作业一:练习UserCF和ItemCF代码
critics={'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
'The Night Listener': 3.0},
'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 3.5},
'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
'Superman Returns': 3.5, 'The Night Listener': 4.0},
'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, 'The Night Listener': 3.0,
'You, Me and Dupree': 2.0},
'Jack Matthews': {'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},
'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}
critics['Lisa Rose']['Lady in the Water']
critics['Toby']['Snakes on a Plane']
critics['Toby']
#找到相似的users
# 欧几里得距离
import numpy as np
np.sqrt(np.power(5-4, 2) + np.power(4-1, 2))
1.0 /(1 + np.sqrt(np.power(5-4, 2) + np.power(4-1, 2)) )
def sim_distance(prefs,person1,person2):
# Get the list of shared_items
si={}
for item in prefs[person1]:
if item in prefs[person2]:
si[item]=1
# if they have no ratings in common, return 0
if len(si)==0: return 0
# Add up the squares of all the differences
sum_of_squares=np.sum([np.power(prefs[person1][item]-prefs[person2][item],2)
for item in prefs[person1] if item in prefs[person2]])
#for item in si.keys()])#
return 1/(1+np.sqrt(sum_of_squares) )
sim_distance(critics, 'Lisa Rose','Toby')
#Pearson相关系数
def sim_pearson(prefs,p1,p2):
# Get the list of mutually rated items
si={}
for item in prefs[p1]:
if item in prefs[p2]: si[item]=1
# Find the number of elements
n=len(si)
# if they are no ratings in common, return 0
if n==0: return 0
# Add up all the preferences
sum1=np.sum([prefs[p1][it] for it in si])
sum2=np.sum([prefs[p2][it] for it in si])
# Sum up the squares
sum1Sq=np.sum([np.power(prefs[p1][it],2) for it in si])
sum2Sq=np.sum([np.power(prefs[p2][it],2) for it in si])
# Sum up the products
pSum=np.sum([prefs[p1][it]*prefs[p2][it] for it in si])
# Calculate Pearson score
num=pSum-(sum1*sum2/n)
den=np.sqrt((sum1Sq-np.power(sum1,2)/n)*(sum2Sq-np.power(sum2,2)/n))
if den==0: return 0
return num/den
sim_pearson(critics, 'Lisa Rose','Toby')
def topMatches(prefs,person,n=5,similarity=sim_pearson):
scores=[(similarity(prefs,person,other),other)
for other in prefs if other!=person]
# Sort the list so the highest scores appear at the top
scores.sort( )
scores.reverse( )
return scores[0:n]
topMatches(critics,'Toby',n=3) # topN
#推荐项目
def getRecommendations(prefs,person,similarity=sim_pearson):
totals={}
simSums={}
for other in prefs:
if other==person: continue
sim=similarity(prefs,person,other)
if sim<=0: continue
for item in prefs[other]:
if item not in prefs[person]:
totals.setdefault(item,0)
totals[item]+=prefs[other][item]*sim
simSums.setdefault(item,0)
simSums[item]+=sim
rankings=[(total/simSums[item],item) for item,total in totals.items()]
rankings.sort()
rankings.reverse()
return rankings
getRecommendations(critics,'Toby')
getRecommendations(critics,'Toby',similarity=sim_distance)
#将item-user字典的键值翻转¶
def transformPrefs(prefs):
result={}
for person in prefs:
for item in prefs[person]:
result.setdefault(item,{})
result[item][person]=prefs[person][item]
return result
movies = transformPrefs(critics)
#计算item的相似性¶
topMatches(movies,'Superman Returns')
#给item推荐user
def calculateSimilarItems(prefs,n=10):
# Create a dictionary of items showing which other items they
# are most similar to.
result={}
# Invert the preference matrix to be item-centric
itemPrefs=transformPrefs(prefs)
c=0
for item in itemPrefs:
# Status updates for large datasets
c+=1
if c%100==0:
print("%d / %d" % (c,len(itemPrefs)))
# Find the most similar items to this one
scores=topMatches(itemPrefs,item,n=n,similarity=sim_distance)
result[item]=scores
return result
itemsim=calculateSimilarItems(critics)
itemsim['Superman Returns']
def getRecommendedItems(prefs,itemMatch,user):
userRatings=prefs[user]
scores={}
totalSim={}
# Loop over items rated by this user
for (item,rating) in userRatings.items( ):
# Loop over items similar to this one
for (similarity,item2) in itemMatch[item]:
# Ignore if this user has already rated this item
if item2 in userRatings: continue
# Weighted sum of rating times similarity
scores.setdefault(item2,0)
scores[item2]+=similarity*rating
# Sum of all the similarities
totalSim.setdefault(item2,0)
totalSim[item2]+=similarity
# Divide each total score by total weighting to get an average
rankings=[(score/totalSim[item],item) for item,score in scores.items( )]
# Return the rankings from highest to lowest
rankings.sort( )
rankings.reverse( )
return rankings
getRecommendedItems(critics,itemsim,'Toby')
getRecommendations(movies,'Just My Luck')
getRecommendations(movies, 'You, Me and Dupree')
作业二:使用GraphLab对于音乐数据进行电影推荐
import turicreate as tc
train_file = '/Users/apple/Desktop/10000.txt'
sf = tc.SFrame.read_csv(train_file, header=False, delimiter='\t', verbose=False)
sf=sf.rename({'X1':'user_id', 'X2':'music_id', 'X3':'rating'})
sf
train_set, test_set = sf.random_split(0.8, seed=1)
popularity_model = tc.popularity_recommender.create(train_set,
'user_id', 'music_id',
target = 'rating')
item_sim_model = tc.item_similarity_recommender.create(train_set,
'user_id', 'music_id',
target = 'rating',
similarity_type='cosine')
factorization_machine_model = tc.recommender.factorization_recommender.create(train_set,
'user_id', 'music_id',
target='rating')
len(train_set)
result = tc.recommender.util.compare_models(test_set,
[popularity_model, item_sim_model, factorization_machine_model],
user_sample=.5, skip_set=train_set)
K = 10
users = tc.SArray(sf['user_id'].unique().head(100))
recs = item_sim_model.recommend(users=users, k=K)
recs.head()