从PySpark中的两个不同数据帧中减去列的值，得到均方根

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

spark = SparkSession.builder.appName("Calculate RMSE").getOrCreate()

df1 = spark.read.csv("path_to_file1.csv", header=True, inferSchema=True)
df2 = spark.read.csv("path_to_file2.csv", header=True, inferSchema=True)

df_diff = df1.select(col("column1") - col("column2")).alias("diff")
rmse = df_diff.select(sqrt(df_diff["diff"])).alias("rmse")

rmse.show()