def test_transformPrefs(self):
self.assertEqual(
recommendations.transformPrefs(
recommendations.critics)['Lady in the Water'], {
'Lisa Rose': 2.5,
'Jack Matthews': 3.0,
'Michael Phillips': 2.5,
'Gene Seymour': 3.0,
'Mick LaSalle': 3.0
})
def test_topMatches_movies(self):
movies = rec.transformPrefs(rec.critics)
matches_long = rec.topMatches(movies, 'Superman Returns')
matches = round_sequence(matches_long, 3, trunc_n)
self.assertEqual(
matches,
[(0.657, 'You, Me and Dupree'),
(0.487, 'Lady in the Water'),
(0.111, 'Snakes on a Plane'),
(-0.179, 'The Night Listener'),
(-0.422, 'Just My Luck')])
def test_transformPrefs(self):
byname = {'Lisa Rose':
{'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5},
'Gene Seymour':
{'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5}}
bymovie = {'Lady in the Water':
{'Lisa Rose':2.5,'Gene Seymour':3.0},
'Snakes on a Plane':
{'Lisa Rose':3.5,'Gene Seymour':3.5}}
actual = rec.transformPrefs(byname)
expected = bymovie
self.assertEqual(actual, expected)
def testDelicious():
import recommendations
delusers = initializeUserDict('programming')
fillItems(delusers)
user = delusers.keys()[random.randint(0, len(delusers) - 1)]
print user
print recommendations.topMatches(delusers, user, similarity=recommendations.simEuclidean)
recUrls = recommendations.getRecommendations(delusers, user, similarity=recommendations.simEuclidean)[0:10]
print recUrls
url = recUrls[0][1]
print url
print recommendations.topMatches(recommendations.transformPrefs(delusers), url)
def real_you_favorite(self):
print("List of movies :")
prefs = recommendations.transformPrefs(self.prefs)
idx = 1
movies = []
for movie in prefs:
print("[%s] %s" % (idx, movie))
movies.append(movie)
idx = idx + 1
fav = input("Select your most favorite movie")
fav_title = movies[int(fav)-1]
scores=[(recommendations.sim_pearson(prefs, fav_title, other),other) for other in prefs if other!=fav_title]
scores.sort()
scores.reverse()
total = len(scores)
return (fav_title, scores[0:5], scores[total-6:total-1])
def check_database(self, data_dir='data'):
conv = convert_data.Converter(self.db)
conv.setup()
rs = self.cursor.execute("SELECT COUNT(*) FROM user;")
for count, in rs.fetchall():
if count < len(self.prefs):
conv.import_user(data_dir + '/u.user')
prefs = recommendations.transformPrefs(self.prefs)
rs = self.cursor.execute("SELECT COUNT(*) FROM item;")
for count, in rs.fetchall():
if count < len(prefs):
conv.import_item(data_dir + '/u.item')
num_data = 0
for mov in prefs:
num_data = num_data + len(prefs[mov])
rs = self.cursor.execute("SELECT COUNT(*) FROM data;")
for count, in rs.fetchall():
if count < num_data:
conv.import_data(data_dir + '/u.data')
def testBasics(self):
d = { 'a': {'b': 0.4}, 'c': {'d': 0.5} }
expected = { 'b': {'a': 0.4}, 'd': {'c' : 0.5} }
self.assertEquals(expected, recommendations.transformPrefs(d))
# calculate the simmilarity
sim = similarity(prefs, person, other)
# ignore any people who aren't simmilar
if sim <= 0:
continue
for item in prefs[other]:
# only consider movies they haven't seen
if item not in prefs[person]:
# if it doesn't exist in the list of totals, set it's count as 0
totals.setdefault(item, 0)
totals[item] += prefs[other][item] * sim
simmilarity_sums.setdefault(item, 0)
simmilarity_sums[item] += sim
rankings = [(total / simmilarity_sums[item], item)
for item, total in totals.items()]
rankings.sort(key=lambda x: x[0])
rankings.reverse()
return rankings
for score, item in getRecommendations(critics, 'Toby'):
print("For ", item, " the score is ", score)
for score, item in getRecommendations(transformPrefs(critics), 'Just My Luck'):
print("For ", item, " the score is ", score)
def testEmptyPrefsList(self):
d = { 'a': {}, 'c': {'d': 0.5} }
expected = { 'd': {'c' : 0.5} }
self.assertEquals(expected, recommendations.transformPrefs(d))
__author__ = 'ponomarevandrew' from recommendations import critics import recommendations print critics['Lisa Rose']['Lady in the Water'] critics['Toby']['Snakes on a Plane'] = 4.5 print critics['Toby'] print critics print "-----------" print recommendations.getRecommendations(recommendations.critics, 'Toby') print "-----------" movies = recommendations.transformPrefs(recommendations.critics) print recommendations.topMatches(movies, 'Superman Returns') print "-----------" itemsim = recommendations.calculateSimilarItems(recommendations.critics) print itemsim print "-----------" print recommendations.getRecommendedItems(recommendations.critics, itemsim, 'Toby') print "-----------" prefs = recommendations.loadMovieLens() print prefs['1'] print "-----------" print recommendations.getRecommendations(prefs,'42')[31:60] print "-----------" ##itemsim = recommendations.calculateSimilarItems(prefs, n =50) ##print itemsim print "-----------" ##print recommendations.getRecommendedItems(prefs,itemsim, '87')[0:30] print "-----------"
def testAllEmpty(self):
