Examples with UpstreamTransformer org.apache.ignite.ml.dataset.UpstreamTransformer used on opensource projects

Example 1 with UpstreamTransformer

use of org.apache.ignite.ml.dataset.UpstreamTransformer in project ignite by apache.

the class DataStreamGeneratorTest method testAsDatasetBuilder.

/**
 */
@Test
public void testAsDatasetBuilder() throws Exception {
    AtomicInteger cntr = new AtomicInteger();
    DataStreamGenerator generator = new DataStreamGenerator() {

        @Override
        public Stream<LabeledVector<Double>> labeled() {
            return Stream.generate(() -> {
                int val = cntr.getAndIncrement();
                return new LabeledVector<>(VectorUtils.of(val), (double) val % 2);
            });
        }
    };
    int N = 100;
    cntr.set(0);
    DatasetBuilder<Vector, Double> b1 = generator.asDatasetBuilder(N, 2);
    cntr.set(0);
    DatasetBuilder<Vector, Double> b2 = generator.asDatasetBuilder(N, (v, l) -> l == 0, 2);
    cntr.set(0);
    DatasetBuilder<Vector, Double> b3 = generator.asDatasetBuilder(N, (v, l) -> l == 1, 2, new UpstreamTransformerBuilder() {

        @Override
        public UpstreamTransformer build(LearningEnvironment env) {
            return new UpstreamTransformerForTest();
        }
    });
    checkDataset(N, b1, v -> (Double) v.label() == 0 || (Double) v.label() == 1);
    checkDataset(N / 2, b2, v -> (Double) v.label() == 0);
    checkDataset(N / 2, b3, v -> (Double) v.label() < 0);
}

Example 2 with UpstreamTransformer

use of org.apache.ignite.ml.dataset.UpstreamTransformer in project ignite by apache.

the class ComputeUtils method initContext.

/**
 * Initializes partition {@code context} by loading it from a partition {@code upstream}.
 * @param ignite Ignite instance.
 * @param upstreamCacheName Name of an {@code upstream} cache.
 * @param filter Filter for {@code upstream} data.
 * @param transformerBuilder Upstream transformer builder.
 * @param ctxBuilder Partition {@code context} builder.
 * @param envBuilder Environment builder.
 * @param isKeepBinary Support of binary objects.
 * @param deployingCtx Deploy context.
 * @param <K> Type of a key in {@code upstream} data.
 * @param <V> Type of a value in {@code upstream} data.
 * @param <C> Type of a partition {@code context}.
 */
public static <K, V, C extends Serializable> void initContext(Ignite ignite, String upstreamCacheName, UpstreamTransformerBuilder transformerBuilder, IgniteBiPredicate<K, V> filter, String datasetCacheName, PartitionContextBuilder<K, V, C> ctxBuilder, LearningEnvironmentBuilder envBuilder, int retries, int interval, boolean isKeepBinary, DeployingContext deployingCtx) {
    affinityCallWithRetries(ignite, Arrays.asList(datasetCacheName, upstreamCacheName), part -> {
        Ignite locIgnite = Ignition.localIgnite();
        LearningEnvironment env = envBuilder.buildForWorker(part);
        IgniteCache<K, V> locUpstreamCache = locIgnite.cache(upstreamCacheName);
        if (isKeepBinary)
            locUpstreamCache = locUpstreamCache.withKeepBinary();
        ScanQuery<K, V> qry = new ScanQuery<>();
        qry.setLocal(true);
        qry.setPartition(part);
        qry.setFilter(filter);
        C ctx;
        UpstreamTransformer transformer = transformerBuilder.build(env);
        UpstreamTransformer transformerCp = Utils.copy(transformer);
        long cnt = computeCount(locUpstreamCache, qry, transformer);
        try (QueryCursor<UpstreamEntry<K, V>> cursor = locUpstreamCache.query(qry, e -> new UpstreamEntry<>(e.getKey(), e.getValue()))) {
            Iterator<UpstreamEntry<K, V>> it = cursor.iterator();
            Stream<UpstreamEntry> transformedStream = transformerCp.transform(Utils.asStream(it, cnt).map(x -> (UpstreamEntry) x));
            it = Utils.asStream(transformedStream.iterator()).map(x -> (UpstreamEntry<K, V>) x).iterator();
            Iterator<UpstreamEntry<K, V>> iter = new IteratorWithConcurrentModificationChecker<>(it, cnt, "Cache expected to be not modified during dataset data building [partition=" + part + ']');
            ctx = ctxBuilder.build(env, iter, cnt);
        }
        IgniteCache<Integer, C> datasetCache = locIgnite.cache(datasetCacheName);
        datasetCache.put(part, ctx);
        return part;
    }, retries, interval, deployingCtx);
}

Example 3 with UpstreamTransformer

use of org.apache.ignite.ml.dataset.UpstreamTransformer in project ignite by apache.

the class LocalDatasetBuilder method build.

