在pyspark中保持至少有一个元素满足条件的组

from pyspark.sql import SparkSession

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

# 创建示例数据
data = [("group1", 1), ("group1", 2), ("group2", 3), ("group3", 4), ("group3", 5)]
df = spark.createDataFrame(data, ["group", "value"])

# 按照组进行分组
grouped_df = df.groupBy("group")

# 筛选出至少有一个元素满足条件的组
filtered_df = grouped_df.filter(lambda x: x["value"] > 3)

# 显示结果
filtered_df.show()