Java Code Examples for org.apache.flink.api.java.tuple.Tuple#getField()

@Override
public Object[] extract(Tuple in) {
	Object[] output;

	if (order == null) {
		// copy the whole tuple
		output = new Object[in.getArity()];
		for (int i = 0; i < in.getArity(); i++) {
			output[i] = in.getField(i);
		}
	} else {
		// copy user specified order
		output = new Object[order.length];
		for (int i = 0; i < order.length; i++) {
			output[i] = in.getField(order[i]);
		}
	}

	return output;
}
 

@Override
public Object[] extract(Tuple in) {
	Object[] output;

	if (order == null) {
		// copy the whole tuple
		output = new Object[in.getArity()];
		for (int i = 0; i < in.getArity(); i++) {
			output[i] = in.getField(i);
		}
	} else {
		// copy user specified order
		output = new Object[order.length];
		for (int i = 0; i < order.length; i++) {
			output[i] = in.getField(order[i]);
		}
	}

	return output;
}
 

private boolean deepEqualsTuple(Tuple tuple1, Tuple tuple2) {
	if (tuple1.getArity() != tuple2.getArity()) {
		return false;
	}

	for (int i = 0; i < tuple1.getArity(); i++) {
		Object o1 = tuple1.getField(i);
		Object o2 = tuple2.getField(i);

		if (!deepEquals(o1, o2)) {
			return false;
		}
	}

	return true;
}
 

public static final void compareTupleArrays(Object[] expected, Object[] found) {
	if (expected.length != found.length) {
		Assert.assertEquals("Length of result is wrong", expected.length, found.length);
	}
	
	for (int i = 0; i < expected.length; i++) {
		Tuple v1 = (Tuple) expected[i];
		Tuple v2 = (Tuple) found[i];
		
		for (int k = 0; k < v1.getArity(); k++) {
			Object o1 = v1.getField(k);
			Object o2 = v2.getField(k);
			Assert.assertEquals(o1, o2);
		}
	}
}
 

private void receiveParameters(ExecutionEnvironment env) throws IOException {
	for (int x = 0; x < Parameters.values().length; x++) {
		Tuple value = (Tuple) streamer.getRecord(true);
		switch (Parameters.valueOf(((String) value.getField(0)).toUpperCase())) {
			case DOP:
				Integer dop = value.<Integer>getField(1);
				env.setParallelism(dop);
				break;
			case RETRY:
				int retry = value.<Integer>getField(1);
				env.setRestartStrategy(RestartStrategies.fixedDelayRestart(retry, 10000L));
				break;
			case ID:
				currentEnvironmentID = value.<Integer>getField(1);
				break;
		}
	}
	if (env.getParallelism() < 0) {
		env.setParallelism(1);
	}
}
 

private static String[] tupleToStringArray(Tuple tuple) {
	String[] keys = new String[tuple.getArity()];
	for (int y = 0; y < tuple.getArity(); y++) {
		keys[y] = (String) tuple.getField(y);
	}
	return keys;
}
 

/**
 * Sends the given message to all vertices that adjacent to the changed vertex.
 * This method is mutually exclusive to the method {@link #getEdges()} and may be called only once.
 *
 * @param m The message to send.
 */
public final void sendMessageToAllNeighbors(Message m) {
	verifyEdgeUsage();
	outMsg.f1 = m;
	while (edges.hasNext()) {
		Tuple next = edges.next();
		outMsg.f0 = next.getField(1);
		out.collect(Either.Right(outMsg));
	}
}
 

public Object[] getRow(T input) {
    Preconditions.checkArgument(input.getClass() == schema.getTypeInfo().getTypeClass(),
        "Invalid input type: " + input + ", expected: " + schema.getTypeInfo());

    Object[] data;
    if (schema.isAtomicType()) {
        data = new Object[]{input};
    } else if (schema.isTupleType()) {
        Tuple tuple = (Tuple) input;
        data = new Object[schema.getFieldIndexes().length];
        for (int i = 0; i < schema.getFieldIndexes().length; i++) {
            data[i] = tuple.getField(schema.getFieldIndexes()[i]);
        }
    } else if (schema.isRowType()) {
        Row row = (Row) input;
        data = new Object[schema.getFieldIndexes().length];
        for (int i = 0; i < schema.getFieldIndexes().length; i++) {
            data[i] = row.getField(schema.getFieldIndexes()[i]);
        }
    } else if (schema.isPojoType() || schema.isCaseClassType()) {
        data = new Object[schema.getFieldIndexes().length];
        for (int i = 0; i < schema.getFieldNames().length; i++) {
            data[i] = getFieldValue(schema.getFieldNames()[i], input);
        }
    } else {
        throw new IllegalArgumentException("Failed to get field values from " + schema.getTypeInfo());
    }
    return data;
}
 

