This article is about how to bring your graph into a format the Graph module of Hama can read and successfully let you run algorithms on it.
For this concrete example, the Google web graph from 2002 is used (http://snap.stanford.edu/data/web-Google.html), we will give you a step by step guide from the download to a run of Pagerank on this dataset. To run this example in your code, you will need the http://code.google.com/p/guava-libraries/.
# to be extended
Path txtPath = new Path(
"/tmp/web-Google.txt");
Path input = new Path(
"/tmp/pagerankin.seq");
HamaConfiguration conf = new HamaConfiguration(new Configuration());
FileSystem fileSystem = FileSystem.get(conf);
HashMultimap<Integer, Integer> map = HashMultimap.create();
BufferedReader br = new BufferedReader(new InputStreamReader(
fileSystem.open(txtPath)));
String line = null;
while ((line = br.readLine()) != null) {
String[] split = line.split("\t");
map.put(Integer.parseInt(split[0]), Integer.parseInt(split[1]));
}
Set<Entry<Integer, Collection<Integer>>> entries = map.asMap().entrySet();
VertexWritable.CONFIGURATION = conf;
SequenceFile.Writer writer = new SequenceFile.Writer(fileSystem, conf,
input, VertexWritable.class, VertexArrayWritable.class);
for (Entry<Integer, Collection<Integer>> entry : entries) {
VertexWritable<IntWritable, DoubleWritable> key = new VertexWritable<IntWritable, DoubleWritable>(
new DoubleWritable(0.0d), new IntWritable(entry.getKey()),
IntWritable.class, DoubleWritable.class);
ArrayList<Integer> arrayList = new ArrayList<Integer>(entry.getValue());
@SuppressWarnings("unchecked")
VertexWritable<IntWritable, NullWritable>[] adjacents = new VertexWritable[entry
.getValue().size()];
for (int i = 0; i < adjacents.length; i++) {
adjacents[i] = new VertexWritable<IntWritable, NullWritable>(
NullWritable.get(), new IntWritable(arrayList.get(i)),
IntWritable.class, NullWritable.class);
}
VertexArrayWritable val = new VertexArrayWritable();
val.set(adjacents);
writer.append(key, val);
}
writer.close();