来自两个不同表Pyspark的数据帧中的CountDistinct

from pyspark.sql import SparkSession
from pyspark.sql.functions import countDistinct

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

df1 = spark.read.format("csv").option("header", "true").load("table1.csv")
df2 = spark.read.format("csv").option("header", "true").load("table2.csv")

distinct_count_df1 = df1.select(countDistinct("column_name"))
distinct_count_df2 = df2.select(countDistinct("column_name"))

distinct_count_df1.show()
distinct_count_df2.show()