public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage)
{
//Preconditions.checkNotNull(recommenderBuilder);
//Preconditions.checkNotNull(dataModel);
//Preconditions.checkArgument(trainingPercentage >= 0.0 && trainingPercentage <= 1.0,
// "Invalid trainingPercentage: " + trainingPercentage + ". Must be: 0.0 <= trainingPercentage <= 1.0");
//Preconditions.checkArgument(evaluationPercentage >= 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 <= evaluationPercentage <= 1.0");
log.Info("Beginning evaluation using {} of {}", trainingPercentage, dataModel);
int numUsers = dataModel.GetNumUsers();
FastByIDMap <IPreferenceArray> trainingPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
FastByIDMap <IPreferenceArray> testPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage)
{
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return(result);
}
public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage) {
//Preconditions.checkNotNull(recommenderBuilder);
//Preconditions.checkNotNull(dataModel);
//Preconditions.checkArgument(trainingPercentage >= 0.0 && trainingPercentage <= 1.0,
// "Invalid trainingPercentage: " + trainingPercentage + ". Must be: 0.0 <= trainingPercentage <= 1.0");
//Preconditions.checkArgument(evaluationPercentage >= 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 <= evaluationPercentage <= 1.0");
log.Info("Beginning evaluation using {} of {}", trainingPercentage, dataModel);
int numUsers = dataModel.GetNumUsers();
FastByIDMap<IPreferenceArray> trainingPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
FastByIDMap<IPreferenceArray> testPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage) {
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return result;
}
public IRStatistics Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
IDRescorer rescorer,
int at,
double relevanceThreshold,
double evaluationPercentage) {
//Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null");
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(at >= 1, "at must be at least 1");
//Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 < evaluationPercentage <= 1.0");
int numItems = dataModel.GetNumItems();
IRunningAverage precision = new FullRunningAverage();
IRunningAverage recall = new FullRunningAverage();
IRunningAverage fallOut = new FullRunningAverage();
IRunningAverage nDCG = new FullRunningAverage();
int numUsersRecommendedFor = 0;
int numUsersWithRecommendations = 0;
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
if (random.nextDouble() >= evaluationPercentage) {
// Skipped
continue;
}
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
// List some most-preferred items that would count as (most) "relevant" results
double theRelevanceThreshold = Double.IsNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold;
FastIDSet relevantItemIDs = dataSplitter.GetRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel);
int numRelevantItems = relevantItemIDs.Count();
if (numRelevantItems <= 0) {
continue;
}
FastByIDMap<IPreferenceArray> trainingUsers = new FastByIDMap<IPreferenceArray>(dataModel.GetNumUsers());
var it2 = dataModel.GetUserIDs();
while (it2.MoveNext()) {
dataSplitter.ProcessOtherUser(userID, relevantItemIDs, trainingUsers, it2.Current, dataModel);
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingUsers)
: dataModelBuilder.BuildDataModel(trainingUsers);
try {
trainingModel.GetPreferencesFromUser(userID);
} catch (NoSuchUserException nsee) {
continue; // Oops we excluded all prefs for the user -- just move on
}
int size = numRelevantItems + trainingModel.GetItemIDsFromUser(userID).Count();
if (size < 2 * at) {
// Really not enough prefs to meaningfully evaluate this user
continue;
}
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
int intersectionSize = 0;
var recommendedItems = recommender.Recommend(userID, at, rescorer);
foreach (IRecommendedItem recommendedItem in recommendedItems) {
if (relevantItemIDs.Contains(recommendedItem.GetItemID())) {
intersectionSize++;
}
}
int numRecommendedItems = recommendedItems.Count;
// Precision
if (numRecommendedItems > 0) {
precision.AddDatum((double) intersectionSize / (double) numRecommendedItems);
}
// Recall
recall.AddDatum((double) intersectionSize / (double) numRelevantItems);
// Fall-out
if (numRelevantItems < size) {
fallOut.AddDatum((double) (numRecommendedItems - intersectionSize)
/ (double) (numItems - numRelevantItems));
}
// nDCG
// In computing, assume relevant IDs have relevance 1 and others 0
double cumulativeGain = 0.0;
double idealizedGain = 0.0;
for (int i = 0; i < numRecommendedItems; i++) {
IRecommendedItem item = recommendedItems[i];
double discount = 1.0 / log2(i + 2.0); // Classical formulation says log(i+1), but i is 0-based here
if (relevantItemIDs.Contains(item.GetItemID())) {
cumulativeGain += discount;
}
// otherwise we're multiplying discount by relevance 0 so it doesn't do anything
