使用PySpark删除spark数据帧中嵌套结构中的行(文本中的详细信息)

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

spark = SparkSession.builder.appName("Nested Dataframe").getOrCreate()

data = [
    ("John", [("Math", 90), ("Science", 95)]),
    ("Alice", [("Math", 85), ("Science", 92)]),
    ("Bob", [("Math", 80), ("Science", 88)])
]

df = spark.createDataFrame(data, ["Name", "Subjects"])

df_exploded = df.select(col("Name"), explode(col("Subjects")).alias("Subject"))

df_filtered = df_exploded.filter(col("Subject._2") >= 90)

result = df_filtered.select(col("Name"), col("Subject._1").alias("Subject"), col("Subject._2").alias("Score"))