Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- oceniPoKorisnici={
- 'Lisa Rose': {'Catch Me If You Can': 3.0 , 'Snakes on a Plane': 3.5, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5, 'The Night Listener': 3.0, 'Snitch': 3.0},
- 'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5, 'Just My Luck': 1.5, 'The Night Listener': 3.0,'You, Me and Dupree': 3.5},
- 'Michael Phillips': {'Catch Me If You Can': 2.5, 'Lady in the Water': 2.5,'Superman Returns': 3.5, 'The Night Listener': 4.0, 'Snitch': 2.0},
- 'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,'The Night Listener': 4.5, 'Superman Returns': 4.0,'You, Me and Dupree': 2.5},
- 'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,'Just My Luck': 2.0, 'Superman Returns': 3.0, 'You, Me and Dupree': 2.0},
- 'Jack Matthews': {'Catch Me If You Can': 4.5, 'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5, 'Snitch': 4.5},
- 'Toby': {'Snakes on a Plane':4.5, 'Snitch': 5.0},
- 'Michelle Nichols': {'Just My Luck' : 1.0, 'The Night Listener': 4.5, 'You, Me and Dupree': 3.5, 'Catch Me If You Can': 2.5, 'Snakes on a Plane': 3.0},
- 'Gary Coleman': {'Lady in the Water': 1.0, 'Catch Me If You Can': 1.5, 'Superman Returns': 1.5, 'You, Me and Dupree': 2.0},
- 'Larry': {'Lady in the Water': 3.0, 'Just My Luck': 3.5, 'Snitch': 1.5, 'The Night Listener': 3.5}
- }
- from math import sqrt
- # Vrakja merka za slicnost bazirana na rastojanieto za person1 i person2
- def sim_distance(oceni,person1,person2):
- # Se pravi lista na zaednicki predmeti (filmovi)
- zaednicki={}
- for item in oceni[person1].keys():
- if item in oceni[person2]:
- zaednicki[item]=1
- # ako nemaat zaednicki rejtinzi, vrati 0
- if len(zaednicki)==0:
- return 0
- # Soberi gi kvadratite na site razliki
- # sum_of_squares=sum([pow(oceni[person1][item]-oceni[person2][item],2)
- # for item in oceni[person1] if item in oceni[person2]])
- sum_of_squares=0
- for item in zaednicki.keys():
- sum_of_squares+=(oceni[person1][item]-oceni[person2][item])**2
- return 1/(1+sqrt(sum_of_squares))
- # return 1/(1+(sum_of_squares))
- def sim_pearson(oceni,person1,person2):
- # Se pravi lista na zaednicki predmeti (filmovi)
- zaednicki=[]
- for item in oceni[person1].keys():
- if item in oceni[person2]:
- zaednicki.append(item)
- # ako nemaat zaednicki rejtinzi, vrati 0
- if len(zaednicki)==0:
- return 0
- sumaOceni1=0
- sumaOceni2=0
- sumaOceniKvadrati1=0
- sumaOceniKvadrati2=0
- sumaZaednickiProizvodi=0
- for item in zaednicki:
- ocena1=oceni[person1][item]
- ocena2=oceni[person2][item]
- sumaOceni1+=ocena1
- sumaOceni2+=ocena2
- sumaOceniKvadrati1+=ocena1**2
- sumaOceniKvadrati2+=ocena2**2
- sumaZaednickiProizvodi+=ocena1*ocena2
- # print ocena1,ocena2,item
- n=len(zaednicki)
- broitel=n*sumaZaednickiProizvodi-sumaOceni1*sumaOceni2
- imenitel=(n*sumaOceniKvadrati1-sumaOceni1**2)**0.5 * (n*sumaOceniKvadrati2-sumaOceni2**2)**0.5
- if imenitel==0:
- if broitel>0:
- return 1
- elif broitel<0:
- return -1
- else:
- return -2
- formula=broitel/imenitel
- return formula
- def transformPrefs(prefs):
- result={}
- for person in prefs:
- for item in prefs[person]:
- result.setdefault(item,{})
- # Zameni gi mestata na licnosta i predmetot
- result[item][person]=prefs[person][item]
- return result
- def topMatches(prefs,person,n=5,similarity=sim_pearson):
- scores=[(similarity(prefs,person,other),other)
- for other in prefs if other!=person]
- # Se sortira listata vo rastecki redosled
- scores.sort( )
- # Se prevrtuva za najslicnite (so najgolema vrednost) da bidat prvi
- scores.reverse( )
- return scores[0:n]
- def getRecommendations(prefs,person,similarity=sim_pearson):
- totals={}
- simSums={}
- for other in prefs:
- # Za da ne se sporeduva so samiot sebe
- if other==person: continue
- sim=similarity(prefs,person,other)
- # ne se zemaat vo predvid rezultati <= 0
- if sim<=0: continue
- for item in prefs[other]:
- # za tekovniot korisnik gi zemame samo filmovite sto gi nemame veke gledano
- if item not in prefs[person] or prefs[person][item]==0:
- # Similarity * Score (Slicnost * Ocena)
- totals.setdefault(item,0)
- totals[item]+=prefs[other][item]*sim
- # Sumuma na slicnosti
- simSums.setdefault(item,0)
- simSums[item]+=sim
- # Kreiranje na normalizirana lista so rejtinzi
- rankings=[(total/simSums[item],item) for item,total in totals.items()]
- # Sortiranje na listata vo rastecki redosled
- rankings.sort()
- # Prevrtuvanje na lista za najgolemite vrednosti da bidat napred
- rankings.reverse()
- return rankings
- def getUserBasedRecomendations(oceni,korisnik,similarity=sim_pearson):
- rankings = []
- slicni=getRecommendations(oceni,korisnik)
- for item in slicni:
- rankings.append(item[1])
- rankings=rankings[0:3]
- rankings.sort()
- return rankings
- def getItemBasedRecomendations(oceni,korisnik,similarity=sim_pearson):
- rankings = []
- itemsBased = transformPrefs(oceni)
- movies = oceni[korisnik]
- notWatch = []
- for movie in itemsBased:
- if movie not in movies:
- notWatch.append(movie)
- added={}
- for movie in movies:
- slicni = topMatches(itemsBased,movie)
- for slicen in slicni:
- if slicen[1] in notWatch:
- if slicen[0] >= 0:
- if slicen[1] in added:
- if slicen[0] > added[slicen[1]]:
- added[slicen[1]]=slicen[0]
- else:
- added[slicen[1]]=slicen[0]
- reverse = []
- for x in added:
- reverse.append((added[x],x))
- reverse.sort()
- reverse.reverse()
- if len(reverse) > 3:
- for x in range(0,3):
- rankings.append(reverse[x][1])
- else:
- for x in range(0,len(reverse)):
- rankings.append(reverse[x][1])
- rankings.sort()
- return rankings
- if __name__ == "__main__":
- korisnik=input()
- print "user-based: %s"%(getUserBasedRecomendations(oceniPoKorisnici,korisnik))
- print "item-based: %s"%(getItemBasedRecomendations(oceniPoKorisnici,korisnik))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement