private static PreferenceArray cloneAndMergeInto(PreferenceArray delegatePrefs, long itemID, long newUserID, float value)
{
int num4;
int num = (delegatePrefs == null) ? 0 : delegatePrefs.length();
int size = num + 1;
PreferenceArray array = new GenericItemPreferenceArray(size);
array.setItemID(0, itemID);
int i = 0;
while ((i < num) && (newUserID > delegatePrefs.getUserID(i)))
{
i++;
}
for (num4 = 0; num4 < i; num4++)
{
array.setUserID(num4, delegatePrefs.getUserID(num4));
array.setValue(num4, delegatePrefs.getValue(num4));
}
array.setUserID(i, newUserID);
array.setValue(i, value);
for (num4 = i + 1; num4 < size; num4++)
{
array.setUserID(num4, delegatePrefs.getUserID(num4 - 1));
array.setValue(num4, delegatePrefs.getValue(num4 - 1));
}
return(array);
}
private float doEstimatePreference(long userID, long itemID)
{
double count = 0.0;
double totalPreference = 0.0;
PreferenceArray prefs = getDataModel().getPreferencesFromUser(userID);
RunningAverage[] averages = diffStorage.getDiffs(userID, itemID, prefs);
int size = prefs.length();
for (int i = 0; i < size; i++)
{
RunningAverage averageDiff = averages[i];
if (averageDiff != null)
{
double averageDiffValue = averageDiff.getAverage();
if (weighted)
{
double weight = averageDiff.getCount();
if (stdDevWeighted)
{
var raaStdDev = averageDiff as RunningAverageAndStdDev;
if (raaStdDev != null)
{
double stdev = raaStdDev.getStandardDeviation();
if (!Double.IsNaN(stdev))
{
weight /= 1.0 + stdev;
}
}
// If stdev is NaN, then it is because count is 1. Because we're weighting by count,
// the weight is already relatively low. We effectively assume stdev is 0.0 here and
// that is reasonable enough. Otherwise, dividing by NaN would yield a weight of NaN
// and disqualify this pref entirely
// (Thanks Daemmon)
}
totalPreference += weight * (prefs.getValue(i) + averageDiffValue);
count += weight;
}
else
{
totalPreference += prefs.getValue(i) + averageDiffValue;
count += 1.0;
}
}
}
if (count <= 0.0)
{
RunningAverage itemAverage = diffStorage.getAverageItemPref(itemID);
return(itemAverage == null ? float.NaN : (float)itemAverage.getAverage());
}
else
{
return((float)(totalPreference / count));
}
}
protected virtual float doEstimatePreference(long userID, PreferenceArray preferencesFromUser, long itemID)
{
double num = 0.0;
double num2 = 0.0;
int num3 = 0;
double[] numArray = this.similarity.itemSimilarities(itemID, preferencesFromUser.getIDs());
for (int i = 0; i < numArray.Length; i++)
{
double d = numArray[i];
if (!double.IsNaN(d))
{
num += d * preferencesFromUser.getValue(i);
num2 += d;
num3++;
}
}
if (num3 <= 1)
{
return(float.NaN);
}
float estimate = (float)(num / num2);
if (this.capper != null)
{
estimate = this.capper.capEstimate(estimate);
}
return(estimate);
}
public void removeItemPref(long userID, long itemIDA, float prefValue)
{
PreferenceArray userPreferences = dataModel.getPreferencesFromUser(userID);
try
{
buildAverageDiffsLock.EnterWriteLock();
FastByIDMap <RunningAverage> aMap = averageDiffs.get(itemIDA);
int length = userPreferences.length();
for (int i = 0; i < length; i++)
{
long itemIDB = userPreferences.getItemID(i);
float bValue = userPreferences.getValue(i);
if (itemIDA < itemIDB)
{
if (aMap != null)
{
RunningAverage average = aMap.get(itemIDB);
if (average != null)
{
if (average.getCount() <= 1)
{
aMap.remove(itemIDB);
}
else
{
average.removeDatum(bValue - prefValue);
}
}
}
}
else if (itemIDA > itemIDB)
{
FastByIDMap <RunningAverage> bMap = averageDiffs.get(itemIDB);
if (bMap != null)
{
RunningAverage average = bMap.get(itemIDA);
if (average != null)
{
if (average.getCount() <= 1)
{
aMap.remove(itemIDA);
}
else
{
average.removeDatum(prefValue - bValue);
}
}
}
}
}
}
finally
{
buildAverageDiffsLock.ExitWriteLock();
}
}
public RandomRecommender(DataModel dataModel)
: base(dataModel)
{
this.random = RandomUtils.getRandom();
float negativeInfinity = float.NegativeInfinity;
