Examples with Dataset org.apache.spark.sql.Dataset used on opensource projects

Example 26 with Dataset

use of org.apache.spark.sql.Dataset in project Gaffer by gchq.

the class DataFrameToIterableRowTest method shouldConvertDataFrameToIterableOfRows.

@Test
public void shouldConvertDataFrameToIterableOfRows() {
    // Given
    final SparkSession sparkSession = SparkSessionProvider.getSparkSession();
    final Function<Dataset<Row>, Iterable<? extends Row>> function = new DataFrameToIterableRow();
    final Dataset<Row> dataframe = Graphs$.MODULE$.friends().vertices();
    // When
    final Iterable<? extends Row> result = function.apply(dataframe);
    final List<Row> resultList = Lists.newArrayList(result);
    // Then
    assertThat(resultList).hasSize(7);
}

Example 27 with Dataset

use of org.apache.spark.sql.Dataset in project beam by apache.

the class ParDoTranslatorBatch method translateTransform.

@Override
public void translateTransform(PTransform<PCollection<InputT>, PCollectionTuple> transform, AbstractTranslationContext context) {
    String stepName = context.getCurrentTransform().getFullName();
    // Check for not supported advanced features
    // TODO: add support of Splittable DoFn
    DoFn<InputT, OutputT> doFn = getDoFn(context);
    checkState(!DoFnSignatures.isSplittable(doFn), "Not expected to directly translate splittable DoFn, should have been overridden: %s", doFn);
    // TODO: add support of states and timers
    checkState(!DoFnSignatures.isStateful(doFn), "States and timers are not supported for the moment.");
    checkState(!DoFnSignatures.requiresTimeSortedInput(doFn), "@RequiresTimeSortedInput is not " + "supported for the moment");
    DoFnSchemaInformation doFnSchemaInformation = ParDoTranslation.getSchemaInformation(context.getCurrentTransform());
    // Init main variables
    PValue input = context.getInput();
    Dataset<WindowedValue<InputT>> inputDataSet = context.getDataset(input);
    Map<TupleTag<?>, PCollection<?>> outputs = context.getOutputs();
    TupleTag<?> mainOutputTag = getTupleTag(context);
    List<TupleTag<?>> outputTags = new ArrayList<>(outputs.keySet());
    WindowingStrategy<?, ?> windowingStrategy = ((PCollection<InputT>) input).getWindowingStrategy();
    Coder<InputT> inputCoder = ((PCollection<InputT>) input).getCoder();
    Coder<? extends BoundedWindow> windowCoder = windowingStrategy.getWindowFn().windowCoder();
    // construct a map from side input to WindowingStrategy so that
    // the DoFn runner can map main-input windows to side input windows
    List<PCollectionView<?>> sideInputs = getSideInputs(context);
    Map<PCollectionView<?>, WindowingStrategy<?, ?>> sideInputStrategies = new HashMap<>();
    for (PCollectionView<?> sideInput : sideInputs) {
        sideInputStrategies.put(sideInput, sideInput.getPCollection().getWindowingStrategy());
    }
    SideInputBroadcast broadcastStateData = createBroadcastSideInputs(sideInputs, context);
    Map<TupleTag<?>, Coder<?>> outputCoderMap = context.getOutputCoders();
    MetricsContainerStepMapAccumulator metricsAccum = MetricsAccumulator.getInstance();
    List<TupleTag<?>> additionalOutputTags = new ArrayList<>();
    for (TupleTag<?> tag : outputTags) {
        if (!tag.equals(mainOutputTag)) {
            additionalOutputTags.add(tag);
        }
    }
    Map<String, PCollectionView<?>> sideInputMapping = ParDoTranslation.getSideInputMapping(context.getCurrentTransform());
    @SuppressWarnings("unchecked") DoFnFunction<InputT, OutputT> doFnWrapper = new DoFnFunction(metricsAccum, stepName, doFn, windowingStrategy, sideInputStrategies, context.getSerializableOptions(), additionalOutputTags, mainOutputTag, inputCoder, outputCoderMap, broadcastStateData, doFnSchemaInformation, sideInputMapping);
    MultiOutputCoder multipleOutputCoder = MultiOutputCoder.of(SerializableCoder.of(TupleTag.class), outputCoderMap, windowCoder);
    Dataset<Tuple2<TupleTag<?>, WindowedValue<?>>> allOutputs = inputDataSet.mapPartitions(doFnWrapper, EncoderHelpers.fromBeamCoder(multipleOutputCoder));
    if (outputs.entrySet().size() > 1) {
        allOutputs.persist();
        for (Map.Entry<TupleTag<?>, PCollection<?>> output : outputs.entrySet()) {
            pruneOutputFilteredByTag(context, allOutputs, output, windowCoder);
        }
    } else {
        Coder<OutputT> outputCoder = ((PCollection<OutputT>) outputs.get(mainOutputTag)).getCoder();
        Coder<WindowedValue<?>> windowedValueCoder = (Coder<WindowedValue<?>>) (Coder<?>) WindowedValue.getFullCoder(outputCoder, windowCoder);
        Dataset<WindowedValue<?>> outputDataset = allOutputs.map((MapFunction<Tuple2<TupleTag<?>, WindowedValue<?>>, WindowedValue<?>>) value -> value._2, EncoderHelpers.fromBeamCoder(windowedValueCoder));
        context.putDatasetWildcard(outputs.entrySet().iterator().next().getValue(), outputDataset);
    }
}