[ 
https://issues.apache.org/jira/browse/FLINK-2570?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14711345#comment-14711345
 ] 

ASF GitHub Bot commented on FLINK-2570:
---------------------------------------

Github user vasia commented on a diff in the pull request:

    https://github.com/apache/flink/pull/1054#discussion_r37869769
  
    --- Diff: 
flink-staging/flink-gelly/src/main/java/org/apache/flink/graph/library/GSATriangleCount.java
 ---
    @@ -0,0 +1,187 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one
    + * or more contributor license agreements.  See the NOTICE file
    + * distributed with this work for additional information
    + * regarding copyright ownership.  The ASF licenses this file
    + * to you under the Apache License, Version 2.0 (the
    + * "License"); you may not use this file except in compliance
    + * with the License.  You may obtain a copy of the License at
    + *
    + *     http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.flink.graph.library;
    +
    +
    +import org.apache.flink.api.common.functions.MapFunction;
    +import org.apache.flink.api.common.functions.ReduceFunction;
    +import org.apache.flink.api.java.DataSet;
    +import org.apache.flink.api.java.ExecutionEnvironment;
    +import org.apache.flink.api.java.tuple.Tuple1;
    +import org.apache.flink.api.java.tuple.Tuple2;
    +import org.apache.flink.graph.GraphAlgorithm;
    +import org.apache.flink.graph.ReduceNeighborsFunction;
    +import org.apache.flink.graph.Vertex;
    +import org.apache.flink.graph.Edge;
    +import org.apache.flink.graph.Triplet;
    +import org.apache.flink.graph.EdgeDirection;
    +import org.apache.flink.graph.Graph;
    +import org.apache.flink.types.NullValue;
    +
    +import java.util.TreeMap;
    +
    +/**
    + * Triangle Count Algorithm.
    + *
    + * This algorithm operates in three phases. First, vertices select 
neighbors with id greater than theirs
    + * and send messages to them. Each received message is then propagated to 
neighbors with higher id.
    + * Finally, if a node encounters the target id in the list of received 
messages, it increments the number
    + * of triangles found.
    + *
    + * This implementation is non - iterative. The total number of triangles 
can be determined by performing
    + * a single pass through the graph.
    + */
    +public class GSATriangleCount implements
    +           GraphAlgorithm<Long, NullValue, NullValue, 
DataSet<Tuple1<Integer>>> {
    +
    +   @Override
    +   public DataSet<Tuple1<Integer>> run(Graph<Long, NullValue, NullValue> 
input) throws Exception {
    +
    +           ExecutionEnvironment env = input.getContext();
    +
    +           // order the edges so that src is always higher than trg
    +           DataSet<Edge<Long, NullValue>> edges = input.getEdges()
    +                           .map(new OrderEdges()).distinct();
    --- End diff --
    
    this call to `distinct()` here means that basically if you have 2 edges 
a->b and b->a in the input, and they are both part of a triangle, then you only 
count it once?


> Add a Triangle Count Library Method
> -----------------------------------
>
>                 Key: FLINK-2570
>                 URL: https://issues.apache.org/jira/browse/FLINK-2570
>             Project: Flink
>          Issue Type: Task
>          Components: Gelly
>    Affects Versions: 0.10
>            Reporter: Andra Lungu
>            Assignee: Andra Lungu
>            Priority: Minor
>
> The Gather-Sum-Apply-Scatter version of this algorithm receives an undirected 
> graph as input and outputs the total number of triangles formed by the 
> graph's edges. 
> The implementation consists of three phases:
> 1). Select neighbours with id greater than the current vertex id.
> Gather: no-op
> Sum: create a set out of these neighbours
> Apply: attach the computed values to the vertices
> 2). Propagate each received value to neighbours with higher id (again using 
> GSA)
> 3). Compute the number of Triangles by verifying if the final vertex contains 
> the sender's id in its list. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to