float positiveInfinity = float.PositiveInfinity;
IEnumerator <long> enumerator = dataModel.getUserIDs();
while (enumerator.MoveNext())
{
long current = enumerator.Current;
PreferenceArray array = dataModel.getPreferencesFromUser(current);
for (int i = 0; i < array.length(); i++)
{
float num5 = array.getValue(i);
if (num5 < positiveInfinity)
{
positiveInfinity = num5;
}
if (num5 > negativeInfinity)
{
negativeInfinity = num5;
}
}
}
this.minPref = positiveInfinity;
this.maxPref = negativeInfinity;
}
private long processOneUser(long averageCount, long userID)
{
log.debug("Processing prefs for user {}", userID);
// Save off prefs for the life of this loop iteration
PreferenceArray userPreferences = dataModel.getPreferencesFromUser(userID);
int length = userPreferences.length();
for (int i = 0; i < length - 1; i++)
{
float prefAValue = userPreferences.getValue(i);
long itemIDA = userPreferences.getItemID(i);
FastByIDMap <RunningAverage> aMap = averageDiffs.get(itemIDA);
if (aMap == null)
{
aMap = new FastByIDMap <RunningAverage>();
averageDiffs.put(itemIDA, aMap);
}
for (int j = i + 1; j < length; j++)
{
// This is a performance-critical block
long itemIDB = userPreferences.getItemID(j);
RunningAverage average = aMap.get(itemIDB);
if (average == null && averageCount < maxEntries)
{
average = buildRunningAverage();
aMap.put(itemIDB, average);
averageCount++;
}
if (average != null)
{
average.addDatum(userPreferences.getValue(j) - prefAValue);
}
}
RunningAverage itemAverage = averageItemPref.get(itemIDA);
if (itemAverage == null)
{
itemAverage = buildRunningAverage();
averageItemPref.put(itemIDA, itemAverage);
}
itemAverage.addDatum(prefAValue);
}
return(averageCount);
}
public void addItemPref(long userID, long itemIDA, float prefValue)
{
PreferenceArray userPreferences = dataModel.getPreferencesFromUser(userID);
try
{
buildAverageDiffsLock.EnterWriteLock();
FastByIDMap <RunningAverage> aMap = averageDiffs.get(itemIDA);
if (aMap == null)
{
aMap = new FastByIDMap <RunningAverage>();
averageDiffs.put(itemIDA, aMap);
}
int length = userPreferences.length();
for (int i = 0; i < length; i++)
{
long itemIDB = userPreferences.getItemID(i);
float bValue = userPreferences.getValue(i);
if (itemIDA < itemIDB)
{
RunningAverage average = aMap.get(itemIDB);
if (average == null)
{
average = buildRunningAverage();
aMap.put(itemIDB, average);
}
average.addDatum(bValue - prefValue);
}
else
{
FastByIDMap <RunningAverage> bMap = averageDiffs.get(itemIDB);
if (bMap == null)
{
bMap = new FastByIDMap <RunningAverage>();
averageDiffs.put(itemIDB, bMap);
}
RunningAverage average = bMap.get(itemIDA);
if (average == null)
{
average = buildRunningAverage();
bMap.put(itemIDA, average);
}
average.addDatum(prefValue - bValue);
}
}
}
finally
{
buildAverageDiffsLock.ExitWriteLock();
}
}
private static float?getPreferenceForItem(PreferenceArray preferencesFromUser, long itemID)
{
int num = preferencesFromUser.length();
for (int i = 0; i < num; i++)
{
if (preferencesFromUser.getItemID(i) == itemID)
{
return(new float?(preferencesFromUser.getValue(i)));
}
}
return(null);
}
public override float?getPreferenceValue(long userID, long itemID)
{
PreferenceArray array = this.getPreferencesFromUser(userID);
int num = array.length();
for (int i = 0; i < num; i++)
{
if (array.getItemID(i) == itemID)
{
return(new float?(array.getValue(i)));
}
}
return(null);
}
private static double computeThreshold(PreferenceArray prefs)
{
if (prefs.length() < 2)
{
return(double.NegativeInfinity);
}
RunningAverageAndStdDev dev = new FullRunningAverageAndStdDev();
int num = prefs.length();
for (int i = 0; i < num; i++)
{
dev.addDatum((double)prefs.getValue(i));
}
return(dev.getAverage() + dev.getStandardDeviation());
}
public FastIDSet getRelevantItemsIDs(long userID, int at, double relevanceThreshold, DataModel dataModel)
{
