# A dictionary of movie critics and their ratings of a small
# set of movies
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']
# 相似性计算逻辑1：欧几里得距离
import numpy as np
np.sqrt(np.power(5-4, 2) + np.power(4-1, 2)) # 5-4是坐标点，power为幂次，2即表示平方
1.0 /(1 + np.sqrt(np.power(5-4, 2) + np.power(4-1, 2)) )
# Returns a distance-based similarity score for person1 and person2 利用上述逻辑来判断某两个人之间的相似性
def sim_distance(prefs,person1,person2):
# Get the list of shared_items 找到两个人相同的物品
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 si.keys()])
#for item in prefs[person1] if item in prefs[person2]])
return 1/(1+np.sqrt(sum_of_squares) )
sim_distance(critics, 'Lisa Rose','Toby')
# 相似性计算逻辑2：Pearson correlation coefficient
# Returns the Pearson correlation coefficient for p1 and p2
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')
# Returns the best matches for person from the prefs dictionary.
# Number of results and similarity function are optional params.
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
# Gets recommendations for a person by using a weighted average
# of every other user's rankings
def getRecommendations(prefs,person,similarity=sim_pearson):
totals={}
simSums={}
for other in prefs:
# don't compare me to myself
if other==person: continue
sim=similarity(prefs,person,other)
# ignore scores of zero or lower
if sim<=0: continue
for item in prefs[other]:
# only score movies I haven't seen yet
if item not in prefs[person] or prefs[person][item]==0:
# Similarity * Score
totals.setdefault(item,0)
totals[item]+=prefs[other][item]*sim
# Sum of similarities
simSums.setdefault(item,0)
simSums[item]+=sim
# Create the normalized list
rankings=[(total/simSums[item],item) for item,total in totals.items()]
# Return the sorted list
rankings.sort()
rankings.reverse()
return rankings
# Now you can find out what movies I should watch next:
getRecommendations(critics,'Toby')
# You’ll find that the results are only affected very slightly by the choice of similarity metric.
getRecommendations(critics,'Toby',similarity=sim_distance)
# you just need to swap the people and the items.
def transformPrefs(prefs):
result={}
for person in prefs:
for item in prefs[person]:
result.setdefault(item,{})
# Flip item and person
result[item][person]=prefs[person][item]
return result
movies = transformPrefs(critics)
movies
topMatches(movies,'Superman Returns')
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
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')
import graphlab as gl
# set canvas to show sframes and sgraphs in ipython notebook
gl.canvas.set_target('ipynb')
import matplotlib.pyplot as plt
%matplotlib inline
#train_file = 'http://s3.amazonaws.com/dato-datasets/millionsong/10000.txt'
train_file = 'F:/Anaconda/cjc/millionsong/song_usage_10000.txt'
sf = gl.SFrame.read_csv(train_file, header=False, delimiter='\t', verbose=False)
sf.rename({'X1':'user_id', 'X2':'music_id', 'X3':'rating'}).show()
(train_set, test_set) = sf.random_split(0.8, seed=1)
popularity_model = gl.popularity_recommender.create(train_set, 'user_id', 'music_id', target = 'rating')
item_sim_model = gl.item_similarity_recommender.create(train_set, 'user_id', 'music_id', target = 'rating',
similarity_type='cosine')
factorization_machine_model = gl.recommender.factorization_recommender.create(train_set, 'user_id', 'music_id',
target='rating')
result = gl.recommender.util.compare_models(test_set,
[popularity_model, item_sim_model, factorization_machine_model],
user_sample=.5, skip_set=train_set)
K = 10
users = gl.SArray(sf['user_id'].unique().head(100))
recs = item_sim_model.recommend(users=users, k=K)
recs.head()