/**
* Write a user or item index to the file.
*
* @param map The index to write.
*/
private void writeIndex(Long2ObjectMap<IntList> map) throws IOException {
LongSortedSet keys = LongUtils.packedSet(map.keySet());
BinaryIndexTableWriter tableWriter =
BinaryIndexTableWriter.create(format, channel, keys.size());
SortComparator indexComparator = new SortComparator();
LongIterator iter = keys.iterator();
while (iter.hasNext()) {
final long key = iter.nextLong();
int[] indexes = map.get(key).toIntArray();
if (needsSorting) {
IntArrays.quickSort(indexes, indexComparator);
}
if (translationMap != null) {
for (int i = 0; i < indexes.length; i++) {
indexes[i] = translationMap[indexes[i]];
}
}
logger.debug("writing {} indices for id {}", key, indexes.length);
tableWriter.writeEntry(key, indexes);
}
}
/**
* Creates a matrix to process genre data and generate the second factor of the proximity matrix
* needed for a {@code HIRItemScorer}.
*
* @param dao The DataAccessObject interfacing with the item data for the model
* @param gDao The genreDataAccessObject interfacing with the genre data for the model
*/
public TransposedFactorOfProximity(ItemDAO dao, ItemGenreDAO gDao) {
LongSet items = dao.getItemIds();
genreSize = gDao.getGenreSize();
int itemSize = items.size();
double[][] dataTransposed = new double[genreSize][itemSize];
transposed = MatrixUtils.createRealMatrix(dataTransposed);
int i = 0;
LongIterator iter = items.iterator();
while (iter.hasNext()) {
long item = iter.nextLong();
transposed.setColumnVector(i, gDao.getItemGenre(item));
i++;
}
}
/** Compute the DCG of a list of items with respect to a value vector. */
static double computeDCG(LongList items, SparseVector values) {
final double lg2 = log(2);
double gain = 0;
int rank = 0;
LongIterator iit = items.iterator();
while (iit.hasNext()) {
final long item = iit.nextLong();
final double v = values.get(item, 0);
rank++;
if (rank < 2) {
gain += v;
} else {
gain += v * lg2 / log(rank);
}
}
return gain;
}
@Test
public void itShouldDecompressLists() throws IOException {
final Input input =
getInput(
"1 1 01101 00101 0101 01100 1"
+ "0100 1 1 1 01101 00001 1 1 00100011"
+ "0101 1 1 1 1"
+ "1 0100 00001 001000111"
+ "0101 1 1 1 1"
+ "01101 0101 0 0101 01100 1 1");
final PebbleOffsetsStore offsetsStore =
new LongListPebbleOffsetsStore(new long[] {0L, 22L, 49L, 57L, 76L, 84L});
final PebbleBytesStore bytesStore = new BytesArrayPebbleBytesStore(input.buffer, offsetsStore);
final int valueBitSize = 5;
final LongList[] expectedLists =
new LongList[] {
new LongArrayList(new long[] {5L, 8L, 12L, 13L}),
new LongArrayList(new long[] {1L, 2L, 3L, 5L, 8L, 12L, 13L, 14L}),
new LongArrayList(new long[] {5L, 8L, 12L, 13L}),
new LongArrayList(
new long[] {1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L}),
new LongArrayList(new long[] {5L, 8L, 12L, 13L}),
new LongArrayList(new long[] {5L, 8L, 12L, 13L})
};
final LongList[] lists = new LongList[expectedLists.length];
LongList list;
LongIterator iterator;
for (int i = 0; i < lists.length; i++) {
iterator = StrictlyIncrementalListIterator.build(i, valueBitSize, bytesStore);
lists[i] = list = new LongArrayList();
while (iterator.hasNext()) {
list.add(iterator.nextLong());
}
}
assertEquals(
Helper.<Long, LongList>translateToUtilsCollection(expectedLists),
Helper.<Long, LongList>translateToUtilsCollection(lists));
}