一文了解 Nebula Graph 上的 Spark 项目

  def readVertex(spark: SparkSession): Unit = {
    LOG.info("start to read nebula vertices")
    val config =
      NebulaConnectionConfig
        .builder()
        .withMetaAddress("metad0:9559,metad1:9559,metad2:9559")
        .withConenctionRetry(2)
        .build()
    val nebulaReadVertexConfig: ReadNebulaConfig = ReadNebulaConfig
      .builder()
      .withSpace("basketballplayer")
      .withLabel("player")
      .withNoColumn(false)
      .withReturnCols(List("name", "age"))
      .withLimit(10)
      .withPartitionNum(10)
      .build()
    val vertex = spark.read.nebula(config, nebulaReadVertexConfig).loadVerticesToDF()
    vertex.printSchema()
    vertex.show(20)
    println("vertex count: " + vertex.count())
  }

docker exec -it sparkmaster bash
# in the container shell

export MAVEN_VERSION=3.5.4
export MAVEN_HOME=/usr/lib/mvn
export PATH=$MAVEN_HOME/bin:$PATH

wget http://archive.apache.org/dist/maven/maven-3/$MAVEN_VERSION/binaries/apache-maven-$MAVEN_VERSION-bin.tar.gz && \
  tar -zxvf apache-maven-$MAVEN_VERSION-bin.tar.gz && \
  rm apache-maven-$MAVEN_VERSION-bin.tar.gz && \
  mv apache-maven-$MAVEN_VERSION /usr/lib/mvn

# call Nebula Spark Connector Reader
df = spark.read.format(
  "com.vesoft.nebula.connector.NebulaDataSource").option(
    "type", "vertex").option(
    "spaceName", "basketballplayer").option(
    "label", "player").option(
    "returnCols", "name,age").option(
    "metaAddress", "metad0:9559").option(
    "partitionNumber", 1).load()

# show the dataframe with limit of 2
df.show(n=2)

      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /__ / .__/\_,_/_/ /_/\_\   version 2.4.5
      /_/

Using Python version 2.7.16 (default, Jan 14 2020 07:22:06)
SparkSession available as 'spark'.
>>> df = spark.read.format(
...   "com.vesoft.nebula.connector.NebulaDataSource").option(
...     "type", "vertex").option(
...     "spaceName", "basketballplayer").option(
...     "label", "player").option(
...     "returnCols", "name,age").option(
...     "metaAddress", "metad0:9559").option(
...     "partitionNumber", 1).load()
>>> df.show(n=2)
+---------+--------------+---+
|_vertexId|          name|age|
+---------+--------------+---+
|player105|   Danny Green| 31|
|player109|Tiago Splitter| 34|
+---------+--------------+---+
only showing top 2 rows

package com.vesoft.nebula.examples.connector

import com.facebook.thrift.protocol.TCompactProtocol
import com.vesoft.nebula.connector.connector.NebulaDataFrameReader
import com.vesoft.nebula.connector.{NebulaConnectionConfig, ReadNebulaConfig}
import org.apache.spark.SparkConf
import org.apache.spark.sql.SparkSession
import org.slf4j.LoggerFactory

object NebulaSparkReaderExample {

  private val LOG = LoggerFactory.getLogger(this.getClass)

  def main(args: Array[String]): Unit = {

    val sparkConf = new SparkConf
    sparkConf
      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
      .registerKryoClasses(Array[Class[_]](classOf[TCompactProtocol]))
    val spark = SparkSession
      .builder()
      .master("local")
      .config(sparkConf)
      .getOrCreate()

    readVertex(spark)
    readEdges(spark)

    spark.close()
    sys.exit()
  }

  def readVertex(spark: SparkSession): Unit = {
    LOG.info("start to read nebula vertices")
    val config =
      NebulaConnectionConfig
        .builder()
        .withMetaAddress("metad0:9559,metad1:9559,metad2:9559")
        .withConenctionRetry(2)
        .build()
    val nebulaReadVertexConfig: ReadNebulaConfig = ReadNebulaConfig
      .builder()
      .withSpace("basketballplayer")
      .withLabel("player")
      .withNoColumn(false)
      .withReturnCols(List("name", "age"))
      .withLimit(10)
      .withPartitionNum(10)
      .build()
    val vertex = spark.read.nebula(config, nebulaReadVertexConfig).loadVerticesToDF()
    vertex.printSchema()
    vertex.show(20)
    println("vertex count: " + vertex.count())
  }

  def readEdges(spark: SparkSession): Unit = {
    LOG.info("start to read nebula edges")

    val config =
      NebulaConnectionConfig
        .builder()
        .withMetaAddress("metad0:9559,metad1:9559,metad2:9559")
        .withTimeout(6000)
        .withConenctionRetry(2)
        .build()
    val nebulaReadEdgeConfig: ReadNebulaConfig = ReadNebulaConfig
      .builder()
      .withSpace("basketballplayer")
      .withLabel("follow")
      .withNoColumn(false)
      .withReturnCols(List("degree"))
      .withLimit(10)
      .withPartitionNum(10)
      .build()
    val edge = spark.read.nebula(config, nebulaReadEdgeConfig).loadEdgesToDF()
    edge.printSchema()
    edge.show(20)
    println("edge count: " + edge.count())
  }

