def __init__(self, dataset, test, N=20, I=300):
""" Input:
-> dataset <list> : all data in list form.
-> N <Integer> : Length of the recommendation list.
-> I <Integer> : Number of Pseudo-items. The assumption is that
all of these items are not relevant for our user[1].
-> test <<user => {movie => rating}>,
<movie => {user => rating}>>: Contains test dbs.
[1]: Cremonesi, P., Milano, P. & Turrin, R., 2010. Performance of
Recommender Algorithms on Top-N Recommendation Tasks. Methodology,
p.39. Available at: http://portal.acm.org/citation.cfm?id=
1864708.1864721
"""
self.test_db, self.test_idb = test
self.N = N
self.db, self.idb, movies = dataload.read_data_to_hash(dataset)
self.I = I
self.n_hit = 0
self.n_miss = 0
self.recall = 0
self.precision = 0
print self
def __init__(self, dataset, test, N=20, I=300):
""" Input:
-> dataset <list> : all data in list form.
-> N <Integer> : Length of the recommendation list.
-> I <Integer> : Number of Pseudo-items. The assumption is that
all of these items are not relevant for our user[1].
-> test <<user => {movie => rating}>,
<movie => {user => rating}>>: Contains test dbs.
[1]: Cremonesi, P., Milano, P. & Turrin, R., 2010. Performance of
Recommender Algorithms on Top-N Recommendation Tasks. Methodology,
p.39. Available at: http://portal.acm.org/citation.cfm?id=
1864708.1864721
"""
self.test_db, self.test_idb = test
self.N = N
self.db, self.idb, movies = dataload.read_data_to_hash(dataset)
self.I = I
self.n_hit = 0
self.n_miss = 0
self.recall = 0
self.precision = 0
print self
def createRecSystem(self):
db, idb, movies = dataload.read_data_to_hash(self.trainset)
self.rec = KNeighborRegressor(db,
idb,
k=self.k,
sim_method=self.sim_method,
rec_type=self.rec_type)
def evaluate(self, k=1, N=20, I=300):
"""
Input:
-> k: Number of item(s) which are/is the user appreciates
most. (Only for Precision & Recall)
"""
test_db, test_idb, m = dataload.read_data_to_hash(self.testset)
if self.rec_type == 'ib':
test_db, test_idb = test_idb, test_db
if self.eval_metric == 'mae':
return self.__calc_mae(test_db)
elif self.eval_metric == 'pr': # precision & Recall
return self.__calc_pr((test_db, test_idb), k, N, I)
else:
stderr.write("There is no such evaluation metric you can use")
exit(1)
def evaluate(self, k=1, N=20, I=300):
"""
Input:
-> k: Number of item(s) which are/is the user appreciates
most. (Only for Precision & Recall)
"""
test_db, test_idb, m = dataload.read_data_to_hash(self.testset)
if self.rec_type == 'ib':
test_db, test_idb = test_idb, test_db
if self.eval_metric == 'mae':
return self.__calc_mae(test_db)
elif self.eval_metric == 'pr': # precision & Recall
return self.__calc_pr((test_db, test_idb), k, N, I)
else:
stderr.write("There is no such evaluation metric you can use")
exit(1)
def createRecSystem(self):
db, idb, movies = dataload.read_data_to_hash(self.trainset)
self.rec = KNeighborRegressor(db, idb, k=self.k,
sim_method=self.sim_method, rec_type=self.rec_type)
