private static void getStatistics(String dataset, boolean writeAll) {
if (TOPIC_NAME != null) {
dataset += ("_" + TOPIC_NAME);
}
BookmarkReader reader = new BookmarkReader(0, false);
reader.readFile(dataset);
int bookmarks = reader.getBookmarks().size();
System.out.println("Posts: " + bookmarks);
int users = reader.getUsers().size();
System.out.println("Users: " + users);
int resources = reader.getResources().size();
System.out.println("Resources: " + resources);
int tags = reader.getTags().size();
System.out.println("Tags: " + tags);
int tagAssignments = reader.getTagAssignmentsCount();
System.out.println("Tag-Assignments: " + tagAssignments);
int categories = reader.getCategories().size();
System.out.println("Topics: " + categories);
double avgTASPerPost = (double) tagAssignments / bookmarks;
System.out.println("Avg. TAS per post: " + avgTASPerPost);
double avgBookmarksPerUser = (double) bookmarks / users;
System.out.println("Avg. resources/posts per user: "******"Avg. users/posts per resource: " + avgBookmarksPerResource);
if (writeAll) {
try {
getTrainTestSize(dataset);
FileWriter userWriter =
new FileWriter(new File("./data/metrics/" + dataset + "_userStats.txt"));
BufferedWriter userBW = new BufferedWriter(userWriter);
userBW.write("UserID| NoOfResources| NoOfTopics| Topic-Similarity\n");
List<Bookmark> trainList = reader.getBookmarks().subList(0, TRAIN_SIZE);
List<Integer> testUsers = reader.getUniqueUserListFromTestSet(TRAIN_SIZE);
System.out.println();
double avgTopicsPerUser = 0.0;
double avgTopicDiversityPerUser = 0.0;
List<Map<Integer, Double>> userTopics = Utilities.getRelativeTopicMaps(trainList, false);
List<List<Bookmark>> userBookmarks = Utilities.getBookmarks(trainList, false);
for (int userID : testUsers) {
Map<Integer, Double> topicsOfUser = userTopics.get(userID);
double topicDiversityOfUser = Bookmark.getBookmarkDiversity(userBookmarks.get(userID));
userBW.write(
userID
+ "| "
+ reader.getUserCounts().get(userID)
+ "| "
+ topicsOfUser.keySet().size()
+ "| "
+ topicDiversityOfUser
+ "\n");
avgTopicsPerUser += topicsOfUser.keySet().size();
avgTopicDiversityPerUser += topicDiversityOfUser;
}
System.out.println("Avg. topics per user: "******"Avg. topic-similarity per user: "******"Avg. topics per resource: " + avgTopicsPerResource);
userBW.flush();
userBW.close();
} catch (IOException e) {
System.out.println(e.getMessage());
}
}
System.out.println();
}
public MetricsCalculator(
PredictionFileReader reader,
String outputFile,
int k,
BookmarkReader bookmarkReader,
boolean recommTags) {
this.reader = reader;
if (recommTags) { // TODO: check
this.bookmarkReader = bookmarkReader;
}
BufferedWriter bw = null;
// TODO: Enable if you need data for statistical tests
if ((recommTags && (k == 5 || k == 10)) || (!recommTags && k == 20)) {
try {
FileWriter writer = new FileWriter(new File(outputFile + "_" + k + ".txt"), true);
bw = new BufferedWriter(writer);
} catch (Exception e) {
e.printStackTrace();
}
}
// double count = this.reader.getPredictionCount(); // only user where there are recommendations
double count = this.reader.getPredictionData().size(); // all users
double recall = 0.0,
precision = 0.0,
mrr = 0.0,
fMeasure = 0.0,
map = 0.0,
nDCG = 0.0,
diversity = 0.0,
serendipity = 0.0;
List<Map<Integer, Double>> entityFeatures = null;
List<Map<Integer, Integer>> tagCountMaps = null;
List<Bookmark> trainList = null;
if (this.bookmarkReader != null) {
trainList =
this.bookmarkReader.getBookmarks().subList(0, this.bookmarkReader.getCountLimit());
if (recommTags) {
tagCountMaps = Utilities.getResMaps(trainList);
entityFeatures = Utilities.getResourceMapsForTags(trainList);
} else {
entityFeatures =
Utilities.getUniqueTopicMaps(trainList, true); // TODO: check regarding unique!
}
}
// process each predicted line
for (PredictionData data : this.reader.getPredictionData()) {
if (data == null) {
if (bw != null) {
try {
bw.write("0.0;0.0;0.0;0.0;0.0;0.0;0.0;0.0;0.0\n");
} catch (Exception e) {
e.printStackTrace();
}
}
continue;
}
double cRecall = data.getRecall();
recall += cRecall;
double cPrecision = data.getPrecision(recommTags);
precision += cPrecision;
double cFMeasure = data.getFMeasure(recommTags);
fMeasure += cFMeasure;
double cMRR = data.getMRR();
mrr += cMRR;
double cMAP = data.getMAP();
map += cMAP;
double cNDCG = data.getNDCG();
nDCG += cNDCG;
double cDiversity = 0.0, cSerendipity = 0.0;
if (this.bookmarkReader != null) {
if (recommTags) {
cDiversity = data.getTagDiversity(entityFeatures);
if (data.getResID() < tagCountMaps.size()) {
Map<Integer, Integer> tagCountMap = tagCountMaps.get(data.getResID());
cSerendipity = data.getTagSerendipity(tagCountMap, false);
} else {
cSerendipity = 1.0;
}
} else {
List<Integer> knownEntities = Bookmark.getResourcesFromUser(trainList, data.getUserID());
cDiversity = data.getDiversity(entityFeatures, true);
cSerendipity = data.getSerendipity(entityFeatures, knownEntities);
}
diversity += cDiversity;
serendipity += cSerendipity;
}
if (bw != null) {
try {
bw.write(Double.toString(cRecall).replace(',', '.') + ";");
bw.write(Double.toString(cPrecision).replace(',', '.') + ";");
bw.write(Double.toString(cFMeasure).replace(',', '.') + ";");
bw.write(Double.toString(cMRR).replace(',', '.') + ";");
bw.write(Double.toString(cMAP).replace(',', '.') + ";");
bw.write(Double.toString(cNDCG).replace(',', '.') + ";");
bw.write(Double.toString(data.getCoverage()).replace(',', '.') + ";");
bw.write(Double.toString(cDiversity).replace('.', ',') + ";");
bw.write(Double.toString(cSerendipity).replace('.', ','));
bw.write("\n");
} catch (Exception e) {
e.printStackTrace();
}
}
}
this.recall = recall / count;
this.precision = precision / count;
this.fMeasure = fMeasure / count;
this.mrr = mrr / count;
this.map = map / count;
this.nDCG = nDCG / count;
this.userCoverage =
(double) this.reader.getPredictionCount() / (double) this.reader.getPredictionData().size();
this.diversity = diversity / count;
this.serendipity = serendipity / count;
// TODO: enable in case statistics are needed
if (bw != null) {
try {
// bw.write("\n");
bw.flush();
bw.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
