public void count() {
TIntIntHashMap docCounts = new TIntIntHashMap();
int index = 0;
if (instances.size() == 0) {
logger.info("Instance list is empty");
return;
}
if (instances.get(0).getData() instanceof FeatureSequence) {
for (Instance instance : instances) {
FeatureSequence features = (FeatureSequence) instance.getData();
for (int i = 0; i < features.getLength(); i++) {
docCounts.adjustOrPutValue(features.getIndexAtPosition(i), 1, 1);
}
int[] keys = docCounts.keys();
for (int i = 0; i < keys.length - 1; i++) {
int feature = keys[i];
featureCounts[feature] += docCounts.get(feature);
documentFrequencies[feature]++;
}
docCounts = new TIntIntHashMap();
index++;
if (index % 1000 == 0) {
System.err.println(index);
}
}
} else if (instances.get(0).getData() instanceof FeatureVector) {
for (Instance instance : instances) {
FeatureVector features = (FeatureVector) instance.getData();
for (int location = 0; location < features.numLocations(); location++) {
int feature = features.indexAtLocation(location);
double value = features.valueAtLocation(location);
documentFrequencies[feature]++;
featureCounts[feature] += value;
}
index++;
if (index % 1000 == 0) {
System.err.println(index);
}
}
} else {
logger.info("Unsupported data class: " + instances.get(0).getData().getClass().getName());
}
}
public void testP2PMap() {
// Long-long
TLongLongHashMap llmap = new TLongLongHashMap();
assertTrue(serializesCorrectly(llmap, "p2p-ll-1"));
llmap.put(0, 1);
assertTrue(serializesCorrectly(llmap, "p2p-ll-2"));
llmap.put(Long.MIN_VALUE, Long.MIN_VALUE);
assertTrue(serializesCorrectly(llmap, "p2p-ll-3"));
llmap.put(Long.MAX_VALUE, Long.MAX_VALUE);
assertTrue(serializesCorrectly(llmap, "p2p-ll-4"));
// Int-int
TIntIntHashMap iimap = new TIntIntHashMap();
assertTrue(serializesCorrectly(iimap, "p2p-ii-1"));
iimap.put(0, 1);
assertTrue(serializesCorrectly(iimap, "p2p-ii-2"));
iimap.put(Integer.MIN_VALUE, Integer.MIN_VALUE);
assertTrue(serializesCorrectly(iimap, "p2p-ii-3"));
iimap.put(Integer.MAX_VALUE, Integer.MAX_VALUE);
assertTrue(serializesCorrectly(iimap, "p2p-ii-4"));
// Double-double
TDoubleDoubleHashMap ddmap = new TDoubleDoubleHashMap();
assertTrue(serializesCorrectly(ddmap, "p2p-dd-1"));
ddmap.put(0, 1);
assertTrue(serializesCorrectly(ddmap, "p2p-dd-2"));
ddmap.put(Double.MIN_VALUE, Double.MIN_VALUE);
assertTrue(serializesCorrectly(ddmap, "p2p-dd-3"));
ddmap.put(Double.MAX_VALUE, Double.MAX_VALUE);
assertTrue(serializesCorrectly(ddmap, "p2p-dd-4"));
ddmap.put(Double.POSITIVE_INFINITY, Double.POSITIVE_INFINITY);
assertTrue(serializesCorrectly(ddmap, "p2p-dd-5"));
ddmap.put(Double.NEGATIVE_INFINITY, Double.NEGATIVE_INFINITY);
assertTrue(serializesCorrectly(ddmap, "p2p-dd-6"));
// NOTE: trove doesn't deal well with NaN
// ddmap.put( Double.NaN, Double.NaN );
// assertTrue( serializesCorrectly( ddmap ) );
// Float-float
TFloatFloatHashMap ffmap = new TFloatFloatHashMap();
assertTrue(serializesCorrectly(ffmap, "p2p-ff-1"));
ffmap.put(0, 1);
assertTrue(serializesCorrectly(ffmap, "p2p-ff-2"));
ffmap.put(Float.MIN_VALUE, Float.MIN_VALUE);
assertTrue(serializesCorrectly(ffmap, "p2p-ff-3"));
ffmap.put(Float.MAX_VALUE, Float.MAX_VALUE);
assertTrue(serializesCorrectly(ffmap, "p2p-ff-4"));
ffmap.put(Float.POSITIVE_INFINITY, Float.POSITIVE_INFINITY);
assertTrue(serializesCorrectly(ffmap, "p2p-ff-5"));
ffmap.put(Float.NEGATIVE_INFINITY, Float.NEGATIVE_INFINITY);
assertTrue(serializesCorrectly(ffmap, "p2p-ff-6"));
// NOTE: trove doesn't deal well with NaN
// ffmap.put( Float.NaN, Float.NaN );
// assertTrue( serializesCorrectly( ffmap ) );
}
