>>> df.show()
+---+-------+-----+-------+
| id| ranges|score|    uom|
+---+-------+-----+-------+
|  1|    low|   20|percent|
|  1|verylow|   10|percent|
|  1|   high|   70|  bytes|
|  1| medium|   40|percent|
|  1|   high|   60|percent|
|  1|verylow|   10|percent|
|  1|   high|   70|percent|
+---+-------+-----+-------+

results = spark.sql('select percentile_approx(score,0.95) as score, first(ranges)  from subset GROUP BY id')

>>> results.show()
+-----+--------------------+
|score|first(ranges, false)|
+-----+--------------------+
|   70|                 low|
+-----+--------------------+

> pyspark.sql.utils.AnalysisException: u"expression 'subset.`ranges`' is
> neither present in the group by, nor is it an aggregate function. Add
> to group by or wrap in first() (or first_value) if you don't care
> which value you get.;;nAggregate [id#0L],
> [percentile_approx(score#2L, cast(0.95 as double), 10000, 0, 0) AS
> score#353L, ranges#1]n+- SubqueryAlias subsetn   +- LogicalRDD
> [id#0L, ranges#1, score#2L, uom#3], falsen

>>> map = spark.sql('select ranges, score from df')

>>> results = spark.sql('select percentile_approx(score,0.95) as score from subset GROUP BY id')

>>> final_result = spark.sql('select r.score, m.ranges from results as r join map as m on r.score = m.score')