amaliujia commented on code in PR #40070:
URL: https://github.com/apache/spark/pull/40070#discussion_r1110380640
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala:
##########
@@ -149,4 +149,111 @@ class RelationalGroupedDataset protected[sql] (
}
builder.build()
}
+
+ /**
+ * Compute aggregates by specifying a series of aggregate columns. Note that
this function by
+ * default retains the grouping columns in its output. To not retain
grouping columns, set
+ * `spark.sql.retainGroupColumns` to false.
+ *
+ * The available aggregate methods are defined in
[[org.apache.spark.sql.functions]].
+ *
+ * {{{
+ * // Selects the age of the oldest employee and the aggregate expense for
each department
+ *
+ * // Scala:
+ * import org.apache.spark.sql.functions._
+ * df.groupBy("department").agg(max("age"), sum("expense"))
+ *
+ * // Java:
+ * import static org.apache.spark.sql.functions.*;
+ * df.groupBy("department").agg(max("age"), sum("expense"));
+ * }}}
+ *
+ * Note that before Spark 1.4, the default behavior is to NOT retain
grouping columns. To change
+ * to that behavior, set config variable `spark.sql.retainGroupColumns` to
`false`.
+ * {{{
+ * // Scala, 1.3.x:
+ * df.groupBy("department").agg($"department", max("age"), sum("expense"))
+ *
+ * // Java, 1.3.x:
+ * df.groupBy("department").agg(col("department"), max("age"),
sum("expense"));
+ * }}}
+ *
+ * @since 3.4.0
+ */
+ @scala.annotation.varargs
+ def agg(expr: Column, exprs: Column*): DataFrame = {
+ toDF((expr +: exprs).map { case c =>
+ c
+ // TODO: deal with typed columns.
+ })
+ }
+
+ /**
+ * Count the number of rows for each group. The resulting `DataFrame` will
also contain the
+ * grouping columns.
+ *
+ * @since 3.4.0
+ */
+ def count(): DataFrame =
toDF(Seq(functions.count(functions.lit(1)).alias("count")))
+
+ /**
+ * Compute the average value for each numeric columns for each group. This
is an alias for
+ * `avg`. The resulting `DataFrame` will also contain the grouping columns.
When specified
+ * columns are given, only compute the average values for them.
+ *
+ * @since 3.4.0
+ */
+ @scala.annotation.varargs
+ def mean(colNames: String*): DataFrame = {
+ toDF(colNames.map(colName => functions.mean(colName)).toSeq)
Review Comment:
hmmm I see. Removing those `toSeq`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