PreferenceArray array = dataModel.getPreferencesFromUser(userID);
FastIDSet set = new FastIDSet(at);
array.sortByValueReversed();
for (int i = 0; (i < array.length()) && (set.size() < at); i++)
{
if (array.getValue(i) >= relevanceThreshold)
{
set.add(array.getItemID(i));
}
}
return(set);
}
public override float?getPreferenceValue(long userID, long itemID)
{
if (this.isAnonymousUser(userID))
{
PreferenceArray array = this.tempPrefs[userID];
for (int i = 0; i < array.length(); i++)
{
if (array.getItemID(i) == itemID)
{
return(new float?(array.getValue(i)));
}
}
return(null);
}
return(base.getDelegate().getPreferenceValue(userID, itemID));
}
public float get(long key)
{
PreferenceArray array = this.inf.dataModel.getPreferencesFromUser(key);
int num = array.length();
if (num == 0)
{
return(AveragingPreferenceInferrer.ZERO);
}
RunningAverage average = new FullRunningAverage();
for (int i = 0; i < num; i++)
{
average.addDatum((double)array.getValue(i));
}
return((float)average.getAverage());
}
private void buildAverageDiffs()
{
lock (this)
{
DataModel model = this.getDataModel();
IEnumerator <long> enumerator = model.getUserIDs();
while (enumerator.MoveNext())
{
long current = enumerator.Current;
PreferenceArray array = model.getPreferencesFromUser(current);
int num2 = array.length();
for (int i = 0; i < num2; i++)
{
long itemID = array.getItemID(i);
float num5 = array.getValue(i);
addDatumAndCreateIfNeeded(itemID, num5, this.itemAverages);
addDatumAndCreateIfNeeded(current, num5, this.userAverages);
this.overallAveragePrefValue.addDatum((double)num5);
}
}
}
}
private void splitOneUsersPrefs(double trainingPercentage, FastByIDMap <PreferenceArray> trainingPrefs, FastByIDMap <PreferenceArray> testPrefs, long userID, DataModel dataModel)
{
List <Preference> prefs = null;
List <Preference> list2 = null;
PreferenceArray array = dataModel.getPreferencesFromUser(userID);
int num = array.length();
for (int i = 0; i < num; i++)
{
Preference item = new GenericPreference(userID, array.getItemID(i), array.getValue(i));
if (this.random.nextDouble() < trainingPercentage)
{
if (prefs == null)
{
prefs = new List <Preference>(3);
}
prefs.Add(item);
}
else
{
if (list2 == null)
{
list2 = new List <Preference>(3);
}
list2.Add(item);
}
}
if (prefs != null)
{
trainingPrefs.put(userID, new GenericUserPreferenceArray(prefs));
if (list2 != null)
{
testPrefs.put(userID, new GenericUserPreferenceArray(list2));
}
}
}
private void buildAverageDiffs()
{
lock (this)
{
DataModel model = this.getDataModel();
IEnumerator <long> enumerator = model.getUserIDs();
while (enumerator.MoveNext())
{
PreferenceArray array = model.getPreferencesFromUser(enumerator.Current);
int num = array.length();
for (int i = 0; i < num; i++)
{
long key = array.getItemID(i);
RunningAverage average = this.itemAverages.get(key);
if (average == null)
{
average = new FullRunningAverage();
this.itemAverages.put(key, average);
}
average.addDatum((double)array.getValue(i));
}
}
}
}
public override double itemSimilarity(long itemID1, long itemID2)
{
double num18;
DataModel model = base.getDataModel();
PreferenceArray array = model.getPreferencesForItem(itemID1);
PreferenceArray array2 = model.getPreferencesForItem(itemID2);
int num = array.length();
int num2 = array2.length();
if ((num == 0) || (num2 == 0))
{
return(double.NaN);
}
long num3 = array.getUserID(0);
long num4 = array2.getUserID(0);
int i = 0;
int num6 = 0;
double num7 = 0.0;
double num8 = 0.0;
double num9 = 0.0;
double num10 = 0.0;
double sumXY = 0.0;
double num12 = 0.0;
int n = 0;
while (true)
{
int num14 = (num3 < num4) ? -1 : ((num3 > num4) ? 1 : 0);
if (num14 == 0)
{
double num15 = array.getValue(i);
double num16 = array2.getValue(num6);
sumXY += num15 * num16;
num7 += num15;
num8 += num15 * num15;
num9 += num16;
num10 += num16 * num16;
double num17 = num15 - num16;
num12 += num17 * num17;
n++;
}
if (num14 <= 0)
{
if (++i == num)
{
