Решение без окна (Не очень красиво ..) и самое простое, на мой взгляд, решение rdd:
from pyspark.sql import functions as F
from pyspark.sql import HiveContext
hiveCtx = HiveContext(sc)
rdd = sc.parallelize([(1 , "abc" , "short-alias"),
(1 , "abc" , "short"),
(1 , "abc" , "ailas-long-1"),
(1 , "abc" , "another-long-alias"),
(2 , "xyz" , "same_length"),
(2 , "xyz" , "same_length1"),
(3 , "def" , "short_alias") ])
df = hiveCtx.createDataFrame(\
rdd, ["id", "name", "alias"])
len_df = df.groupBy(["id", "name"]).agg(F.min(F.length("alias")).alias("alias_len"))
df = df.withColumn("alias_len", F.length("alias"))
cond = ["alias_len", "id", "name"]
df.join(len_df, cond).show()
print rdd.map(lambda x: ((x[0], x[1]), x[2]))\
.reduceByKey(lambda x,y: x if len(x) < len(y) else y ).collect()
Выход:
+---------+---+----+-----------+
|alias_len| id|name| alias|
+---------+---+----+-----------+
| 11| 3| def|short_alias|
| 11| 2| xyz|same_length|
| 5| 1| abc| short|
+---------+---+----+-----------+
[((2, 'xyz'), 'same_length'), ((3, 'def'), 'short_alias'), ((1, 'abc'), 'short')]