/**
 * Sends the given message to all vertices that adjacent to the changed vertex.
 * This method is mutually exclusive to the method {@link #getEdges()} and may be called only once.
 *
 * @param m The message to send.
 */
public final void sendMessageToAllNeighbors(Message m) {
	verifyEdgeUsage();
	outMsg.f1 = m;
	while (edges.hasNext()) {
		Tuple next = edges.next();
		outMsg.f0 = next.getField(1);
		out.collect(Either.Right(outMsg));
	}
}
 

@Override
public double[] extract(Tuple in) {
	double[] out = new double[indexes.length];
	for (int i = 0; i < indexes.length; i++) {
		out[i] = (Double) in.getField(indexes[i]);
	}
	return out;
}
 

/**
 * Sends the given message to all vertices that adjacent to the changed vertex.
 * This method is mutually exclusive to the method {@link #getEdges()} and may be called only once.
 *
 * @param m The message to send.
 */
public final void sendMessageToAllNeighbors(Message m) {
	verifyEdgeUsage();
	outMsg.f1 = m;
	while (edges.hasNext()) {
		Tuple next = edges.next();
		outMsg.f0 = next.getField(1);
		out.collect(Either.Right(outMsg));
	}
}
 

private static <T> void compareResult(List<T> result, String expected, boolean asTuples, boolean sort) {
	String[] expectedStrings = expected.split("\n");
	String[] resultStrings = new String[result.size()];

	for (int i = 0; i < resultStrings.length; i++) {
		T val = result.get(i);

		if (asTuples) {
			if (val instanceof Tuple) {
				Tuple t = (Tuple) val;
				Object first = t.getField(0);
				StringBuilder bld = new StringBuilder(first == null ? "null" : first.toString());
				for (int pos = 1; pos < t.getArity(); pos++) {
					Object next = t.getField(pos);
					bld.append(',').append(next == null ? "null" : next.toString());
				}
				resultStrings[i] = bld.toString();
			}
			else {
				throw new IllegalArgumentException(val + " is no tuple");
			}
		}
		else {
			resultStrings[i] = (val == null) ? "null" : val.toString();
		}
	}

	if (sort) {
		Arrays.sort(expectedStrings);
		Arrays.sort(resultStrings);
	}

	// Include content of both arrays to provide more context in case of a test failure
	String msg = String.format(
		"Different elements in arrays: expected %d elements and received %d\n expected: %s\n received: %s",
		expectedStrings.length, resultStrings.length,
		Arrays.toString(expectedStrings), Arrays.toString(resultStrings));

	assertEquals(msg, expectedStrings.length, resultStrings.length);

	for (int i = 0; i < expectedStrings.length; i++) {
		assertEquals(msg, expectedStrings[i], resultStrings[i]);
	}
}
 

@Test
public void testSummarize() throws Exception {
	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	List<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> data = new ArrayList<>();
	data.add(new Tuple8<>((short) 1, 1, 100L, 0.1f, 1.012376, "hello", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 2, 2, 1000L, 0.2f, 2.003453, "hello", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 4, 10, 10000L, 0.2f, 75.00005, "null", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 10, 4, 100L, 0.9f, 79.5, "", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 5, 5, 1000L, 0.2f, 10.0000001, "a", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 6, 6, 10L, 0.1f, 0.0000000000023, "", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 7, 7, 1L, 0.2f, Double.POSITIVE_INFINITY, "abcdefghijklmnop", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 8, 8, -100L, 0.001f, Double.NaN, "abcdefghi", true, new DoubleValue(100.0)));

	Collections.shuffle(data);

	DataSet<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> ds = env.fromCollection(data);

	// call method under test
	Tuple results = DataSetUtils.summarize(ds);

	Assert.assertEquals(8, results.getArity());

