如何根据等级和值过滤PySpark数据帧中按字段分组的记录

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, sum as _sum

# 初始化SparkSession
spark = SparkSession.builder.appName("FilterByRankAndValue").getOrCreate()

# 假设我们有一个DataFrame df，它有以下列：group_id, value, rank
data = [
    (1, 10, 1),
    (1, 20, 2),
    (2, 30, 1),
    (2, 40, 2),
    (2, 50, 3)
]
columns = ["group_id", "value", "rank"]

df = spark.createDataFrame(data, columns)

# 定义过滤条件，例如我们想要过滤出每个分组中rank为1且value总和大于40的分组
grouped_df = df.groupBy("group_id").agg(_sum("value").alias("total_value"))

# 应用过滤条件
filtered_df = grouped_df.filter((col("rank") == 1) & (col("total_value") > 40))

# 显示结果
filtered_df.show()