d = { }
expected = { }
self.assertEquals(expected, recommendations.transformPrefs(d))
def testOnlyEmptyPrefs(self):
d = { 'a': {} }
expected = { }
self.assertEquals(expected, recommendations.transformPrefs(d))
#
from appdata import AppData
import recommendations as rec
import sys
import pickle
if __name__ == '__main__':
prefs = rec.loadMovieLens('../data/movielens-100k')
itemPrefs=rec.transformPrefs(prefs)
try:
input = open('itemNeighbours.pkl', 'rb')
itemNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating itemNeighbours.pkl"
itemNeighbours = rec.calcNarestNeighbours(prefs, 10)
output = open('itemNeighbours.pkl', 'wb')
pickle.dump(itemNeighbours, output)
output.close()
try:
input = open('userNeighbours.pkl', 'rb')
userNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating userNeighbours.pkl"
userNeighbours = rec.calcNarestNeighbours(itemPrefs, 10)
output = open('userNeighbours.pkl', 'wb')
pickle.dump(userNeighbours, output)
output.close()
#
from appdata import AppData
import recommendations as rec
import sys
import pickle
if __name__ == '__main__':
prefs = rec.loadMovieLens('../data/movielens-100k')
itemPrefs = rec.transformPrefs(prefs)
try:
input = open('itemNeighbours.pkl', 'rb')
itemNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating itemNeighbours.pkl"
itemNeighbours = rec.calcNarestNeighbours(prefs, 10)
output = open('itemNeighbours.pkl', 'wb')
pickle.dump(itemNeighbours, output)
output.close()
try:
input = open('userNeighbours.pkl', 'rb')
userNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating userNeighbours.pkl"
userNeighbours = rec.calcNarestNeighbours(itemPrefs, 10)
output = open('userNeighbours.pkl', 'wb')
pickle.dump(userNeighbours, output)
output.close()
print recommendations.topMatches(critics, user, 3,
recommendations.sim_distance), '\n'
print 'Recommended books according to the euclidian distance\n'
print recommendations.getRecommendations(
critics, user, similarity=recommendations.sim_distance)[0:3], '\n'
else:
if dischoice == '2':
print 'top matched user according to the pearson corelation\n'
print recommendations.topMatches(critics, user, 3), '\n'
print 'Recommended books according to the pearson corelaton\n'
print recommendations.getRecommendations(critics, user)[0:3], '\n'
else:
print 'invalid choice... try again'
else:
if choice == '2':
critic = recommendations.transformPrefs(critics)
book = raw_input('enter the book name:\t')
print '\n'
print 'Users who have read the book till now are:\n'
print critic[book], '\n'
disch = raw_input(
'enter your choice\n1.euclidian distance\n2.pearson corelation\nchoice:\t'
)
if disch == '1':
print 'top matched book according to the euclidian distance\n'
print recommendations.topMatches(
critic, book, 3, recommendations.sim_distance), '\n'
print 'Recommended user according to the euclidian distance\n'
print recommendations.getRecommendations(
critic, book,
similarity=recommendations.sim_distance)[0:3], '\n'
print 'Euclidean Distance Score of Lisa Rose and Gene Seymour is ' print sim_distance(critics, 'Lisa Rose', 'Gene Seymour') print 'Pearson Correlation Score of Lisa Rose and Gene Seymour is ' print sim_pearson(critics, 'Lisa Rose', 'Gene Seymour') print 'TopMatches 3 for Toby is ' print topMatches(critics, 'Toby', n=3) # User-Based CF print '通过按人群与 Toby 相似度，加权重新评分，为影片排名获得推荐: ' print getRecommendations(critics, 'Toby') print '通过查看哪些人喜欢 Superman Returns，以及这些人喜欢哪些其他物品来确定相似度：' movies = transformPrefs(critics) print topMatches(movies, 'Superman Returns') print '可能最喜欢 Just My Luck 的人群列表（对调人和物不一定能获得有用信息）：' print getRecommendations(movies, 'Just My Luck') # Item-Based CF print '构造物品比较数据集：' itemsim = calculateSimilarItems(critics) print itemsim print '基于物品的推荐为 Toby 提供推荐列表：' print getRecommendedItems(critics, itemsim, 'Toby')
def testCollect(self):
d = { 'a': {'z': 0.1}, 'b': {'z' : 0.2}, 'c': {'z': 0.3} }
expected = { 'z': {'a': 0.1, 'b': 0.2, 'c': 0.3} }
self.assertEquals(expected, recommendations.transformPrefs(d))
#!/usr/local/bin/python
import sys
import recommendations
if __name__ == '__main__':
fav_moviename = "Die Hard (1988)"
hate_moviename = "Kazaam (1996)"
prefs = recommendations.loadMovieLens()
itemPrefs = recommendations.transformPrefs(prefs)
fav_results = recommendations.topMatches(itemPrefs, fav_moviename, 2000)