/**
 * {@inheritDoc}
 */
@Override
public <C extends Serializable, D extends AutoCloseable> LocalDataset<C, D> build(LearningEnvironmentBuilder envBuilder, PartitionContextBuilder<K, V, C> partCtxBuilder, PartitionDataBuilder<K, V, C, D> partDataBuilder, LearningEnvironment learningEnvironment) {
    List<C> ctxList = new ArrayList<>();
    List<D> dataList = new ArrayList<>();
    List<UpstreamEntry<K, V>> entriesList = new ArrayList<>();
    upstreamMap.entrySet().stream().filter(en -> filter.apply(en.getKey(), en.getValue())).map(en -> new UpstreamEntry<>(en.getKey(), en.getValue())).forEach(entriesList::add);
    int partSize = Math.max(1, entriesList.size() / partitions);
    Iterator<UpstreamEntry<K, V>> firstKeysIter = entriesList.iterator();
    Iterator<UpstreamEntry<K, V>> secondKeysIter = entriesList.iterator();
    Iterator<UpstreamEntry<K, V>> thirdKeysIter = entriesList.iterator();
    int ptr = 0;
    List<LearningEnvironment> envs = IntStream.range(0, partitions).boxed().map(envBuilder::buildForWorker).collect(Collectors.toList());
    for (int part = 0; part < partitions; part++) {
        int cntBeforeTransform = part == partitions - 1 ? entriesList.size() - ptr : Math.min(partSize, entriesList.size() - ptr);
        LearningEnvironment env = envs.get(part);
        UpstreamTransformer transformer1 = upstreamTransformerBuilder.build(env);
        UpstreamTransformer transformer2 = Utils.copy(transformer1);
        UpstreamTransformer transformer3 = Utils.copy(transformer1);
        int cnt = (int) transformer1.transform(Utils.asStream(new IteratorWindow<>(thirdKeysIter, k -> k, cntBeforeTransform))).count();
        Iterator<UpstreamEntry> iter = transformer2.transform(Utils.asStream(new IteratorWindow<>(firstKeysIter, k -> k, cntBeforeTransform)).map(x -> (UpstreamEntry) x)).iterator();
        Iterator<UpstreamEntry<K, V>> convertedBack = Utils.asStream(iter).map(x -> (UpstreamEntry<K, V>) x).iterator();
        C ctx = cntBeforeTransform > 0 ? partCtxBuilder.build(env, convertedBack, cnt) : null;
        Iterator<UpstreamEntry> iter1 = transformer3.transform(Utils.asStream(new IteratorWindow<>(secondKeysIter, k -> k, cntBeforeTransform))).iterator();
        Iterator<UpstreamEntry<K, V>> convertedBack1 = Utils.asStream(iter1).map(x -> (UpstreamEntry<K, V>) x).iterator();
        D data = cntBeforeTransform > 0 ? partDataBuilder.build(env, convertedBack1, cnt, ctx) : null;
        ctxList.add(ctx);
        dataList.add(data);
        ptr += cntBeforeTransform;
    }
    return new LocalDataset<>(envs, ctxList, dataList);
}

Example 4 with UpstreamTransformer

use of org.apache.ignite.ml.dataset.UpstreamTransformer in project ignite by apache.

the class ComputeUtils method getData.

/**
 * Extracts partition {@code data} from the local storage, if it's not found in local storage recovers this {@code
 * data} from a partition {@code upstream} and {@code context}. Be aware that this method should be called from
 * the node where partition is placed.
 *
 * @param ignite Ignite instance.
 * @param upstreamCacheName Name of an {@code upstream} cache.
 * @param filter Filter for {@code upstream} data.
 * @param transformerBuilder Builder of upstream transformers.
 * @param datasetCacheName Name of a partition {@code context} cache.
 * @param datasetId Dataset ID.
 * @param partDataBuilder Partition data builder.
 * @param env Learning environment.
 * @param <K> Type of a key in {@code upstream} data.
 * @param <V> Type of a value in {@code upstream} data.
 * @param <C> Type of a partition {@code context}.
 * @param <D> Type of a partition {@code data}.
 * @return Partition {@code data}.
 */
public static <K, V, C extends Serializable, D extends AutoCloseable> D getData(Ignite ignite, String upstreamCacheName, IgniteBiPredicate<K, V> filter, UpstreamTransformerBuilder transformerBuilder, String datasetCacheName, UUID datasetId, PartitionDataBuilder<K, V, C, D> partDataBuilder, LearningEnvironment env, boolean isKeepBinary) {
    PartitionDataStorage dataStorage = (PartitionDataStorage) ignite.cluster().nodeLocalMap().computeIfAbsent(String.format(DATA_STORAGE_KEY_TEMPLATE, datasetId), key -> new PartitionDataStorage());
    final int part = env.partition();
    return dataStorage.computeDataIfAbsent(part, () -> {
        IgniteCache<Integer, C> learningCtxCache = ignite.cache(datasetCacheName);
        C ctx = learningCtxCache.get(part);
        IgniteCache<K, V> upstreamCache = ignite.cache(upstreamCacheName);
        if (isKeepBinary)
            upstreamCache = upstreamCache.withKeepBinary();
        ScanQuery<K, V> qry = new ScanQuery<>();
        qry.setLocal(true);
        qry.setPartition(part);
        qry.setFilter(filter);
        UpstreamTransformer transformer = transformerBuilder.build(env);
        UpstreamTransformer transformerCp = Utils.copy(transformer);
        long cnt = computeCount(upstreamCache, qry, transformer);
        if (cnt > 0) {
            try (QueryCursor<UpstreamEntry<K, V>> cursor = upstreamCache.query(qry, e -> new UpstreamEntry<>(e.getKey(), e.getValue()))) {
                Iterator<UpstreamEntry<K, V>> it = cursor.iterator();
                Stream<UpstreamEntry> transformedStream = transformerCp.transform(Utils.asStream(it, cnt).map(x -> (UpstreamEntry) x));
                it = Utils.asStream(transformedStream.iterator()).map(x -> (UpstreamEntry<K, V>) x).iterator();
                Iterator<UpstreamEntry<K, V>> iter = new IteratorWithConcurrentModificationChecker<>(it, cnt, "Cache expected to be not modified during dataset data building [partition=" + part + ']');
                return partDataBuilder.build(env, iter, cnt, ctx);
            }
        }
        return null;
    });
}