def vectActMovTag():
actors = di.getAllActors()
tags = di.getAllTags()
movies = di.getAllMovies()
years = di.getAllYears()
movYearsArray = di.getAllMovieYrs()
movYears = {}
for arr in movYearsArray:
movYears[arr[0]] = arr[1]
#print("movYears", movYears)
actMoviesDb = {}
for act in actors:
actMovies = di.getActorMovieIds(act[0])
actMov = []
for mov in actMovies:
actMov.append(mov[0])
actMoviesDb[act[0]] = actMov
vect = defaultdict(lambda: defaultdict(dict))
for mov in movies:
movTags = di.getMovieTagIds(mov[0])[0][0].split(",")
#print(len(movTags))
for act in actors:
actMovies = actMoviesDb[act[0]]
#print("actMovies:",actMovies)
for tag in tags:
#print("tag",tag[0])
vect[mov[0]][act[0]][tag[0]] = 0
#print("i am here")
# Set the value to 1 if the given cond. is satisfied
if ((mov[0] in actMovies) and
(tag[0] in movTags)): #and (movYears[mov[0]] == yr[0])):
vect[act[0]][mov[0]][tag[0]] = movYears[mov[0]]
#print(vect['1'])
return (vect, actors, movies, years)
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 getCoactorMatrix():
actorList = di.getAllActors()
actLen = len(actorList)
sim = np.zeros((actLen, actLen))
actMovies = [0 for i in range(actLen)]
for i in range(actLen):
actMovies[i] = di.getActorMovieIds(actorList[i][0])
for i in range(actLen):
for j in range(actLen):
set1 = set(actMovies[i])
set2 = set(actMovies[j])
sim[i][j] = len(set1 & set2)
return sim
def getActorTagMatrix():
tagIds = di.getAllTags()
tagLen = len(tagIds)
actorNames = di.getAllActorNames()
actorlist = di.getAllActors()
actorTags = np.zeros((len(actorlist), tagLen))
i = 0
idfActVector = idf.idfActorTag()
for actor in actorlist:
actVect = idf.tfIdfActorTag(actor[0], idfActVector)
for j in range(tagLen):
if (tagIds[j][0] in actVect.keys()):
actorTags[i][j] = actVect[tagIds[j][0]]
i += 1
return actorTags
def idfActorTag():
idfActVect = {}
allTags = di.getAllTags()
allActors = di.getAllActors()
actorCount = len(allActors)
for tag in allTags:
tagCount = 0
idfActVect[tag[0]] = 0
for actor in allActors:
tags = di.getActorTags(actor[0])
if (tag[0] in tags[0]):
tagCount = tagCount + 1
if (tagCount != 0):
idfActVect[tag[0]] = math.log(actorCount / tagCount)
#print(idfActVect)
return idfActVect
def formLdaMat(numSemantics): movies1 = tuple(movies) actors = di.getAllActors() actors1 = tuple(actors) actLen = len(actors) movAct = [] for movie in movies1: arr = [] for i in range(0,actLen): arr.append(0) acts = tuple(di.getMovieActorIds(movie[0])) for actor in actors1: for act in acts: if actor == act: arr[actors1.index(actor)] = 1 movAct.append(arr) movAct = np.array(movAct) model = lda.LDA(n_topics = numSemantics, n_iter = 100, random_state = 1) model.fit(movAct) #component = model.components_ return model.doc_topic_
def vectActMovYr():
actors = di.getAllActors()
movies = di.getAllMovies()
years = di.getAllYears()
movYearsArray = di.getAllMovieYrs()
movYears = {}
for arr in movYearsArray:
movYears[arr[0]] = arr[1]
#print("movYears", movYears)
actMoviesDb = {}
moviesArr = []
for mov in movies:
moviesArr.append(mov[0])
for act in actors:
actMovies = di.getActorMovieIds(act[0])
actMov = []
chk = 0
for mov in actMovies:
actMov.append(mov[0])
if (mov[0] in moviesArr):
chk = 1
if (chk == 1):
actMoviesDb[act[0]] = actMov
print("\ngot the actor movies\n")
vect = defaultdict(lambda: defaultdict(dict))
for act in actMoviesDb:
#print("movie set", act)
for mov in moviesArr:
#print("mov",mov)
for yr in years:
#print("yr",yr[0])
vect[act][mov][yr[0]] = 0
# Set the value to 1 if the given cond. is satisfied
if ((mov in actMoviesDb[act]) and (movYears[mov] == yr[0])):
vect[act][mov][yr[0]] = 1
#print(vect['1'])
return (vect, actors, movies, years)
import dbInfo as di
import tfIdfCalc as idf
import numpy as np
import utils
import similarity
from scipy.spatial import distance
actorTags = similarity.getActorTagMatrix()
actorList = di.getAllActors()
actorNames = di.getAllActorNames()
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 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]
di.delRows("movie_actor", "movie_id", mov)
di.delRows("movie_info", "movie_id", mov)
allUsers = di.getAllUsers()
delUsers = []
for usr in allUsers:
if (int(usr[0]) <= 71550):
delUsers.append(usr[0])
print("delUsers", len(delUsers))
for usr in delUsers:
di.delRows("mlratings", "user_id", usr)
di.delRows("mltags", "user_id", usr)
di.delRows("mlusers", "user_id", usr)
print("usr ="******"actor = ", act[0])
di.delRows("imdb_actor_info", "actor_id", act[0])
for tag in allTags:
if (tag[0] not in mlTg):
print("tag =", tag[0])
import dbInfo as db
import numpy as np
import svd
import utils
import similarity
#np.set_printoptions(threshold=np.nan)
actorTags = similarity.getActorTagMatrix()
mat = np.matmul(actorTags, np.transpose(actorTags))
svdSem = svd.svdCalc(mat, 3)
allActors = db.getAllActors()
actorNames = db.getAllActorNames()
print("\n\nActor-Actor similarity matrix:\n\n", mat, "\n\nsize of matrix :",
mat.shape)
print("\n\nTop 3 Latent Semantics:\n")
for sem in svdSem:
print("\n\n", utils.rankSem(sem, allActors))
groups = utils.form_groups_semantics(np.transpose(svdSem), actorNames, 3)
print("\n\n3 Non overlapping groups:")
for grp in groups.keys():
print("\n\n", grp, ":", groups[grp])
import numpy as np
import utils
import persPageRank as ppr
import dbInfo as db
import similarity
#np.set_printoptions(threshold=np.nan)
actTags = similarity.getActorTagMatrix()
sim = np.matmul(actTags, np.transpose(actTags))
print("\n\nActor-Actor similarity matrix:\n", sim, "\n\nsize of matrix :",
sim.shape)
seeds = input("\nGive Seed Actors: ").split(",")
actorNames = db.getAllActorNames()
actorIds = db.getAllActors()
seedNames = []
for i in range(len(actorIds)):
if (actorIds[i][0] in seeds):
seedNames.append(actorNames[i][0])
seedMat = ppr.formSeed(seeds, actorIds)
pprOut = ppr.personalizedPageRank(sim, seedMat, 0.85)
print("\n\n10 most related actors:\n")
for act in ppr.rankedList(pprOut, actorNames, seedNames, 10):
print(act)