hate_results = recommendations.topMatches(itemPrefs, hate_moviename, 2000)
print "Most 5 correlated for my top favourite movie"
for i in fav_results[0:5]:
print i[0], i[1]
print '\n'
print "Least 5 correlated for my top favourite movie"
fav_results.reverse()
for i in fav_results[0:5]:
print i[0], i[1]
print '\n'
print "Most 5 correlated for my least favourite movie"
for i in hate_results[0:5]:
print i[0], i[1]
print '\n'
print "Least 5 correlated for my least favourite movie"
hate_results.reverse()
for i in hate_results[0:5]:
print i[0], i[1]
def main(): movies=recommendations.transformPrefs(recommendations.critics) print recommendations.getRecommendations(movies,'Just My Luck')
#!/usr/local/bin/python
import sys
import recommendations
if __name__ == '__main__':
fav_moviename = "Die Hard (1988)"
hate_moviename = "Kazaam (1996)"
prefs = recommendations.loadMovieLens()
itemPrefs = recommendations.transformPrefs(prefs)
fav_results = recommendations.topMatches(itemPrefs,fav_moviename,2000)
hate_results = recommendations.topMatches(itemPrefs,hate_moviename,2000)
print "Most 5 correlated for my top favourite movie"
for i in fav_results[0:5]:
print i[0],i[1]
print '\n'
print "Least 5 correlated for my top favourite movie"
fav_results.reverse()
for i in fav_results[0:5]:
print i[0],i[1]
print '\n'
print "Most 5 correlated for my least favourite movie"
for i in hate_results[0:5]:
print i[0],i[1]
print '\n'
print "Least 5 correlated for my least favourite movie"
hate_results.reverse()
for i in hate_results[0:5]:
print i[0],i[1]
def product(product_id):
ratings = Rating.query.filter_by(product_id=product_id).all()
product = Product.query.filter_by(id=product_id).first()
category = Category.query.filter_by(id=product.category_id).first()
total = 0
for r in ratings:
total += r.rating
if product.rating_count != 0:
product.rating = total / product.rating_count
product.rating = round(product.rating, 2)
total = 0
users = []
comments = []
rating = []
ratings = db.engine.execute(
text(
"select User.username, Rating.rating, Rating.comment from Rating left join User on Rating.user_id = User.id where Rating.product_id = "
+ str(product_id)))
for r in ratings:
rating.append(r[1])
users.append(r[0])
comments.append(r[2])
total += 1
ratings = Rating.query.all()
recommended_products = {}
for i in range(len(ratings)):
user = User.query.filter_by(id=ratings[i].user_id).first()
product_check = Product.query.filter_by(
id=ratings[i].product_id).first()
if user.username not in recommended_products.keys():
recommended_products[user.username] = {}
if product_check.name not in recommended_products[
user.username].keys():
recommended_products[user.username][
product_check.name] = ratings[i].rating
recommended_products = transformPrefs(recommended_products)
if product.name not in recommended_products:
product_list = []
else:
recommended_products = topMatches(recommended_products, product.name,
4)
product_list = [
Product.query.filter_by(name=product[1]).first()
for product in recommended_products
]
return render_template("product_details.html",
recommended_products=product_list,
product=product,
category=category,
ratings=rating,
users=users,
comments=comments,
total=total)
#print recommendations.critics['Lisa Rose']['Lady in the Water'] print recommendations.critics['Lisa Rose'] print recommendations.critics['Gene Seymour'] print recommendations.sim_distance(recommendations.critics,'Lisa Rose','Gene Seymour') print recommendations.sim_pearson(recommendations.critics,'Lisa Rose','Gene Seymour') print recommendations.topMatches(recommendations.critics,'Toby',n=3) print recommendations.topMatches(recommendations.critics,'Toby',n=3,similarity=recommendations.sim_distance) recommendations.getRecommendations(recommendations.critics,'Toby') recommendations.getRecommendations(recommendations.critics,'Toby',similarity=recommendations.sim_distance) movies=recommendations.transformPrefs(recommendations.critics) #print movies recommendations.topMatches(movies,'Superman Returns') recommendations.getRecommendations(movies,'Just My Luck') recommendations.getRecommendations(movies,'Lady in the Water') itemsim=recommendations.calculateSimilarItems(recommendations.critics,n=8) itemsim recommendations.getRecommendedItems(recommendations.critics,itemsim,'Toby') prefs=recommendations.loadMovieLens()
def test_transformPrefs(self):
self.assertEqual(recommendations.transformPrefs(recommendations.critics)['Lady in the Water'],
{'Lisa Rose': 2.5, 'Jack Matthews': 3.0, 'Michael Phillips': 2.5, 'Gene Seymour': 3.0, 'Mick LaSalle': 3.0})