Major Description
scala> val df = spark.range(1, 10).withColumn("value", lit(1))
df: org.apache.spark.sql.DataFrame = [id: bigint, value: int]
scala> df.createOrReplaceTempView("table")
scala> df.groupBy("id").agg(count_distinct($"value"))
res1: org.apache.spark.sql.DataFrame = [id: bigint, count(value): bigint]
scala> spark.sql(" SELECT id, COUNT(DISTINCT value) FROM table GROUP BY id ")
res2: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT value): bigint]
scala> df.groupBy("id").agg(count_distinct($"*"))
res3: org.apache.spark.sql.DataFrame = [id: bigint, count(unresolvedstar()): bigint]
scala> spark.sql(" SELECT id, COUNT(DISTINCT *) FROM table GROUP BY id ")
res4: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT id, value): bigint]
