将pyspark groupedData转换为pandas DataFrame

# 导入必要的库
from pyspark.sql import SparkSession
import pandas as pd

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

# 创建示例数据
data = [("Alice", "Math", 80),
        ("Alice", "Science", 90),
        ("Bob", "Math", 75),
        ("Bob", "Science", 85),
        ("Bob", "English", 70)]

# 创建pyspark DataFrame
df = spark.createDataFrame(data, ["Name", "Subject", "Score"])

# 使用groupby函数进行分组操作
grouped_data = df.groupby("Name")

# 使用agg函数进行聚合操作
aggregated_data = grouped_data.agg({"Score": "avg"})

# 将聚合结果转换为pyspark DataFrame
aggregated_df = aggregated_data.toDF("Name", "AverageScore")

# 将pyspark DataFrame转换为pandas DataFrame
pandas_df = aggregated_df.toPandas()

# 打印结果
print(pandas_df)