public void testStddev()
{
IRunningAverageAndStdDev runningAverage = new FullRunningAverageAndStdDev();
Assert.AreEqual(0, runningAverage.GetCount());
Assert.True(Double.IsNaN(runningAverage.GetAverage()));
runningAverage.AddDatum(1.0);
Assert.AreEqual(1, runningAverage.GetCount());
Assert.AreEqual(1.0, runningAverage.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(runningAverage.GetStandardDeviation()));
runningAverage.AddDatum(1.0);
Assert.AreEqual(2, runningAverage.GetCount());
Assert.AreEqual(1.0, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(0.0, runningAverage.GetStandardDeviation(), EPSILON);
runningAverage.AddDatum(7.0);
Assert.AreEqual(3, runningAverage.GetCount());
Assert.AreEqual(3.0, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(3.464101552963257, runningAverage.GetStandardDeviation(), EPSILON);
runningAverage.AddDatum(5.0);
Assert.AreEqual(4, runningAverage.GetCount());
Assert.AreEqual(3.5, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(3.0, runningAverage.GetStandardDeviation(), EPSILON);
}
public void testFull()
{
IRunningAverageAndStdDev average = new FullRunningAverageAndStdDev();
Assert.AreEqual(0, average.GetCount());
Assert.True(Double.IsNaN(average.GetAverage()));
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(6.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(6.0);
Assert.AreEqual(2, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.AreEqual(0.0, average.GetStandardDeviation(), EPSILON);
average.RemoveDatum(6.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(-4.0);
Assert.AreEqual(2, average.GetCount());
Assert.AreEqual(1.0, average.GetAverage(), EPSILON);
Assert.AreEqual(5.0 * 1.4142135623730951, average.GetStandardDeviation(), EPSILON);
average.RemoveDatum(4.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(-2.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
}
public void testFull()
{
IRunningAverageAndStdDev average = new FullRunningAverageAndStdDev();
Assert.AreEqual(0, average.GetCount());
Assert.True(Double.IsNaN(average.GetAverage()));
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(6.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(6.0);
Assert.AreEqual(2, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.AreEqual(0.0, average.GetStandardDeviation(), EPSILON);
average.RemoveDatum(6.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(6.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
average.AddDatum(-4.0);
Assert.AreEqual(2, average.GetCount());
Assert.AreEqual(1.0, average.GetAverage(), EPSILON);
Assert.AreEqual(5.0 * 1.4142135623730951, average.GetStandardDeviation(), EPSILON);
average.RemoveDatum(4.0);
Assert.AreEqual(1, average.GetCount());
Assert.AreEqual(-2.0, average.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(average.GetStandardDeviation()));
}
public void testFullBig()
{
IRunningAverageAndStdDev average = new FullRunningAverageAndStdDev();
var r = RandomUtils.getRandom();
for (int i = 0; i < 1000000; i++) {
average.AddDatum(r.nextDouble() * 1000.0);
}
Assert.AreEqual(500.0, average.GetAverage(), SMALL_EPSILON);
Assert.AreEqual(1000.0 / Math.Sqrt(12.0), average.GetStandardDeviation(), SMALL_EPSILON);
}
public void testAverageAndStdDev()
{
IRunningAverageAndStdDev avg = new FullRunningAverageAndStdDev();
IRunningAverageAndStdDev inverted = new InvertedRunningAverageAndStdDev(avg);
Assert.AreEqual(0, inverted.GetCount());
avg.AddDatum(1.0);
Assert.AreEqual(1, inverted.GetCount());
Assert.AreEqual(-1.0, inverted.GetAverage(), EPSILON);
avg.AddDatum(2.0);
Assert.AreEqual(2, inverted.GetCount());
Assert.AreEqual(-1.5, inverted.GetAverage(), EPSILON);
Assert.AreEqual(Math.Sqrt(2.0)/2.0, inverted.GetStandardDeviation(), EPSILON);
}
public void testFullBig()
{
IRunningAverageAndStdDev average = new FullRunningAverageAndStdDev();