// Ideally results would be ordered with all relevant ones first, so this theoretical
// ideal list starts with number of relevant items equal to the total number of relevant items
if (i < numRelevantItems) {
idealizedGain += discount;
}
}
if (idealizedGain > 0.0) {
nDCG.AddDatum(cumulativeGain / idealizedGain);
}
// Reach
numUsersRecommendedFor++;
if (numRecommendedItems > 0) {
numUsersWithRecommendations++;
}
stopWatch.Stop();
log.Info("Evaluated with user {} in {}ms", userID, stopWatch.ElapsedMilliseconds);
log.Info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}",
precision.GetAverage(), recall.GetAverage(), fallOut.GetAverage(), nDCG.GetAverage(),
(double) numUsersWithRecommendations / (double) numUsersRecommendedFor);
}
return new IRStatisticsImpl(
precision.GetAverage(),
recall.GetAverage(),
fallOut.GetAverage(),
nDCG.GetAverage(),
(double) numUsersWithRecommendations / (double) numUsersRecommendedFor);
}
public IRStatistics Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
IDRescorer rescorer,
int at,
double relevanceThreshold,
double evaluationPercentage)
{
//Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null");
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(at >= 1, "at must be at least 1");
//Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 < evaluationPercentage <= 1.0");
int numItems = dataModel.GetNumItems();
IRunningAverage precision = new FullRunningAverage();
IRunningAverage recall = new FullRunningAverage();
IRunningAverage fallOut = new FullRunningAverage();
IRunningAverage nDCG = new FullRunningAverage();
int numUsersRecommendedFor = 0;
int numUsersWithRecommendations = 0;
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() >= evaluationPercentage)
{
// Skipped
continue;
}
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
// List some most-preferred items that would count as (most) "relevant" results
double theRelevanceThreshold = Double.IsNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold;
FastIDSet relevantItemIDs = dataSplitter.GetRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel);
int numRelevantItems = relevantItemIDs.Count();
if (numRelevantItems <= 0)
{
continue;
}
FastByIDMap <IPreferenceArray> trainingUsers = new FastByIDMap <IPreferenceArray>(dataModel.GetNumUsers());
var it2 = dataModel.GetUserIDs();
while (it2.MoveNext())
{
dataSplitter.ProcessOtherUser(userID, relevantItemIDs, trainingUsers, it2.Current, dataModel);
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingUsers)
: dataModelBuilder.BuildDataModel(trainingUsers);
try {
trainingModel.GetPreferencesFromUser(userID);
} catch (NoSuchUserException nsee) {
continue; // Oops we excluded all prefs for the user -- just move on
}
int size = numRelevantItems + trainingModel.GetItemIDsFromUser(userID).Count();
if (size < 2 * at)
{
// Really not enough prefs to meaningfully evaluate this user
continue;
}
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
int intersectionSize = 0;
var recommendedItems = recommender.Recommend(userID, at, rescorer);
foreach (IRecommendedItem recommendedItem in recommendedItems)
{
if (relevantItemIDs.Contains(recommendedItem.GetItemID()))
{
intersectionSize++;
}
}
int numRecommendedItems = recommendedItems.Count;
// Precision
if (numRecommendedItems > 0)
{
precision.AddDatum((double)intersectionSize / (double)numRecommendedItems);
}
// Recall
recall.AddDatum((double)intersectionSize / (double)numRelevantItems);
// Fall-out
if (numRelevantItems < size)
{
fallOut.AddDatum((double)(numRecommendedItems - intersectionSize)
/ (double)(numItems - numRelevantItems));
}
// nDCG
// In computing, assume relevant IDs have relevance 1 and others 0
double cumulativeGain = 0.0;
double idealizedGain = 0.0;
for (int i = 0; i < numRecommendedItems; i++)
{
IRecommendedItem item = recommendedItems[i];
double discount = 1.0 / log2(i + 2.0); // Classical formulation says log(i+1), but i is 0-based here
if (relevantItemIDs.Contains(item.GetItemID()))
{
cumulativeGain += discount;
}
// otherwise we're multiplying discount by relevance 0 so it doesn't do anything
// Ideally results would be ordered with all relevant ones first, so this theoretical
// ideal list starts with number of relevant items equal to the total number of relevant items
if (i < numRelevantItems)
{
idealizedGain += discount;
}
}
if (idealizedGain > 0.0)
{
nDCG.AddDatum(cumulativeGain / idealizedGain);
}
// Reach
numUsersRecommendedFor++;
if (numRecommendedItems > 0)
{
numUsersWithRecommendations++;
}
stopWatch.Stop();
log.Info("Evaluated with user {} in {}ms", userID, stopWatch.ElapsedMilliseconds);
log.Info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}",
precision.GetAverage(), recall.GetAverage(), fallOut.GetAverage(), nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor);
}
return(new IRStatisticsImpl(
precision.GetAverage(),
recall.GetAverage(),
fallOut.GetAverage(),
nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor));
}
