是否可以在Spark中根据列的值的总和来过滤列？

from pyspark.sql import SparkSession
from pyspark.sql.functions import sum, col, when

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

# 读取数据
df = spark.read.csv("data.csv", header=True, inferSchema=True)

# 计算列的值的总和
total_sum = df.select(sum(col("column_name"))).collect()[0][0]

# 根据总和的值过滤列
filtered_df = df.filter(when(col("column_name") > total_sum, True).otherwise(False))

# 显示过滤后的结果
filtered_df.show()