	NumericColumnSummary<Short> col0Summary = results.getField(0);
	Assert.assertEquals(8, col0Summary.getNonMissingCount());
	Assert.assertEquals(1, col0Summary.getMin().shortValue());
	Assert.assertEquals(10, col0Summary.getMax().shortValue());
	Assert.assertEquals(5.375, col0Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Integer> col1Summary = results.getField(1);
	Assert.assertEquals(1, col1Summary.getMin().intValue());
	Assert.assertEquals(10, col1Summary.getMax().intValue());
	Assert.assertEquals(5.375, col1Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Long> col2Summary = results.getField(2);
	Assert.assertEquals(-100L, col2Summary.getMin().longValue());
	Assert.assertEquals(10000L, col2Summary.getMax().longValue());

	NumericColumnSummary<Float> col3Summary = results.getField(3);
	Assert.assertEquals(8, col3Summary.getTotalCount());
	Assert.assertEquals(0.001000, col3Summary.getMin().doubleValue(), 0.0000001);
	Assert.assertEquals(0.89999999, col3Summary.getMax().doubleValue(), 0.0000001);
	Assert.assertEquals(0.2376249988883501, col3Summary.getMean().doubleValue(), 0.000000000001);
	Assert.assertEquals(0.0768965488108089, col3Summary.getVariance().doubleValue(), 0.00000001);
	Assert.assertEquals(0.27730226975415995, col3Summary.getStandardDeviation().doubleValue(), 0.000000000001);

	NumericColumnSummary<Double> col4Summary = results.getField(4);
	Assert.assertEquals(6, col4Summary.getNonMissingCount());
	Assert.assertEquals(2, col4Summary.getMissingCount());
	Assert.assertEquals(0.0000000000023, col4Summary.getMin().doubleValue(), 0.0);
	Assert.assertEquals(79.5, col4Summary.getMax().doubleValue(), 0.000000000001);

	StringColumnSummary col5Summary = results.getField(5);
	Assert.assertEquals(8, col5Summary.getTotalCount());
	Assert.assertEquals(0, col5Summary.getNullCount());
	Assert.assertEquals(8, col5Summary.getNonNullCount());
	Assert.assertEquals(2, col5Summary.getEmptyCount());
	Assert.assertEquals(0, col5Summary.getMinLength().intValue());
	Assert.assertEquals(16, col5Summary.getMaxLength().intValue());
	Assert.assertEquals(5.0, col5Summary.getMeanLength().doubleValue(), 0.0001);

	BooleanColumnSummary col6Summary = results.getField(6);
	Assert.assertEquals(8, col6Summary.getTotalCount());
	Assert.assertEquals(2, col6Summary.getFalseCount());
	Assert.assertEquals(6, col6Summary.getTrueCount());
	Assert.assertEquals(0, col6Summary.getNullCount());

	NumericColumnSummary<Double> col7Summary = results.getField(7);
	Assert.assertEquals(100.0, col7Summary.getMax().doubleValue(), 0.00001);
	Assert.assertEquals(50.0, col7Summary.getMin().doubleValue(), 0.00001);
}
 

@Override
public OUT extract(Tuple in) {
	return in.getField(fieldId);
}
 

@Override
public OUT extract(Tuple in) {
	return in.getField(fieldId);
}
 

@Test
public void testSummarize() throws Exception {
	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	List<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> data = new ArrayList<>();
	data.add(new Tuple8<>((short) 1, 1, 100L, 0.1f, 1.012376, "hello", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 2, 2, 1000L, 0.2f, 2.003453, "hello", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 4, 10, 10000L, 0.2f, 75.00005, "null", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 10, 4, 100L, 0.9f, 79.5, "", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 5, 5, 1000L, 0.2f, 10.0000001, "a", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 6, 6, 10L, 0.1f, 0.0000000000023, "", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 7, 7, 1L, 0.2f, Double.POSITIVE_INFINITY, "abcdefghijklmnop", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 8, 8, -100L, 0.001f, Double.NaN, "abcdefghi", true, new DoubleValue(100.0)));

	Collections.shuffle(data);

	DataSet<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> ds = env.fromCollection(data);

	// call method under test
	Tuple results = DataSetUtils.summarize(ds);

	Assert.assertEquals(8, results.getArity());

	NumericColumnSummary<Short> col0Summary = results.getField(0);
	Assert.assertEquals(8, col0Summary.getNonMissingCount());
	Assert.assertEquals(1, col0Summary.getMin().shortValue());
	Assert.assertEquals(10, col0Summary.getMax().shortValue());
	Assert.assertEquals(5.375, col0Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Integer> col1Summary = results.getField(1);
	Assert.assertEquals(1, col1Summary.getMin().intValue());
	Assert.assertEquals(10, col1Summary.getMax().intValue());
	Assert.assertEquals(5.375, col1Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Long> col2Summary = results.getField(2);
	Assert.assertEquals(-100L, col2Summary.getMin().longValue());
	Assert.assertEquals(10000L, col2Summary.getMax().longValue());

