            (4, "Bob", 40)], ["id", "name", "age"])

# 按照name列进行分组，并计算平均年龄，并为结果列提供别名
result = df.groupBy("name").agg(avg("age").alias("avg_age"))

# 显示结果
result.show()

+-----+-------+
| name|avg_age|
+-----+-------+
|Alice|   30.0|
|  Bob|   35.0|
+-----+-------+

from pyspark.sql import SparkSession
from pyspark.sql.functions import avg, round

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

# 创建DataFrame
df = spark.createDataFrame([(1, "Alice", 85.123),
                            (2, "Bob", 90.456),
                            (3, "Alice", 95.789),
                            (4, "Bob", 80.123)], ["id", "name", "score"])

# 按照name列进行分组，并计算平均分数，并进行舍入
result = df.groupBy("name").agg(round(avg("score"), 2).alias("avg_score"))

# 显示结果
result.show()

+-----+---------+
| name|avg_score|
+-----+---------+
|Alice|    90.46|
|  Bob|    85.29|
+-----+---------+