Github user cloud-fan commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18307#discussion_r125873943
  
    --- Diff: sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala 
---
    @@ -712,6 +707,76 @@ class DataFrameSuite extends QueryTest with 
SharedSQLContext {
         checkAnswer(emptyDescription, emptyDescribeResult)
       }
     
    +  test("summary") {
    +    val describeTestData = person2
    +
    +    val describeResult = Seq(
    +      Row("count", "4", "4", "4"),
    +      Row("mean", null, "33.0", "178.0"),
    +      Row("stddev", null, "19.148542155126762", "11.547005383792516"),
    +      Row("min", "Alice", "16", "164"),
    +      Row("25%", null, "24.0", "176.0"),
    +      Row("50%", null, "24.0", "176.0"),
    +      Row("75%", null, "32.0", "180.0"),
    +      Row("max", "David", "60", "192"))
    +
    +    val emptyDescribeResult = Seq(
    +      Row("count", "0", "0", "0"),
    +      Row("mean", null, null, null),
    +      Row("stddev", null, null, null),
    +      Row("min", null, null, null),
    +      Row("25%", null, null, null),
    +      Row("50%", null, null, null),
    +      Row("75%", null, null, null),
    +      Row("max", null, null, null))
    +
    +    def getSchemaAsSeq(df: DataFrame): Seq[String] = df.schema.map(_.name)
    +
    +    val describeTwoCols = describeTestData.summary()
    +    assert(getSchemaAsSeq(describeTwoCols) === Seq("summary", "name", 
"age", "height"))
    +    checkAnswer(describeTwoCols, describeResult)
    +    // All aggregate value should have been cast to string
    +    describeTwoCols.collect().foreach { row =>
    +      assert(row.get(2).isInstanceOf[String], "expected string but found " 
+ row.get(2).getClass)
    +      assert(row.get(3).isInstanceOf[String], "expected string but found " 
+ row.get(3).getClass)
    +    }
    +
    +    val describeAllCols = describeTestData.summary()
    +    assert(getSchemaAsSeq(describeAllCols) === Seq("summary", "name", 
"age", "height"))
    +    checkAnswer(describeAllCols, describeResult)
    +
    +    val describeOneCol = describeTestData.select("age").summary()
    +    assert(getSchemaAsSeq(describeOneCol) === Seq("summary", "age"))
    +    checkAnswer(describeOneCol, describeResult.map { case Row(s, _, d, _) 
=> Row(s, d)} )
    +
    +    val describeNoCol = describeTestData.select("name").summary()
    --- End diff --
    
    `describeNoCol`?


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to