	NumericColumnSummary<Float> col3Summary = results.getField(3);
	Assert.assertEquals(8, col3Summary.getTotalCount());
	Assert.assertEquals(0.001000, col3Summary.getMin().doubleValue(), 0.0000001);
	Assert.assertEquals(0.89999999, col3Summary.getMax().doubleValue(), 0.0000001);
	Assert.assertEquals(0.2376249988883501, col3Summary.getMean().doubleValue(), 0.000000000001);
	Assert.assertEquals(0.0768965488108089, col3Summary.getVariance().doubleValue(), 0.00000001);
	Assert.assertEquals(0.27730226975415995, col3Summary.getStandardDeviation().doubleValue(), 0.000000000001);

	NumericColumnSummary<Double> col4Summary = results.getField(4);
	Assert.assertEquals(6, col4Summary.getNonMissingCount());
	Assert.assertEquals(2, col4Summary.getMissingCount());
	Assert.assertEquals(0.0000000000023, col4Summary.getMin().doubleValue(), 0.0);
	Assert.assertEquals(79.5, col4Summary.getMax().doubleValue(), 0.000000000001);

	StringColumnSummary col5Summary = results.getField(5);
	Assert.assertEquals(8, col5Summary.getTotalCount());
	Assert.assertEquals(0, col5Summary.getNullCount());
	Assert.assertEquals(8, col5Summary.getNonNullCount());
	Assert.assertEquals(2, col5Summary.getEmptyCount());
	Assert.assertEquals(0, col5Summary.getMinLength().intValue());
	Assert.assertEquals(16, col5Summary.getMaxLength().intValue());
	Assert.assertEquals(5.0, col5Summary.getMeanLength().doubleValue(), 0.0001);

	BooleanColumnSummary col6Summary = results.getField(6);
	Assert.assertEquals(8, col6Summary.getTotalCount());
	Assert.assertEquals(2, col6Summary.getFalseCount());
	Assert.assertEquals(6, col6Summary.getTrueCount());
	Assert.assertEquals(0, col6Summary.getNullCount());

	NumericColumnSummary<Double> col7Summary = results.getField(7);
	Assert.assertEquals(100.0, col7Summary.getMax().doubleValue(), 0.00001);
	Assert.assertEquals(50.0, col7Summary.getMin().doubleValue(), 0.00001);
}
 

/**
 * Sends the given message to all vertices that are targets of an edge of the changed vertex.
 * This method is mutually exclusive to the method {@link #getEdges()} and may be called only once.
 *
 * <p>If the {@link EdgeDirection} is OUT (default), the message will be sent to out-neighbors.
 *
 * <p>If the {@link EdgeDirection} is IN, the message will be sent to in-neighbors.
 *
 * <p>If the {@link EdgeDirection} is ALL, the message will be sent to all neighbors.
 *
 * @param m The message to send.
 */
public void sendMessageToAllNeighbors(Message m) {
	if (edgesUsed) {
		throw new IllegalStateException("Can use either 'getEdges()' or 'sendMessageToAllNeighbors()'"
				+ "exactly once.");
	}

	edgesUsed = true;
	outValue.f1 = m;

	while (edges.hasNext()) {
		Tuple next = (Tuple) edges.next();

		/*
		 * When EdgeDirection is OUT, the edges iterator only has the out-edges
		 * of the vertex, i.e. the ones where this vertex is src.
		 * next.getField(1) gives the neighbor of the vertex running this ScatterFunction.
		 */
		if (getDirection().equals(EdgeDirection.OUT)) {
			outValue.f0 = next.getField(1);
		}
		/*
		 * When EdgeDirection is IN, the edges iterator only has the in-edges
		 * of the vertex, i.e. the ones where this vertex is trg.
		 * next.getField(10) gives the neighbor of the vertex running this ScatterFunction.
		 */
		else if (getDirection().equals(EdgeDirection.IN)) {
			outValue.f0 = next.getField(0);
		}
		 // When EdgeDirection is ALL, the edges iterator contains both in- and out- edges
		if (getDirection().equals(EdgeDirection.ALL)) {
			if (next.getField(0).equals(vertexId)) {
				// send msg to the trg
				outValue.f0 = next.getField(1);
			}
			else {
				// send msg to the src
				outValue.f0 = next.getField(0);
			}
		}
		out.collect(outValue);
	}
}
 

