static void Main(string[] args)
{
// 1. allocate a new dataflow computation.
using (var computation = NewComputation.FromArgs(ref args))
{
if (args.Length != 6)
{
PrintHelp();
return;
}
Int32 procid = computation.Configuration.ProcessID;
Int32 thread_num = computation.Configuration.WorkerCount;
Int32 worker_num = computation.Configuration.Processes;
Int32 dimension = Int32.Parse(args[0]);
Int32 cluster_num = Int32.Parse(args[1]);
Int32 iteration_num = Int32.Parse(args[2]);
Int32 partition_num = Int32.Parse(args[3]);
double sample_num_m = Convert.ToDouble(args[4]);
Int64 spin_wait = Int64.Parse(args[5]);
Console.Out.WriteLine("dimension: " + dimension);
Console.Out.WriteLine("cluster_num: " + cluster_num);
Console.Out.WriteLine("iteration_num: " + iteration_num);
Console.Out.WriteLine("partition_num: " + partition_num);
Console.Out.WriteLine("sample_num_m: " + sample_num_m);
Console.Out.WriteLine("spin_wait: " + spin_wait);
Console.Out.WriteLine("procid: " + procid);
Console.Out.WriteLine("worker_num: " + worker_num);
Console.Out.WriteLine("thread_num: " + thread_num);
Console.Out.Flush();
KMeans km =
new KMeans(dimension,
cluster_num,
iteration_num,
partition_num,
sample_num_m,
spin_wait,
procid,
worker_num,
thread_num);
Stream <SampleBatch, Epoch> samples = km.GenerateSamples().AsNaiadStream(computation);
samples = samples.PartitionBy(s => (int)(s[0][0]));
var end_samples = samples.Iterate((lc, s) => km.Advance(s), iteration_num, "KMeans");
// var output = end_samples.Subscribe(x => {
// Console.Out.WriteLine("Final center 0: " + PrintList(km.means_[0]));
// Console.Out.Flush();
// });
Console.Out.WriteLine("Before Activate!");
Console.Out.Flush();
// start the computation, fixing the structure of the dataflow graph.
computation.Activate();
Console.Out.WriteLine("After Activate!");
Console.Out.Flush();
// block until all work is finished.
computation.Join();
Console.Out.WriteLine("After Join!");
double average_total = km.total_times_.GetRange(truncate_index_, iteration_num - truncate_index_).Average();
double average_compute = km.compute_times_.GetRange(truncate_index_, iteration_num - truncate_index_).Average();
double average_idle = average_total - average_compute;
Console.Out.WriteLine("*** Average for the last {0:D2} iterations: compute(ms): {1:F2} total(ms): {2:F2} (idle(ms): {3:F2})",
iteration_num - truncate_index_, 1000 * average_compute, 1000 * average_total, 1000 * average_idle);
for (int i = 0; i < cluster_num; ++i)
{
Console.Out.WriteLine("Final center {0:D2}: {1:S}: ", i, PrintList(km.means_[i]));
}
Console.Out.WriteLine("Samples Counts: " + PrintList(km.sample_counter));
Console.Out.WriteLine("Reduce Level 1 Counts: " + PrintList(km.reduce_l1_counter_));
Console.Out.WriteLine("Reduce Level 2 Counts: " + PrintList(km.reduce_l2_counter_));
Console.Out.WriteLine("Sync Level 1 Counts: " + PrintList(km.sync_l1_counter_));
Console.Out.WriteLine("Sync Level 2 Counts: " + PrintList(km.sync_l2_counter_));
Console.Out.WriteLine("Sync Tags: " + PrintHashSet(km.sync_tags_));
Console.Out.WriteLine("Reduce Tags: " + PrintHashSet(km.reduce_tags_));
Console.Out.WriteLine("Clustering Tags: " + PrintHashSet(km.clustering_tags_));
Console.Out.Flush();
}
}
