def tfUserTag(userId):
usrObj = User(userId)
movies = di.getUserMovies(userId)
for movieId in movies:
movieId = movieId[0]
mv = Movie(
movieId,
0) # Here the actor movie rank is not reqd., setting this to 0
movieTags = di.getMovieTags(movieId)
for movieTag in movieTags:
tagId = movieTag[0]
timeStamp = movieTag[1]
mv.addTag(tagId, timeStamp)
usrObj.addMovie(mv)
tfVector = {}
usrObj.setUnqTags()
unqTags = usrObj.getUnqTags()
#print(unqTags)
for tagId in unqTags:
tfFactorTag = 0
for movie in usrObj.getMovies():
searchTags = movie.getTags()
tfFactor = 0
totalMovieWeight = 0
for tag in searchTags:
if (tag.getId() == tagId):
tfFactor = tfFactor + tag.getTimeWeight()
#print(tfFactor)
totalMovieWeight = totalMovieWeight + 1
if (totalMovieWeight != 0):
tfFactorTag = tfFactorTag + tfFactor / totalMovieWeight
tfVector[tagId] = tfFactorTag
tfVector = utils.sortByValue(tfVector)
return utils.normalizeVector(tfVector)
def movieTagSpace(movieId):
tagIds = di.getMovieTags(movieId)
tagLen = len(tagIds)
actorlist = di.getAllActors()
actorNames = di.getAllActorNames()
idfActVector = idf.idfActorTag()
mov = di.getMovieActorIds(movieId)
movieActors = [0 for i in range(len(mov))]
for i in range(len(mov)):
movieActors[i] = mov[i][0]
mat = [[0 for i in range(tagLen)] for j in range(len(movieActors))]
newMat = [[0 for i in range(tagLen)] for j in range(len(actorlist))]
for i in range(len(movieActors)):
taglist = idf.tfIdfActorTag(movieActors[i], idfActVector)
for j in range(tagLen):
if (tagIds[j][0] in taglist.keys()):
mat[i][j] = taglist[tagIds[j][0]]
for i in range(0, len(actorlist)):
if (actorlist[i][0] not in movieActors):
taglist = idf.tfIdfActorTag(actorlist[i][0], idfActVector)
for j in range(tagLen):
if (tagIds[j][0] in taglist.keys()):
newMat[i][j] = taglist[tagIds[j][0]]
actVect = [0 for i in range(tagLen)]
for j in range(len(movieActors)):
for i in range(tagLen):
actVect[i] = actVect[i] + mat[j][i]
dist = {}
for i in range(len(newMat)):
if (actorlist[i][0] not in movieActors):
dist[actorNames[i][0]] = distance.euclidean(newMat[i], actVect)
return utils.sortByValue(dist)[-10:]
def simActors(actId):
for i in range(len(actorTags)):
if(actId == actorList[i][0]):
givenActor = actorTags[i]
d = {}
for i in range(len(actorList)):
if(actId != actorList[i][0]):
d[actorNames[i][0]] = distance.euclidean(givenActor,actorTags[i])
return utils.sortByValue(d)[-10:]
def tfIdfActorTag(actorId, idfActVector):
tfVector = tfCalc.tfActorTag(actorId)
tfIdfVector = {}
tags = tfVector.keys()
for tag in tags:
tfIdfVector[tag] = tfVector[tag] * idfActVector[tag]
#print('actor',tfIdfVector)
tfIdfVector = utils.sortByValue(tfIdfVector)
return utils.normalizeVector(tfIdfVector)
def tfIdfGenreTag(genre, idfGenVector):
tfVector = tfCalc.tfGenreTag(genre)
tfIdfVector = {}
tags = tfVector.keys()
for tag in tags:
tfIdfVector[tag] = tfVector[tag] * idfGenVector[tag]
#print('genre',tfIdfVector)
tfIdfVector = utils.sortByValue(tfIdfVector)
return utils.normalizeVector(tfIdfVector)
def getSimilarity(mat, query, usrMovies):
