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 ldaInputTags(genre):
movies = di.getGenreMovies(genre)
movieTags = []
for movie in movies:
arr = []
tags = di.getMovieTags(movie[0])
for tag in tags:
arr.append(tag[0])
if (len(tags) != 0):
movieTags.append(arr)
return movieTags
def tfMovTag(movieId):
mv = Movie(movieId,
0) # Here the actor movie rank is not reqd., setting this to 0
movieTags = di.getMovieTags(movieId)
#print("tags are")
#print(movieTags)
for movieTag in movieTags:
tagId = movieTag[0]
timeStamp = movieTag[1]
mv.addTag(tagId, timeStamp)
tfArray = utils.getGenreMovieTags(mv)
return tfArray
#print(tfMovTag('3854'))
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 formLdaMat1(numSemantics): movies1 = tuple(movies) tags1 = tuple(tagIds) movTag = [] for movie in movies1: arr = [] for i in range(allTagLen): arr.append(0) tgs = tuple(di.getMovieTags(movie[0])) for tag in tags1: for tg in tgs: if tag[0] == tg[0]: arr[tags1.index(tag)] += 1 movTag.append(arr) movTag = np.array(movTag) #print(movTag) model = lda.LDA(n_topics = numSemantics, n_iter = 100, random_state = 1) model.fit(movTag) return model.doc_topic_
def createGenObj(genre):
genObj = Genre(genre)
movies = di.getGenreMovies(genre)
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)
#print("tags are")
#print(movieTags)
for movieTag in movieTags:
tagId = movieTag[0]
timeStamp = movieTag[1]
mv.addTag(tagId, timeStamp)
genObj.addMovie(mv)
#print("mv unq tags are")
#print(mv.getUnqTags())
genObj.setUnqTags()
return genObj
import dbInfo as db
import numpy as np
import persPageRank as ppr
userId = input("\nGive User Id: ")
movies = db.getAllMovies()
movieNames = db.getAllMovieNames()
tfmovies = {}
for movieId in movies:
Taglist = db.getMovieTags(movieId[0])
UnqTags = db.getMovieTagIds(movieId[0])[0][0].split(",")
#print(UnqTags,movieId,Taglist)
tfvect = {}
for tag in UnqTags:
tffact = 0
for t in Taglist:
if (t[0] == tag):
tffact += 1
tfvect[tag[0]] = tffact / len(Taglist)
tfmovies[movieId[0]] = tfvect
tagids = db.getAllTags()
#print(tagids)
movietf = np.zeros((len(tfmovies), len(tagids)))
for i in range(len(tfmovies)):
for j in range(len(tagids)):
if (tagids[j][0] in tfmovies[movies[i][0]].keys()):
movietf[i][j] = tfmovies[movies[i][0]][tagids[j][0]]
matrix = np.matmul(movietf, np.transpose(movietf))
seedList = db.getUserMoviesRates(userId)
seeds = []
import dbInfo as di
import numpy as np
import lda
np.set_printoptions(threshold=np.nan)
movies = di.getAllMovies()
movies1 = tuple(movies)
tags = di.getAllTags()
tags1 = tuple(tags)
n1 = len(movies1)
n2 = len(tags)
movTag = []
for movie in movies1:
arr = []
for i in range(0,n2):
arr.append(0)
tgs = tuple(di.getMovieTags(movie[0]))
for tag in tags1:
for tg in tgs:
if tag[0] == tg[0]:
arr[tags1.index(tag)] += 1
print("i = ",tags1.index(tag))
movTag.append(arr)
movTag = np.array(movTag)
print(movTag)
#model = lda.LDA(n_topics = 500, n_iter = 100, random_state = 1)
#model.fit(movTag)
#doc2topic = model.doc_topic_
with open('../testdata/movie-actor.csv', encoding='utf8') as movie_actor:
entries = csv.DictReader(movie_actor)
for entry in entries:
#print(entry)
myDbCurr.execute("insert into movie_actor values(?,?,?)",[entry['movieid'],entry['actorid'],entry['actor_movie_rank']])
myDbConn.commit()
print("6")
# Add tags to actors
actors = di.getAllActors()
for actor in actors:
movies = di.getActorMovies(actor[0])
tags = ''
for movie in movies:
movieTags = di.getMovieTags(movie[0])
for movieTag in movieTags:
if(tags == ''):
tags = movieTag[0]
elif(movieTag[0] not in tags):
tags = tags + ',' + movieTag[0]
myDbCurr.execute("update imdb_actor_info set tags = ? where actor_id = ?",(tags, actor[0]))
myDbConn.commit()
print("5")
# Add tags to Genres
myDbCurr.execute("select distinct genre from mlmovies")
genres = myDbCurr.fetchall()
for genre in genres:
movies = di.getGenreMovies(genre[0])
tags = ''
for movie in movies: