def test_split_data(self):
ratings = pd.DataFrame(
[
[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
],
columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
bpr = BayesianPersonalizationRanking('')
bpr.initialize_factors(ratings)
for d in bpr.draw(2):
print(d)
def test_split_data(self):
ratings = pd.DataFrame(
[[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
], columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
bpr = BayesianPersonalizationRanking('')
bpr.initialize_factors(ratings)
for d in bpr.draw(2):
print(d)
def evaluate_bpr_recommender():
number_of_factors = 30
number_of_iterations = 5
N = 10
save_path = './models/bpr/'
timestr = time.strftime("%Y%m%d-%H%M%S")
file_name = '{}-bpr-k.csv'.format(timestr)
with open(file_name, 'a', 1) as logfile:
logfile.write(
"ar, map, mae, N, error, factors, number_of_iterations\n")
builder = BayesianPersonalizationRanking(save_path)
for number_of_factors in np.arange(5, 50, 5):
recommender = BPRRecs(save_path + 'model/')
er = EvaluationRunner(0,
builder,
recommender,
N,
params={
'k': number_of_factors,
'num_iterations': number_of_iterations,
'save_path': save_path + 'model/'
})
result = er.calculate(10, 5)
map = result['map']
mae = result['mae']
ar = result['ar']
error = builder.error if builder else 0
logfile.write("{}, {}, {}, {}, {}, {}, {}\n".format(
ar, map, mae, N, error, number_of_factors,
number_of_iterations))
logfile.flush()
def evaluate_bpr_recommender(coverage=False):
save_path = './models/bpr/'
timestr = time.strftime("%Y%m%d-%H%M%S")
file_name = '{}-bpr-k.csv'.format(timestr)
with open(file_name, 'a', 1) as logfile:
logfile.write("rak,pak,mae,k,user_coverage,movie_coverage\n")
builder = BayesianPersonalizationRanking(save_path)
for k in np.arange(0, 20, 2):
recommender = BPRRecs()
er = EvaluationRunner(0,
builder,
recommender,
k,
params={
'k': 10,
'num_iterations': 20,
'save_path': save_path + 'model/'
})
result = er.calculate(1, 5)
builder = None
user_coverage, movie_coverage = 0, 0
if coverage:
user_coverage, movie_coverage = RecommenderCoverage(
recommender).calculate_coverage(k)
map = result['map']
mae = result['mae']
ar = result['ar']
logfile.write("{}, {}, {}, {}, {}, {}\n".format(
ar, map, mae, k, user_coverage, movie_coverage))
logfile.flush()