def run_model(model_name, dataset_name, test_size=0.3, clean=False):
print('*' * 70)
print('\tThis is %s model trained on %s with test_size = %.2f' %
(model_name, dataset_name, test_size))
print('*' * 70 + '\n')
model_manager = utils.ModelManager(dataset_name, test_size)
try:
trainset = model_manager.load_model('trainset')
testset = model_manager.load_model('testset')
except OSError:
ratings = DataSet.load_dataset(name=dataset_name)
trainset, testset = DataSet.train_test_split(ratings,
test_size=test_size)
model_manager.save_model(trainset, 'trainset')
model_manager.save_model(testset, 'testset')
'''Do you want to clean workspace and retrain model again?'''
'''if you want to change test_size or retrain model, please set clean_workspace True'''
model_manager.clean_workspace(clean)
if model_name == 'UserCF':
model = UserBasedCF()
elif model_name == 'ItemCF':
model = ItemBasedCF()
elif model_name == 'Random':
model = RandomPredict()
elif model_name == 'MostPopular':
model = MostPopular()
elif model_name == 'UserCF-IIF':
model = UserBasedCF(use_iif_similarity=True)
elif model_name == 'ItemCF-IUF':
model = ItemBasedCF(use_iuf_similarity=True)
else:
raise ValueError('No model named' + model_name)
model.fit(trainset)
recommend_test(model, [1, 100, 233, 666, 888])
model.test(testset)
count = cur.execute(
"select `id` from `book` where `id` not in("
"select distinct `book_id` from `read_record`) "
"and `id` not in(select distinct `book_id` from `buy_record`)")
result = cur.fetchmany(count)
all_book_not_been_read = []
for row in result:
all_book_not_been_read.append(row[0])
cur.close()
conn.commit()
conn.close()
except Exception, e:
print Exception, ':', e
preprocessed_dataset = data_preprocessing.preprocess_data(dataset)
mp = MostPopular(preprocessed_dataset)
mp.calc_item_popularity()
mp_by_ratio = MPByCategoryRatio(preprocessed_dataset, item_category_map)
mp_by_ratio.calc_item_popularity()
user_cf = HieraKmeansUserCF(preprocessed_dataset, item_category_map,
n_sample, max_iter)
user_cf.calc_user_sim()
mutex.acquire()
PREPROCESSED_DATASET = preprocessed_dataset
ALL_BOOK_NOT_BEEN_READ = all_book_not_been_read
MP = mp
MP_BY_RATIO = mp_by_ratio
USER_CF = user_cf
mutex.release()
print 'update complete'