break;
}
num3 = array.getUserID(i);
}
if (num14 >= 0)
{
if (++num6 == num2)
{
break;
}
num4 = array2.getUserID(num6);
}
}
if (this.centerData)
{
double num19 = n;
double num20 = num7 / num19;
double num21 = num9 / num19;
double num22 = sumXY - (num21 * num7);
double num23 = num8 - (num20 * num7);
double num24 = num10 - (num21 * num9);
num18 = this.computeResult(n, num22, num23, num24, num12);
}
else
{
num18 = this.computeResult(n, sumXY, num8, num10, num12);
}
if (!double.IsNaN(num18))
{
num18 = this.normalizeWeightResult(num18, n, this.cachedNumUsers);
}
return(num18);
}
public double userSimilarity(long userID1, long userID2)
{
double num18;
DataModel model = base.getDataModel();
PreferenceArray array = model.getPreferencesFromUser(userID1);
PreferenceArray array2 = model.getPreferencesFromUser(userID2);
int num = array.length();
int num2 = array2.length();
if ((num == 0) || (num2 == 0))
{
return(double.NaN);
}
long itemID = array.getItemID(0);
long num4 = array2.getItemID(0);
int i = 0;
int num6 = 0;
double num7 = 0.0;
double num8 = 0.0;
double num9 = 0.0;
double num10 = 0.0;
double sumXY = 0.0;
double num12 = 0.0;
int n = 0;
bool flag = this.inferrer != null;
while (true)
{
int num14 = (itemID < num4) ? -1 : ((itemID > num4) ? 1 : 0);
if (flag || (num14 == 0))
{
double num15;
double num16;
if (itemID == num4)
{
num15 = array.getValue(i);
num16 = array2.getValue(num6);
}
else if (num14 < 0)
{
num15 = array.getValue(i);
num16 = this.inferrer.inferPreference(userID2, itemID);
}
else
{
num15 = this.inferrer.inferPreference(userID1, num4);
num16 = array2.getValue(num6);
}
sumXY += num15 * num16;
num7 += num15;
num8 += num15 * num15;
num9 += num16;
num10 += num16 * num16;
double num17 = num15 - num16;
num12 += num17 * num17;
n++;
}
if (num14 <= 0)
{
if (++i >= num)
{
if (!flag || (num4 == 0x7fffffffffffffffL))
{
break;
}
itemID = 0x7fffffffffffffffL;
}
else
{
itemID = array.getItemID(i);
}
}
if (num14 >= 0)
{
if (++num6 >= num2)
{
if (!flag || (itemID == 0x7fffffffffffffffL))
{
break;
}
num4 = 0x7fffffffffffffffL;
}
else
{
num4 = array2.getItemID(num6);
}
}
}
if (this.centerData)
{
double num19 = num7 / ((double)n);
double num20 = num9 / ((double)n);
double num21 = sumXY - (num20 * num7);
double num22 = num8 - (num19 * num7);
double num23 = num10 - (num20 * num9);
num18 = this.computeResult(n, num21, num22, num23, num12);
}
else
{
num18 = this.computeResult(n, sumXY, num8, num10, num12);
}
if (!double.IsNaN(num18))
{
num18 = this.normalizeWeightResult(num18, n, this.cachedNumItems);
}
return(num18);
}
public double userSimilarity(long userID1, long userID2)
{
int num4;
PreferenceArray array = this.dataModel.getPreferencesFromUser(userID1);
PreferenceArray array2 = this.dataModel.getPreferencesFromUser(userID2);
int num = array.length();
int num2 = array2.length();
if ((num <= 1) || (num2 <= 1))
{
return(double.NaN);
}
array = array.clone();
array2 = array2.clone();
array.sortByValue();
array2.sortByValue();
float num3 = 1f;
for (num4 = 0; num4 < num; num4++)
{
if (array2.hasPrefWithItemID(array.getItemID(num4)))
{
array.setValue(num4, num3);
num3++;
}
}
num3 = 1f;
for (num4 = 0; num4 < num2; num4++)
{
if (array.hasPrefWithItemID(array2.getItemID(num4)))
{
array2.setValue(num4, num3);
num3++;
}
}
array.sortByItem();
array2.sortByItem();
long num5 = array.getItemID(0);
long num6 = array2.getItemID(0);
int i = 0;
int num8 = 0;
double num9 = 0.0;
int num10 = 0;
while (true)
{
int num11 = (num5 < num6) ? -1 : ((num5 > num6) ? 1 : 0);
if (num11 == 0)
{
double num12 = array.getValue(i) - array2.getValue(num8);
num9 += num12 * num12;
num10++;
}
if (num11 <= 0)
{
if (++i >= num)
{
break;
}
num5 = array.getItemID(i);
}
if (num11 >= 0)
{
if (++num8 >= num2)
{
break;
}
num6 = array2.getItemID(num8);
}
}
if (num10 <= 1)
{
return(double.NaN);
}
return(1.0 - ((6.0 * num9) / ((double)(num10 * ((num10 * num10) - 1)))));
}
