private double doItemSimilarity(long itemID1, long itemID2, FastIDSet preferring1)
throws TasteException {
double intersection = 0.0;
double union = 0.0;
for (Preference pref : getDataModel().getPreferencesForItem(itemID2)) {
long userID = pref.getUserID();
double weight = (double) getDataModel().getNumItems() / mUserPrefNum.get(userID);
if (preferring1.contains(userID)) {
intersection += weight;
union -= weight;
}
union += weight;
}
for (LongPrimitiveIterator it_user = preferring1.iterator(); it_user.hasNext(); ) {
long userID = (long) it_user.nextLong();
double weight = (double) getDataModel().getNumItems() / mUserPrefNum.get(userID);
union += weight;
}
if (intersection == 0) {
return Double.NaN;
}
return Math.log(intersection) / Math.log(union);
}
private FastIDSet toUserFastIDSet(PreferenceArray array) {
FastIDSet fastIDSet = new FastIDSet();
for (Preference preference : array) {
fastIDSet.add(preference.getUserID());
}
return fastIDSet;
}
@Override
public Void call() throws TasteException {
for (Preference realPref : prefs) {
float estimatedPreference = Float.NaN;
try {
estimatedPreference = recommender.estimatePreference(testUserID, realPref.getItemID());
} catch (NoSuchUserException nsue) {
// It's possible that an item exists in the test data but
// not training data in which case
// NSEE will be thrown. Just ignore it and move on.
log.info("User exists in test data but not training data: {}", testUserID);
} catch (NoSuchItemException nsie) {
log.info("Item exists in test data but not training data: {}", realPref.getItemID());
}
if (Float.isNaN(estimatedPreference)) {
noEstimateCounter.incrementAndGet();
} else {
estimatedPreference = capEstimatedPreference(estimatedPreference);
processOneEstimate(estimatedPreference, realPref);
}
}
return null;
}
private void splitOneUsersPrefs(
double trainingPercentage,
FastByIDMap<PreferenceArray> trainingPrefs,
FastByIDMap<PreferenceArray> testPrefs,
long userID,
DataModel dataModel)
throws TasteException {
List<Preference> oneUserTrainingPrefs = null;
List<Preference> oneUserTestPrefs = null;
PreferenceArray prefs = dataModel.getPreferencesFromUser(userID);
int size = prefs.length();
boolean isInstanceOfContextualUserPreferenceArray =
prefs instanceof ContextualUserPreferenceArray;
for (int i = 0; i < size; i++) {
Preference newPref =
isInstanceOfContextualUserPreferenceArray
? new ContextualPreference(
userID,
prefs.getItemID(i),
prefs.getValue(i),
((ContextualUserPreferenceArray) prefs).getContextualPreferences(i))
: new GenericPreference(userID, prefs.getItemID(i), prefs.getValue(i));
if (this.idrescorer != null && this.idrescorer.isFiltered(newPref.getItemID())) { // adiciona
// ratings
// de
// source
// domain
// sempre
// em
// training
// set
if (oneUserTrainingPrefs == null) {
oneUserTrainingPrefs = Lists.newArrayListWithCapacity(3);
}
oneUserTrainingPrefs.add(newPref);
totalOfTrainingRatingsFromSource++;
continue;
}
if (this.contextualCriteria != null
&& isInstanceOfContextualUserPreferenceArray) { // adiciona
// ratings
// de outro
// contexto
// sempre em
// training
// set
ContextualPreference contextualPref = (ContextualPreference) newPref;
if (!this.contextualCriteria.containsAllContextualAttributes(
contextualPref.getContextualPreferences())) {
if (oneUserTrainingPrefs == null) {
oneUserTrainingPrefs = Lists.newArrayListWithCapacity(3);
}
oneUserTrainingPrefs.add(newPref);
totalOfTrainingRatingsFromTargetWithoutContext++;
continue;
}
}
// para ratings do target e do contexto, fazer proporcao definida
if (random.nextDouble() < trainingPercentage) {
if (oneUserTrainingPrefs == null) {
oneUserTrainingPrefs = Lists.newArrayListWithCapacity(3);
}
oneUserTrainingPrefs.add(newPref);
totalOfTrainingRatingsFromTargetWithContext++;
} else {
if (oneUserTestPrefs == null) {
oneUserTestPrefs = Lists.newArrayListWithCapacity(3);
}
oneUserTestPrefs.add(newPref);
totalOfTestRatings++;
}
// OLD training/test set
/*
* if (random.nextDouble() < trainingPercentage) { if
* (oneUserTrainingPrefs == null) { oneUserTrainingPrefs =
* Lists.newArrayListWithCapacity(3); }
* oneUserTrainingPrefs.add(newPref); totalOfTrainingRatings++; }
* else { if (oneUserTestPrefs == null) { oneUserTestPrefs =
* Lists.newArrayListWithCapacity(3); } //testa somente com um tipo
* de rating (rescorer e/ou context) if(this.idrescorer == null &&
* this.contextualCriteria == null){ oneUserTestPrefs.add(newPref);
* totalOfTestRatings++; }else{ if(this.idrescorer != null &&
* !this.idrescorer.isFiltered(newPref.getItemID())){
* if(this.contextualCriteria != null &&
* isInstanceOfContextualUserPreferenceArray){ ContextualPreference
* contextualPref = (ContextualPreference) newPref;
* if(this.contextualCriteria
* .containsAllContextualAttributes(contextualPref
* .getContextualPreferences())){ oneUserTestPrefs.add(newPref);
* totalOfTestRatings++; } }else{ oneUserTestPrefs.add(newPref);
* totalOfTestRatings++; } }else if(this.idrescorer == null &&
* this.contextualCriteria != null &&
* isInstanceOfContextualUserPreferenceArray){ ContextualPreference
* contextualPref = (ContextualPreference) newPref;
* if(this.contextualCriteria
* .containsAllContextualAttributes(contextualPref
* .getContextualPreferences())){ oneUserTestPrefs.add(newPref);
* totalOfTestRatings++; } } } }
*/
}
if (oneUserTrainingPrefs != null) {
trainingPrefs.put(
userID,
isInstanceOfContextualUserPreferenceArray
? new ContextualUserPreferenceArray(oneUserTrainingPrefs)
: new GenericUserPreferenceArray(oneUserTrainingPrefs));
if (oneUserTestPrefs != null) {
testPrefs.put(
userID,
isInstanceOfContextualUserPreferenceArray
? new ContextualUserPreferenceArray(oneUserTestPrefs)
: new GenericUserPreferenceArray(oneUserTestPrefs));
}
}
}
