/** * Post processes the output of clustering algorithms and groups them into respective clusters. Each * cluster's vectors are written into a directory named after its clusterId. * * @param input The output path provided to the clustering algorithm, whose would be post processed. Hint: The * path of the directory containing clusters-*-final and clusteredPoints. * @param output The post processed data would be stored at this path. * @param runSequential If set to true, post processes it sequentially, else, uses. MapReduce. Hint: If the clustering * was done sequentially, make it sequential, else vice versa. */ public static void run(Path input, Path output, boolean runSequential) throws IOException, InterruptedException, ClassNotFoundException { if (runSequential) { postProcessSeq(input, output); } else { Configuration conf = new Configuration(); postProcessMR(conf, input, output); movePartFilesToRespectiveDirectories(conf, output); } }
/** * Post processes the output of clustering algorithms and groups them into respective clusters. Each * cluster's vectors are written into a directory named after its clusterId. * * @param input The output path provided to the clustering algorithm, whose would be post processed. Hint: The * path of the directory containing clusters-*-final and clusteredPoints. * @param output The post processed data would be stored at this path. * @param runSequential If set to true, post processes it sequentially, else, uses. MapReduce. Hint: If the clustering * was done sequentially, make it sequential, else vice versa. */ public static void run(Path input, Path output, boolean runSequential) throws IOException, InterruptedException, ClassNotFoundException { if (runSequential) { postProcessSeq(input, output); } else { Configuration conf = new Configuration(); postProcessMR(conf, input, output); movePartFilesToRespectiveDirectories(conf, output); } }
/** * Post processes the output of clustering algorithms and groups them into respective clusters. Each * cluster's vectors are written into a directory named after its clusterId. * * @param input The output path provided to the clustering algorithm, whose would be post processed. Hint: The * path of the directory containing clusters-*-final and clusteredPoints. * @param output The post processed data would be stored at this path. * @param runSequential If set to true, post processes it sequentially, else, uses. MapReduce. Hint: If the clustering * was done sequentially, make it sequential, else vice versa. */ public static void run(Path input, Path output, boolean runSequential) throws IOException, InterruptedException, ClassNotFoundException { if (runSequential) { postProcessSeq(input, output); } else { Configuration conf = new Configuration(); postProcessMR(conf, input, output); movePartFilesToRespectiveDirectories(conf, output); } }