使用pyspark查找每个相应列的两个数据帧上的值的差异

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

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

data1 = [("John", 25, "USA"), ("Alice", 30, "Canada"), ("Bob", 35, "UK")]
data2 = [("John", 25, "USA"), ("Alice", 28, "Canada"), ("Bob", 35, "UK")]

df1 = spark.createDataFrame(data1, ["Name", "Age", "Country"])
df2 = spark.createDataFrame(data2, ["Name", "Age", "Country"])

joined_df = df1.join(df2, on=["Name", "Age"], how="inner")

diff_df = joined_df.select("Name", "Age", (col("Country_x") != col("Country_y")).alias("CountryDiff"))

diff_df.show()