var r = RandomUtils.getRandom();
for (int i = 0; i < 1000000; i++)
{
average.AddDatum(r.nextDouble() * 1000.0);
}
Assert.AreEqual(500.0, average.GetAverage(), SMALL_EPSILON);
Assert.AreEqual(1000.0 / Math.Sqrt(12.0), average.GetStandardDeviation(), SMALL_EPSILON);
}
public void testAverageAndStdDev()
{
IRunningAverageAndStdDev avg = new FullRunningAverageAndStdDev();
IRunningAverageAndStdDev inverted = new InvertedRunningAverageAndStdDev(avg);
Assert.AreEqual(0, inverted.GetCount());
avg.AddDatum(1.0);
Assert.AreEqual(1, inverted.GetCount());
Assert.AreEqual(-1.0, inverted.GetAverage(), EPSILON);
avg.AddDatum(2.0);
Assert.AreEqual(2, inverted.GetCount());
Assert.AreEqual(-1.5, inverted.GetAverage(), EPSILON);
Assert.AreEqual(Math.Sqrt(2.0) / 2.0, inverted.GetStandardDeviation(), EPSILON);
}
public static LoadStatistics runLoad(IRecommender recommender, int howMany) {
IDataModel dataModel = recommender.GetDataModel();
int numUsers = dataModel.GetNumUsers();
double sampleRate = 1000.0 / numUsers;
var userSampler =
SamplinglongPrimitiveIterator.MaybeWrapIterator(dataModel.GetUserIDs(), sampleRate);
if (userSampler.MoveNext())
recommender.Recommend(userSampler.Current, howMany); // Warm up
var callables = new List<Action>();
while (userSampler.MoveNext()) {
callables.Add(new LoadCallable(recommender, userSampler.Current).call);
}
AtomicInteger noEstimateCounter = new AtomicInteger();
IRunningAverageAndStdDev timing = new FullRunningAverageAndStdDev();
AbstractDifferenceRecommenderEvaluator.execute(callables, noEstimateCounter, timing);
return new LoadStatistics(timing);
}
public void testStddev()
{
IRunningAverageAndStdDev runningAverage = new FullRunningAverageAndStdDev();
Assert.AreEqual(0, runningAverage.GetCount());
Assert.True(Double.IsNaN(runningAverage.GetAverage()));
runningAverage.AddDatum(1.0);
Assert.AreEqual(1, runningAverage.GetCount());
Assert.AreEqual(1.0, runningAverage.GetAverage(), EPSILON);
Assert.True(Double.IsNaN(runningAverage.GetStandardDeviation()));
runningAverage.AddDatum(1.0);
Assert.AreEqual(2, runningAverage.GetCount());
Assert.AreEqual(1.0, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(0.0, runningAverage.GetStandardDeviation(), EPSILON);
runningAverage.AddDatum(7.0);
Assert.AreEqual(3, runningAverage.GetCount());
Assert.AreEqual(3.0, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(3.464101552963257, runningAverage.GetStandardDeviation(), EPSILON);
runningAverage.AddDatum(5.0);
Assert.AreEqual(4, runningAverage.GetCount());
Assert.AreEqual(3.5, runningAverage.GetAverage(), EPSILON);
Assert.AreEqual(3.0, runningAverage.GetStandardDeviation(), EPSILON);
}
private static double computeThreshold(IPreferenceArray prefs) {
if (prefs.Length() < 2) {
// Not enough data points -- return a threshold that allows everything
return Double.NegativeInfinity;
}
IRunningAverageAndStdDev stdDev = new FullRunningAverageAndStdDev();
int size = prefs.Length();
for (int i = 0; i < size; i++) {
stdDev.AddDatum(prefs.GetValue(i));
}
return stdDev.GetAverage() + stdDev.GetStandardDeviation();
}
private double getEvaluation(FastByIDMap<IPreferenceArray> testPrefs, IRecommender recommender)
{
reset();
var estimateCallables = new List<Action>();
AtomicInteger noEstimateCounter = new AtomicInteger();
foreach (var entry in testPrefs.EntrySet()) {
estimateCallables.Add( () => {
var testUserID = entry.Key;
var prefs = entry.Value;
foreach (IPreference realPref in 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);
}
}
});
// new PreferenceEstimateCallable(recommender, entry.Key, entry.Value, noEstimateCounter));
}
log.Info("Beginning evaluation of {} users", estimateCallables.Count);
IRunningAverageAndStdDev timing = new FullRunningAverageAndStdDev();
execute(estimateCallables, noEstimateCounter, timing);
return computeFinalEvaluation();
}