res = {}
for i in range(movieLen):
if(movies[i][0] not in usrMovies):
res[movies[i][0]] = np.dot(query, mat[i])
ranks = utils.sortByValue(res)
rankedRes = []
for i in ranks:
rankedRes.append(i[0])
return rankedRes
def tfIdfUserTag(userId, idfUserVector):
tfVector = tfCalc.tfUserTag(userId)
tfIdfVector = {}
tags = tfVector.keys()
for tag in tags:
tfIdfVector[tag] = tfVector[tag] * idfUserVector[tag]
#print('user',tfIdfVector)
tfIdfVector = utils.sortByValue(tfIdfVector)
return utils.normalizeVector(tfIdfVector)
#idfVect = idfMovieTag()
#tfIdfVect = tfIdfMovieTag('3189', idfVect)
#print((tfIdfVect))
def simActors2(actId):
numSemantics = 5
u,s,v = np.linalg.svd(actorTags,0)
x=np.zeros((len(u),numSemantics))
givenActor = np.zeros(numSemantics)
for i in range(len(u)):
for j in range(numSemantics):
if(actId == actorList[i][0]):
givenActor[j] = u[i][j]
x[i][j] = u[i][j]
d = {}
for i in range(len(actorList)):
if(actId != actorList[i][0]):
d[actorNames[i][0]] = distance.euclidean(givenActor,x[i])
return utils.sortByValue(d)[-10:]
def tfActorTag(actorId):
movies = di.getActorMovies(actorId)
#print(movies)
actor = Actor(actorId)
for movie in movies:
# Here the first element in the entry is movieId and second is the actor rank
movieId = movie[0]
rank = movie[1]
# Create the Movie obj and add to the Actor
mv = Movie(movieId, rank)
# Get the tags of movie
movieTags = di.getMovieTags(movieId)
#print(movieId)
#print(movieTags)
# Calculate the weight of the tags
for movieTag in movieTags:
tagId = movieTag[0]
timeStamp = movieTag[1]
mv.addTag(tagId, timeStamp)
actor.addMovie(mv)
tfVector = {}
actor.setUnqTags()
unqTags = actor.getUnqTags()
for tagId in unqTags:
tfFactorTag = 0
#print("tagId "+tagId)
for movie in actor.getMovies():
searchTags = movie.getTags()
tfFactor = 0
totalMovieWeight = 0
movRankWeight = movie.getRWeight()
#print(movRankWeight)
for tag in searchTags:
#print(tag.getId())
if (tag.getId() == tagId):
tfFactor = tfFactor + tag.getTimeWeight()
totalMovieWeight = totalMovieWeight + 1
#print(tfFactor)
#print(totalMovieWeight)
if (
totalMovieWeight != 0
): # Check this condition because their are movies with no tags
tfFactorTag = tfFactorTag + (movRankWeight *
tfFactor) / totalMovieWeight
tfVector[tagId] = tfFactorTag
tfVector = utils.sortByValue(tfVector)
return utils.normalizeVector(tfVector)
def rankedList(arr, list, seeds, n):
d = {}
#print("before srt =",arr,list)
for i in range(len(arr)):
d[list[i][0]] = arr[i]
sortedList = utils.sortByValue(d)
#print(sortedList)
retList = []
k = 0
for i in range(len(arr)):
if (sortedList[i][0] not in seeds):
k += 1
retList.append(sortedList[i][0])
if (k >= n):
break
#print("s = ",retList)
return retList
def tfGenreTag(genre):
genObj = createGenObj(genre)
unqTags = genObj.getUnqTags()
tfVector = {}
#print(unqTags)
for tagId in unqTags:
tfFactorTag = 0
for movie in genObj.getMovies():
searchTags = movie.getTags()
tfFactor = 0
totalMovieWeight = 0
for tag in searchTags:
if (tag.getId() == tagId):
tfFactor = tfFactor + tag.getTimeWeight()
