記事のディレクトリ
people.txt
Michael,29
Andy,30
Justin,19
EET转データフレーム
scala> val rdd=sc.textFile("people.txt")
rdd: org.apache.spark.rdd.RDD[String] = people.txt MapPartitionsRDD[44] at textFile at <console>:24
1:直接列名とデータ型を指定します
scala> val ds=rdd.map(_.split(",")).map(x=>(x(0),x(1).trim().toInt)).toDF("name","age")
ds: org.apache.spark.sql.DataFrame = [name: string, age: int]
第二の方法:変換を反映させることにより
scala> case class people(name:String,age:Long)
defined class people
scala> rdd.map(_.split(",")).map(x=>(people(x(0),x(1).trim.toInt))).toDF()
res44: org.apache.spark.sql.DataFrame = [name: string, age: bigint]
三つの方法:プログラミングスキーマによって(StructType)
# 在一些时候不能直接定义case类,就用这种方法
scala> val rdd=sc.textFile("people.txt")
rdd: org.apache.spark.rdd.RDD[String] = people.txt MapPartitionsRDD[97] at textFile at <console>:27
scala> val schemaString = "name age"
schemaString: String = name age
scala> import org.apache.spark.sql.types._
import org.apache.spark.sql.types._
scala> val fields = schemaString.split(" ").map(fieldName => StructField(fieldName, StringType, nullable = true))
fields: Array[org.apache.spark.sql.types.StructField] = Array(StructField(name,StringType,true), StructField(age,StringType,true))
scala> val schems=StructType(fields)
schems: org.apache.spark.sql.types.StructType = StructType(StructField(name,StringType,true), StructField(age,StringType,true))
scala> import org.apache.spark.sql._
import org.apache.spark.sql._
scala> val rowrdd=rdd.map(_.split(",")).map(attributes => Row(attributes(0), attributes(1).trim))
rowrdd: org.apache.spark.rdd.RDD[org.apache.spark.sql.Row] = MapPartitionsRDD[99] at map at <console>:35
scala> spark.createDataFrame(rowrdd,schems)
res46: org.apache.spark.sql.DataFrame = [name: string, age: string]
EET转データセット
scala> rdd.map(_.split(",")).map(x=>(x(0),x(1).trim().toInt)).toDS()
res17: org.apache.spark.sql.Dataset[(String, Int)] = [_1: string, _2: int]
データフレーム/データセット转EET
scala> ds.rdd
scala> df.rdd
データフレーム转データセット
scala> case class people(name:String,age:Long)
defined class people
scala> df.as[people]
res39: org.apache.spark.sql.Dataset[people] = [age: bigint, name: string]
データセット转データフレーム
scala> ds.toDF()