public void testStep0Mapper() throws Exception {
Random rng = RandomUtils.getRandom();
// create a dataset large enough to be split up
String descriptor = Utils.randomDescriptor(rng, numAttributes);
double[][] source = Utils.randomDoubles(rng, descriptor, numInstances);
String[] sData = Utils.double2String(source);
// write the data to a file
Path dataPath = Utils.writeDataToTestFile(sData);
JobConf job = new JobConf();
job.setNumMapTasks(numMaps);
FileInputFormat.setInputPaths(job, dataPath);
// retrieve the splits
TextInputFormat input = (TextInputFormat) job.getInputFormat();
InputSplit[] splits = input.getSplits(job, numMaps);
InputSplit[] sorted = Arrays.copyOf(splits, splits.length);
Builder.sortSplits(sorted);
Step0OutputCollector collector = new Step0OutputCollector(numMaps);
Reporter reporter = Reporter.NULL;
for (int p = 0; p < numMaps; p++) {
InputSplit split = sorted[p];
RecordReader<LongWritable, Text> reader = input.getRecordReader(split, job, reporter);
LongWritable key = reader.createKey();
Text value = reader.createValue();
Step0Mapper mapper = new Step0Mapper();
mapper.configure(p);
Long firstKey = null;
int size = 0;
while (reader.next(key, value)) {
if (firstKey == null) {
firstKey = key.get();
}
mapper.map(key, value, collector, reporter);
size++;
}
mapper.close();
// validate the mapper's output
assertEquals(p, collector.keys[p]);
assertEquals(firstKey.longValue(), collector.values[p].getFirstId());
assertEquals(size, collector.values[p].getSize());
}
}
public void testProcessOutput() throws Exception {
Random rng = RandomUtils.getRandom();
// create a dataset large enough to be split up
String descriptor = Utils.randomDescriptor(rng, numAttributes);
double[][] source = Utils.randomDoubles(rng, descriptor, numInstances);
// each instance label is its index in the dataset
int labelId = Utils.findLabel(descriptor);
for (int index = 0; index < numInstances; index++) {
source[index][labelId] = index;
}
String[] sData = Utils.double2String(source);
// write the data to a file
Path dataPath = Utils.writeDataToTestFile(sData);
// prepare a data converter
Dataset dataset = DataLoader.generateDataset(descriptor, sData);
DataConverter converter = new DataConverter(dataset);
JobConf job = new JobConf();
job.setNumMapTasks(numMaps);
FileInputFormat.setInputPaths(job, dataPath);
// retrieve the splits
TextInputFormat input = (TextInputFormat) job.getInputFormat();
InputSplit[] splits = input.getSplits(job, numMaps);
InputSplit[] sorted = Arrays.copyOf(splits, splits.length);
Builder.sortSplits(sorted);
Reporter reporter = Reporter.NULL;
int[] keys = new int[numMaps];
Step0Output[] values = new Step0Output[numMaps];
int[] expectedIds = new int[numMaps];
for (int p = 0; p < numMaps; p++) {
InputSplit split = sorted[p];
RecordReader<LongWritable, Text> reader = input.getRecordReader(split, job, reporter);
LongWritable key = reader.createKey();
Text value = reader.createValue();
Long firstKey = null;
int size = 0;
while (reader.next(key, value)) {
if (firstKey == null) {
firstKey = key.get();
expectedIds[p] = converter.convert(0, value.toString()).label;
}
size++;
}
keys[p] = p;
values[p] = new Step0Output(firstKey, size);
}
Step0Output[] partitions = Step0Job.processOutput(keys, values);
int[] actualIds = Step0Output.extractFirstIds(partitions);
assertTrue(
"Expected: " + Arrays.toString(expectedIds) + " But was: " + Arrays.toString(actualIds),
Arrays.equals(expectedIds, actualIds));
}