使用来自另一个Pyspark数据框的行信息对另一个Pyspark数据框进行过滤和求和

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

spark = SparkSession.builder.appName("FilterAndSum").getOrCreate()

# 创建第一个数据框df1
df1 = spark.createDataFrame([(1, "A", 100), (2, "B", 200), (3, "C", 300)], ["id", "name", "value"])

# 创建第二个数据框df2
df2 = spark.createDataFrame([(1, "A"), (3, "C")], ["id", "name"])

filtered_df = df1.join(df2, on=["id", "name"], how="inner")

sum_df = filtered_df.select(sum("value").alias("sum_value"))

sum_df.show()