#print(tfFactor)
totalMovieWeight = totalMovieWeight + 1
if (totalMovieWeight != 0):
tfFactorTag = tfFactorTag + tfFactor / totalMovieWeight
tfVector[tagId] = tfFactorTag
tfVector = utils.sortByValue(tfVector)
return utils.normalizeVector(tfVector)
u = [0 for i in range(0,movieVectors)]
result = [[0 for i in range(movieVectors)] for j in range(0,movies)]
#pre-calculating ri values
for movie in rel:
for movieVector in range(0,movieVectors):
if(semMatrix[movie][movieVector] != 0):
r[movieVector] += 1
#pre-calculating ni values
for movie in range(0,movies):
for movieVector in range(0,movieVectors):
if(semMatrix[movie][movieVector] != 0):
n[movieVector] += 1
print(n)
#pre-calculating pi and ui values for the formula
for movieVector in range(0,movieVectors):
p[movieVector] = (r[movieVector] + n[movieVector]/N)/(R + 1)
u[movieVector] = (n[movieVector] - r[movieVector] +n[movieVector]/N)/(N - R + 1)
print(p)
print(u)
#computing the values of sim(mi) for each movie mi
for movieVector in range(0,movieVectors):
q = math.log((p[movieVector]*(1-u[movieVector]))/(u[movieVector]*(1-p[movieVector])))
for movie in range(0,movies):
result[movie][movieVector] = semMatrix[movie][movieVector] * q
print("result = ",result)
for movie in range(0,movies):
ranks[movie] = sum(result[movie])
return ranks
revisedRanks = getRevisedRanks(semMatrix, rel, irrel)
revisedRanks = utils.sortByValue(revisedRanks)
print(revisedRanks)
def getRevisedRanks(semMatrix, rel, irr, objList, usrMovies, queryVect):
N = len(objList) # Number of movies
numSemantics = len(semMatrix[0])
R = len(rel)
Q = len(irr)
ranks = {}
r = np.zeros(numSemantics)
q = np.zeros(numSemantics)
n = np.zeros(numSemantics)
p = np.zeros(numSemantics)
u = np.zeros(numSemantics)
#pre-calculating ri values
for i in rel:
#print("rel = ",i)
#print("relevent =",semMatrix[i])
for sem in range(numSemantics):
if (semMatrix[i][sem] != 0):
r[sem] += 1
#pre-calculating qi values
for i in irr:
#print("irrelevant =", semMatrix[i])
for sem in range(numSemantics):
if (semMatrix[i][sem] != 0):
q[sem] += 1
#pre-calculating ni values
for i in range(N):
for sem in range(numSemantics):
if (semMatrix[i][sem] != 0):
n[sem] += 1
#pre-calculating pi and ui values for the formula
#print("r =",r,R,"\nn =",n,N,"\nq =",q,Q)
for i in range(len(r)):
p[i] = (r[i] + n[i] / N) / (R + 1)
u[i] = (q[i] + n[i] / N) / (Q + 1)
pSum = np.sum(p)
uSum = np.sum(u)
if (pSum == 0): pSum = 1
if (uSum == 0): uSum = 1
p = p / pSum
u = u / uSum
print("\np =", p)
print("\nu =", u)
for sem in range(numSemantics):
nr = p[sem] * (1 - u[sem])
dr = u[sem] * (1 - p[sem])
#print(nr,dr)
if (nr != 0 and dr != 0 and nr != dr):
sim = math.log(nr / dr)
else:
sim = 1
queryVect[sem] = sim * queryVect[sem]
print("\nNew Query Vector:")
utils.printVect(queryVect)
for i in range(N):
if (objList[i][0] not in usrMovies):
ranks[objList[i][0]] = np.dot(queryVect, semMatrix[i])
revisedRanks = utils.sortByValue(ranks)
ranks = []
for r in revisedRanks:
ranks.append(r[0])
#print(revisedRanks)
return ranks