@SuppressWarnings({ "unchecked", "rawtypes" })
private <X> TypeInformation<X> privateGetForObject(X value) {
	checkNotNull(value);

	// check if type information can be produced using a factory
	final ArrayList<Type> typeHierarchy = new ArrayList<>();
	typeHierarchy.add(value.getClass());
	final TypeInformation<X> typeFromFactory = createTypeInfoFromFactory(value.getClass(), typeHierarchy, null, null);
	if (typeFromFactory != null) {
		return typeFromFactory;
	}

	// check if we can extract the types from tuples, otherwise work with the class
	if (value instanceof Tuple) {
		Tuple t = (Tuple) value;
		int numFields = t.getArity();
		if(numFields != countFieldsInClass(value.getClass())) {
			// not a tuple since it has more fields.
			return analyzePojo((Class<X>) value.getClass(), new ArrayList<Type>(), null, null, null); // we immediately call analyze Pojo here, because
			// there is currently no other type that can handle such a class.
		}

		TypeInformation<?>[] infos = new TypeInformation[numFields];
		for (int i = 0; i < numFields; i++) {
			Object field = t.getField(i);

			if (field == null) {
				throw new InvalidTypesException("Automatic type extraction is not possible on candidates with null values. "
						+ "Please specify the types directly.");
			}

			infos[i] = privateGetForObject(field);
		}
		return new TupleTypeInfo(value.getClass(), infos);
	}
	else if (value instanceof Row) {
		Row row = (Row) value;
		int arity = row.getArity();
		for (int i = 0; i < arity; i++) {
			if (row.getField(i) == null) {
				LOG.warn("Cannot extract type of Row field, because of Row field[" + i + "] is null. " +
					"Should define RowTypeInfo explicitly.");
				return privateGetForClass((Class<X>) value.getClass(), new ArrayList<Type>());
			}
		}
		TypeInformation<?>[] typeArray = new TypeInformation<?>[arity];
		for (int i = 0; i < arity; i++) {
			typeArray[i] = TypeExtractor.getForObject(row.getField(i));
		}
		return (TypeInformation<X>) new RowTypeInfo(typeArray);
	}
	else {
		return privateGetForClass((Class<X>) value.getClass(), new ArrayList<Type>());
	}
}
 

/**
 * Sends the given message to all vertices that are targets of an edge of the changed vertex.
 * This method is mutually exclusive to the method {@link #getEdges()} and may be called only once.
 *
 * <p>If the {@link EdgeDirection} is OUT (default), the message will be sent to out-neighbors.
 *
 * <p>If the {@link EdgeDirection} is IN, the message will be sent to in-neighbors.
 *
 * <p>If the {@link EdgeDirection} is ALL, the message will be sent to all neighbors.
 *
 * @param m The message to send.
 */
public void sendMessageToAllNeighbors(Message m) {
	if (edgesUsed) {
		throw new IllegalStateException("Can use either 'getEdges()' or 'sendMessageToAllNeighbors()'"
				+ "exactly once.");
	}

	edgesUsed = true;
	outValue.f1 = m;

	while (edges.hasNext()) {
		Tuple next = (Tuple) edges.next();

		/*
		 * When EdgeDirection is OUT, the edges iterator only has the out-edges
		 * of the vertex, i.e. the ones where this vertex is src.
		 * next.getField(1) gives the neighbor of the vertex running this ScatterFunction.
		 */
		if (getDirection().equals(EdgeDirection.OUT)) {
			outValue.f0 = next.getField(1);
		}
		/*
		 * When EdgeDirection is IN, the edges iterator only has the in-edges
		 * of the vertex, i.e. the ones where this vertex is trg.
		 * next.getField(10) gives the neighbor of the vertex running this ScatterFunction.
		 */
		else if (getDirection().equals(EdgeDirection.IN)) {
			outValue.f0 = next.getField(0);
		}
		 // When EdgeDirection is ALL, the edges iterator contains both in- and out- edges
		if (getDirection().equals(EdgeDirection.ALL)) {
			if (next.getField(0).equals(vertexId)) {
				// send msg to the trg
				outValue.f0 = next.getField(1);
			}
			else {
				// send msg to the src
				outValue.f0 = next.getField(0);
			}
		}
		out.collect(outValue);
	}
}
 

