@Override
public double similarity(SparseVector vec1, SparseVector vec2) {
final double distance;
// One of the vector is empty
if (Scalars.isZero(vec1.norm()) || Scalars.isZero(vec2.norm())) {
return Double.NaN;
}
LongSet ts = LongUtils.setUnion(vec1.keySet(), vec2.keySet());
MutableSparseVector v1 = MutableSparseVector.create(ts);
v1.fill(0);
v1.set(vec1);
v1.multiply(1.0 / v1.norm());
v1.addScaled(vec2, -1.0 / vec2.norm());
distance = v1.norm();
return 1 - distance;
}
/**
* This method is where the model should actually be computed.
*
* @return The TF-IDF model (a model of item tag vectors).
*/
@Override
public TFIDFModel get() {
// Build a map of tags to numeric IDs. This lets you convert tags (which are strings)
// into long IDs that you can use as keys in a tag vector.
Map<String, Long> tagIds = buildTagIdMap();
// Create a vector to accumulate document frequencies for the IDF computation
MutableSparseVector docFreq = MutableSparseVector.create(tagIds.values());
docFreq.fill(0);
// We now proceed in 2 stages. First, we build a TF vector for each item.
// While we do this, we also build the DF vector.
// We will then apply the IDF to each TF vector and normalize it to a unit vector.
// Create a map to store the item TF vectors.
Map<Long, MutableSparseVector> itemVectors = Maps.newHashMap();
// Create a work vector to accumulate each item's tag vector.
// This vector will be re-used for each item.
MutableSparseVector work = MutableSparseVector.create(tagIds.values());
// Iterate over the items to compute each item's vector.
LongSet items = dao.getItemIds();
for (long item : items) {
// Reset the work vector for this item's tags.
// work.clear();
work.fill(0);
// Now the vector is empty (all keys are 'unset').
HashMap<String, Integer> DFcount = new HashMap<String, Integer>();
// TODO Populate the work vector with the number of times each tag is applied to this item.
// TODO Increment the document frequency vector once for each unique tag on the item.
List<String> tags = dao.getItemTags(item);
// System.out.println(tags.toString());
for (String tag : tags) {
// System.out.println(tag);
// System.out.println(tagIds.get(tag));
// System.out.println(work.size());
work.set(tagIds.get(tag), work.get(tagIds.get(tag)) + 1);
if (!DFcount.containsKey(tag)) {
DFcount.put(tag, 1);
docFreq.set(tagIds.get(tag), docFreq.get(tagIds.get(tag)) + 1);
}
}
/*for(VectorEntry e: work.fast()){
if(e.getValue() == 0){
work.unset(e.getKey());
}
}*/
// Save a shrunk copy of the vector (only storing tags that apply to this item) in
// our map, we'll add IDF and normalize later.
itemVectors.put(item, work.shrinkDomain());
// work is ready to be reset and re-used for the next item
}
// Now we've seen all the items, so we have each item's TF vector and a global vector
// of document frequencies.
// Invert and log the document frequency. We can do this in-place.
for (VectorEntry e : docFreq.fast()) {
// TODO Update this document frequency entry to be a log-IDF value
docFreq.set(e, Math.log(items.size() * 1.0 / e.getValue()));
}
// Now docFreq is a log-IDF vector.
// So we can use it to apply IDF to each item vector to put it in the final model.
// Create a map to store the final model data.
Map<Long, SparseVector> modelData = Maps.newHashMap();
for (Map.Entry<Long, MutableSparseVector> entry : itemVectors.entrySet()) {
MutableSparseVector tv = entry.getValue();
// TODO Convert this vector to a TF-IDF vector
for (Long i : tagIds.values()) {
tv.set(i, tv.get(i) * docFreq.get(i));
}
// TODO Normalize the TF-IDF vector to be a unit vector
// HINT The method tv.norm() will give you the Euclidian length of the vector
tv.multiply(1.0 / tv.norm());
// Store a frozen (immutable) version of the vector in the model data.
modelData.put(entry.getKey(), tv.freeze());
}
// we technically don't need the IDF vector anymore, so long as we have no new tags
return new TFIDFModel(tagIds, modelData);
}
/**
* This method is where the model should actually be computed.
*
* @return The TF-IDF model (a model of item tag vectors).
*/
@Override
public TFIDFModel get() {
// Build a map of tags to numeric IDs. This lets you convert tags (which are strings)
// into long IDs that you can use as keys in a tag vector.
Map<String, Long> tagIds = buildTagIdMap();
// Create a vector to accumulate document frequencies for the IDF computation
MutableSparseVector docFreq = MutableSparseVector.create(tagIds.values());
docFreq.fill(0);
// We now proceed in 2 stages. First, we build a TF vector for each item.
// While we do this, we also build the DF vector.
// We will then apply the IDF to each TF vector and normalize it to a unit vector.
// Create a map to store the item TF vectors.
Map<Long, MutableSparseVector> itemVectors = Maps.newHashMap();
// Create a work vector to accumulate each item's tag vector.
// This vector will be re-used for each item.
MutableSparseVector work = MutableSparseVector.create(tagIds.values());
// Iterate over the items to compute each item's vector.
LongSet items = dao.getItemIds();
for (long item : items) {
// Reset the work vector for this item's tags.
work.clear();
// Now the vector is empty (all keys are 'unset').
List<String> hashtag = new ArrayList<String>();
for (String tag : dao.getItemTags(item)) {
Long id = tagIds.get(tag);
try {
// if id is not in the key set, throw the Exception.
work.set(id, work.get(id) + 1);
} catch (Exception e) {
// if you catch the Exception, which means that id has not been set yet.
work.set(id, 1.0); // use set method to "set" the Key
}
if (!hashtag.contains(tag)) {
docFreq.set(id, docFreq.get(id) + 1);
hashtag.add(tag);
}
}
// Save a shrunk copy of the vector (only storing tags that apply to this item) in
// our map, we'll add IDF and normalize later.
itemVectors.put(item, work.shrinkDomain());
// work is ready to be reset and re-used for the next item
}
// Now we've seen all the items, so we have each item's TF vector and a global vector
// of document frequencies.
// Invert and log the document frequency. We can do this in-place.
for (VectorEntry e : docFreq.fast()) {
docFreq.set(e.getKey(), Math.log(items.size() / e.getValue()));
}
// Now docFreq is a log-IDF vector.
// So we can use it to apply IDF to each item vector to put it in the final model.
// Create a map to store the final model data.
Map<Long, SparseVector> modelData = Maps.newHashMap();
for (Map.Entry<Long, MutableSparseVector> entry : itemVectors.entrySet()) {
MutableSparseVector tv = entry.getValue();
// DA FARE Convert this vector to a TF-IDF vector
for (VectorEntry e : tv.fast()) {
tv.set(e.getKey(), ((e.getValue() * docFreq.get(e.getKey()))));
}
// DA FARE Normalize the TF-IDF vector to be a unit vector
// HINT The method tv.norm() will give you the Euclidian length of the vector
tv.multiply(1 / tv.norm());
// Store a frozen (immutable) version of the vector in the model data.
modelData.put(entry.getKey(), tv.freeze());
}
// we technically don't need the IDF vector anymore, so long as we have no new tags
return new TFIDFModel(tagIds, modelData);
}