Spark SQL DataFrame新增一列的四种方法

方法一：利用createDataFrame方法，新增列的过程包含在构建rdd和schema中
方法二：利用withColumn方法，新增列的过程包含在udf函数中
方法三：利用SQL代码，新增列的过程直接写入SQL代码中
方法四：以上三种是增加一个有判断的列，如果想要增加一列唯一序号，可以使用monotonically_increasing_id

代码块：

//dataframe新增一列方法1，利用createDataFrame方法
val trdd = input.select(targetColumns).rdd.map(x=>{ if (x.get(0).toString().toDouble > critValueR || x.get(0).toString().toDouble < critValueL) Row(x.get(0).toString().toDouble,"F") else Row(x.get(0).toString().toDouble,"T") }) val schema = input.select(targetColumns).schema.add("flag", StringType, true) val sample3 = ss.createDataFrame(trdd, schema).distinct().withColumnRenamed(targetColumns, "idx") //dataframe新增一列方法2
val code :(Int => String) = (arg: Int) => {if (arg > critValueR || arg < critValueL) "F" else "T"} val addCol = udf(code) val sample3 = input.select(targetColumns).withColumn("flag", addCol(input(targetColumns))) .withColumnRenamed(targetColumns, "idx") //dataframe新增一列方法3
input.select(targetColumns).createOrReplaceTempView("tmp") val sample3 = ss.sqlContext.sql("select distinct "+targetColname+
    " as idx,case when "+targetColname+">"+critValueR+" then 'F'"+
    " when "+targetColname+"<"+critValueL+" then 'F' else 'T' end as flag from tmp") //添加序号列新增一列方法4
import org.apache.spark.sql.functions.monotonically_increasing_id val inputnew = input.withColumn("idx", monotonically_increasing_id)