Examples with BisectingKMeans com.alibaba.alink.pipeline.clustering.BisectingKMeans used on opensource projects

Example 1 with BisectingKMeans

use of com.alibaba.alink.pipeline.clustering.BisectingKMeans in project Alink by alibaba.

the class Chap17 method c_4.

static void c_4() throws Exception {
    AkSourceBatchOp source = new AkSourceBatchOp().setFilePath(DATA_DIR + VECTOR_FILE);
    new BisectingKMeans().setK(3).setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).enableLazyPrintModelInfo("BiSecting KMeans EUCLIDEAN").fit(source).transform(source).link(new EvalClusterBatchOp().setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setLabelCol(LABEL_COL_NAME).lazyPrintMetrics("Bisecting KMeans EUCLIDEAN"));
    BatchOperator.execute();
    new BisectingKMeans().setDistanceType(DistanceType.COSINE).setK(3).setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).enableLazyPrintModelInfo("BiSecting KMeans COSINE").fit(source).transform(source).link(new EvalClusterBatchOp().setDistanceType("COSINE").setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setLabelCol(LABEL_COL_NAME).lazyPrintMetrics("Bisecting KMeans COSINE"));
    BatchOperator.execute();
}

Example 2 with BisectingKMeans

use of com.alibaba.alink.pipeline.clustering.BisectingKMeans in project Alink by alibaba.

the class Chap18 method c_1.

static void c_1() throws Exception {
    AkSourceBatchOp dense_source = new AkSourceBatchOp().setFilePath(DATA_DIR + DENSE_TRAIN_FILE);
    AkSourceBatchOp sparse_source = new AkSourceBatchOp().setFilePath(DATA_DIR + SPARSE_TRAIN_FILE);
    Stopwatch sw = new Stopwatch();
    ArrayList<Tuple2<String, Pipeline>> pipelineList = new ArrayList<>();
    pipelineList.add(new Tuple2<>("KMeans EUCLIDEAN", new Pipeline().add(new KMeans().setK(10).setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME))));
    pipelineList.add(new Tuple2<>("KMeans COSINE", new Pipeline().add(new KMeans().setDistanceType(DistanceType.COSINE).setK(10).setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME))));
    pipelineList.add(new Tuple2<>("BisectingKMeans", new Pipeline().add(new BisectingKMeans().setK(10).setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME))));
    for (Tuple2<String, Pipeline> pipelineTuple2 : pipelineList) {
        sw.reset();
        sw.start();
        pipelineTuple2.f1.fit(dense_source).transform(dense_source).link(new EvalClusterBatchOp().setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setLabelCol(LABEL_COL_NAME).lazyPrintMetrics(pipelineTuple2.f0 + " DENSE"));
        BatchOperator.execute();
        sw.stop();
        System.out.println(sw.getElapsedTimeSpan());
        sw.reset();
        sw.start();
        pipelineTuple2.f1.fit(sparse_source).transform(sparse_source).link(new EvalClusterBatchOp().setVectorCol(VECTOR_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setLabelCol(LABEL_COL_NAME).lazyPrintMetrics(pipelineTuple2.f0 + " SPARSE"));
        BatchOperator.execute();
        sw.stop();
        System.out.println(sw.getElapsedTimeSpan());
    }
}