直接提交算法包跑louvain报错

[user82]

nebula graph版本：3.3.0
nebula studio版本：3.5.0
部署方式：分布式
是否为线上版本：N

数据量：
节点是Comment，关系为画红框的几个

application.conf:

{
  # Spark relation config
  spark: {
    app: {
        name: louvain
        # spark.app.partitionNum
        partitionNum:50
    }
    master:local
  }

  data: {
    # data source. optional of nebula,csv,json
    source: nebula
    # data sink, means the algorithm result will be write into this sink. optional of nebula,csv,text
    sink: nebula
    # if your algorithm needs weight
    hasWeight: false
  }

  # Nebula Graph relation config
  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: "192.168.200.100:9559,192.168.200.101:9559,192.168.200.111:9559"
        # Nebula space
        space: ldbc
        # Nebula edge types, multiple labels means that data from multiple edges will union together
        labels: ["HAS_CREATOR","HAS_TAG","IS_LOCATED_IN","REPLY_OF"]
        # 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: [""]
    }

    # algo result sink into Nebula. If data.sink is nebula, then this nebula.write config can be valid.
    write:{
        # Nebula graphd server address， multiple addresses are split by English comma
        graphAddress: "192.168.200.100:9669,192.168.200.101:9669,192.168.200.111:9669,192.168.200.112:9669,192.168.200.114:9669"
        # Nebula metad server address, multiple addresses are split by English comma
        metaAddress: "192.168.200.100:9559,192.168.200.101:9559,192.168.200.111:9559"
        user:root
        pswd:nebula
        # Nebula space name
        space:ldbc
        # Nebula tag name, the algorithm result will be write into this tag
        tag:Comment
        # algorithm result is insert into new tag or update to original tag. type: insert/update
        type:update
    }
  }

  local: {
    # algo's data source from Nebula. If data.source is csv or json, then this local.read can be valid.
    read:{
        filePath: "file:///tmp/edge_follow.csv"
        # srcId column
        srcId:"_c0"
        # dstId column
        dstId:"_c1"
        # weight column
        #weight: "col3"
        # if csv file has header
        header: false
        # csv file's delimiter
        delimiter:","
    }

    # algo result sink into local file. If data.sink is csv or text, then this local.write can be valid.
    write:{
        resultPath:/tmp/count
    }
  }


  algorithm: {
    # the algorithm that you are going to execute，pick one from [pagerank, louvain, connectedcomponent,
    # labelpropagation, shortestpaths, degreestatic, kcore, stronglyconnectedcomponent, trianglecount,
    # betweenness, graphtriangleCount, clusteringcoefficient, bfs, hanp, closeness, jaccard, node2vec]
    executeAlgo: louvain

    # PageRank parameter
    pagerank: {
        maxIter: 10
        resetProb: 0.15  # default 0.15
    }

    # Louvain parameter
    louvain: {
        maxIter: 20
        internalIter: 10
        tol: 0.5
   }

   # connected component parameter.
    connectedcomponent: {
        maxIter: 20
   }

   # LabelPropagation parameter
    labelpropagation: {
        maxIter: 20
   }

   # ShortestPaths parameter
    shortestpaths: {
        # several vertices to compute the shortest path to all vertices.
        landmarks: "1"
   }

    # Vertex degree statistics parameter
    degreestatic: {}

   # KCore parameter
   kcore:{
        maxIter:10
        degree:1
   }

   # Trianglecount parameter
   trianglecount:{}

   # graphTriangleCount parameter
   graphtrianglecount:{}

   # Betweenness centrality parameter. maxIter parameter means the max times of iterations.
   betweenness:{
        maxIter:5
   }

   # Clustering Coefficient parameter. The type parameter has two choice, local or global
   # local type will compute the clustering coefficient for each vertex, and print the average coefficient for graph.
   # global type just compute the graph's clustering coefficient.
   clusteringcoefficient:{
        type: local
   }

   # ClosenessAlgo parameter
   closeness:{}

   # BFS parameter
   bfs:{
       maxIter:5
       root:"10"
   }

   # HanpAlgo parameter
   hanp:{
       hopAttenuation:0.1
       maxIter:10
       preference:1.0
   }

   #Node2vecAlgo parameter
   node2vec:{
       maxIter: 10,
       lr: 0.025,
       dataNumPartition: 10,
       modelNumPartition: 10,
       dim: 10,
       window: 3,
       walkLength: 5,
       numWalks: 3,
       p: 1.0,
       q: 1.0,
       directed: false,
       degree: 30,
       embSeparate: ",",
       modelPath: "hdfs://127.0.0.1:9000/model"
   }

   # JaccardAlgo parameter
   jaccard:{
       tol: 1.0
   }
 }
}

执行spark-submit --master "local" --class com.vesoft.nebula.algorithm.Main /opt/offline/nebula/nebula-algorithm-3.0.0.jar -p /opt/offline/nebula/application.conf

报错：

storage.info和graphd.info日志：
nebula-graphd.INFO (565.3 KB)
nebula-storaged.INFO (25.3 KB)

请问大佬，应该如何解决呢？

[user82]

找到原因了，是application.conf文件中的weightcols如果为空的话，不能加引号：

[nicole]

是的，可以是空的[] ，也可以把该配置注释掉

[user82]

好的，谢谢！
我还想问下，做完社区划分后，能否找出每个社区的重要节点呢？例如点度中心性/中介中心性/接近中心性等。咱们的nebula algorithm中有相关的配置吗？需要在每个社区中找这样的重要节点

[steam]

一样的问题，以 做完Louvain社区划分后，如何找到每个社区中的重要节点？ 帖子回复为准可好？

[user82]

OK

[user82]

我从早上开始跑，到现在还没跑完，我看打印的日志中有

joining two vertexpartitions with different indexes is slow.

是这个导致跑得慢吗？

[nicole]

join操作耗时会比较久，要看你的数据量有多少，以及你配置的迭代次数是多少

[user82]

这个节点的数据量是200多万。您说的这个迭代次数是指application.conf中louvain的迭代次数吗？

    # Louvain parameter
    louvain: {
        maxIter: 20
        internalIter: 10
        tol: 0.5
   }

[steam]

去另外个帖子回复吧，我这个帖子先行关闭了。