def getRevisedRanksPPR(semMatrix, seeds, rel, irr, objList, usrMovies):
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("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
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
for i in range(N):
semMatrix[i][sem] = semMatrix[i][sem] * sim
matrix = np.matmul(semMatrix, np.transpose(semMatrix))
seedMat = ppr.formSeed(seeds, objList)
pprOut = ppr.personalizedPageRank(matrix, seedMat, 0.15)
rankedRes = ppr.rankedList(pprOut, objList, usrMovies, N)
#print(rankedRes)
return rankedRes
#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 = []
for seed in seedList:
seeds.append(seed[0])
seedNames = []
for i in range(len(movies)):
if (movies[i][0] in seeds):
seedNames.append(movieNames[i][0])
#print("seed names = ", seedNames)
seedMat = ppr.formSeed(seeds, movies)
pprOut = ppr.personalizedPageRank(matrix, seedMat, 0.15)
result = ppr.rankedList(pprOut, movieNames, seedNames, 5)
print("\n5 Recomended Movies:\n\n", result)
def pprRes(matrix, seeds): seedMat = ppr.formSeed(seeds, movies) pprOut = ppr.personalizedPageRank(matrix, seedMat, 0.15) return ppr.rankedList(pprOut, movies, seeds, movieLen)
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)