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 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
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]
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])
# print(tl.unfold(factors[i],1))
actorSemantics = tl.unfold(factors[0], 1)
movieSemantics = tl.unfold(factors[1], 1)
yearSemantics = tl.unfold(factors[2], 1)
print("\n\nActor Semantics:")
for sem in actorSemantics:
print("\n\n", utils.rankSem(sem, actors))
print("\n\nMovie Semantics:")
for sem in movieSemantics:
print("\n\n", utils.rankSem(sem, movies))
print("\n\nYear Semantics:")
for sem in yearSemantics:
print("\n\n", utils.rankSem(sem, years))
actList = di.getAllActorNames()
movList = di.getAllMovieNames()
years = di.getAllYears()
actGroups = utils.form_groups_semantics(factors[0], actList, numGroups)
movGroups = utils.form_groups_semantics(factors[1], movList, numGroups)
yearGroups = utils.form_groups_semantics(factors[2], years, numGroups)
print("\n\n5 Non overlapping Actor groups:")
for grp in actGroups.keys():
print("\n\n", grp, ":", actGroups[grp])
print("\n\n5 Non overlapping Movie groups:")
for grp in movGroups.keys():
print("\n\n", grp, ":", movGroups[grp])
print("\n\n5 Non overlapping Year groups:")
for grp in yearGroups.keys():