private static List<int[]> getPerfectTags(BookmarkReader reader, int sampleSize, int limit) {
List<int[]> tags = new ArrayList<int[]>();
int trainSize = reader.getUserLines().size() - sampleSize;
for (UserData data : reader.getUserLines().subList(trainSize, trainSize + sampleSize)) {
List<Integer> t = data.getTags();
while (t.size() < limit) {
t.add(-1);
}
tags.add(Ints.toArray(t));
}
return tags;
}
public static void predictPopularTags(String filename, int trainSize, int sampleSize) {
// filename += "_res";
BookmarkReader reader = new BookmarkReader(trainSize, false);
reader.readFile(filename);
List<int[]> values = getPopularTags(reader, sampleSize, 10);
// List<int[]> values = getPerfectTags(reader, sampleSize, 10);
reader.setUserLines(reader.getUserLines().subList(trainSize, reader.getUserLines().size()));
PredictionFileWriter writer = new PredictionFileWriter(reader, values);
writer.writeFile(filename + "_mp");
Utilities.writeStringToFile("./data/metrics/" + filename + "_mp" + "_TIME.txt", timeString);
}
private static List<int[]> getPopularResources(BookmarkReader reader, int count, int trainSize) {
List<int[]> resources = new ArrayList<int[]>();
Map<Integer, Integer> countMap = new LinkedHashMap<Integer, Integer>();
for (int i = 0; i < reader.getResources().size(); i++) {
countMap.put(i, reader.getResourceCounts().get(i));
}
Map<Integer, Integer> sortedCountMap =
new TreeMap<Integer, Integer>(new IntMapComparator(countMap));
sortedCountMap.putAll(countMap);
for (int userID : reader.getUniqueUserListFromTestSet(trainSize)) {
List<Integer> userResources =
UserData.getResourcesFromUser(reader.getUserLines().subList(0, trainSize), userID);
// System.out.println(userResources.size());
List<Integer> resIDs = new ArrayList<Integer>();
int i = 0;
for (Integer key : sortedCountMap.keySet()) {
if (i < count) {
if (!userResources.contains(key)) {
resIDs.add(key);
i++;
}
} else {
break;
}
}
resources.add(Ints.toArray(resIDs));
}
return resources;
}
private static List<int[]> getRandomResources(BookmarkReader reader, int count, int trainSize) {
List<int[]> resources = new ArrayList<int[]>();
int resCount = reader.getResources().size();
for (int userID : reader.getUniqueUserListFromTestSet(trainSize)) {
List<Integer> userResources =
UserData.getResourcesFromUser(reader.getUserLines().subList(0, trainSize), userID);
List<Integer> resIDs = new ArrayList<Integer>();
int i = 0;
for (Integer res : Utilities.getRandomIndices(0, resCount - 1)) {
if (i < count) {
if (!userResources.contains(res)) {
resIDs.add(res);
i++;
}
} else {
break;
}
}
resources.add(Ints.toArray(resIDs));
}
return resources;
}