/**
* Run the canopy clustering job on an input dataset using the given distance measure, t1 and t2
* parameters. All output data will be written to the output directory, which will be initially
* deleted if it exists. The clustered points will reside in the path <output>/clustered-points.
* By default, the job expects the a file containing synthetic_control.data as obtained from
* http://archive.ics.uci.edu/ml/datasets/Synthetic+Control+Chart+Time+Series resides in a
* directory named "testdata", and writes output to a directory named "output".
*
* @param input the String denoting the input directory path
* @param output the String denoting the output directory path
* @param measure the DistanceMeasure to use
* @param t1 the canopy T1 threshold
* @param t2 the canopy T2 threshold
*/
private static void run(Path input, Path output, DistanceMeasure measure, double t1, double t2)
throws Exception {
Path directoryContainingConvertedInput = new Path(output, DIRECTORY_CONTAINING_CONVERTED_INPUT);
InputDriver.runJob(
input,
directoryContainingConvertedInput,
"org.apache.mahout.math.RandomAccessSparseVector");
CanopyDriver.run(
new Configuration(),
directoryContainingConvertedInput,
output,
measure,
t1,
t2,
true,
0.0,
false);
// run ClusterDumper
ClusterDumper clusterDumper =
new ClusterDumper(
new Path(output, "clusters-0-final"), new Path(output, "clusteredPoints"));
clusterDumper.printClusters(null);
}