}

22/04/19 07:29:34 INFO DAGScheduler: Job 1 finished: show at NebulaSparkReaderExample.scala:57, took 0.199310 s
+---------+------------------+---+
|_vertexId|              name|age|
+---------+------------------+---+
|player105|       Danny Green| 31|
|player109|    Tiago Splitter| 34|
|player111|        David West| 38|
|player118| Russell Westbrook| 30|
|player143|Kristaps Porzingis| 23|
|player114|     Tracy McGrady| 39|
|player150|       Luka Doncic| 20|
|player103|          Rudy Gay| 32|
|player113|   Dejounte Murray| 29|
|player121|        Chris Paul| 33|
|player128|   Carmelo Anthony| 34|
|player130|       Joel Embiid| 25|
|player136|        Steve Nash| 45|
|player108|        Boris Diaw| 36|
|player122|    DeAndre Jordan| 30|
|player123|       Ricky Rubio| 28|
|player139|        Marc Gasol| 34|
|player142|     Klay Thompson| 29|
|player145|      JaVale McGee| 31|
|player102| LaMarcus Aldridge| 33|
+---------+------------------+---+
only showing top 20 rows

22/04/19 07:29:36 INFO DAGScheduler: Job 4 finished: show at NebulaSparkReaderExample.scala:82, took 0.135543 s
+---------+---------+-----+------+
|   _srcId|   _dstId|_rank|degree|
+---------+---------+-----+------+
|player105|player100|    0|    70|
|player105|player104|    0|    83|
|player105|player116|    0|    80|
|player109|player100|    0|    80|
|player109|player125|    0|    90|
|player118|player120|    0|    90|
|player118|player131|    0|    90|
|player143|player150|    0|    90|
|player114|player103|    0|    90|
|player114|player115|    0|    90|
|player114|player140|    0|    90|
|player150|player120|    0|    80|
|player150|player137|    0|    90|
|player150|player143|    0|    90|
|player103|player102|    0|    70|
|player113|player100|    0|    99|
|player113|player101|    0|    99|
|player113|player104|    0|    99|
|player113|player105|    0|    99|
|player113|player106|    0|    99|
+---------+---------+-----+------+
only showing top 20 rows

{
  # Spark relation config
  spark: {
    app: {
      name: Nebula Exchange
    }

    master:local

    driver: {
      cores: 1
      maxResultSize: 1G
    }

    executor: {
        memory: 1G
    }

    cores:{
      max: 16
    }
  }

  # Nebula Graph relation config
  nebula: {
    address:{
      graph:["graphd:9669"]
      meta:["metad0:9559", "metad1:9559", "metad2:9559"]
    }
    user: root
    pswd: nebula
    space: basketballplayer

    # parameters for SST import, not required
    path:{
        local:"/tmp"
        remote:"/sst"
        hdfs.namenode: "hdfs://localhost:9000"
    }

    # nebula client connection parameters
    connection {
      # socket connect & execute timeout, unit: millisecond
      timeout: 30000
    }

    error: {
      # max number of failures, if the number of failures is bigger than max, then exit the application.
      max: 32
      # failed import job will be recorded in output path
      output: /tmp/errors
    }

    # use google's RateLimiter to limit the requests send to NebulaGraph
    rate: {
      # the stable throughput of RateLimiter
      limit: 1024
      # Acquires a permit from RateLimiter, unit: MILLISECONDS
      # if it can't be obtained within the specified timeout, then give up the request.
      timeout: 1000
    }
  }

  # Processing tags
  # There are tag config examples for different dataSources.
  tags: [

    # HDFS csv
    # Import mode is client, just change type.sink to sst if you want to use client import mode.
    {
      name: player
      type: {
        source: csv
        sink: client
      }
      path: "file:///root/player.csv"
      # if your csv file has no header, then use _c0,_c1,_c2,.. to indicate fields
      fields: [_c1, _c2]
      nebula.fields: [name, age]
      vertex: {
        field:_c0
      }
      separator: ","
      header: false
      batch: 256
      partition: 32
    }

  ]
}

  nebula: {
    # algo's data source from Nebula. If data.source is nebula, then this nebula.read config can be valid.
    read: {
        # Nebula metad server address, multiple addresses are split by English comma
        metaAddress: "metad0:9559"
        # Nebula space
        space: livejournal
        # Nebula edge types, multiple labels means that data from multiple edges will union together
        labels: ["follow"]
        # Nebula edge property name for each edge type, this property will be as weight col for algorithm.
        # Make sure the weightCols are corresponding to labels.
        weightCols: []
    }