你可以加入，分组 v1 并得到 c3 .

import pyspark.sql.functions as F

result = (df1.join(df2, df1.c2 == df2.v1)
             .groupBy('v1')
             .agg(F.countDistinct('c3').alias('v2'))
         )

result.show()
+---+---+
| v1| v2|
+---+---+
|193|  2|
|192|  2|
|194|  1|
+---+---+

您可以尝试以下操作：

from pyspark.sql.types import *
from pyspark.sql.functions import *
sdf1 = spark.createDataFrame([
(1,192,1),
(3,192,2),
(4,193,3),
(5,193,3),
(7,193,5),
(9,194,7)
], ["c1", "c2", "c3"])

df2 = spark.createDataFrame([
(192,),
(193,),
(194,)
], ["v1"])

df1 = sdf1.groupBy("c2").agg(countDistinct("c3").alias("cnt"))
df2.join(df1, df1.c2 == df2.v1).select(df2.v1,df1.cnt).show()