@Test
public void testSummarize() throws Exception {
	final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

	List<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> data = new ArrayList<>();
	data.add(new Tuple8<>((short) 1, 1, 100L, 0.1f, 1.012376, "hello", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 2, 2, 1000L, 0.2f, 2.003453, "hello", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 4, 10, 10000L, 0.2f, 75.00005, "null", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 10, 4, 100L, 0.9f, 79.5, "", true, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 5, 5, 1000L, 0.2f, 10.0000001, "a", false, new DoubleValue(50.0)));
	data.add(new Tuple8<>((short) 6, 6, 10L, 0.1f, 0.0000000000023, "", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 7, 7, 1L, 0.2f, Double.POSITIVE_INFINITY, "abcdefghijklmnop", true, new DoubleValue(100.0)));
	data.add(new Tuple8<>((short) 8, 8, -100L, 0.001f, Double.NaN, "abcdefghi", true, new DoubleValue(100.0)));

	Collections.shuffle(data);

	DataSet<Tuple8<Short, Integer, Long, Float, Double, String, Boolean, DoubleValue>> ds = env.fromCollection(data);

	// call method under test
	Tuple results = DataSetUtils.summarize(ds);

	Assert.assertEquals(8, results.getArity());

	NumericColumnSummary<Short> col0Summary = results.getField(0);
	Assert.assertEquals(8, col0Summary.getNonMissingCount());
	Assert.assertEquals(1, col0Summary.getMin().shortValue());
	Assert.assertEquals(10, col0Summary.getMax().shortValue());
	Assert.assertEquals(5.375, col0Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Integer> col1Summary = results.getField(1);
	Assert.assertEquals(1, col1Summary.getMin().intValue());
	Assert.assertEquals(10, col1Summary.getMax().intValue());
	Assert.assertEquals(5.375, col1Summary.getMean().doubleValue(), 0.0);

	NumericColumnSummary<Long> col2Summary = results.getField(2);
	Assert.assertEquals(-100L, col2Summary.getMin().longValue());
	Assert.assertEquals(10000L, col2Summary.getMax().longValue());

	NumericColumnSummary<Float> col3Summary = results.getField(3);
	Assert.assertEquals(8, col3Summary.getTotalCount());
	Assert.assertEquals(0.001000, col3Summary.getMin().doubleValue(), 0.0000001);
	Assert.assertEquals(0.89999999, col3Summary.getMax().doubleValue(), 0.0000001);
	Assert.assertEquals(0.2376249988883501, col3Summary.getMean().doubleValue(), 0.000000000001);
	Assert.assertEquals(0.0768965488108089, col3Summary.getVariance().doubleValue(), 0.00000001);
	Assert.assertEquals(0.27730226975415995, col3Summary.getStandardDeviation().doubleValue(), 0.000000000001);

	NumericColumnSummary<Double> col4Summary = results.getField(4);
	Assert.assertEquals(6, col4Summary.getNonMissingCount());
	Assert.assertEquals(2, col4Summary.getMissingCount());
	Assert.assertEquals(0.0000000000023, col4Summary.getMin().doubleValue(), 0.0);
	Assert.assertEquals(79.5, col4Summary.getMax().doubleValue(), 0.000000000001);

	StringColumnSummary col5Summary = results.getField(5);
	Assert.assertEquals(8, col5Summary.getTotalCount());
	Assert.assertEquals(0, col5Summary.getNullCount());
	Assert.assertEquals(8, col5Summary.getNonNullCount());
	Assert.assertEquals(2, col5Summary.getEmptyCount());
	Assert.assertEquals(0, col5Summary.getMinLength().intValue());
	Assert.assertEquals(16, col5Summary.getMaxLength().intValue());
	Assert.assertEquals(5.0, col5Summary.getMeanLength().doubleValue(), 0.0001);

	BooleanColumnSummary col6Summary = results.getField(6);
	Assert.assertEquals(8, col6Summary.getTotalCount());
	Assert.assertEquals(2, col6Summary.getFalseCount());
	Assert.assertEquals(6, col6Summary.getTrueCount());
	Assert.assertEquals(0, col6Summary.getNullCount());

	NumericColumnSummary<Double> col7Summary = results.getField(7);
	Assert.assertEquals(100.0, col7Summary.getMax().doubleValue(), 0.00001);
	Assert.assertEquals(50.0, col7Summary.getMin().doubleValue(), 0.00001);
}