collect_set去除重復元素；collect_list不去除重復元素select gender, concat_ws(',', collect_set(children)), ...

select gender, age, row_number() over(partition by gender order by age) as rowNumber, ...

val df4=spark.sql("SELECT mean(age),variance(age),stddev(age),corr(age,yearsmarried),skewness(age ...

val df6 = spark.sql("select gender,children,max(age),avg(age),count(age) from Affairs group by Cu ...