def read_user_data_from_ratings(data_file):
data = Data()
format = {'col':0, 'row':1, 'value':2, 'ids': 'int'}
data.load(dat_file, sep='::', format=format)
userdict = {}
for d in data.get():
if d[2] in userdict:
user = userdict[d[2]]
else:
user = User(d[2])
user.add_item(d[1],d[0])
userdict[d[2]] = user
return userdict
def read_user_data_from_ratings(data_file):
data = Data()
format = {'col': 0, 'row': 1, 'value': 2, 'ids': 'int'}
data.load(dat_file, sep='::', format=format)
userdict = {}
for d in data.get():
if d[2] in userdict:
user = userdict[d[2]]
else:
user = User(d[2])
user.add_item(d[1], d[0])
userdict[d[2]] = user
return userdict
def setup():
global user, items, data
user = User(USERID)
items = _read_items(os.path.join(MOVIELENS_DATA_PATH, 'movies.dat'))
data = Data()
data.load(os.path.join(MOVIELENS_DATA_PATH, 'ratings.dat'),
sep='::',
format={
'col': 0,
'row': 1,
'value': 2,
'ids': int
})
def test_user_add_item():
u = User(USERID)
item = Item(ARTISTID)
item.add_data({'name': ARTISTID})
u.add_item(item, PLAYS)
assert_equal(str(u.get_items()), '[(u2, 25)]')
def test_user_build():
u = User(USERID)
assert_equal(u.get_id(), USERID)
def test_user_add_item():
u = User(USERID)
item = Item(ARTISTID)
item.add_data({'name': ARTISTID})
u.add_item(item, PLAYS)
assert_equal(str(u.get_items()), '[(u2, 25)]')
def test_user_build():
u = User(USERID)
assert_equal(u.get_id(), USERID)
A minimalistic command line recommender system using
SVD decomposistion.
"""
#Create and train model
svd = create_svd_model(ratings)
N = 10000
choice = 5
while True:
#recommend
if choice == 5:
user_id = str(raw_input("Please enter a username: "))
user = User(user_id)
try:
results = svd.recommend(user_id, is_row=False, n=N)
except KeyError:
results = []
if choice == 4: # See ratings
see_ratings(user_id, movies, ratings)
if choice == 1: # Rate movies
ratings = random_rating(user_id, movies, ratings)
svd = create_svd_model(ratings) # Update model
try:
results = svd.recommend(user_id, is_row=False, n=N)
except KeyError:
results = []
if choice == 2: # Filter by genre
results = select_genre(results, movies)
itemId = 0
item = Item(itemId)
item.add_data({'name': 'project0',
'popularity': 0.5,
'tags': [0, 0, 1]
})
item2 = Item(1)
item2.add_data({'name': 'project1',
'popularity': 0.5,
'tags': [0, 0, 1]
})
# create a user
userId = 0
user = User(userId)
# link an item with a user
rating = 1
user.add_item(itemId, rating)
data = Data()
data.add_tuple((rating, itemId, userId))
data.add_tuple((10, 1, 2))
svd = SVD()
svd.set_data(data)
svd.compute(k=100, min_values=0, pre_normalize=None, mean_center=True, post_normalize=True)
svd.similarity(0, 0)
